A copywriting content generation method and device, computer equipment and storage medium

Abstract

The application discloses a copywriting content generation method and device, computer equipment and a storage medium, belonging to the technical field of artificial intelligence. First, the key words in the requirement document are obtained and semantic analysis is performed to generate semantic representation of the key words. Then, the key words are mapped to a pre-constructed product knowledge graph, the semantic association between the key words and knowledge nodes is identified through graph reasoning to obtain deep semantic information related to copywriting generation. Subsequently, the format information of the target copywriting is extracted from the requirement document, and the control rules in the format rule engine are combined to ensure that the copywriting meets the requirements in structure and style. Finally, based on the semantic association representation and the format control rules, a pre-trained large language model is guided to generate copywriting that is highly matched with the requirements, coherent in content and meets the format requirements. The application also relates to the field of blockchain technology, and the copywriting content is stored on a blockchain node. The application improves the practicality and flexibility of automatic generation of copywriting content.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to a method, apparatus, computer equipment and storage medium for generating copy content. Background Art

[0002] With the rapid advancement and widespread penetration of social media technology, companies are increasingly demanding diversified marketing strategies. To broaden their customer base and attract more potential customers, companies urgently need to carefully plan a variety of promotional materials, including creative copy for holiday offers and promotional campaigns, as well as eye-catching product images, in order to stand out in the fierce market competition. For example, for insurance products, companies need to customize product copy and imagery for holiday promotions to accurately convey the advantages of insurance and attract the attention and trust of potential customers.

[0003] The traditional copywriting process relies heavily on the experience and subjective judgment of professionals. These professionals must meticulously plan and organize content based on established goals, content categories, and specific needs. This manual approach has limitations in terms of time and resource allocation. In recent years, significant breakthroughs in AI-powered text and image generation have made it possible to automatically create copy and images, significantly improving creative efficiency. However, current automated copywriting technologies still have limitations in terms of creativity, customization, and adaptability to the diverse styles of different communication platforms. Summary of the Invention

[0004] The purpose of the embodiments of this application is to propose a copy content generation method, device, computer equipment and storage medium to solve the technical problem that the current current copy content automatic generation technology still has certain limitations in terms of creativity, personalized customization and adaptation to the style requirements of different communication platforms.

[0005] In order to solve the above technical problems, the present application provides a method for generating copy content, which adopts the following technical solutions:

[0006] A method for generating copy content, comprising:

[0007] Obtain the requirements document for the content to be generated and read the requirements keywords in the requirements document;

[0008] Perform semantic analysis on demand keywords to obtain keyword semantic representation;

[0009] Obtain a pre-built product knowledge graph and map the keyword semantic representation to the product knowledge graph;

[0010] In the product knowledge graph, the semantic association between the demand keywords and the knowledge nodes of the product knowledge graph is identified based on the keyword semantic representation through graph reasoning, and a semantic association representation is obtained.

[0011] The script format corresponding to the script content to be generated is obtained from the demand document, and the format control rule matched with the script format is obtained in the preset format rule engine.

[0012] Based on the semantic association representation and the format control rule, the pre-trained large language model is guided to generate the script content matched with the demand document.

[0013] Further, the product knowledge graph is obtained, and the step of mapping the keyword semantic representation to the product knowledge graph specifically includes:

[0014] A feature mapping space is constructed, and a plurality of feature points are created in the feature mapping space;

[0015] The knowledge nodes of the product knowledge graph are identified, and the knowledge nodes of the product knowledge graph are paired with the feature points in the feature mapping space to obtain a knowledge feature pairing result;

[0016] According to the knowledge feature pairing result, the product knowledge graph is imported into the feature mapping space.

[0017] Further, in the product knowledge graph, the semantic association between the demand keywords and the knowledge nodes of the product knowledge graph is identified based on the keyword semantic representation through graph reasoning, and a semantic association representation is obtained. The step specifically includes:

[0018] The knowledge nodes of the product knowledge graph are subjected to semantic analysis to obtain a knowledge node semantic representation;

[0019] Based on the keyword semantic representation and the knowledge node semantic representation, it is judged whether there is a semantic association between the demand keywords and the knowledge nodes;

[0020] If there is a semantic association between the demand keywords and the knowledge nodes, the semantic association feature is extracted, and a semantic association representation is generated.

[0021] Further, based on the keyword semantic representation and the knowledge node semantic representation, it is judged whether there is a semantic association between the demand keywords and the knowledge nodes. The step specifically includes:

[0022] The semantic similarity between the keyword semantic representation and the knowledge node semantic representation is calculated;

[0023] The semantic similarity is compared with a preset similarity threshold;

[0024] When the semantic similarity is greater than or equal to the similarity threshold, it is determined that there is a semantic association between the demand keywords and the knowledge nodes.

[0025] When the semantic similarity is less than the similarity threshold, it is determined that there is no semantic association between the demand keyword and the knowledge node.

