Cboth generation method and device, electronic equipment and storage medium

Abstract

The invention relates to a copywriting generation method and device, electronic equipment and a storage medium. The method comprises the following steps: loading a target corpus; the target corpus comprises a plurality of candidate language elements; the candidate language elements are language elements meeting a preset judgment condition; acquiring copywriting content prompt information of the target copywriting; the target copywriting is a copywriting to be generated; determining a target language element matched with the target copywriting in a target corpus based on the copywriting content prompt information; generating a target copywriting based on the copywriting content prompt information and the target language element; the target copywriting comprises a target language element; the target language elements are used for constructing statements or paragraphs of the target copywriting, and the essence of the target language elements is that a method for improving the quality, real-time performance or specific characteristics of the generated copywriting (namely the generated text) is provided, and the use requirement of a user for generating the high-quality copywriting can be met.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to a copywriting generation method, device, electronic device and storage medium. Background Art

[0002] In recent years, with the rapid development of natural language processing (NLP) technology, copywriting generation technology (i.e., text generation technology) has made significant progress. From early rule-based methods to modern deep learning models, copywriting generation technology has been widely used in many fields, such as machine translation, dialogue systems, and intelligent writing. However, existing copywriting generation technology still faces many challenges, especially in terms of the quality of generated copywriting. Therefore, how to improve the quality of generated copywriting and enhance the real-time or specific features of copywriting is a problem that needs to be solved urgently. Summary of the invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a copy generation method, device, electronic device and storage medium.

[0004] In a first aspect, the present disclosure provides a method for generating a copy, comprising:

[0005] Loading a target corpus; the target corpus includes a plurality of candidate language elements; the candidate language elements are language elements that meet a preset determination condition;

[0006] Obtaining content prompt information of a target copy; the target copy is a copy to be generated;

[0007] Based on the text content prompt information, determining a target language element adapted to the target text in the target corpus;

[0008] A target copy is generated based on the copy content prompt information and the target language element; the target copy includes the target language element; and the target language element is used to construct sentences or paragraphs of the target copy.

[0009] In a second aspect, the present disclosure further provides a copywriting generation device, comprising:

[0010] A loading module, used for loading a target corpus; the target corpus includes a plurality of candidate language elements; the candidate language elements are language elements that meet a preset determination condition;

[0011] An acquisition module, used to acquire content prompt information of a target copy; the target copy is the copy to be generated;

[0012] A language element determination module, configured to determine, in the target corpus, a target language element adapted to the target text based on the text content prompt information;

[0013] The copywriting generation module is used to generate a target copywriting based on the copywriting content prompt information and the target language elements; the target copywriting includes the target language elements; the target language elements are used to construct sentences or paragraphs of the target copywriting.

[0014] In a third aspect, the present disclosure further provides an electronic device, the electronic device comprising:

[0015] one or more processors;

[0016] A storage device for storing one or more programs;

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the document generation method as described above.

[0018] In a fourth aspect, the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the document generation method as described above.

[0019] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0020] The technical solution provided by the embodiment of the present disclosure is configured to load a target corpus; the target corpus includes multiple candidate language elements; the candidate language elements are language elements that meet preset judgment conditions; the text content prompt information of the target text is obtained; the target text is the text to be generated; based on the text content prompt information, the target language element adapted to the target text is determined in the target corpus; based on the text content prompt information and the target language element, the target text is generated; the target text includes the target language element; the target language element is used to construct sentences or paragraphs of the target text. The essence of the technical solution is to provide a method for improving the quality, real-time performance or specific features of the generated text, which can meet the user's needs for generating high-quality text. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0023] Figure 1 A flowchart of a method for generating a document provided by an embodiment of the present disclosure;

[0024] Figure 2 is a structural schematic diagram of a copywriting generation device in an embodiment of the present disclosure;

