Intelligent processing method and system for new media data

Abstract

The application relates to the field of information technology, in particular to an intelligent processing method and system for new media data. The method comprises the following steps: reading historical new media material data; analyzing the historical new media material data, calculating an availability estimation value of the historical new media material, and sorting and screening the historical new media resource according to the availability estimation value; storing the analyzed historical new media material data in a classified manner, and establishing a multidimensional index of the historical new media material data; receiving a new media content generation demand, converting the new media content generation demand into a new media material matching condition; screening and sorting new media materials based on the new media material matching condition, and selecting the first N new media material data as basic new media material data; and fusing a theme content based on the basic new media material, generating multi-form new media content, and realizing intelligent processing of high-efficiency, high-quality and self-optimizable new media content.

Description

Technical Field

[0001] Several embodiments of this specification relate to the field of information technology, specifically to intelligent processing methods and systems for new media data. Background Technology

[0002] With the rapid development of new media technologies, intelligent processing methods are becoming increasingly important in content generation, recommendation, and distribution. However, existing intelligent processing technologies for new media still have certain shortcomings in historical material analysis, theme generation, and multimodal content fusion, affecting the efficiency of content production.

[0003] Publication number CN118349671A presents a multi-platform new media information source comprehensive tag learning system. It employs deep learning-based natural language processing technology to semantically understand new media information source data, mine key information and content features, and intelligently generate content theme tags. However, this technical solution primarily focuses on tag generation, lacking comprehensive analysis and classification management of historical materials, and failing to effectively combine historical data to generate new content themes. Furthermore, its application scenarios are concentrated on single-modal text content processing, exhibiting limitations in the fusion of multi-modal content such as text, images, and videos.

[0004] Patent CN110765359A discloses a method for recommending new media content. This patent uses a semantic neural network to improve a three-layer attention model by introducing external knowledge and a feedback mechanism, thereby achieving intelligent recommendation of new media content. However, this technical solution focuses on optimizing the content recommendation algorithm and does not involve in-depth analysis and reuse of historical new media material data, thus affecting the ability to quickly generate new promotional content based on specific themes. Summary of the Invention

[0005] This application provides an intelligent processing method and system for new media data, which can effectively solve the problems of low content production efficiency, uncontrollable quality, lack of intelligent analysis and data-driven decision-making, and inability to self-iterate and optimize in the existing technology.

[0006] Firstly, this application provides an intelligent processing method for new media data, including the following steps:

[0007] Read historical new media material data, which includes at least one of text, images, and videos;

[0008] The historical new media material data is analyzed, multiple core features of the historical new media material data are extracted, and multiple core features are aggregated to calculate the usability estimate of the historical new media material. The historical new media resources are then sorted and filtered according to the usability estimate.

[0009] The parsed historical new media material data is classified and stored according to the core features, and a multi-dimensional index of the historical new media material data is established based on the core features;

[0010] Receive new media content generation requests and convert the new media content generation requests into new media material matching conditions;

[0011] Based on the new media material matching conditions, the new media material data is filtered and sorted, and the top N new media material data are selected as the basic new media material data.

[0012] Based on the aforementioned basic new media materials and thematic content integration requirements, various forms of new media content are generated.

[0013] By adopting the above technical solution, the system achieves automatic parsing, multi-dimensional index construction, and precise matching of historical materials, replacing the cumbersome traditional method of manually searching and filtering materials. Simultaneously, the system can intelligently generate various forms of new media content based on the content framework of historical materials, eliminating the need for operations personnel to conceive content structures and design layouts from scratch, thus significantly shortening the overall cycle from request submission to content production. This method effectively addresses the pain points of manual production methods, such as "long cycles, low efficiency, and difficulty in adapting to high-frequency content demands," reducing reliance on the personal experience and continuous effort of operations personnel.

[0014] Furthermore, the core features include at least one of the following: the relevance of the material to the preset theme, the adaptability of the material to the theme, and the historical click volume of the material. The steps for obtaining the relevance of the material to the preset theme include: performing natural language processing on the material content and extracting semantic features, calculating the similarity with the keywords of the preset theme, and obtaining the relevance value.