[0026] Furthermore, based on the semantic association representation and format control rules, the steps of guiding the pre-trained large language model to generate copy content that matches the requirement document include:

[0027] Input semantic association representation and format control rules into the pre-trained large language model;

[0028] Traverse the text library of the large language model and identify the target text that matches the semantic association representation;

[0029] Combine the target text according to the format control rules to obtain the copy content that matches the requirement document.

[0030] Furthermore, before the step of guiding the pre-trained large language model to generate copy content matching the requirement document based on the semantic association representation and format control rules, the following steps are also included:

[0031] Acquire training sample data, wherein the training sample data includes historical copy keywords, historical copy format control rules, and historical copy content;

[0032] Perform semantic analysis on historical copy keywords to obtain semantic representation of historical copy keywords;

[0033] Map the semantic representation of historical copywriting keywords into the product knowledge graph;

[0034] In the product knowledge graph, based on the semantic representation of historical copy keywords, the semantic association between historical copy keywords and knowledge nodes of the product knowledge graph is identified through graph reasoning to obtain the historical semantic association representation;

[0035] Inputting the historical semantic association representation and the historical copy format control rules into a preset initial large language model, so that the initial large language model learns the historical semantic association representation and the historical copy format control rules and outputs the predicted copy content;

[0036] Compare the predicted content with the historical content to obtain the model prediction error;

[0037] The initial large language model is iteratively updated according to the model prediction error until the model is fitted to obtain a pre-trained large language model.

[0038] Furthermore, after obtaining the requirement document of the content to be generated and reading the requirement keywords in the requirement document, the method further includes:

[0039] Classify the demand keywords, and group the demand keywords according to the keyword classification results to obtain several keyword groups;

[0040] Assign corresponding keyword group weight to each keyword group;

[0041] The steps of performing semantic analysis on demand keywords and obtaining semantic representation of keywords include:

[0042] For each demand keyword, identify the keyword group to which the demand keyword belongs, and obtain the keyword group weight corresponding to the demand keyword;

[0043] Perform semantic analysis on the demand keywords, and use the corresponding keyword group weights to weight the semantic analysis results of the demand keywords to obtain keyword semantic representation.

[0044] In order to solve the above technical problems, the present application also provides a copywriting content generation device, which adopts the following technical solutions:

[0045] A copy content generating device, comprising:

[0046] The keyword reading module is used to obtain the demand document of the content to be generated and read the demand keywords in the demand document;

[0047] Semantic analysis module, used to perform semantic analysis on demand keywords and obtain keyword semantic representation;

[0048] The semantic mapping module is used to obtain the pre-built product knowledge graph and map the keyword semantic representation into the product knowledge graph;

[0049] The semantic association module is used to identify the semantic association between demand keywords and knowledge nodes in the product knowledge graph through graph reasoning based on keyword semantic representation in the product knowledge graph, and obtain the semantic association representation;

[0050] The control rule module is used to obtain the document format corresponding to the content of the document to be generated from the demand document, and obtain the format control rules that match the document format from the preset format rule engine;

[0051] The copywriting generation module is used to guide the pre-trained large language model to generate copywriting content that matches the requirement document based on semantic association representation and format control rules.

[0052] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0053] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the copy content generation method as described in any one of the above items are implemented.

[0054] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0055] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the copywriting content generation method as described in any one of the above.

[0056] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0057] The present application discloses a method, device, computer equipment and storage medium for generating copy content, and belongs to the field of artificial intelligence technology. This application addresses the limitations of existing automatic copy generation technologies in terms of creativity, personalized customization and platform adaptability. By combining semantic analysis, knowledge graph reasoning and format control rules, it guides a large language model to generate copy, so that the generated content is not only more semantically accurate, but also adaptable to different demand scenarios and communication platforms. The introduction of knowledge graphs improves the professionalism and information relevance of copy, and format control rules ensure that the structure and style of the copy meet the requirements of specific platforms. Through these optimizations, more personalized, creative and multi-platform style copy can be generated, which improves the practicality and flexibility of automatic generation of copy content. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0059] Figure 1 shows an exemplary system architecture diagram in which the present application can be applied;

[0060] Figure 2 A flowchart of an embodiment of a method for generating copy content according to the present application is shown;

[0061] Figure 3 A schematic structural diagram of an embodiment of a device for generating text content according to the present application is shown;

[0062] Figure 4A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0064] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0065] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0066] like Figure 1 As shown, system architecture 100 may include a terminal device 101, a network 102, and a server 103. Terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. Network 102 is a medium for providing a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0067] The user can use the terminal device 101 to interact with the server 103 via the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0068] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0069] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0070] It should be noted that the copy content generation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the copy content generation device is generally set in the server / terminal device.

[0071] It should be understood that Figure 1 The numbers of terminal devices, networks and servers in the embodiment are merely illustrative. The above system may have any number of terminal devices, networks and servers according to implementation requirements.

[0072] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for generating text content according to the present application. The method for generating text content includes the following steps:

[0073] S201, obtaining a requirement document of the content to be generated, and reading the requirement keywords in the requirement document.