[0025] Figure 3 It is a structural schematic diagram of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0028] Figure 1 A flowchart of a copywriting generation method provided for an embodiment of the present disclosure, this embodiment is applicable to the case where copywriting is generated in a client, the method can be executed by a copywriting generation device, the device can be implemented by software and / or hardware, the device can be configured in an electronic device, such as a terminal, specifically including but not limited to smart headphones, smart glasses, smart phones, PDAs, tablet computers, wearable devices with display screens, desktop computers, laptop computers, all-in-one machines, smart home devices, etc. Alternatively, this embodiment is applicable to the case where copywriting is generated in a server, the method can be executed by a copywriting generation device, the device can be implemented by software and / or hardware, the device can be configured in an electronic device, such as a server. In this application, copywriting, that is, text, or long text. Copywriting generation is text generation.

[0029] like Figure 1 As shown, the method may specifically include:

[0030] S110, loading a target corpus; the target corpus includes a plurality of candidate language elements; the candidate language elements are language elements that meet preset determination conditions.

[0031] A language element may be, for example, a single word, a word group, a phrase, a sentence or a paragraph.

[0032] The target corpus is a pre-constructed corpus that includes a plurality of candidate language elements.

[0033] Candidate language elements are language elements included in the target corpus, which are selected using preset judgment conditions and can make words and sentences more exquisite. The use of candidate language elements can improve the literary grace of the copy (i.e., text).

[0034] The preset judgment condition may be, for example, a condition for screening out language elements having the same or multiple characteristics. The characteristics of a language element may be, for example, a humorous characteristic, a professional characteristic, or a characteristic that is popular during a certain period of time. The present application does not limit the specific conditions of the preset judgment condition. In practice, it may be determined based on the quality standard of the copy (i.e., text) to be generated. For example, if the copy (i.e., text) includes Internet buzzwords, it will shorten the distance between the copy (i.e., text) and the reader. If the distance between the copy (i.e., text) to be generated and the reader is required to be smaller, the preset judgment condition may be set to include a heat parameter of the language element being greater than or equal to a set threshold. The heat parameter may be, for example, the frequency of use or the range of dissemination of the candidate language element within a preset period of time.

[0035] S120, obtaining content prompt information of a target copy; the target copy is a copy to be generated.

[0036] The copy content prompt information can be, for example, information input by the user according to his / her own needs, which is used to control and limit the target copy generated subsequently. The copy content prompt information can help the copy generation model (ie, the text generation model) better understand and meet the specific needs of the user.

[0037] Exemplarily, the content prompt information of the target copy may include at least one of the following: a theme, an outline, keywords, a summary, and a conclusion of the target copy.

[0038] Furthermore, the content prompt information of the target copy may also include at least one of style, type, and usage scenario. Among them, the style may be, for example, the language style characteristics of the target copy, such as ancient style, martial arts style, or suspense style, and the type may be, for example, the stylistic characteristics of the target copy, such as expository, narrative, or argumentative. The usage scenario of the target copy may be, for example, a written language scenario or a spoken communication scenario. Furthermore, both the written language scenario and the spoken communication scenario may be further subdivided into multiple scenarios such as academic research scenarios, education and teaching scenarios, commercial office scenarios, and media communication scenarios.

[0039] S130: Determine, based on the content prompt information of the text, a target language element that is compatible with the target text in the target corpus.

[0040] In practice, in the target corpus, different candidate language elements have different meanings and are applicable to different scenarios. For example, each candidate language element in the target corpus is a popular Internet word, of which two candidate language elements are "next level" and "city is not city". "next level" is applicable to describing a scenario where someone / thing has been upgraded and evolved to a new level. "city is not city" is applicable to emphasizing to the other party that someone / thing is very fashionable.

[0041] There are many methods for implementing this step, and this application does not limit this. Exemplarily, the target corpus includes multiple records, and the records include candidate language elements and associated information of the candidate language elements; the associated information of the candidate language elements is information used to reflect the applicable scenarios of the candidate language elements; the implementation method of this step may include: semantically understanding the content prompt information of the copy to obtain a semantic understanding result; based on the semantic understanding result and the associated information of the candidate language elements in the target corpus, determining the degree of fit between the content prompt information of the copy and the candidate language elements; based on the degree of fit between the content prompt information of the copy and the candidate language elements, determining the target language element in the target corpus.