[0015] The steps for obtaining the theme suitability of the material include: judging the consistency between the theme category of the material and the preset theme based on the classification model; if the theme category of the material is consistent with the preset theme, combining the integrity score and clarity score of the material content, a comprehensive score of the theme suitability of the material is obtained by weighted calculation; the comprehensive score is compared with a preset threshold; if it is higher than the threshold, the material is marked as a high-suitability material.

[0016] The steps for obtaining the historical click count of the material include: obtaining it based on the statistical data of the material's historical exposure and clicks, and adjusting it using a time decay factor.

[0017] Furthermore, the multi-dimensional index includes: topic index, association type index, sentiment index, and availability index.

[0018] Furthermore, the steps to transform the content generation requirements into new media material matching conditions include:

[0019] Refine the vague themes in the requirements;

[0020] The default setting for content format requirements is based on the proportion of historically high-click-through-rate content.

[0021] Transform the requirements into structured matching conditions.

[0022] Furthermore, the first N new media material data points selected as the basic new media material data include:

[0023] Select new media materials with a theme relevance of ≥80%;

[0024] Select new media materials with a usability estimate of ≥0.6;

[0025] Sort by availability estimate and dynamically adjust thresholds to supplement new media materials.

[0026] Furthermore, the thematic content based on the aforementioned basic new media material integration requirements includes:

[0027] Extract the framework features of the basic materials;

[0028] Generate a draft of new media content by filling in the theme content according to the framework;

[0029] Optimize the richness of associations and the degree of emotional matching of the initial draft of new media content.

[0030] Furthermore, it also includes content quality detection, which includes policy compliance detection, text error detection, and semantic similarity detection. The policy compliance detection, text error detection, and semantic similarity detection are weighted and summed to obtain a comprehensive score for the quality of the generated content.

[0031] Furthermore, it also includes an evaluation of the predicted effects of generated content, specifically including:

[0032] Calculate the estimated click-through rate of the generated new media content, and decide whether to re-screen the materials based on the estimated click-through rate value. The estimated click-through rate is determined by weighting the similarity of the layout, the relevance of the content, and the similarity of the main body of the new media materials.

[0033] Furthermore, it also includes: using the generated new media content as new historical new media material data, updating the historical new media material data, and updating the multi-dimensional index.

[0034] Secondly, embodiments of this specification provide an intelligent processing system for new media data, characterized in that it includes:

[0035] The data acquisition module reads historical new media material data, which includes at least one of text, images, and videos.

[0036] The data parsing module parses the historical new media material data, extracts multiple core features of the historical new media material data according to the preset theme, aggregates the multiple core features, calculates the usability estimate of the historical new media material, and sorts and filters the historical new media resources according to the usability estimate.

[0037] The data storage and indexing module classifies and stores the parsed historical new media material data according to the core features, and establishes a multi-dimensional index of the historical new media material data based on the core features.

[0038] The demand receiving and conversion module receives new media content generation demands and converts these demands into new media material matching conditions.

[0039] The matching and filtering module filters and sorts new media material data based on the new media material matching conditions, and selects the top N new media material data as the basic new media material data;

[0040] The data generation module generates new media content in various forms based on the basic new media materials and the theme content required.

[0041] The beneficial effects of the technical solutions provided in some embodiments of this specification include at least the following:

[0042] 1. This application replaces the tedious process of manually searching and screening materials by analyzing historical materials, constructing multi-dimensional indexes, and accurately matching them. At the same time, it intelligently generates multi-format content based on the historical material framework, eliminating the need for operations personnel to build content structures and layouts from scratch. This significantly shortens the cycle from request to content generation, effectively solving the problems of time-consuming, inefficient, and difficult-to-handle high-frequency content demands under the manual production model, and reducing the dependence on the experience and effort of operations personnel.

[0043] 2. This application employs a multi-stage quality inspection mechanism, which covers basic risk points such as policy compliance and textual errors to avoid issues such as conflicts with unpublished policies and inappropriate wording. At the same time, it uses pre-evaluation of the expected effects to judge the attractiveness of the content in advance, reducing the probability of publishing low-quality new media content. This overcomes the limitations of existing technologies that rely on manual verification of quality and make it difficult to avoid risks in advance, thus ensuring the stability and compliance of content output.

[0044] 3. This application feeds back the actual operational data of the output content to the system to update the weighting coefficients for calculating material availability and estimated click-through rate, and incorporates new content into the historical material library to enrich the data foundation. This iterative logic addresses the shortcomings of existing technologies, such as "lack of learning ability and easy homogenization with long-term use."

