Novel material distribution method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a novel material distribution method and device, electronic equipment and storage medium, relates to the technical field of data processing, in particular to the technical field of big data and content distribution, and includes: obtaining novel data; obtaining a plurality of random materials of a novel according to the novel data; distributing the plurality of random materials of the novel to a user; generating a first preset number of intelligent materials according to the plurality of random materials, user interaction data after the plurality of random materials are distributed, and the novel data by using a graph model; sorting the plurality of random materials and the first preset number of intelligent materials; and distributing a second preset number of materials in front of the sorted materials to the user.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of data processing, and particularly relates to the technical field of big data and content distribution. BACKGROUND

[0002] Currently, there are two methods for distributing novel materials. One is to collect a large number of titles, train a title generation model, generate a novel title using the title generation model, manually generate a corresponding novel picture, and then combine the novel picture and the novel title into a material to distribute to users. This method requires a large amount of human cost. The other is to collect a large number of titles and pictures, train a deep neural network, generate a novel title and picture using the deep neural network, and then combine the novel picture and the novel title into a material to distribute to users. This method does not consider user interaction data, and the generated title and picture are less attractive to users. The click rate of the material distributed to users is also low. SUMMARY

[0003] The present disclosure provides a novel material distribution method, device, electronic equipment and storage medium.

[0004] According to an aspect of the present disclosure, a novel material distribution method is provided, comprising:

[0005] acquiring novel data;

[0006] According to the novel data, a plurality of random materials of a novel are obtained;

[0007] The plurality of random materials of the novel are distributed to users;

[0008] A first preset number of intelligent materials are generated using a graph model according to the plurality of random materials, user interaction data after distribution of the plurality of random materials, and novel data;

[0009] The plurality of random materials and the first preset number of intelligent materials are sorted;

[0010] The second preset number of materials in the front after sorting are distributed to users.

[0011] According to another aspect of the present disclosure, a novel material distribution device is provided, comprising:

[0012] A collection module is configured to acquire novel data, wherein the novel data includes novels and novel categories;

[0013] A processing module is configured to obtain a plurality of random materials of a novel according to the novel data, wherein the random materials include novel titles and novel covers;

[0014] A distribution module is configured to distribute the plurality of random materials of the novel to users;

[0015] generating a first preset number of intelligent materials according to the plurality of random materials, user interaction data after distribution of the plurality of random materials, and novel data by using the graph model;

[0016] The distribution module is further configured to sort the plurality of random materials and the first preset number of intelligent materials.

[0017] The distribution module is further configured to distribute a second preset number of materials in front of the sorted materials to the user.

[0018] According to another aspect of the present disclosure, an electronic device is provided, comprising:

[0019] at least one processor; and

[0020] a memory connected to the at least one processor in communication; wherein

[0021] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of the above.

[0022] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to perform the method of any one of the above.

[0023] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of any one of the above.

[0024] It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description.

[0025] In the above method of the present disclosure, the intelligent material is generated according to the user interaction data and novel data after the distribution of the plurality of random materials, so that the generated intelligent material is most consistent with the aesthetics of the user, and after being pushed to the user, the user has a great possibility to click, read and search the intelligent material, thereby improving the attraction of the novel material to the user. The novel material is generated by randomly selecting a novel title and a novel cover from a preset title slot library and a picture library and forming a random material, and the user interaction data is provided for the subsequent generation of the intelligent material after the distribution of the random material. The overall method does not require manual selection or generation of titles and pictures, thereby automatically generating novel materials and reducing a large amount of labor cost. Finally, the random material and the intelligent material are sorted, and the second preset number of materials in the front after sorting are distributed to the user. The materials in the front are more attractive to the user to click, thereby improving the click rate of the distribution of the novel material. BRIEF DESCRIPTION OF DRAWINGS

[0026] The accompanying drawings are used to better understand the present scheme and do not constitute a limitation on the present disclosure. Among them:

[0027] Figure 1 is a flowchart of a novel material distribution method according to an embodiment of the present disclosure;

[0028] Figure 2 is a structural schematic diagram of a novel material distribution method device according to an embodiment of the present disclosure;

[0029] Figure 3 is a block diagram of an electronic device for implementing the novel material distribution method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to help understanding, and should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Also, in order to be clear and concise, the description below omits the description of well-known functions and structures.

[0031] In order to automatically generate novel materials and improve the attraction of the novel materials to the user, as shown in Figure 1 An embodiment of the present disclosure provides a novel material distribution method, which comprises:

[0032] Step 101, obtaining novel data.

