Propaganda material generation method and device, electronic equipment and storage medium

Abstract

The invention relates to a propaganda material generation method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the analysis of a to-be-analyzed propaganda material based on a preset data structure, and obtaining an initial data structure body corresponding to the to-be-analyzed propaganda material, the initial data structural body comprises structural units in the preset data structure and elements corresponding to the structural units respectively; elements included in the initial data structural body are replaced, multiple updated candidate data structural bodies are obtained, and one candidate data structural body is a data structural body obtained after the elements corresponding to one or more structural units in the initial data structural body are replaced; generating candidate propaganda materials corresponding to the plurality of candidate data structural bodies; and evaluating the delivery effects corresponding to the plurality of candidate propaganda materials, and determining a target propaganda material for delivery from the plurality of candidate propaganda materials according to an evaluation result. The method disclosed by the invention can improve the advertising effect of the propaganda materials.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for generating promotional materials. Background Art

[0002] With the development of computer technology, intelligent generation technology has been increasingly used. For example, using intelligent generation technology to generate promotional materials can help users create materials better and optimize material delivery compared to manually generating promotional materials.

[0003] However, the method of generating promotional materials by applying intelligent generation technology in the related art has the problem of poor generation effect of promotional materials. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a promotional material generation method, device, electronic device and storage medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a method for generating promotional materials is provided, the method comprising:

[0006] Parsing the to-be-parsed promotional material based on the preset data structure to obtain an initial data structure corresponding to the to-be-parsed promotional material, wherein the initial data structure includes each structural unit in the preset data structure and elements corresponding to each structural unit;

[0007] Replacing the elements included in the initial data structure to obtain a plurality of updated candidate data structures, wherein one candidate data structure is a data structure obtained by replacing elements corresponding to one or more structural units in the initial data structure;

[0008] Generating candidate promotional materials corresponding to the plurality of candidate data structures respectively;

[0009] The delivery effects corresponding to each of the plurality of candidate promotional materials are evaluated, and a target promotional material for delivery is determined from the plurality of candidate promotions according to the evaluation result.

[0010] In some embodiments, the method further comprises:

[0011] Obtain the actual delivery effect indicators corresponding to the target promotional materials being delivered;

[0012] According to the actual delivery effect index, promotional materials that meet the preset effect index are determined from the delivered target promotional materials, wherein the promotional materials that meet the preset effect index are used as new promotional materials to be parsed, or are used for parsing to obtain data to replace the elements included in the initial data structure.

[0013] In some implementations, generating candidate promotional materials corresponding to the plurality of candidate data structures respectively includes:

[0014] Creating tasks for generating corresponding candidate promotional materials according to the candidate data structure;

[0015] Send each task to a message queue to control the execution timing of each task through the message queue;

[0016] When any task reaches the execution time, the task is executed through the corresponding task execution thread to generate candidate promotional materials corresponding to the task.

[0017] In some implementations, generating candidate promotional materials corresponding to the plurality of candidate data structures respectively includes:

[0018] For any candidate data structure, materials corresponding to the structural units in the candidate data structure are drawn in parallel, and the materials corresponding to a structural unit are drawn according to the elements corresponding to the structural unit;

[0019] After drawing the materials respectively corresponding to the structural units in the candidate data structure, the materials respectively corresponding to the structural units in the candidate data structure are merged to obtain the candidate promotional materials corresponding to the candidate data structure.

[0020] In some embodiments, the method further comprises:

[0021] For any structural unit, when the structural unit includes multiple sub-units, the materials corresponding to the sub-units in the structural unit are drawn in parallel, and the material corresponding to a sub-unit is drawn according to the element corresponding to the sub-unit;

[0022] After the materials respectively corresponding to the sub-units in the structural unit are drawn, the materials respectively corresponding to the sub-units in the structural unit are merged to obtain the materials corresponding to the structural unit.

[0023] In some implementations, the evaluating the delivery effects corresponding to each of the plurality of candidate promotional materials includes:

[0024] At every preset time period, the delivery effect evaluation model is used to evaluate the delivery effect of the candidate promotional materials generated within the time period.

[0025] In some embodiments, the structural units in the preset data structure include at least one of the following: a color matching unit, a background unit, a text unit, a template layout structure unit, a decoration unit, a main image unit, and a superscript unit.