[0042] The associated information of the candidate language element may include, for example, at least one of the following: explanation of the candidate language element, inapplicable topics, synonyms, applicable topic examples, and usage examples. Exemplarily, a candidate language element is "city is not city", and the associated information of the candidate language element includes: explanation, inapplicable topics, synonyms, applicable topic examples, and usage examples. Specifically, the explanation of the candidate language element is: asking the other party whether something is fashionable as a question, or as a rhetorical question to emphasize to the other party that something is very fashionable, with an entertaining and funny nature, corresponding to a light-hearted tone; inapplicable topics are: not applicable to serious topics; synonyms are: fashionable, trendy, foreign, trendy, advanced or cool; applicable topic examples are: the latest electronic products; usage examples are: My dears, is this latest mobile phone city or not? I would like to call this mobile phone the best fashion item of the year.

[0043] The degree of compatibility between the copy content prompt information and the candidate language element reflects whether the copy content prompt information forms the basic conditions for satisfying the usage scenario of the candidate language element.

[0044] Determining the degree of compatibility between the copy content prompt information and the candidate language element is essentially to determine to what extent the copy content prompt information is suitable for using the candidate language element. The higher the degree of compatibility, the more suitable the target copy to be generated is for using the candidate language element.

[0045] “Determining the target language element in the target corpus based on the degree of fit between the text content prompt information and the candidate language element” may, for example, be determining the candidate language element whose degree of fit with the text content prompt information is greater than or equal to a set threshold as the target language element.

[0046] S140, generating a target copy based on the copy content prompt information and the target language elements; the target copy includes the target language elements; the target language elements are used to construct sentences or paragraphs of the target copy.

[0047] The purpose of this step is to use the target language elements in the generated target copy. Here, "using the target language elements" can include, for example, using the target language elements to form sentences or paragraphs in the target copy, aiming to optimize and upgrade the words and sentences. It is not about changing the content and viewpoint, but focusing on the language expression itself, making the sentences from simple and straightforward to brilliant.

[0048] There are many methods for implementing this step, and this application does not limit this. Exemplarily, the implementation method of this step includes: generating an intermediate copy based on the copy content prompt information and the target language elements; continuing to write the intermediate copy based on the copy content prompt information to obtain the target copy; the target copy includes the intermediate copy.

[0049] The intermediate copy can be, for example, a sentence obtained by using the target language elements to construct words and sentences. "Continuing writing based on the intermediate copy" can, for example, be adding other content before or after the intermediate copy so that the final target copy meets the requirements of the copy content prompt information.

[0050] The target text includes the intermediate text. For example, the intermediate text is a sentence or paragraph constituting the target text.

[0051] In some embodiments, "generating an intermediate copy based on the copy content prompt information and the target language elements" and "based on the copy content prompt information, continuing to write based on the intermediate copy to obtain the target copy; the target copy includes the intermediate copy" can be generated by two different copy generation models (i.e., text generation modules).

[0052] Furthermore, based on the prompt information of the copy content, continuing writing based on the intermediate copy to obtain the target copy can also include: obtaining the position information of the intermediate copy in the target copy; based on the prompt information of the copy content and the position information of the intermediate copy in the target copy, continuing writing based on the intermediate copy to obtain the target copy.

[0053] The position information of the intermediate copy in the target copy can indicate whether the supplement is to be written before the intermediate copy or after the intermediate copy. For example, if the position information of the intermediate copy in the target copy indicates that the intermediate copy is used as the first sentence of the target copy, then the supplemented content will be placed after the intermediate copy to form a complete paragraph or article. If the position information of the intermediate copy in the target copy indicates that the intermediate copy is used as the last sentence of the target copy, then the supplemented content will be placed before the intermediate copy as a prelude to the intermediate copy. In addition, in some scenarios, the position information of the intermediate copy in the target copy can also indicate the amount of supplementation required. For example, the position information of the intermediate copy in the target copy can be specific to the natural paragraph in which the intermediate copy is located in the target copy, so as to more accurately guide the position and length of the supplement. In this way, by clarifying the position information of the intermediate copy, it can be ensured that the generated target copy has a reasonable structure and coherent content, which meets the expected creation needs.