[0033] The novel data contains novels and novel categories of the novels.

[0034] For example, if a novel is a romance novel, then the novel data for that novel will include both the novel itself and its novel category, "romance novel".

[0035] Step 102: Obtain multiple random materials from the novel based on the novel data.

[0036] Based on the novel data, obtain multiple random materials for the novel. Each random material contains a novel title and a novel cover. The novel titles of each random material may be the same or different. The novel covers of each random material may be the same or different. However, the combination of novel title and novel cover of each random material is different. That is, the novel title and novel cover of each random material cannot be the same.

[0037] Step 103: Distribute multiple random materials from the novel to the user.

[0038] Multiple random materials from the novel are pushed to the user. This is called a cold start push, which means that these random materials are not discarded.

[0039] Step 104: Using a graph model, generate a first preset number of smart materials based on the multiple random materials, user interaction data after the multiple random materials are distributed, and novel data.

[0040] Using a graph model, a first preset number of smart materials are generated based on novel titles and covers from multiple random materials, user interaction data after the distribution of multiple random materials, and novel categories and content from the novel data.

[0041] In this embodiment, the first preset quantity can be set to 5, and the user interaction data includes user behavior data such as clicking, reading, and searching for a certain material of the novel;

[0042] Specifically, a heterogeneous graph based on user interaction data, materials, novels, novel titles, and novel covers is constructed. The metapath2vec++ algorithm is used, and based on the objective of maximizing random walk revenue, five walk paths are set: user-material-novel cover-material-user, user-material-novel title-material-user, user-material-novel-material-user, novel-material-novel title-material-novel, and novel-material-novel cover-material-novel. The walk is performed according to these five walk paths based on posterior duration weights, and feature vectors of materials, novel titles, novel covers, novels, and novel categories are obtained. Based on these feature vectors, the novel title and novel cover combination with the highest similarity to the novel is generated, which is the intelligent material.

[0043] Step 105: Sort the multiple random materials and the first preset number of smart materials.

[0044] The coarse-sorting model and the fine-sorting model are used to sort multiple random materials and a first preset number of smart materials. The order of sorting can represent the attractiveness of the materials to users. The higher the ranking of a material, the greater its attractiveness to users.

[0045] Step 106: Distribute the second-most preset quantity of materials after sorting to the user.

[0046] Distribute the second-most preset quantity of materials after sorting to the user.

[0047] By generating intelligent materials based on user interaction data, multiple novel titles, multiple novel covers, novel categories, and novel content, the generated intelligent materials are designed to best suit users' aesthetic preferences. After being pushed to users, these intelligent materials are highly likely to be clicked, read, and searched, thus increasing the attractiveness of the novel materials to users. Furthermore, by randomly selecting novel titles and covers from a preset title slot library and image library to form random materials, and distributing these random materials, user interaction data is provided for the subsequent generation of intelligent materials. The entire method eliminates the need for manual selection or generation of titles and images, thereby automatically generating novel materials and reducing significant labor costs. Finally, the random and intelligent materials are sorted, and the second-to-last preset number of materials in the sorted list are distributed to users. Materials that rank higher are more likely to attract user clicks, increasing the click-through rate of novel material distribution.

[0048] In step 102, which involves obtaining multiple random materials of the novel based on the novel data, one possible implementation includes:

[0049] Step 201: Obtain the novel category.

[0050] Novel categories are derived from novel data.

[0051] Step 202: Select multiple novel titles from the title slot library and multiple novel covers from the image library according to the novel classification.

[0052] Multiple novel titles are selected from the title slot library based on the novel category. The novel titles must match the novel's genre. For example, if the novel is a romance novel, then the selected novel titles must all be related to romance novels.

[0053] Select multiple novel covers from the image library based on the novel's genre. The novel covers should match the novel's genre. For example, if the novel is a romance novel, then all the selected novel covers should be related to romance novels.

[0054] Step 203: Extract multiple novel titles from the novel data.

[0055] The novel data also includes novel synopses, from which multiple novel titles are extracted using a model.

[0056] Step 204: Randomly combine the multiple novel titles and multiple novel covers to obtain multiple random materials for the novel.

[0057] The system randomly combines multiple novel titles selected from the title slot library, multiple novel titles extracted from the novel synopsis, and multiple novel covers selected from the image library to obtain multiple random materials that match the novel type. This can generate a large number of random materials, which can be distributed to users to obtain user interaction data, and then further generate intelligent materials based on the user interaction data.