[0026] According to a second aspect of an embodiment of the present disclosure, a promotional material generating device is provided, the device comprising:

[0027] A parsing module is configured to parse the to-be-parsed promotional material based on a preset data structure to obtain an initial data structure corresponding to the to-be-parsed promotional material, wherein the initial data structure includes each structural unit in the preset data structure and elements corresponding to each structural unit;

[0028] a replacement module configured to replace elements included in the initial data structure to obtain multiple updated candidate data structures, wherein one candidate data structure is a data structure obtained by replacing elements corresponding to one or more structural units in the initial data structure;

[0029] A generating module, configured to generate candidate promotional materials corresponding to the plurality of candidate data structures respectively;

[0030] The first determination module is configured to evaluate the delivery effects corresponding to each of the plurality of candidate promotional materials, and determine the target promotional material for delivery from the plurality of candidate promotions according to the evaluation results.

[0031] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the promotional material generation method provided in the first aspect of the present disclosure are implemented.

[0032] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the steps of the promotional material generation method mentioned in the first aspect of the present disclosure.

[0033] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by deconstructing the promotional material to be parsed into different data structure units, and then obtaining a variety of candidate data structures by replacing the elements in different data structure units, the diversity of the generated candidate promotional materials can be guaranteed, and further, when the delivery effects corresponding to the multiple candidate promotional materials are subsequently evaluated, the target promotional material for delivery can be determined from more promotional materials, thereby improving the delivery effect of the target promotional material.

[0034] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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.

[0036] Figure 1 The figure is a flow chart of a method for generating promotional materials according to an exemplary embodiment of the present disclosure.

[0037] Figure 2 The figure is a flowchart of another method for generating promotional materials according to an exemplary embodiment of the present disclosure.

[0038] Figure 3 The figure is a flowchart of another method for generating promotional materials according to an exemplary embodiment of the present disclosure.

[0039] Figure 4 The figure is a flowchart of another method for generating promotional materials according to an exemplary embodiment of the present disclosure.

[0040] Figure 5 The figure is a structural block diagram of a promotional material generating device according to an exemplary embodiment of the present disclosure.

[0041] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0043] It should be noted that all actions of acquiring signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0044] Among the related technologies, there are intelligent generation technology solutions that use artificial intelligence to generate promotional materials. For example, natural language generation technology (such as GPT-3, Generative Pre-trained Transformer-3) can be used to automatically generate advertising copy, social media posts, product descriptions and other content, which helps improve the efficiency and consistency of advertising materials.

[0045] However, the method of generating promotional materials based on artificial intelligence, since artificial intelligence is trained based on a certain type of sample material, the promotional materials subsequently generated using the trained model tend to have the characteristics of the samples, reducing the diversity of the generated promotional materials and making it difficult to guarantee the effectiveness of the generated promotional materials.

[0046] It should be noted that the promotional materials of the embodiments of the present disclosure may be, for example, advertising materials, social media posts, website homepage images, etc.

[0047] The present disclosure is described below in conjunction with specific embodiments.

[0048] Figure 1 is a flow chart of a method for generating promotional materials according to an exemplary embodiment. The method is applied to an electronic device. The method may include:

[0049] S110, parsing the promotional material to be parsed based on a preset data structure to obtain an initial data structure corresponding to the promotional material to be parsed.

[0050] The initial data structure includes each structural unit in the preset data structure and elements corresponding to each structural unit.

[0051] The preset data structure may be a DSL (Domain Specific Language) data structure preset according to the type of the promotional material. Optionally, the preset data structure may be manually extracted, or alternatively, the preset data structure may be obtained through extraction model recognition.

[0052] In some implementations, the preset data structure may be saved in JSON (JavaScript Object Notation) format.

[0053] In some embodiments, the preset data structure may be composed of structural units, and the structural units included in the preset data structure may include at least one of the following: color matching unit, background unit, text unit, template layout structure unit, decoration unit, main image unit, and superscript unit.

[0054] That is to say, in the embodiments of the present disclosure, depending on the type of promotional material, the promotional material may include multiple features such as color matching, background, copy, template layout structure, decoration, main image, superscript, etc.

[0055] The elements corresponding to the structural units can be understood as the content corresponding to the structural units. The structural units in the preset data structure and the elements corresponding to the structural units can be understood as a data structure.

[0056] In the disclosed embodiment, after obtaining the promotional material to be analyzed, it can be analyzed based on the preset data structure to obtain the elements corresponding to each structural unit in the preset data structure, thereby obtaining the data structure corresponding to the promotional material to be analyzed, that is, the initial data structure.