[0054] For example, in order to complete a certain copywriting (i.e., text) writing task, the user inputs the copywriting theme as "XXX chip, the latest research and development achievement of Institute A", and the writing outline is "Write from four aspects: research and development background, technical characteristics and performance, application prospects and impact, and future prospects". The copywriting theme and writing outline are used as the copywriting content prompt information of the target copywriting, and based on the copywriting content prompt information of the target copywriting, "nextlevel" is selected from the Internet buzzword library (i.e., the target corpus) as the target language element. Then, based on the copywriting content prompt information and the target language element, an intermediate copy is generated. The intermediate copy is: "A major technological breakthrough! The next level XXX chip, Institute A takes you to explore the future!". Set the position of the intermediate copy in the target copywriting as the first sentence. Next. Based on the copywriting content prompt information, continue writing with the intermediate copy as the first sentence to obtain a complete target copy. The target copy conforms to the writing outline and copywriting theme in the copywriting content prompt information.

[0055] Those skilled in the art can understand that, since the target language element has certain characteristics, if the target text includes the target language element, the target text will also have such characteristics. For example, in some scenarios, if the target language element is a phrase with humorous characteristics, the target text containing the target language element will also have humorous characteristics. In other scenarios, if the target language element is a professional term in certain fields (such as the Internet industry or the technology industry, etc.) and has professional characteristics, the target text containing the target language element will also have professional characteristics. In some other scenarios, if the target language element is a popular term for a period of time and has real-time characteristics, the target text containing the target language element will also have real-time characteristics.

[0056] The above technical solution is configured to load a target corpus; the target corpus includes multiple candidate language elements; the candidate language elements are language elements that meet preset judgment conditions; the copy content prompt information of the target copy is obtained; the target copy is the copy to be generated; based on the copy content prompt information, the target language element adapted to the target copy is determined in the target corpus; based on the copy content prompt information and the target language element, the target copy is generated; the target copy includes the target language element; the target language element is used to construct sentences or paragraphs of the target copy. Its essence is to use the target language element so that the target copy has the characteristics of the target language element, thereby achieving the method of improving the quality, real-time or specific characteristics of the generated copy (i.e., text), which can meet the user's use needs of generating high-quality copy (i.e., text).

[0057] Based on the above technical solutions, optionally, the method for constructing the target corpus may include: determining candidate language elements based on preset judgment conditions; the preset judgment conditions are related to the copy quality standard; determining associated information corresponding to the candidate language elements; and adding the candidate language elements and the associated information corresponding thereto as a record to the target corpus.

[0058] The judgment condition is used to screen out high-quality candidate language elements. This application does not limit the specific conditions of the preset judgment condition. In practice, it can be determined according to the quality requirements of the copy to be generated. For example, if the copy (i.e., text) includes Internet buzzwords, it will shorten the distance between the copy (i.e., text) and the reader, so that the reader can fully understand the content of the copy (i.e., text). If the distance between the copy (i.e., text) and the reader is defined to be smaller, the higher the quality of the copy, the preset judgment condition can be set to include the heat parameter of the candidate language element being greater than or equal to the set threshold.

[0059] There are many specific implementation methods for "determining the associated information corresponding to the candidate language element", which is not limited in this application. Optionally, "determining the associated information corresponding to the candidate language element" may include: obtaining a segment including the candidate language element; and determining the associated information corresponding to the candidate language element by semantically understanding the segment including the candidate language element.

[0060] Through the above method, a target corpus can be constructed, so that the target corpus includes language elements that can effectively improve the quality of wording and sentence construction in the copy, and assist the execution subject of the technical solution of this application to understand the candidate language elements, so as to facilitate the subsequent rapid determination of the target language elements that are compatible with the target copy, thereby improving the execution efficiency of the technical solution of this application.