[0058] In step 202, selecting multiple novel titles from the title slot library according to the novel classification, in one possible implementation, includes:

[0059] Step 301: Randomly select multiple words from the corresponding category in the title word slot library according to the novel category.

[0060] Based on the novel's genre, multiple words are randomly selected from the corresponding genre in the title word slot library;

[0061] For example, if a novel is categorized as a romance novel, then multiple words are randomly selected from the corresponding romance novel category in the title keyword slot library.

[0062] Step 302: Randomly combine the multiple words to obtain multiple novel titles.

[0063] Multiple selected words are randomly combined to obtain multiple novel titles;

[0064] For example, by selecting four first-segment words "a", "b", "c" and "d" and two second-segment words "e" and "f" from the title word slot library, eight novel titles can be randomly generated: "ae", "af", "be", "bf", "ce", "cf", "de" and "df". This automatically generates multiple novel titles that conform to the novel category. On the one hand, it can provide suitable titles for combining random materials, and on the other hand, it can save a lot of manpower costs for manually combining or generating titles.

[0065] After distributing the second preset quantity of materials, which is the first in the sorted sequence, to the user in step 106, in one possible implementation, the method further includes:

[0066] Step 401: Determine whether the generation time of the distributed materials has exceeded the first preset time.

[0067] It is determined whether the time elapsed since the first distribution of the randomly generated or intelligent material exceeds the first preset time. In this embodiment, the first preset time is set to 14 days to ensure that the material has sufficient exposure. Exposure refers to the material's exposure count increasing by one after it is pushed to the user once.

[0068] Step 402: If the limit has been exceeded, determine whether the user interaction data after the material distribution meets the preset elimination conditions.

[0069] Preset elimination criteria can be set in advance based on multiple data points in user interaction data;

[0070] For example, if a material has more than 300 impressions but a click-through rate of less than 5%, it means that the material meets the preset elimination criteria.

[0071] For example, if a material has more than 300 impressions but a read rate of less than 2%, it means that the material meets the preset elimination criteria.

[0072] Step 403: If the conditions are met, the material is discarded.

[0073] If the conditions are met, the material is eliminated. By setting preset elimination conditions, materials that meet the preset elimination conditions can be eliminated, which can filter out some materials with poor user interaction data, so that distribution resources are not wasted and the multiple materials corresponding to the novel are more in line with the user's aesthetics. Since the intelligent materials are generated based on the data of all materials of the novel, the quality of the generated intelligent materials can be further improved.

[0074] In one possible implementation, it further includes:

[0075] Step 501: Update the parameters of the graph model based on user interaction data and novel data after the distribution of multiple random materials and multiple smart materials, multiple random materials and multiple smart materials.

[0076] In this embodiment, the graph model can be updated periodically based on the novel titles, novel images, user interaction data after distribution of the random and intelligent materials, novel categories, and novel content in the novel data. This can be set to 14 days, meaning the graph model is updated every 14 days based on these same data.

[0077] Step 502: Determine whether the quantity of smart materials is less than a third preset quantity, wherein the third preset quantity is less than a first preset quantity.

[0078] In this embodiment, the third preset quantity can be set to 2, which means determining whether the number of smart materials in the novel is less than 2.

[0079] Step 503: If the number is less than the third preset number, then use the updated graph model to generate multiple smart materials based on user interaction data and novel data after the distribution of multiple random materials and multiple smart materials, so that the number of smart materials in the novel reaches the first preset number.

[0080] If the number of smart materials for the novel is less than the third preset number, then the updated graph model is used to generate multiple smart materials based on the novel title in multiple random materials and multiple smart materials, the novel image in multiple random materials and multiple smart materials, the user interaction data after the distribution of multiple random materials and multiple smart materials, the novel category in the novel data, and the novel content in the novel data, so that the number of smart materials for the novel reaches the first preset number.

[0081] For example, in this embodiment, the first preset quantity is 5 and the third preset quantity is 2. The number of smart materials for a certain novel is 1, which is less than 2. Then, the updated graph model is used to generate 4 more smart materials for the novel so that the number of smart materials for the novel is equal to 5.

[0082] Step 504: Re-sort the multiple random materials and the first preset number of smart materials, and distribute the second preset number of materials at the top of the sorted list to the user.

[0083] Repeat steps 105 to 106 to sort the multiple random materials of the novel and the first preset number of smart materials, and distribute the first preset number of materials after sorting to the user.