[0057] In some implementations, the promotional materials to be parsed may be some high-quality promotional materials, such as high-quality PSD (default file format of Photoshop software) images.

[0058] S120, replacing the elements included in the initial data structure to obtain a plurality of updated candidate data structures.

[0059] A candidate data structure is a data structure obtained by replacing elements corresponding to one or more structural units in the initial data structure.

[0060] In the disclosed embodiment, the elements corresponding to the structural units in the initial data structure are replaced to obtain a new data structure, wherein the replacement may be replacing an element corresponding to a structural unit compared to the initial data structure, or replacing elements corresponding to multiple structural units compared to the initial data structure.

[0061] In some embodiments, a structural unit may include one or more sub-units. For example, a main image unit may include an image sub-unit, a first text sub-unit, and a second text sub-unit. For another example, a color matching unit may include a color sub-unit. In this case, the replacement of the element corresponding to the structural unit may be the replacement of the element of one or more sub-units included in the structural unit.

[0062] In the disclosed embodiment, different replacements may be performed on the elements corresponding to the structural units in the initial data structure, thereby obtaining a plurality of replaced data structures, namely, candidate data structures.

[0063] For example, Figure 2 As shown, it is assumed that the initial data structure 20 includes a first structure unit 21, a second structure unit 22 and a third structure unit 23, wherein the first structure unit 21 includes an image sub-unit, the corresponding element is A1, and two text sub-units, the corresponding elements are B1 and B2 respectively, the second structure unit 22 includes an image sub-unit, the corresponding element is A2, and the third structure unit 23 includes a text sub-unit, the corresponding element is B3.

[0064] In one example, the A1 element included in the initial data structure can be replaced by the A3 element, and the other elements A2, B1, B2, and B3 remain unchanged, thereby obtaining a candidate data structure.

[0065] In one example, the A1 element included in the initial data structure can be replaced by the A4 element, the B1 element can replace the B4 element, and the other elements A2, B2, and B3 remain unchanged, thereby obtaining a candidate data structure.

[0066] Thus, through different replacements, multiple different candidate data structures can be obtained.

[0067] It should be noted that, in this example, A1, A2, A3, and A4 represent different images, and B1, B2, B3, and B4 represent different texts.

[0068] S130, generating candidate promotional materials corresponding to the plurality of candidate data structures respectively.

[0069] In the disclosed embodiment, one candidate data structure can generate one corresponding candidate promotional material, and thus, for multiple candidate data structures, candidate promotional materials corresponding to the multiple candidate data structures can be generated.

[0070] S140, evaluating the delivery effects corresponding to the multiple candidate promotional materials, and determining the target promotional material for delivery from the multiple candidate promotions according to the evaluation results.

[0071] In the disclosed embodiment, a plurality of candidate promotional materials are generated, among which some promotional materials may have better delivery effects, while some promotional materials may have relatively poor delivery effects. Therefore, the delivery effects corresponding to the plurality of candidate promotional materials may be further evaluated, so that target promotional materials with better delivery effects may be determined based on the evaluation results, and the determined target promotional materials may be subsequently delivered.

[0072] In the disclosed embodiment, the target promotional material with better delivery effect determined according to the evaluation result may be one or more.

[0073] By adopting the above method, by deconstructing the promotional material to be analyzed into different data structure units, and then replacing the elements in different data structure units to obtain multiple candidate data structures, the diversity of the generated candidate promotional materials can be guaranteed, and further, when the corresponding delivery effects of multiple candidate promotional materials are evaluated subsequently, the target promotional material for delivery can be determined from more promotional materials, thereby improving the delivery effect of the target promotional material.

[0074] In some implementations, the method of the embodiment of the present disclosure may further include the following steps:

[0075] Obtain the actual delivery effect indicators corresponding to the target promotional materials being delivered;

[0076] According to the actual delivery effect index, the promotional material that meets the preset effect index is determined from the target promotional material delivered, wherein the promotional material that meets the preset effect index is used as the new promotional material to be parsed, or is used for parsing to obtain data to replace the elements included in the initial data structure.

[0077] In the disclosed embodiment, after the target promotional material is determined, the target promotional material can be delivered, and then the actual delivery effect index of the target promotional material during the delivery process, i.e., the actual delivery effect index, is collected. Further, based on the actual delivery effect index, the promotional material that meets the preset effect index is determined from the delivered target promotional material.