[0061] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0062] Figure 2 Schematic diagram of the structure of a text generation device in an embodiment of the present disclosure. The text generation device provided in the embodiment of the present disclosure can be configured in a client, or can be configured in a server. Figure 2 , the copywriting generation device specifically includes:

[0063] The loading module 310 is used to load a target corpus; the target corpus includes a plurality of candidate language elements; the candidate language elements are language elements that meet a preset determination condition;

[0064] The acquisition module 320 is used to acquire the content prompt information of the target copy; the target copy is the copy to be generated;

[0065] A language element determination module 330, configured to determine a target language element adapted to the target text in the target corpus based on the text content prompt information;

[0066] The copywriting generation module 340 is used to generate a target copywriting based on the copywriting content prompt information and the target language elements; the target copywriting includes the target language elements; and the target language elements are used to construct sentences or paragraphs of the target copywriting.

[0067] Furthermore, the target corpus includes a plurality of records, each of which includes a candidate language element and associated information of the candidate language element; the associated information of the candidate language element is information used to reflect the applicable scenario of the candidate language element; and the language element determination module is used to:

[0068] Performing semantic understanding on the copy content prompt information to obtain a semantic understanding result;

[0069] Based on the semantic understanding result and the associated information of the candidate language elements in the target corpus, determining the degree of compatibility between the copy content prompt information and the candidate language elements;

[0070] Based on the degree of compatibility between the text content prompt information and the candidate language elements, a target language element is determined in the target corpus.

[0071] Furthermore, the copywriting generation module is used to:

[0072] Generate an intermediate copy based on the copy content prompt information and the target language elements;

[0073] Based on the prompt information of the copy content and taking the intermediate copy as a basis, the target copy is obtained by continuing to write; the target copy includes the intermediate copy.

[0074] Furthermore, the copywriting generation module is used to:

[0075] Obtaining location information of the intermediate copy in the target copy;

[0076] Based on the content prompt information of the copy and the position information of the intermediate copy in the target copy, the intermediate copy is used as a basis for continued writing to obtain the target copy.

[0077] Furthermore, the device also includes a corpus building module, which is used to:

[0078] Determining candidate language elements based on the preset determination conditions; the preset determination conditions are related to the text quality standard;

[0079] Determining association information corresponding to the candidate language element;

[0080] The candidate language element and the associated information corresponding thereto are added as a record to the target corpus.

[0081] Furthermore, the corpus building module is used to:

[0082] Acquire a segment including the candidate language element;

[0083] By performing semantic understanding on a segment including the candidate language element, associated information corresponding to the candidate language element is determined.

[0084] Furthermore, the preset determination condition includes that a heat parameter of a language element is greater than or equal to a set threshold; and / or,

[0085] The content prompt information of the target copy includes at least one of the following: the subject, outline, keywords, summary and conclusion of the target copy.

[0086] The document generation device provided in the embodiment of the present disclosure can execute the steps executed by the client or server in the document generation method provided in the embodiment of the method of the present disclosure, and has execution steps and beneficial effects, which will not be repeated here.

[0087] Figure 3 Schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 3, which shows a schematic diagram of the structure of an electronic device 1000 suitable for implementing the embodiment of the present disclosure. The electronic device 1000 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), wearable electronic devices, etc., and fixed terminals such as digital TVs, desktop computers, smart home devices, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0088] like Figure 3 As shown, the electronic device 1000 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1008 to a random access memory (RAM) 1003 to implement the copywriting generation method of the embodiment described in the present disclosure. In the RAM 1003, various programs and information required for the operation of the electronic device 1000 are also stored. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0089] Typically, the following devices may be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device 1000 to communicate with other devices wirelessly or by wire to exchange information. Although Figure 3 The electronic device 1000 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0090] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the copywriting generation method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0091] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include an information signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated information signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0092] In some embodiments, the client and the server may communicate using any known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital information communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any known or future developed network.