[0045] Other features and advantages of various embodiments of this specification will be further revealed in the following detailed description and accompanying drawings. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this specification, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of the intelligent processing method and system interface for new media data provided in the embodiments of this specification.

[0048] Figure 2 This is a schematic flowchart of the intelligent processing method for new media data provided in the embodiments of this specification.

[0049] Figure 3 This is a schematic diagram illustrating the process of obtaining the relevance between the materials provided in the embodiments of this specification and the preset theme.

[0050] Figure 4 This is a schematic diagram of an intelligent processing system for new media data provided in the embodiments of this specification.

[0051] Figure 5 A schematic diagram of an electronic device provided in an embodiment of this specification. Detailed Implementation

[0052] The technical solutions of the embodiments of this specification will be explained and described below with reference to the accompanying drawings. However, the following embodiments are only preferred embodiments of this specification and not all of them. Other embodiments obtained by those skilled in the art based on the embodiments in the implementation methods without creative effort are all within the protection scope of this specification.

[0053] The terms "first," "second," "third," etc., in the description, claims, and accompanying drawings are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0054] In the following description, terms such as “inner,” “outer,” “upper,” “lower,” “left,” and “right” are used only to facilitate the description of the embodiments and to simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this specification.

[0055] This specification provides an intelligent processing method and system for new media data through its embodiments. Please refer to [link / reference]. Figure 1 , Figure 1 The diagram shown is an interface diagram of a new media data intelligent processing method and system.

[0056] On the one hand, the embodiments of this specification first provide an intelligent processing method for new media data, please refer to... Figure 2 The steps include:

[0057] Step S101: Read historical new media material data, which includes at least one of text, images, and videos. For example, export all content published in the past three years from the backend of a certain account's WeChat official account, Weibo, Douyin, etc., including: text: scenic spot introductions, policy interpretations, event notices, etc.; images: actual photos of scenic spots, photos of cultural activities, poster designs, etc.; videos: tourism promotional videos, festival event recordings, citizen interviews, etc.

[0058] Step S102: Use pre-trained natural language processing and image recognition models to analyze historical new media material data, extracting multiple core features from the historical new media material data. The core features include at least one of the following: the relevance of the material to the preset theme, the theme suitability of the material, and the historical click count. Aggregate these core features to calculate the estimated availability of the historical new media materials, and sort and filter the historical new media resources based on the estimated availability. For example, set α=0.4 (weight for the relevance of the material to the preset theme), β=0.3 (weight for theme suitability), and γ=0.3 (weight for historical click count). If a certain article on "Spring Festival Lantern Festival" has 100,000 historical clicks (normalized H=0.8), a suitability of A=0.9 with the preset theme "Festival," and a relevance of R=0.7 with the current time, then:

[0059] The estimated availability value U = 0.4 × 0.7 + 0.3 × 0.9 + 0.3 × 0.8 = 0.28 + 0.27 + 0.24 = 0.79.

[0060] For details, please refer to the appendix. Figure 3The steps for obtaining the relevance between the material and the preset theme include: using an AI model to perform natural language processing on the material content and extract semantic features, calculating the similarity with the keywords of the preset theme to obtain a relevance value; determining the theme suitability of the material, based on a classification model to determine the consistency between the theme category to which the material belongs and the preset theme, and if the theme category to which the material belongs is consistent with the preset theme, combining the integrity score and clarity score of the material content, and calculating a comprehensive score for the theme suitability of the material through weighted calculation; comparing the comprehensive score with a preset threshold, and if it is higher than the threshold, the material is marked as a highly suitable material; for example, the preset theme keywords are Mid-Autumn Festival, reunion, and happiness. Among the new media material data, there is a new media article titled "Celebrating the Mid-Autumn Festival and Family Reunion". The AI ​​model performs natural language processing on the article and extracts key semantic features from the text, such as "family", "reunion", "moon viewing", "mooncake", "balcony", "dinner", and "laughter". The similarity between the extracted semantic feature set and the preset theme keyword set is calculated. Due to the presence of a large number of highly related words with overlap, the relevance value of this material is very high, which is 0.92. Therefore, it is marked as a highly suitable material.