[0074] Specifically, the system first receives the requirements document provided by the user. The requirements document contains the user's requirements for the content of the copy, usually including key information such as the product to be promoted, the target audience, product features, and promotional highlights. The system will automatically parse the document and extract key demand keywords from it. For example, for insurance products, the requirements document will mention keywords such as "medical insurance", "accidental protection", and "long-term benefits". These keywords are the core elements of copy generation because they can directly reflect the characteristics of the product and user needs. Keyword extraction can be automated through natural language processing technology, such as through part-of-speech tagging, word frequency statistics, or named entity recognition, to ensure that the system can identify the core vocabulary required for copy generation.

[0075] S202: Perform semantic analysis on the demand keywords to obtain keyword semantic representations.

[0076] Specifically, after extracting keywords, the system performs semantic analysis on these keywords with the goal of understanding their true meaning and how they are used in different contexts. This is usually done through word vector technology, such as natural language processing models such as Word2Vec and BERT, which convert keywords into semantic vector representations. In this way, the system can understand the implicit semantic connections between words. For example, for the keyword "medical insurance", the system not only recognizes its surface meaning, but also infers related concepts such as "long-term protection", "beneficiary", and "insurance policy" through semantic analysis. Through semantic analysis, the system can accurately capture the meaning of demand keywords in specific fields.

[0077] S203, obtain a pre-built product knowledge graph and map the keyword semantic representation into the product knowledge graph.

[0078] Specifically, the system obtains and utilizes a pre-built product knowledge graph, which contains structured information about insurance products, such as the characteristics of different types of insurance, the types of risks covered, and the requirements of policyholders. The system establishes a connection between keywords and existing knowledge in the graph by mapping the semantic representation of keywords to relevant nodes in this knowledge graph. For example, the keyword "accidental protection" will be mapped to a node related to "accident insurance" in the graph, and this node is also connected to other information such as "low premiums" and "suitable for short-term needs." Through this mapping, the system can understand the specific relationship between each keyword and the insurance product, so that more appropriate content and expression can be selected when generating copy. At the same time, this process effectively enhances the accuracy and industry professionalism of the copy content.

[0079] S204: In the product knowledge graph, based on the keyword semantic representation, the semantic association between the demand keywords and the knowledge nodes of the product knowledge graph is identified through graph reasoning to obtain a semantic association representation.

[0080] Specifically, after completing the mapping of keywords to the knowledge graph, the system uses graph reasoning technology to further explore the deep semantic associations between keywords and knowledge nodes. By analyzing the relationships between nodes in the graph, the system can identify the associations between demand keywords and other related concepts or characteristics. For example, for the keyword "life insurance," the reasoning process may reveal the relationship between "life insurance" and concepts such as "beneficiary protection," "cash value," or "long-term investment." These inferred semantic associations provide richer information dimensions for copywriting generation, allowing the system to cover more important features related to insurance products when generating copywriting, ensuring that the copywriting is not only accurate but also sufficiently persuasive and in-depth.

[0081] S205: Obtain a document format corresponding to the content of the document to be generated from the requirement document, and obtain a format control rule matching the document format from a preset format rule engine.

[0082] Specifically, the system obtains the user's desired copy format information based on the description in the requirements document. Different communication platforms or usage scenarios usually have different format requirements. For example, the copy on social media may be relatively concise, while the copy placed on the website requires more detailed descriptions. Taking insurance products as an example, if the goal is to generate a social media advertisement, the format may require concise text, such as a sentence, to highlight the protection advantages and attach a call to action. The system obtains control rules that match the format from the format rule engine. These rules will include paragraph structure, word limit, tone and style. For example, social media ads are required to be within 80 words and use direct and powerful sentences to attract customers. Through these format control rules, the system ensures that the generated copy not only meets the format and style requirements of the specific platform or scenario in addition to the content.

[0083] S206, based on semantic association representation and format control rules, guide the pre-trained large language model to generate copy content that matches the demand document.

[0084] Specifically, in the final step, the system utilizes a pre-trained large language model (such as GPT) to generate the final copy. Based on the semantic association representations obtained previously, the system ensures that the content of the copy aligns with the product's core selling points and keyword-related information. Format control rules guide the model to maintain a specific structure and style when generating copy. The large language model combines semantic information with format requirements, dynamically filling in specific content during the generation process, ensuring that the final copy not only closely matches the requirements in the requirements document, but also flows naturally and fluently, meeting the needs of the target audience.

[0085] Furthermore, the steps of obtaining a pre-built product knowledge graph and mapping the keyword semantic representation to the product knowledge graph include:

[0086] Construct a feature mapping space and create several feature points in the feature mapping space;

[0087] Identify the knowledge nodes of the product knowledge graph and pair them with the feature points in the feature mapping space to obtain the knowledge feature pairing results;

[0088] According to the knowledge feature pairing results, the product knowledge graph is imported into the feature mapping space.