[0078] In the embodiment of the present disclosure, if the actual delivery effect index meets the preset effect index, it can be understood that the delivery effect is good. In this case, the promotional materials that meet the preset effect index can be collected.

[0079] In some implementations, after obtaining promotional materials that meet the preset effect index, the promotional materials that meet the preset effect index can be used as new promotional materials to be analyzed, and the steps S110-S140 are performed again using the new promotional materials to be analyzed to obtain the target promotional materials for delivery again. Since the target promotional materials are obtained from high-quality promotional materials with good actual delivery effects, the target promotional materials can inherit the characteristics of the high-quality promotional materials, which is equivalent to evaluating and screening the elements in the promotional material structural unit, and can improve the delivery effect of the target promotional materials obtained subsequently. In addition, the disclosed embodiment makes full use of the actual delivery effect of the promotional materials, belongs to an intelligent generation method driven by real data, and ensures the accuracy and rationality of the evaluation and screening.

[0080] In addition, considering that the elements included in the promotional materials that meet the preset effect indicators bring better delivery effects, when the elements are migrated to the data structure corresponding to other promotional materials, it can also bring better delivery effects. Therefore, in some embodiments, after obtaining the promotional materials that meet the preset effect indicators, the promotional materials that meet the preset effect indicators can be parsed based on the preset data structure to obtain the corresponding data structure. Then, the elements corresponding to each structural unit included in the data structure can be further saved, so as to use them as data to replace the elements included in the initial data structure corresponding to other promotional materials to be parsed.

[0081] In some implementations, generating candidate promotional materials corresponding to a plurality of candidate data structures may include the following steps:

[0082] Creating tasks for generating corresponding candidate promotional materials according to the candidate data structure;

[0083] Send each task to the message queue to control the execution timing of each task through the message queue;

[0084] When any task reaches the execution time, the task is executed through the corresponding task execution thread to generate candidate promotional materials corresponding to the task.

[0085] Taking into account that there are many promotional material generation tasks submitted by the upstream, and each material generation task needs to generate multiple candidate promotional materials, which leads to heavy tasks of generating corresponding candidate promotional materials according to the candidate data structure. Therefore, in the embodiment of the present disclosure, by creating various tasks for generating corresponding candidate promotional materials according to the candidate data structure, and controlling the execution timing of the tasks through message queues, the process of generating the candidate data structure is decoupled from the task of generating the candidate promotional materials, thereby improving the stability of the candidate promotional materials, and by expanding multiple message queues, it is easy to realize parallel generation of candidate promotional materials, thereby improving the efficiency of generating candidate promotional materials.

[0086] In some implementations, there may be multiple message queues. In this case, multiple tasks may be distributed to different message queues so that the execution timing of each task can be controlled through the multiple message queues.

[0087] In some implementations, the message queue can be implemented based on the Kafka (an open source stream processing platform) + Flink (a distributed computing framework) architecture.

[0088] For example, reference Figure 3 , shows a schematic diagram of a candidate promotional material generation system architecture, such as Figure 3 As shown, the producer can create candidate promotional material generation tasks corresponding to multiple candidate data structures, and then assign the multiple tasks to multiple message queues to control each task through multiple message queues. The tasks going out of each message queue can be executed by the corresponding consumer thread to generate corresponding candidate promotional materials.

[0089] In some implementations, generating candidate promotional materials corresponding to a plurality of candidate data structures may include the following steps:

[0090] For any candidate data structure, materials corresponding to the structural units in the candidate data structure are drawn in parallel, and the materials corresponding to a structural unit are drawn according to the elements corresponding to the structural unit;

[0091] After drawing the materials respectively corresponding to the structural units in the candidate data structure, the materials respectively corresponding to the structural units in the candidate data structure are merged to obtain the candidate promotional materials corresponding to the candidate data structure.

[0092] For example, reference Figure 4 Assuming that the candidate data structure includes a first structural unit and a second structural unit, when generating candidate promotional materials corresponding to the candidate data structure, the process of drawing the materials corresponding to the first structural unit according to the elements corresponding to the first structural unit and drawing the materials corresponding to the second structural unit according to the elements corresponding to the second structural unit can be executed in parallel. Then, after drawing the materials corresponding to the first structural unit and the materials corresponding to the second structural unit, the materials corresponding to the first structural unit and the materials corresponding to the second structural unit are merged to obtain the candidate promotional materials corresponding to the candidate data structure.