[0061] Historical click counts are obtained based on historical exposure and click data of the materials, and adjusted using a time decay factor.

[0062] Step S103: Classify and store the parsed historical new media material data according to the core features, and establish a multi-dimensional index for the historical new media material data based on the core features; the multi-dimensional index includes: topic index, sentiment index, association type index, and availability index. For example, the topic index includes "festival", "policy", and "scenic spot"; the sentiment index includes "positive" and "neutral"; the association type index includes "person association" and "policy association"; and the availability index is stored in segments according to U value (e.g., high availability: U≥0.7).

[0063] Step S104: Receive new media content generation requirements and convert the new media content generation requirements into new media material matching conditions; the step of converting the content generation requirements into new media material matching conditions includes:

[0064] Refine the vague themes in the requirements;

[0065] The default setting for content format requirements is based on the proportion of historically high-click-through-rate content.

[0066] The requirements are transformed into structured matching conditions. For example, an operator inputs the requirement: "Publish a post about 'Mid-Autumn Festival cultural and tourism activities,' in the form of a text and image message." The system automatically refines the topic, breaking it down into "Mid-Autumn Festival," "Culture and Tourism," "Activities," and "Local Features."

[0067] Then set the content format requirements: based on historical data, graphic and text messages have a higher click-through rate, so this format is used by default; finally, generate matching conditions: the topic tag contains "Mid-Autumn Festival" and U≥0.6.

[0068] Step S105: Based on the new media material matching conditions, filter and sort the new media material data, and select the top N new media material data as the basic new media material data; selecting the top N new media material data as the basic new media material data includes:

[0069] Select new media materials with a theme relevance of ≥80%;

[0070] Select new media materials with a usability estimate of ≥0.6;

[0071] Sort by availability estimate and dynamically adjust thresholds to supplement new media materials.

[0072] For example, the system filters out all materials in the library that meet the theme of "Mid-Autumn Festival" and have an estimated usability value U≥0.6. A total of 20 materials are selected, sorted from high to low according to the estimated usability value U, and the top 5 are selected as the basic materials.

[0073] Step S106: Based on the basic new media material integration requirements and theme content, generate new media content in multiple formats. The basic new media material integration requirements and theme content include:

[0074] Extract the framework features of the basic materials;

[0075] Generate a first draft by filling in the theme content according to the framework;

[0076] The initial draft was optimized for richness of associations and improved sentiment matching. For example, based on five selected articles, their framework features were extracted, and specific content related to the Mid-Autumn Festival event was added to generate the initial draft. Subsequently, the initial draft underwent sentiment optimization and enhanced richness of associations.

[0077] In some embodiments, for the generated new media content, content quality testing and pre-publication effect evaluation can be performed. If the pre-publication effect score is high, the new media content can be directly published. The generated content quality testing includes: policy compliance testing, text error detection, and semantic similarity testing. Policy compliance testing detects whether the content contains sensitive words or conflicts with the latest policies; text error detection checks for typos and punctuation errors; semantic similarity testing compares the content with historical content to ensure novelty. The policy compliance testing, text error detection, and semantic similarity testing are weighted and summed to obtain a comprehensive quality score for the generated content. For example, if the weight coefficient for policy compliance of an article titled "Celebrating National Day and Mid-Autumn Festival" is set to 0.5, and the score to 0.9; the weight coefficient for text accuracy is set to 0.2, and the score to 0.95; and the weight coefficient for semantic novelty is set to 0.5, and the score to 0.8; then the comprehensive score Q is:

[0078] Q = 0.5 × 0.9 + 0.2 × 0.95 + 0.3 × 0.8 = 0.45 + 0.19 + 0.24 = 0.88. The overall score is higher than the threshold of 0.7, passing the test. Furthermore, the evaluation of the generated content's predicted effect specifically includes: calculating the predicted click-through rate (C) of the generated new media content; and determining whether to re-screen materials based on the predicted C. The predicted C is determined by the layout similarity S of the new media material content. p Content relevance S c Subject similarity S t Weighted determination, C = λ × S p +μ×S c +ν×S t Among them, S p For layout similarity, S c To ensure the content is closely related, S t Let λ be the subject similarity and λ be the layout similarity S. p The weighting coefficient, μ, represents the content relevance S. c The weighting coefficient, ν, represents the subject similarity S. t Weighting coefficients;

[0079] Given λ=0.4, μ=0.4, ν=0.2, if Sp=0.85, Sc=0.9, St=0.8, then:

[0080] C = 0.4 × 0.85 + 0.4 × 0.9 + 0.2 × 0.8 = 0.34 + 0.36 + 0.16 = 0.86. The result 0.86 is higher than the threshold of 0.75, so the generated new media content can be selected and published.