[0089] In this embodiment, the system effectively integrates the relationship between the product knowledge graph and the feature points by constructing a feature mapping space. In this mapping space, first, according to the dimensions of product characteristics, keyword semantic representation, etc., a number of feature points are created, which represent the core elements that need to be focused on in copy generation. Then, the system identifies the knowledge nodes in the product knowledge graph and pairs these nodes with the feature points in the feature mapping space. The pairing process is achieved through semantic similarity calculation, embedding vector matching, etc., to ensure that the knowledge nodes can be accurately mapped to the most relevant feature points. For example, if the node "life insurance" in the knowledge graph has characteristics such as "guarantee period" and "beneficiary", the system will pair these characteristics with the corresponding feature points in the mapping space, such as "long-term protection" and "family safety". Finally, through the pairing results, the entire product knowledge graph is imported into the feature mapping space. In this way, the feature mapping space not only contains the semantic information of the product, but also associates with specific knowledge graph nodes.

[0090] Through the above steps, the close combination of product knowledge graph and feature mapping space is realized, providing more accurate semantic and knowledge association for copy generation. After importing the knowledge graph, the system can more comprehensively understand the product characteristics, thereby generating more targeted and detailed copy, improving the accuracy and professionalism of the copy.

[0091] Further, in the product knowledge graph, based on the keyword semantic representation, the semantic association between the demand keywords and the knowledge nodes of the product knowledge graph is identified through graph reasoning, and the semantic association representation is obtained. The steps specifically include:

[0092] Performing semantic analysis on the knowledge nodes of the product knowledge graph to obtain knowledge node semantic representation;

[0093] Based on the keyword semantic representation and the knowledge node semantic representation, it is judged whether there is a semantic association between the demand keywords and the knowledge nodes;

[0094] If there is a semantic association between the demand keywords and the knowledge nodes, extract the semantic association features and generate the semantic association representation.

[0095] In this embodiment, first, a semantic analysis is performed on the knowledge nodes of the product knowledge graph to generate a semantic representation of the knowledge nodes. This process can be completed through natural language processing (NLP) technology, such as converting knowledge nodes into computable semantic vectors through models such as BERT and Word2Vec. These vectors can represent the semantic features of the knowledge nodes. Next, the system calculates the semantic similarity or correlation between the keyword semantic representation and the knowledge node semantic representation based on the previously acquired keyword semantic representation and the knowledge node semantic representation. Through this similarity calculation, the system can determine whether there is a semantic association between the demand keyword and the knowledge node. If the system detects the existence of a semantic association, it further extracts the associated feature information, such as the associated weight, the type of association, etc. These features are used to generate a semantic association representation, providing detailed semantic association information about the demand keyword and the product characteristics. The generation of the semantic association representation not only includes the direct association between the keyword and the knowledge node, but may also include the implicit semantic connection behind it. This semantic association helps the system to understand the relationship between the keyword and the product characteristics at a deeper level, ensuring that the generated content can accurately reflect the core selling points and needs of the product.

[0096] Through these steps, we analyze the semantic associations between demand keywords and product knowledge nodes, generating a detailed representation of these associations. Leveraging this association information, the system can generate more targeted and semantically precise copy, ensuring that the content is more aligned with user needs and improving the accuracy and intelligence of automatically generated copy.

[0097] Furthermore, based on the semantic representation of the keyword and the semantic representation of the knowledge node, the step of determining whether there is a semantic association between the requirement keyword and the knowledge node specifically includes:

[0098] Calculate the semantic similarity between the semantic representation of keywords and the semantic representation of knowledge nodes;

[0099] Compare the semantic similarity with the preset similarity threshold;

[0100] When the semantic similarity is greater than or equal to the similarity threshold, it is determined that there is a semantic association between the demand keyword and the knowledge node;

[0101] When the semantic similarity is less than the similarity threshold, it is determined that there is no semantic association between the demand keyword and the knowledge node.

[0102] In this embodiment, the system first calculates the semantic similarity between the semantic representation of the demand keyword and the semantic representation of the knowledge node. The similarity calculation usually adopts methods such as cosine similarity or Euclidean distance to compare the two semantic vectors to obtain a similarity value between 0 and 1. Then, the system compares the calculated semantic similarity with the preset similarity threshold to determine the correlation between the demand keyword and the knowledge node. If the similarity is greater than or equal to the threshold, the system determines that there is a semantic association between the demand keyword and the knowledge node, which means that the two have significant semantic correlation and are suitable for subsequent copy generation process. On the contrary, if the similarity is lower than the threshold, it is determined that there is no effective semantic association between the two. Through such a similarity judgment mechanism, the system can efficiently screen out knowledge nodes that are highly relevant to the demand keyword, ensuring that the information used when generating copy is both accurate and targeted, thereby better meeting the needs of users.

[0103] Through the above steps, the semantic association between demand keywords and knowledge nodes is effectively identified, which improves the accuracy and pertinence of copy generation, thereby enhancing the intelligence level of automatically generated copy.

[0104] Furthermore, based on the semantic association representation and format control rules, the steps of guiding the pre-trained large language model to generate copy content that matches the requirement document include:

[0105] Input semantic association representation and format control rules into the pre-trained large language model;

[0106] Traverse the text library of the large language model and identify the target text that matches the semantic association representation;

[0107] Combine the target text according to the format control rules to obtain the copy content that matches the requirement document.