[0084] The smart materials for each novel may be phased out. Therefore, when the number of smart materials for a novel is less than the third preset number, using the updated graph model to generate smart materials of better quality and more attractive to users, and increasing the number of smart materials for that novel to the first preset number, can ensure that sufficient user interaction data is obtained after the smart materials are distributed. Furthermore, since the quality of the smart materials has improved, the quality of the smart materials regenerated based on the data of these smart materials will also improve, greatly enhancing the scalability of the material generation method.

[0085] One embodiment of this disclosure provides a novel material distribution device, such as... Figure 2 As shown, the device includes:

[0086] Acquisition module 10 is used to acquire novel data;

[0087] Processing module 20 is used to obtain multiple random materials from the novel based on the novel data;

[0088] Distribution module 30: The user distributes multiple random materials from the novel to other users;

[0089] The generation module 40 is used to generate a first preset number of smart materials based on the multiple random materials, user interaction data after the multiple random materials are distributed, and novel data using a graph model.

[0090] The distribution module 30 is also used to sort multiple random materials and a first preset number of smart materials;

[0091] The distribution module 30 is also used to distribute the second preset quantity of materials that are first in the sorted sequence to the user.

[0092] The acquisition module is also used to obtain novel categories;

[0093] The processing module 20 is also used to select multiple novel titles from the title slot library and multiple novel covers from the image library according to the novel category;

[0094] The processing module 20 is also used to extract multiple novel titles from the novel data;

[0095] The processing module 20 is also used to randomly combine the multiple novel titles and multiple novel covers to obtain multiple random materials of the novel.

[0096] The processing module 20 is further configured to randomly select multiple words from the corresponding category in the title word slot library according to the novel category;

[0097] The processing module 20 is also used to randomly combine the multiple words to obtain multiple novel titles.

[0098] The processing module 20 is also used to determine whether the generation time of the distributed materials has exceeded the first preset time.

[0099] The processing module 20 is also used to determine whether the user interaction data after the material distribution meets the preset elimination conditions if the conditions have been exceeded.

[0100] The processing module 20 is also used to discard the material if it meets the requirements.

[0101] The generation module 40 is further configured to update the parameters of the graph model based on user interaction data and novel data after the distribution of multiple random materials and multiple smart materials and multiple random materials and multiple smart materials.

[0102] The processing module 20 is also used to determine whether the quantity of smart materials is less than a third preset quantity, wherein the third preset quantity is less than a first preset quantity;

[0103] The generation module 40 is further configured to, if the number is less than a third preset number, use the updated graph model to generate multiple smart materials based on user interaction data and novel data after the distribution of multiple random materials and multiple smart materials, multiple random materials and multiple smart materials, so that the number of smart materials in the novel reaches a first preset number.

[0104] The distribution module 30 is also used to reorder multiple random materials and a first preset number of smart materials and distribute the first preset number of materials after sorting to the user.

[0105] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0106] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0107] Figure 3 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0108] like Figure 3 As shown, device 600 includes a computing unit 601, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 602 or a computer program loaded from storage unit 608 into random access memory (RAM) 603. RAM 603 may also store various programs and data required for the operation of device 600. The computing unit 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0109] Multiple components in device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of monitors, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0110] The computing unit 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a novel material distribution method. For example, in some embodiments, the novel material distribution method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by the computing unit 601, one or more steps of the novel material distribution method described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the novel material distribution method by any other suitable means (e.g., by means of firmware).

[0111] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0113] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0115] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0116] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0117] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0118] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for distributing novel materials, comprising: Acquire novel data, which includes novels and novel categories; Based on the novel data, multiple random materials of the novel are obtained, including the novel title and the novel cover; Distribute multiple random materials from the novel to users; A first preset number of smart materials are generated using a graph model based on the multiple random materials, user interaction data after the distribution of the multiple random materials, and novel data. Sort multiple random materials and a first preset number of smart materials; Distribute the second-most preset quantity of materials after sorting to the user; Determine whether the generation time of the distributed materials has exceeded the first preset time. If the threshold has been exceeded, it is determined whether the user interaction data after the material is distributed meets the preset elimination conditions. The preset elimination conditions are set based on the number of impressions, click-through rate and read rate in the user interaction data. If the conditions are met, the material will be discarded. The graph model is updated with parameters based on user interaction data and novel data after the distribution of multiple random materials and multiple smart materials. The updated graph model generates smart materials with higher quality and user appeal than the graph model before the update. Determine whether the quantity of smart materials is less than a third preset quantity, wherein the third preset quantity is less than a first preset quantity; If the number is less than the third preset number, the updated graph model is used to generate multiple smart materials based on user interaction data and novel data after the distribution of multiple random materials and multiple smart materials, so that the number of smart materials in the novel reaches the first preset number. Reorder multiple random materials and a first preset number of smart materials, and distribute the first preset number of materials after sorting to the user; The step of generating a first preset number of smart materials using a graph model based on the multiple random materials, user interaction data after the distribution of the multiple random materials, and novel data includes: Heterogeneous graphs are constructed based on user interaction data, random materials, novels, novel titles, and novel covers. The metapath2vec++ algorithm is used to traverse five paths based on posterior duration weights: user-material-novel cover-material-user, user-material-novel title-material-user, user-material-novel-material-user, novel-material-novel title-material-novel, and novel-material-novel cover-material-novel. The novel title and novel cover with the highest similarity to the novel are then determined to obtain the intelligent material.