[0093] For any candidate data structure, by drawing the materials corresponding to the structural units in the candidate data structure in parallel, the drawing speed of the candidate promotional materials can be improved, thereby reducing the time consumption of generating the target promotional materials.

[0094] In some implementations, the method of the embodiment of the present disclosure may further include the following steps:

[0095] For any structural unit, when the structural unit includes multiple sub-units, the materials corresponding to the sub-units in the structural unit are drawn in parallel, and the material corresponding to a sub-unit is drawn according to the element corresponding to the sub-unit;

[0096] After the materials respectively corresponding to the sub-units in the structural unit are drawn, the materials respectively corresponding to the sub-units in the structural unit are merged to obtain the materials corresponding to the structural unit.

[0097] For example, continue to refer to Figure 4 , assuming that the first structural unit includes a first image sub-unit, a second image sub-unit and a first text sub-unit, and the second structural unit includes a third image sub-unit and a second text sub-unit.

[0098] When drawing the material corresponding to the first structural unit, the process of drawing the material corresponding to the first image subunit according to the elements corresponding to the first image subunit, drawing the material corresponding to the second image subunit according to the elements corresponding to the second image subunit, and drawing the material corresponding to the first text subunit according to the elements corresponding to the first text subunit can be executed in parallel. Then, after drawing the material corresponding to the first image subunit, the material corresponding to the second image subunit, and the material corresponding to the first text subunit, the material corresponding to the first image subunit, the material corresponding to the second image subunit, and the material corresponding to the first text subunit can be fused to obtain the material corresponding to the first structural unit.

[0099] Similarly, when drawing the material corresponding to the second structural unit, the process of drawing the material corresponding to the third image subunit according to the elements corresponding to the third image subunit and drawing the material corresponding to the second text subunit according to the elements corresponding to the second text subunit can be executed in parallel. Then, after drawing the material corresponding to the third image subunit and the material corresponding to the second text subunit, the material corresponding to the third image subunit and the material corresponding to the second text subunit can be fused to obtain the material corresponding to the second structural unit.

[0100] For any structural unit, by drawing the materials corresponding to each sub-unit in the structural unit in parallel, the drawing speed of the structural unit in the candidate promotional material can be improved, thereby improving the drawing speed of the candidate promotional material and reducing the time consumption of generating the target promotional material.

[0101] In some implementations, evaluating the delivery effects of the plurality of candidate promotional materials may include the following steps:

[0102] At every preset time period, the delivery effect evaluation model is used to evaluate the delivery effect of the candidate promotional materials generated within the time period.

[0103] In the disclosed embodiment, candidate promotional materials generated within a period of time are accumulated and evaluated for delivery effect through a delivery effect evaluation model, without having to evaluate each generated candidate promotional material. This implements batch evaluation of promotional materials based on a time window, and can fully utilize the performance advantage of GPU (Graphic Processing Unit) in large-scale data computing.

[0104] In some embodiments, the generated candidate promotional materials corresponding to the multiple candidate data structures and the evaluation results corresponding to the multiple candidate promotional materials can be cached through Redis (Remote Dictionary Server), which can further improve the page rendering efficiency and reduce the API (Application Programming Interface) service time.

[0105] In some implementations, the delivery effect evaluation model may be a trained neural network model.

[0106] In some implementations, the evaluation can be performed from the perspectives of CTR, aesthetics, personalization, etc. Thus, models such as a CTR prediction model, an aesthetics index prediction model, and a personalization index prediction model can be trained to evaluate the delivery effect of the candidate promotional materials.

[0107] Figure 5 is a structural block diagram of a promotional material generating device 500 according to an exemplary embodiment. Figure 5 , the device 500 comprises:

[0108] The parsing module 510 is configured to parse the promotional material to be parsed based on a preset data structure to obtain an initial data structure corresponding to the promotional material to be parsed, wherein the initial data structure includes each structural unit in the preset data structure and elements corresponding to each structural unit;

[0109] A replacement module 520 is configured to replace the elements included in the initial data structure to obtain multiple updated candidate data structures, where one candidate data structure is a data structure obtained by replacing elements corresponding to one or more structural units in the initial data structure;

[0110] A generating module 530 is configured to generate candidate promotional materials corresponding to the plurality of candidate data structures respectively;

[0111] The first determination module 540 is configured to evaluate the delivery effects corresponding to each of the plurality of candidate promotional materials, and determine the target promotional material for delivery from the plurality of candidate promotions according to the evaluation result.