[0108] In this embodiment, the system first inputs the generated semantic association representation and the format control rule into a pre-trained large language model. The semantic association representation provides detailed information between the demand keywords and the relevant knowledge nodes, while the format control rule ensures that the generated copy conforms to specific structural and stylistic requirements. Next, the system traverses the text library of the large language model to identify target texts that match the semantic association representation. This step aims to find the most relevant sentences or paragraphs to meet the demand of copy generation through the language patterns and knowledge learned by the model in advance. Then, the system combines the identified target texts according to the format control rule to construct the final copy content. Through this combination, the system can ensure that the generated copy is consistent with the demand document in terms of content, while meeting the specified format requirements in terms of form. For example, if the format control rule specifies that the copy should contain a question guide and a call to action, the system will extract appropriate target texts and combine them into a complete copy that conforms to this structure.

[0109] Through the above steps, the semantic information and format requirements are effectively combined, and the generated copy content is more targeted and structured, significantly improving the quality and accuracy of automated copy generation.

[0110] Further, before the step of guiding the pre-trained large language model to generate copy content matching the demand document based on the semantic association representation and the format control rule, the following steps are further included:

[0111] Obtain training sample data, wherein the training sample data includes historical copy keywords, historical copy format control rules, and historical copy content;

[0112] Perform semantic analysis on the historical copy keywords to obtain historical copy keyword semantic representations;

[0113] Map the historical copy keyword semantic representations to the product knowledge graph;

[0114] In the product knowledge graph, identify the semantic association between the historical copy keywords and the knowledge nodes of the product knowledge graph based on the historical copy keyword semantic representations through graph reasoning to obtain historical semantic association representations;

[0115] Input the historical semantic association representations and the historical copy format control rules into the preset initial large language model, so that the initial large language model learns the historical semantic association representations and the historical copy format control rules, and outputs predicted copy content;

[0116] Compare the predicted copy content with the historical copy content to obtain model prediction errors;

[0117] Iteratively update the initial large language model according to the model prediction errors until the model is fitted to obtain the pre-trained large language model.

[0118] In this embodiment, first, the system obtains training sample data containing historical copy keywords, format control rules, and copy content. These data provide rich information about successful copy, which is convenient for the model to learn. Next, the system performs semantic analysis on the historical copy keywords and converts these keywords into semantic vector representations using natural language processing technology. Afterwards, the system maps the semantic representations of these historical copy keywords to the product knowledge graph, establishes the relationship between the keywords and the knowledge nodes, and through graph reasoning, the system identifies the semantic associations between the historical copy keywords and the knowledge nodes, and then generates a historical semantic association representation. This information is then input into the preset initial large language model together with the format control rules of the historical copy so that the model can learn the semantic structure and format specifications in the historical data.

[0119] After learning, the model generates predicted copy. The system compares this content with historical copy and calculates the model's prediction error. By analyzing this error, the system can identify deficiencies in the model's generated content and iteratively update the initial large language model. This process continues until the model effectively fits the historical data and the generated copy achieves a high degree of semantic and formatting similarity with historical copy. This results in a pre-trained large language model that can more accurately generate copy that meets requirements, with greater adaptability and creativity.

[0120] Through the above steps, the large language model was optimized using historical data, enabling it to generate high-quality, structured, and creative copy, significantly improving the accuracy and flexibility of copy generation.

[0121] Furthermore, after obtaining the requirement document of the content to be generated and reading the requirement keywords in the requirement document, the method further includes:

[0122] Classify the demand keywords, and group the demand keywords according to the keyword classification results to obtain several keyword groups;

[0123] Assign a corresponding keyword group weight to each keyword group.

[0124] In this embodiment, the system first classifies the demand keywords in order to better understand their role and importance in the copy generation process. Classification can be based on multiple dimensions such as the semantic characteristics of the keywords, usage scenarios or target audiences. For example, the keyword "life insurance" is classified as "insurance products", while "accidental protection" is classified as "protection type". After classification, the system will group the demand keywords according to the classification results of the keywords to generate several keyword groups. Each keyword group will contain keywords with similar semantics or similar functions. Next, a corresponding weight is assigned to each keyword group. This weight reflects the importance and priority of the keyword group in the entire copy generation. The weight allocation can be based on historical data analysis, keyword usage frequency, user feedback and other factors to ensure that the system can give priority to those more influential and relevant keyword groups when generating copy.

[0125] Through the above steps, the demand keywords are classified and grouped, and weights are assigned to them, which improves the accuracy and relevance of copy generation and makes the generated content more in line with the real needs of users.

[0126] Furthermore, the steps of performing semantic analysis on the demand keywords to obtain the semantic representation of the keywords specifically include:

[0127] For each demand keyword, identify the keyword group to which the demand keyword belongs, and obtain the keyword group weight corresponding to the demand keyword;

[0128] Perform semantic analysis on the demand keywords, and use the corresponding keyword group weights to weight the semantic analysis results of the demand keywords to obtain keyword semantic representation.