[0081] In some embodiments, the intelligent processing method for new media data further includes updating the historical new media material data and the multi-dimensional index by treating the generated new media content as new historical new media material data.

[0082] On the other hand, embodiments of this specification also provide an intelligent processing system for new media data; please refer to [link / reference]. Figure 4 ,include:

[0083] The data acquisition module 100 acquires historical new media material data, which includes at least one of text, images, and videos.

[0084] The data parsing module 200 parses the historical new media material data, extracts the core features of the historical new media material data, the core features include the relevance of the material to the preset theme, the theme adaptability of the material, and the historical click volume of the material, and performs a weighted summation of the relevance of the material to the preset theme, the theme adaptability of the material, and the historical click volume of the material to calculate the estimated availability of the material;

[0085] The data storage and indexing module 300 classifies and stores the parsed historical new media material data according to the core features, and establishes a multi-dimensional index for the historical new media material data;

[0086] The demand receiving and conversion module 400 receives new media content generation demands and converts the content generation demands into new media material matching conditions.

[0087] The matching and filtering module 500 filters and sorts new media material data based on the new media material matching conditions, and selects the top N new media material data as the basic new media material data.

[0088] The data generation module 600 generates new media content in multiple formats based on the basic new media materials and the theme content of the integration requirements.

[0089] Please see Figure 5 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this specification.

[0090] like Figure 5As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. The communication bus 1102 can be used to connect and communicate with the aforementioned components. The user interface 1103 may include buttons, and optionally may include standard wired or wireless interfaces. The network interface 1104 may include, but is not limited to, a Bluetooth module, an NFC module, or a Wi-Fi module. The processor 1101 may include one or more processing cores. The processor 1101 connects to various parts within the electronic device 1100 using various interfaces and lines, and performs various functions of the routing device and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105, and by calling data stored in the memory 1105. Optionally, the processor 1101 may be implemented using at least one hardware form of DSP, FPGA, or PLA. The processor 1101 may integrate one or more combinations of CPU, GPU, and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content that the display screen needs to show; and the modem is used for wireless communication.

[0091] It is understandable that the aforementioned modem may not be integrated into the processor 1101, but may be implemented using a separate chip.

[0092] The memory 1105 may include RAM or ROM. Optionally, the memory 1105 may include a non-transitory computer-readable medium. The memory 1105 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 1105 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1105 may also be at least one storage device located remotely from the aforementioned processor 1101. As a computer storage medium, the memory 1105 may include an operating system, a network communication module, a user interface module, and application programs. The processor 1101 may be used to call the application programs stored in the memory 1105 and execute the methods in the above-described embodiments.

[0093] This specification also provides a computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform multiple steps as described in the above embodiments. If the constituent modules of the above-described electronic device are implemented as software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0094] This specification also provides a computer program product, including a computer program that, when executed by a processor, implements the multiple steps described in the above embodiments.

[0095] Where there is no conflict, the technical features in this embodiment and implementation scheme can be combined arbitrarily.

[0096] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes multiple computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center integrating multiple available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital versatile discs (DVDs)), or semiconductor media (e.g., solid-state drives (SSDs)).

[0097] When implemented through hardware or firmware, the aforementioned method flow is programmed into the hardware circuit to obtain the corresponding hardware circuit structure and achieve the corresponding function. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit, whose logic function is determined by the user programming the device. Designers can program a digital system onto a PLD themselves, eliminating the need for chip manufacturers to design and fabricate dedicated integrated circuit chips. Furthermore, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, similar to the software compiler used in program development. The original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There is not just one HDL, but many. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of the aforementioned hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logic method flow can be easily obtained.

[0098] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Any modifications and improvements made by those skilled in the art to the technical solutions of this specification without departing from the spirit of this specification should fall within the protection scope defined by the claims of this specification.