2. The method according to claim 1, wherein obtaining multiple random materials of the novel based on the novel data includes: Get novel categories; Based on the novel classification, select multiple novel titles from the title slot library and multiple novel covers from the image library; Multiple novel titles were extracted from the novel data; The multiple novel titles and multiple novel covers are randomly combined to obtain multiple random materials for the novel.

3. The method according to claim 2, wherein selecting multiple novel titles from the title slot library according to the novel classification includes: Multiple words are randomly selected from the corresponding category in the title word slot library based on the novel's classification. By randomly combining the aforementioned words, multiple novel titles can be obtained.

4. A novel material distribution device, comprising: The acquisition module is used to acquire novel data, which includes novels and novel categories; The processing module is used to obtain multiple random materials of the novel based on the novel data, wherein the random materials include the novel title and the novel cover; The distribution module allows users to distribute multiple random materials from the novel to other users. The generation module is used to generate a first preset number of smart materials based on the multiple random materials, user interaction data after the multiple random materials are distributed, and novel data using a graph model; The distribution module is also used to sort multiple random materials and a first preset number of smart materials; The distribution module is also used to distribute the second preset quantity of materials that are sorted first to the user; The processing module is also used to determine whether the generation time of the distributed materials has exceeded the first preset time. The processing module is also used to determine whether the user interaction data after the material distribution meets the preset elimination conditions if the limit has been exceeded. The preset elimination conditions are set according to the display volume, click rate and read rate in the user interaction data. The processing module is also used to discard the material if it meets the requirements; The generation module is also used to update the parameters of the graph model based on user interaction data and novel data after the distribution of multiple random materials and multiple smart materials, and the updated graph model generates smart materials with higher quality and user appeal than the graph model before the update. The processing module is also used to determine whether the quantity of smart materials is less than a third preset quantity, wherein the third preset quantity is less than a first preset quantity; The generation module is also used to generate multiple smart materials based on user interaction data and novel data after the distribution of multiple random materials and multiple smart materials, and multiple random materials and multiple smart materials, using the updated graph model to generate multiple smart materials so that the number of smart materials in the novel reaches the first preset number if the number is less than the third preset number. The distribution module is also used to reorder multiple random materials and a first preset number of smart materials and distribute the first preset number of materials after sorting to the user. The generation module is further configured to construct a heterogeneous graph based on user interaction data, random materials, novels, novel titles, and novel covers; and to use the metapath2vec++ algorithm to traverse five paths based on posterior time weights: user-material-novel cover-material-user, user-material-novel title-material-user, user-material-novel-material-user, novel-material-novel title-material-novel, and novel-material-novel cover-material-novel, to determine the novel title and novel cover with the highest similarity to the novel, thereby obtaining the intelligent material.

5. The apparatus according to claim 4, comprising: The acquisition module is also used to obtain novel categories; The processing module is also used to select multiple novel titles from the title slot library and multiple novel covers from the image library according to the novel category; The processing module is also used to extract multiple novel titles from the novel data; The processing module is also used to randomly combine the multiple novel titles and multiple novel covers to obtain multiple random materials for the novel.

6. The apparatus according to claim 5, comprising: The processing module is also used to randomly select multiple words from the corresponding category in the title word slot library according to the novel category; The processing module is also used to randomly combine the multiple words to obtain multiple novel titles.

7. The apparatus according to claim 4, comprising: The processing module is also used to determine whether the generation time of the distributed materials has exceeded the first preset time. The processing module is also used to determine whether the user interaction data after the material distribution meets the preset elimination conditions if the conditions have been exceeded. The processing module is also used to discard the material if it meets the requirements.

8. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.

9. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-3.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-3.

Images