[0129] In this embodiment, for each demand keyword, the system first identifies the keyword group to which the keyword belongs and obtains the corresponding keyword group weight. This process ensures that the system understands the relative importance of each keyword in the copy generation. Next, the system conducts an in-depth semantic analysis of the demand keyword and converts it into a semantic vector using natural language processing technology. These semantic vectors can capture the contextual information of the keyword and its implicit meaning. Subsequently, the system uses the corresponding keyword group weight to weight the semantic analysis results of the demand keyword to reflect the importance of the keyword in the entire copy generation process. For example, if the keyword "life insurance" has a higher weight in its keyword group, then its semantic representation will be given a greater weight. Through this weighting process, the final keyword semantic representation can more accurately reflect the role of the keyword in the generation of a specific copy, so that the generated content not only meets the semantic requirements, but also has higher relevance and effectiveness.

[0130] Through the above steps, the semantic analysis of demand keywords and keyword group weights are effectively integrated, providing a more accurate semantic basis for content generation, thereby improving the accuracy and pertinence of copy generation.

[0131] In the above embodiment, the present application discloses a method for generating copy content, which belongs to the field of artificial intelligence technology. This application targets the limitations of existing automatic copy generation technologies in terms of creativity, personalized customization and platform adaptability, and guides a large language model to generate copy by combining semantic analysis, knowledge graph reasoning and format control rules, so that the generated content is not only more semantically accurate, but also adaptable to different demand scenarios and communication platforms. The introduction of knowledge graphs improves the professionalism and information relevance of copy, and format control rules ensure that the structure and style of the copy meet the requirements of specific platforms. Through these optimizations, more personalized, creative and multi-platform style copy can be generated, which improves the practicality and flexibility of automatic generation of copy content.

[0132] In this embodiment, the electronic device (eg Figure 1 The server shown in the figure can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0133] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned copy content information, the above-mentioned copy content information can also be stored in a blockchain node.

[0134] The blockchain referred to in this application is a new application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0135] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0136] The artificial intelligence basic technology generally includes technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction system, mechatronics, etc. The artificial intelligence software technology mainly includes computer vision technology, robot technology, biometric identification technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0137] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by computer readable instructions instructing related hardware, and the computer readable instructions can be stored in a computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of each method. Among them, the storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0138] It should be understood that, although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or sub-steps or stages of other steps.

[0139] Further referring to Figure 3 , as an implementation of the method shown in the above Figure 2 , the present application provides an embodiment of a script content generation device, which corresponds to the method embodiment shown in Figure 2 , and the device can be specifically applied to various electronic devices.

[0140] As shown in Figure 3 , the script content generation device 300 described in the present embodiment comprises:

[0141] A keyword reading module 301 is configured to obtain a requirement document of a script content to be generated, and read requirement keywords in the requirement document.

[0142] A semantic analysis module 302 is configured to perform semantic analysis on the requirement keywords to obtain semantic representations of the keywords.

[0143] Semantic mapping module 303, used to obtain a pre-built product knowledge graph and map the keyword semantic representation into the product knowledge graph;

[0144] The semantic association module 304 is used to identify the semantic association between the demand keywords and the knowledge nodes of the product knowledge graph in the product knowledge graph based on the keyword semantic representation through graph reasoning to obtain the semantic association representation;

[0145] The control rule module 305 is used to obtain the document format corresponding to the content of the document to be generated from the demand document, and obtain the format control rules that match the document format from the preset format rule engine;

[0146] The copywriting generation module 306 is used to guide the pre-trained large language model to generate copywriting content that matches the requirement document based on semantic association representation and format control rules.

[0147] Furthermore, the semantic mapping module 303 is specifically configured to:

[0148] Construct a feature mapping space and create several feature points in the feature mapping space; identify the knowledge nodes of the product knowledge graph and pair the knowledge nodes of the product knowledge graph with the feature points in the feature mapping space to obtain the knowledge feature pairing results; based on the knowledge feature pairing results, import the product knowledge graph into the feature mapping space.

[0149] Furthermore, the semantic association module 304 is specifically configured to:

[0150] Perform semantic analysis on the knowledge nodes of the product knowledge graph to obtain the semantic representation of the knowledge nodes; based on the semantic representation of keywords and the semantic representation of knowledge nodes, determine whether there is a semantic association between the demand keywords and the knowledge nodes; if there is a semantic association between the demand keywords and the knowledge nodes, extract the semantic association features and generate a semantic association representation.

[0151] Furthermore, the semantic association module 304 is further configured to:

[0152] Calculate the semantic similarity between the semantic representation of the keyword and the semantic representation of the knowledge node; compare the semantic similarity with the preset similarity threshold; when the semantic similarity is greater than or equal to the similarity threshold, determine that there is a semantic association between the demand keyword and the knowledge node; when the semantic similarity is less than the similarity threshold, determine that there is no semantic association between the demand keyword and the knowledge node.

[0153] Furthermore, the copywriting generation module 306 is specifically used to:

[0154] Input the semantic association representation and format control rules into the pre-trained large language model; traverse the text library of the large language model to identify the target text that matches the semantic association representation; combine the target text according to the format control rules to obtain the copy content that matches the requirement document.