[0112] In some embodiments, the apparatus 500 further comprises:

[0113] An acquisition module is configured to acquire actual delivery effect indicators corresponding to target promotional materials being delivered;

[0114] The second determination module is configured to determine the promotional material that meets the preset effect index from the target promotional material that is delivered according to the actual delivery effect index, wherein the promotional material that meets the preset effect index is used as the new promotional material to be parsed, or is used to parse to obtain data to replace the elements included in the initial data structure.

[0115] In some embodiments, the generation module 530 includes:

[0116] A creation submodule configured to create various tasks for generating corresponding candidate promotional materials according to the candidate data structure;

[0117] A sending submodule, configured to send each task to a message queue, so as to control the execution timing of each task through the message queue;

[0118] The execution submodule is configured to execute any task through the corresponding task execution thread when the task reaches the execution timing, so as to generate candidate promotional materials corresponding to the task.

[0119] In some embodiments, the generation module 530 includes:

[0120] The first drawing submodule is configured to draw, for any candidate data structure, materials corresponding to the structural units in the candidate data structure in parallel, wherein the materials corresponding to a structural unit are drawn according to the elements corresponding to the structural unit;

[0121] The first fusion submodule is configured to fuse the materials corresponding to the various structural units in the candidate data structure after drawing the materials corresponding to the various structural units in the candidate data structure, so as to obtain candidate promotional materials corresponding to the candidate data structure.

[0122] In some embodiments, the apparatus 500 further comprises:

[0123] The parallel drawing module is configured to draw, for any structural unit, materials corresponding to the sub-units in the structural unit in parallel when the structural unit includes multiple sub-units, and the material corresponding to a sub-unit is drawn according to the elements corresponding to the sub-unit;

[0124] The fusion module is configured to fuse the materials corresponding to the sub-units in the structural unit after drawing the materials corresponding to the sub-units in the structural unit to obtain the materials corresponding to the structural unit.

[0125] In some embodiments, the first determination module 540 includes:

[0126] The evaluation submodule is configured to evaluate the delivery effect of the candidate promotional materials generated within a preset time period through a delivery effect evaluation model.

[0127] In some embodiments, the structural units in the preset data structure include at least one of the following: a color matching unit, a background unit, a text unit, a template layout structure unit, a decoration unit, a main image unit, and a corner mark unit.

[0128] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0129] The present disclosure also provides a computer-readable storage medium on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the promotional material generation method provided by the present disclosure are implemented.

[0130] Figure 6 is a block diagram of an electronic device according to an exemplary embodiment. Figure 6 , the electronic device 600 may include one or more of the following components: a processing component 602 , a memory 604 , a power component 606 , a multimedia component 608 , an audio component 610 , an input / output interface 612 , a sensor component 614 , and a communication component 616 .

[0131] The processing component 602 generally controls the overall operation of the electronic device 600, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 602 may include one or more processors 620 to execute instructions to complete all or part of the steps of the above-mentioned image processing method. In addition, the processing component 602 may include one or more modules to facilitate the interaction between the processing component 602 and other components. For example, the processing component 602 may include a multimedia module to facilitate the interaction between the multimedia component 608 and the processing component 602.

[0132] The memory 604 is configured to store various types of data to support operations on the electronic device 600. Examples of such data include instructions for any application or method operating on the electronic device 600, contact data, phone book data, messages, pictures, videos, etc. The memory 604 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0133] The power supply component 606 provides power to the various components of the electronic device 600. The power supply component 606 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 600.

[0134] The multimedia component 608 includes a screen that provides an output interface between the electronic device 600 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 608 includes a front camera and / or a rear camera. When the electronic device 600 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0135] The audio component 610 is configured to output and / or input audio signals. For example, the audio component 610 includes a microphone (MIC), and when the electronic device 600 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 604 or sent via the communication component 616. In some embodiments, the audio component 610 also includes a speaker for outputting audio signals.