[0093] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0094] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0095] Loading a target corpus; the target corpus includes a plurality of candidate language elements; the candidate language elements are language elements that meet a preset determination condition;

[0096] Obtaining content prompt information of a target copy; the target copy is a copy to be generated;

[0097] Based on the text content prompt information, determining a target language element adapted to the target text in the target corpus;

[0098] A target copy is generated based on the copy content prompt information and the target language element; the target copy includes the target language element; and the target language element is used to construct sentences or paragraphs of the target copy.

[0099] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0100] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0101] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0102] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0103] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0104] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0105] According to one or more embodiments of the present disclosure, the present disclosure provides an electronic device, including:

[0106] one or more processors;

[0107] A memory for storing one or more programs;

[0108] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the document generation methods provided in the present disclosure.

[0109] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the program implements any of the document generation methods provided by the present disclosure.

[0110] The embodiments of the present disclosure further provide a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the method for generating text as described above is implemented.

[0111] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0112] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A copywriting generation method, characterized in that: include: Load the target corpus; The target corpus includes a plurality of candidate language elements; The candidate language element is a language element that meets a preset determination condition; Get the content prompt information of the target copy; The target text is the text to be generated; Based on the text content prompt information, determining a target language element adapted to the target text in the target corpus; Generate a target copy based on the copy content prompt information and the target language element; the target copy includes the target language element; The target language elements are used to construct sentences or paragraphs of the target text.

2. The method according to claim 1, characterized in that The target corpus includes a plurality of records, each of which includes a candidate language element and associated information of the candidate language element; the associated information of the candidate language element is information used to reflect the applicable scenario of the candidate language element; The determining, based on the text content prompt information, a target language element adapted to the target text in the target corpus includes: Performing semantic understanding on the copy content prompt information to obtain a semantic understanding result; Based on the semantic understanding result and the associated information of the candidate language elements in the target corpus, determining the degree of compatibility between the copy content prompt information and the candidate language elements; Based on the degree of compatibility between the text content prompt information and the candidate language elements, a target language element is determined in the target corpus.

3. The method according to claim 1, characterized in that The generating a target copy based on the copy content prompt information and the target language element includes: Generate an intermediate copy based on the copy content prompt information and the target language elements; Based on the prompt information of the copy content and taking the intermediate copy as a basis, the target copy is obtained by continuing to write; the target copy includes the intermediate copy.

4. The method according to claim 3, characterized in that The step of continuing writing based on the prompt information of the copy content and taking the intermediate copy as a basis to obtain the target copy further includes: Obtaining location information of the intermediate copy in the target copy; Based on the content prompt information of the copy and the position information of the intermediate copy in the target copy, the intermediate copy is used as a basis for continued writing to obtain the target copy.

5. The method according to claim 2, characterized in that: The method for constructing the target corpus includes: Determining candidate language elements based on the preset determination conditions; the preset determination conditions are related to the text quality standard; Determining association information corresponding to the candidate language element; The candidate language element and the associated information corresponding thereto are added as a record to the target corpus.

6. The method according to claim 5, characterized in that The determining of the associated information corresponding to the candidate language element includes: Acquire a segment including the candidate language element; By performing semantic understanding on a segment including the candidate language element, associated information corresponding to the candidate language element is determined.

7. The method according to claim 5, characterized in that The preset judgment condition includes that the heat parameter of the language element is greater than or equal to a set threshold; and / or, The content prompt information of the target copy includes at least one of the following: the subject, outline, keywords, summary and conclusion of the target copy.

8. A copywriting generation device, characterized in that: include: A loading module, used for loading a target corpus; the target corpus includes a plurality of candidate language elements; The candidate language element is a language element that meets a preset determination condition; An acquisition module is used to obtain the content prompt information of the target copy; The target text is the text to be generated; A language element determination module, configured to determine, in the target corpus, a target language element adapted to the target text based on the text content prompt information; A copywriting generation module, configured to generate a target copywriting based on the copywriting content prompt information and the target language element; the target copywriting includes the target language element; The target language elements are used to construct sentences or paragraphs of the target text.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

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

Images