[0155] Furthermore, the copy content generation device 300 further includes a large language model training module, which is specifically used to:

[0156] Acquire training sample data, wherein the training sample data includes historical copy keywords, historical copy format control rules and historical copy content; perform semantic analysis on the historical copy keywords to obtain semantic representations of the historical copy keywords; map the semantic representations of the historical copy keywords to the product knowledge graph; in the product knowledge graph, identify the semantic associations between the historical copy keywords and the knowledge nodes of the product knowledge graph through graph reasoning based on the semantic representations of the historical copy keywords to obtain historical semantic association representations; input the historical semantic association representations and the historical copy format control rules into a preset initial large language model, so that the initial large language model learns the historical semantic association representations and the historical copy format control rules, and outputs predicted copy content; compare the predicted copy content with the historical copy content to obtain a model prediction error; iteratively update the initial large language model according to the model prediction error until the model is fitted to obtain a pre-trained large language model.

[0157] Furthermore, the copy content generation device 300 further includes a weight configuration module, and the large weight configuration is specifically used to:

[0158] Classify the demand keywords, and group the demand keywords according to the keyword classification results to obtain several keyword groups; assign corresponding keyword group weights to each keyword group.

[0159] Furthermore, the semantic analysis module 302 is specifically configured to:

[0160] For each demand keyword, identify the keyword group to which the demand keyword belongs, and obtain the keyword group weight corresponding to the demand keyword; perform semantic analysis on the demand keyword, and use the corresponding keyword group weight to weight the semantic analysis result of the demand keyword to obtain the keyword semantic representation.

[0161] In the above embodiment, the present application discloses a copy content generation device, which belongs to the field of artificial intelligence technology. This application targets the limitations of existing automatic copy generation technology in terms of creativity, personalized customization and platform adaptability. By combining semantic analysis, knowledge graph reasoning and format control rules, it guides a large language model to generate copy, so that the generated content is not only more semantically accurate, but also adaptable to different demand scenarios and communication platforms. The introduction of knowledge graphs improves the professionalism and information relevance of copy, and format control rules ensure that the structure and style of the copy meet the requirements of specific platforms. Through these optimizations, more personalized, creative and multi-platform style copy can be generated, which improves the practicality and flexibility of automatic generation of copy content.

[0162] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0163] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0164] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0165] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the copy content generation method. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0166] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for executing the copywriting content generation method.

[0167] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0168] In the above embodiment, the present application discloses a computer device, which belongs to the field of artificial intelligence. The present application aims at the limitations of existing automatic generation of text in creativity, personalized customization and platform adaptability. By combining semantic analysis, knowledge graph reasoning and format control rules, the present application guides the large language model to generate text, so that the generated content is not only more accurate in semantics, but also can adapt to different demand scenarios and communication platforms. The introduction of the knowledge graph improves the professionalism and information correlation of the text, and the format control rules ensure that the structure and style of the text meet the requirements of specific platforms. Through these optimizations, more personalized, creative and multi-platform style text can be generated, improving the practicality and flexibility of automatic generation of text content.

[0169] The present application also provides another embodiment, that is, a computer readable storage medium storing computer readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the text content generation method as described above.

[0170] In the above embodiment, the present application discloses a computer readable storage medium, which belongs to the field of artificial intelligence. The present application aims at the limitations of existing automatic generation of text in creativity, personalized customization and platform adaptability. By combining semantic analysis, knowledge graph reasoning and format control rules, the present application guides the large language model to generate text, so that the generated content is not only more accurate in semantics, but also can adapt to different demand scenarios and communication platforms. The introduction of the knowledge graph improves the professionalism and information correlation of the text, and the format control rules ensure that the structure and style of the text meet the requirements of specific platforms. Through these optimizations, more personalized, creative and multi-platform style text can be generated, improving the practicality and flexibility of automatic generation of text content.

[0171] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platforms, of course, they can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner or network device) to execute the methods described in the embodiments of the present application.

[0172] The application is operable in numerous general purpose or special purpose computer system environments or configurations. Examples of well-known computing systems, environments, and / or configurations that can be suitable for use with the application include personal computers, server computers, handheld or laptop devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, and the like, that perform particular tasks or implement particular abstract data types. The application can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.

[0173] Obviously, the above-described embodiments are only some embodiments but not all the embodiments of the present application, and the preferred embodiments of the present application are shown in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms, and conversely, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing specific embodiments or equivalently replace some technical features thereof. Any equivalent structure made by using the content of the specification and drawings, directly or indirectly used in other related technical fields, is also within the patent protection scope of the present application.