[0136] The input / output interface 612 provides an interface between the processing component 602 and the peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0137] The sensor assembly 614 includes one or more sensors for providing various aspects of status assessment for the electronic device 600. For example, the sensor assembly 614 can detect the open / closed state of the electronic device 600, the relative positioning of the components, such as the display and keypad of the electronic device 600, and the sensor assembly 614 can also detect the position change of the electronic device 600 or a component of the electronic device 600, the presence or absence of contact between the user and the electronic device 600, the orientation or acceleration / deceleration of the electronic device 600, and the temperature change of the electronic device 600. The sensor assembly 614 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 614 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 614 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0138] The communication component 616 is configured to facilitate wired or wireless communication between the electronic device 600 and other devices. The electronic device 600 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 616 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 616 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0139] In an exemplary embodiment, the electronic device 600 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned image processing method.

[0140] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 604 including instructions, and the instructions can be executed by a processor 620 of an electronic device 600 to perform the above-mentioned image processing method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0141] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned promotional material generating method when executed by the programmable device.

[0142] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the present disclosure. This application is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0143] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for generating promotional materials, characterized in that: The method comprises: Parsing the to-be-parsed promotional material based on the preset data structure to obtain an initial data structure corresponding to the to-be-parsed promotional material, wherein the initial data structure includes each structural unit in the preset data structure and elements corresponding to each structural unit; Replacing the elements included in the initial data structure to obtain a plurality of updated candidate data structures, wherein one candidate data structure is a data structure obtained by replacing elements corresponding to one or more structural units in the initial data structure; Generating candidate promotional materials corresponding to the plurality of candidate data structures respectively; The delivery effects corresponding to each of the plurality of candidate promotional materials are evaluated, and a target promotional material for delivery is determined from the plurality of candidate promotions according to the evaluation result.

2. The method according to claim 1, characterized in that: The method further comprises: Obtain the actual delivery effect indicators corresponding to the target promotional materials being delivered; According to the actual delivery effect index, promotional materials that meet the preset effect index are determined from the delivered target promotional materials, wherein the promotional materials that meet the preset effect index are used as new promotional materials to be parsed, or are used for parsing to obtain data to replace the elements included in the initial data structure.

3. The method according to claim 1, characterized in that The generating of candidate promotional materials corresponding to the plurality of candidate data structures respectively includes: Creating tasks for generating corresponding candidate promotional materials according to the candidate data structure; Send each task to a message queue to control the execution timing of each task through the message queue; When any task reaches the execution time, the task is executed through the corresponding task execution thread to generate candidate promotional materials corresponding to the task.

4. The method according to claim 1, characterized in that: The generating of candidate promotional materials corresponding to the plurality of candidate data structures respectively includes: For any candidate data structure, materials corresponding to the structural units in the candidate data structure are drawn in parallel, and the materials corresponding to a structural unit are drawn according to the elements corresponding to the structural unit; After drawing the materials respectively corresponding to the structural units in the candidate data structure, the materials respectively corresponding to the structural units in the candidate data structure are merged to obtain the candidate promotional materials corresponding to the candidate data structure.

5. The method according to claim 3, characterized in that: The method further comprises: For any structural unit, when the structural unit includes multiple sub-units, the materials corresponding to the sub-units in the structural unit are drawn in parallel, and the material corresponding to a sub-unit is drawn according to the element corresponding to the sub-unit; After the materials respectively corresponding to the sub-units in the structural unit are drawn, the materials respectively corresponding to the sub-units in the structural unit are merged to obtain the materials corresponding to the structural unit.

6. The method according to claim 1, characterized in that The evaluating the delivery effects corresponding to each of the plurality of candidate promotional materials includes: At every preset time period, the delivery effect evaluation model is used to evaluate the delivery effect of the candidate promotional materials generated within the time period.

7. The method according to any one of claims 1 to 6, characterized in that: The structural units in the preset data structure include at least one of the following: a color matching unit, a background unit, a text unit, a template layout structure unit, a decoration unit, a main image unit, and a corner mark unit.

8. A promotional material generating device, characterized in that: The device comprises: A parsing module is configured to parse the to-be-parsed promotional material based on a preset data structure to obtain an initial data structure corresponding to the to-be-parsed promotional material, wherein the initial data structure includes each structural unit in the preset data structure and elements corresponding to each structural unit; a replacement module configured to replace elements included in the initial data structure to obtain multiple updated candidate data structures, wherein one candidate data structure is a data structure obtained by replacing elements corresponding to one or more structural units in the initial data structure; A generating module configured to generate candidate promotional materials corresponding to the plurality of candidate data structures respectively; The first determination module is configured to evaluate the delivery effects corresponding to each of the plurality of candidate promotional materials, and determine the target promotional material for delivery from the plurality of candidate promotions according to the evaluation results.

9. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images