Claims

1. A method for intelligent processing of new media data, characterized in that, The method comprises the steps of: reading historical new media material data, the historical new media material data at least including one of text, picture and video; analyzing the historical new media material data, extracting a plurality of core features of the historical new media material data according to a preset theme, aggregating the plurality of core features, calculating an availability estimation value of the historical new media material, and sorting and screening the historical new media resource according to the availability estimation value; storing the analyzed historical new media material data according to the core features, and establishing a multi-dimensional index of the historical new media material data based on the core features; receiving a new media content generation requirement, and converting the new media content generation requirement into a new media material matching condition; screening and sorting new media material data based on the new media material matching condition, and selecting the top N new media material data as basic new media material data; fusing the theme content based on the basic new media material, and generating multi-form new media content, wherein the fusing the theme content based on the basic new media material comprises: extracting frame features of the basic new media material; filling the theme specific content according to the frame to generate a new media content preliminary draft; optimizing the new media content preliminary draft in terms of association richness and emotion matching degree.

2. The method of claim 1, wherein, The core features at least include one of the following: material and preset theme association degree, material theme adaptation degree, historical material click volume; The association degree of the material and the preset theme comprises the steps of: performing natural language processing on the material content and extracting semantic features, and calculating the similarity of the keywords of the material and the preset theme to obtain the association degree value; The acquisition of the material theme adaptation degree comprises the steps of: judging the consistency of the theme category of the material and the preset theme based on a classification model, if the theme category of the material is consistent with the preset theme, combining the completeness score and the clarity score of the material content, and obtaining a comprehensive score of the material theme adaptation degree through weighted calculation; comparing the comprehensive score with a preset threshold value, if the comprehensive score is higher than the threshold value, the material is marked as a high adaptation degree material; The historical material click volume is obtained according to the historical exposure and click data statistics of the material. 3.The method of claim 1, wherein, The multi-dimensional index includes: theme index, emotion index, association type index and availability index.

4. The method of claim 1, wherein, The step of converting the content generation requirement into a new media material matching condition comprises: refining the fuzzy theme in the requirement; defaulting to set the content form requirement according to the historical high click volume content form proportion; converting the requirement into a structured matching condition.

5. The method of claim 1, wherein, The step of selecting the top N new media material data as basic new media material data comprises: screening new media materials with a theme matching degree of ≥80%; screening new media materials with an availability estimation value of ≥0.6; sorting the new media materials according to the availability estimation value and dynamically adjusting the threshold value to supplement the new media materials.

6. The method of claim 1, wherein, Further comprising a generated content quality detection, the generated content quality detection comprising: policy compliance detection, text error detection, semantic similarity detection, weighted sum of the policy compliance detection, text error detection and semantic similarity detection, and further obtaining a generated content quality comprehensive score.

7. The method of claim 1, wherein, Further comprising a generated content estimated effect evaluation, specifically comprising: The estimated click rate of the newly generated new media content is calculated, and it is determined whether to re-screen the new media material according to the estimated click rate value. The estimated click rate is determined by the layout similarity, content tightness, and subject similarity of the new media material content.

8. The method of claim 1, wherein, Also includes: The generated new media content is updated to the historical new media material data and the multi-dimensional index is updated.

9. An intelligent processing system of new media data, characterized by, Including: The data acquisition module reads the historical new media material data, and the historical new media material data at least includes one of text, picture and video; The data analysis module analyzes the historical new media material data, extracts a plurality of core features of the historical new media material data according to a preset theme, aggregates the plurality of core features, calculates an availability estimation value of the historical new media material, and sorts and filters the historical new media resource according to the availability estimation value; The data storage and index module classifies and stores the analyzed historical new media material data according to the core features, and establishes a multi-dimensional index of the historical new media material data based on the core features; The demand receiving and conversion module receives the new media content generation demand and converts the new media content generation demand into a new media material matching condition; The matching and screening module screens and sorts the new media material data based on the new media material matching condition, and selects the top N new media material data as the basic new media material data; The data generation module generates multi-form new media content based on the basic new media material fusion demand theme content, wherein the basic new media material fusion demand theme content includes: Extracting the frame features of the basic new media material; Filling the theme specific content according to the frame to generate a new media content draft; Optimizing the correlation richness and emotion matching degree of the new media content draft.

Images