Claims

1. A method for generating copy content, characterized in that: include: Obtaining a requirement document for the content to be generated and reading the requirement keywords in the requirement document; Performing semantic analysis on the demand keywords to obtain keyword semantic representations; Obtain a pre-built product knowledge graph, and map the keyword semantic representation into the product knowledge graph; In the product knowledge graph, based on the keyword semantic representation, the semantic association between the demand keyword and the knowledge node of the product knowledge graph is identified through graph reasoning to obtain a semantic association representation; Obtaining a document format corresponding to the document content to be generated from the demand document, and obtaining a format control rule matching the document format in a preset format rule engine; Based on the semantic association representation and format control rules, guide the pre-trained large language model to generate copy content that matches the demand document; After the steps of obtaining the requirement document of the content to be generated and reading the requirement keywords in the requirement document, the method further includes: Classifying the demand keywords, and grouping the demand keywords according to the keyword classification results to obtain a plurality of keyword groups; Assigning a corresponding keyword group weight to each of the keyword groups; The step of performing semantic analysis on the demand keywords to obtain keyword semantic representations specifically includes: For each of the demand keywords, identifying the keyword group to which the demand keyword belongs, and obtaining the keyword group weight corresponding to the demand keyword; The demand keywords are semantically analyzed, and the semantic analysis results of the demand keywords are weighted using corresponding keyword group weights to obtain the keyword semantic representation.

2. The method for generating content of a copywriting according to claim 1, wherein: The step of obtaining a pre-built product knowledge graph and mapping the keyword semantic representation to the product knowledge graph specifically includes: Constructing a feature mapping space and creating a plurality of feature points in the feature mapping space; Identifying knowledge nodes of the product knowledge graph, and pairing the knowledge nodes of the product knowledge graph with feature points in the feature mapping space to obtain knowledge-feature pairing results; According to the knowledge feature pairing result, the product knowledge graph is imported into the feature mapping space.

3. The method for generating content of a copywriting according to claim 1, wherein: The step of identifying the semantic association between the demand keyword and the knowledge node of the product knowledge graph through graph reasoning based on the keyword semantic representation in the product knowledge graph to obtain the semantic association representation specifically includes: Performing semantic analysis on the knowledge nodes of the product knowledge graph to obtain semantic representations of the knowledge nodes; Based on the keyword semantic representation and the knowledge node semantic representation, determining whether there is a semantic association between the requirement keyword and the knowledge node; If there is a semantic association between the demand keyword and the knowledge node, a semantic association feature is extracted and the semantic association representation is generated.

4. The method for generating content of a copywriting according to claim 3, wherein: The step of determining whether there is a semantic association between the requirement keyword and the knowledge node based on the keyword semantic representation and the knowledge node semantic representation specifically includes: Calculating the semantic similarity between the keyword semantic representation and the knowledge node semantic representation; comparing the semantic similarity with a preset similarity threshold; When the semantic similarity is greater than or equal to the similarity threshold, determining that there is a semantic association between the demand keyword and the knowledge node; When the semantic similarity is less than the similarity threshold, it is determined that there is no semantic association between the demand keyword and the knowledge node.

5. The method for generating content of a copywriting according to claim 1, wherein: The step of guiding the pre-trained large language model to generate text content matching the requirement document based on the semantic association representation and format control rules specifically includes: Inputting the semantic association representation and format control rules into the pre-trained large language model; Traversing the text library of the large language model to identify target text that matches the semantic association representation; The target text is combined according to the format control rules to obtain text content that matches the requirement document.

6. The method for generating content of a copywriting according to claim 5, wherein: Before the step of guiding the pre-trained large language model to generate text content matching the requirement document based on the semantic association representation and format control rules, the method further includes: Acquiring training sample data, wherein the training sample data includes historical copy keywords, historical copy format control rules, and historical copy content; Performing semantic analysis on the historical copy keywords to obtain semantic representations of the historical copy keywords; Mapping the semantic representation of the historical copy keywords into the product knowledge graph; In the product knowledge graph, based on the semantic representation of the historical copy keywords, semantic associations between the historical copy keywords and knowledge nodes of the product knowledge graph are identified through graph reasoning to obtain historical semantic association representations; Inputting the historical semantic association representation and the historical text format control rules into a preset initial large language model, so that the initial large language model learns the historical semantic association representation and the historical text format control rules and outputs predicted text content; Comparing the predicted text content with the historical text content to obtain a model prediction error; The initial large language model is iteratively updated according to the model prediction error until the model is fitted, thereby obtaining the pre-trained large language model.

7. A copywriting content generation device, characterized in that: The copy content generation device implements the steps of the copy content generation method according to any one of claims 1 to 6, and the copy content generation device includes: A keyword reading module is used to obtain a demand document of the content to be generated and read the demand keywords in the demand document; A semantic analysis module, configured to perform semantic analysis on the demand keywords to obtain semantic representations of the keywords; A semantic mapping module is used to obtain a pre-built product knowledge graph and map the keyword semantic representation into the product knowledge graph; A semantic association module is used to identify, in the product knowledge graph, the semantic association between the demand keyword and the knowledge node of the product knowledge graph through graph reasoning based on the keyword semantic representation, and obtain a semantic association representation; A control rule module is used to obtain the document format corresponding to the content of the document to be generated from the demand document, and obtain the format control rule matching the document format in a preset format rule engine; The copywriting generation module is used to guide the pre-trained large language model to generate copywriting content that matches the demand document based on the semantic association representation and format control rules.

8. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the method for generating copy content according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the method for generating copy content according to any one of claims 1 to 6 are implemented.

Images