Cboth generation method, system and equipment and storage medium

Abstract

The invention provides a copywriting generation method, system and device and a storage medium, and the method comprises the steps: setting a plurality of copywriting demand frameworks based on a preset copywriting generation scene; in the copywriting demand framework, embedding interest point information corresponding to the copywriting generation scene so as to limit a generation content range corresponding to the copywriting demand framework; performing copywriting generation evaluation on the copywriting demand framework embedded with the interest point information so as to select and store the copywriting demand framework passing the evaluation; and generating required copywriting in batches based on the copywriting demand framework according to the copywriting generation demand. Through the technical scheme provided by the invention, the set text demand framework can be utilized to generate high-quality social media platform delivery copywriting in batches according to the customized demand; in the setting process of the text demand framework, on the basis of embedding and splicing of the content feature information, the limiting feature information and the interest point information, batch copywriting can be generated within a limited range, errors are avoided, it is guaranteed that the generated copywriting is effective, accurate and novel, meanwhile, the labor cost is greatly saved, and the work efficiency is improved. And the generated copywriting can be put to a social media platform to realize corresponding promotion and drainage functions and the like, and has a promotable value.

Description

Background Art

[0002] In the era of digital marketing, social media platforms have become an important channel for brand promotion and user interaction. Traditional social media content publishing usually relies heavily on manual creation, which involves material collection, content planning, writing and review, requiring a lot of human resources, low efficiency and high cost. With the rapid development of artificial intelligence technology, operations colleagues can directly use AI to generate copy to improve creation efficiency, but they will also face the following problems in the process:

[0003] 1) The quality of generated content fluctuates greatly and there are homogeneity issues, and the results still need to be manually reviewed and modified.

[0004] 2) Generative AI models are prone to "hallucination problems" when generating copy, which can generate some erroneous information and affect brand credibility.

[0005] 3) There is a lack of platform tools that can be used directly, and the copywriting requirements need to be written manually each time, and the corresponding copywriting needs to be generated in batches according to the copywriting requirements. There is a lot of repetitive work and it requires a lot of human resources. Summary of the invention

[0006] In view of the problems in the prior art, the purpose of the present disclosure is to provide a copywriting generation method, system, device and storage medium. Specifically, the first aspect of the present disclosure provides a copywriting generation method, which may include the following steps:

[0007] A method for generating a copy, characterized in that it comprises the following steps:

[0008] Based on the preset copy generation scenario, multiple copy requirement frameworks are set, wherein the copy requirement frameworks include multiple content feature information and limiting feature information;

[0009] In the copy requirement framework, the point of interest information corresponding to the copy generation scenario is embedded to limit the scope of generated content corresponding to the copy requirement framework;

[0010] Generating a copy evaluation on the copy requirement framework embedded with the point of interest information, so as to select and store the copy requirement framework that passes the evaluation;

[0011] According to the copy generation requirements, the required copy is generated in batches based on the copy requirement framework.

[0012] In a possible implementation of the first aspect, the content feature information includes at least one or a combination of multiple items of copy role setting information, copy generation description information, generation step description information, reverse sensitive word information, and instance information;

[0013] In the case where the copy requirement framework generates copy content for tourism-related products, the content feature information includes at least one variable field;

[0014] The variable fields include at least one or a combination of multiple items of the following: tourism scene, tourism destination area, tourism period, tourism travel time, and text demand content;

[0015] In the process of setting the copywriting requirement framework, the corresponding text requirement content is obtained according to one or more characteristic variable values ​​of the tourism scene, the tourism destination area, the tourism period, and the travel time.

[0016] In a possible implementation of the first aspect above, the limiting feature information includes word limit information corresponding to the required copy and / or additional information for generating the copy; and

[0017] The limiting characteristic information is associated with the required copy generated in the same batch;

[0018] The limiting feature information is spliced ​​with the content feature information to generate a copywriting requirement framework.

[0019] In a possible implementation of the first aspect, when the copy requirement framework generates copy content for tourism-related products, the point of interest information includes real-time updated strategy route information and / or scenic spot business information associated with the tourism destination area;

[0020] In the process of embedding the POI information corresponding to the copywriting generation scenario, the guide route information and scenic spot business information related to all tourist destination areas are extracted through the database as the generated content scope.

[0021] In a possible implementation of the first aspect, generating a copy evaluation for a copy requirement framework embedded with point of interest information includes the following steps:

[0022] According to the preset copy generation requirements, different copy requirement frameworks are called to generate corresponding copy to be evaluated;

[0023] Based on a preset evaluation model, the quality of the documents to be evaluated and the degree of similarity between the documents to be evaluated are evaluated to screen multiple primary screening results;

[0024] Based on the preset screening criteria, a preferred copywriting requirement framework is screened out from the first screening results, and the preferred copywriting requirement framework is used as the copywriting requirement framework that has passed the evaluation.

[0025] In a possible implementation of the first aspect, in the process of batch generating required documents according to the document generation requirement, the following steps are included:

[0026] Provide a configuration interface corresponding to the copywriting requirement framework, which includes multiple variable field configuration windows;

[0027] According to the copy generation requirements received by the configuration interface, the copy requirement framework is called to generate corresponding copy requirement information;

[0028] According to the copy requirement information, call the preset copy generation model to batch generate the required copy.

[0029] In a possible implementation of the first aspect above, the configuration interface includes a randomness adjustment window for configuring the required similarity of the batch-generated texts according to the text generation requirements;

[0030] The randomness adjustment value corresponding to the randomness adjustment window is inversely proportional to the degree of similarity between the required copies.

[0031] The second aspect of the present disclosure provides a document generation system for implementing the document generation method provided in the first aspect, which may specifically include:

[0032] A copy requirement framework configuration unit, used to set multiple copy requirement frameworks based on preset copy generation scenarios, wherein the copy requirement frameworks include multiple content feature information and limited feature information;

[0033] A copy limitation configuration unit, used to embed the interest point information corresponding to the copy generation scenario in the copy requirement framework, so as to limit the generated content scope corresponding to the copy requirement framework;

[0034] A copy requirement framework evaluation unit, used to generate a copy evaluation for the copy requirement framework embedded with the point of interest information, so as to select and store the copy requirement framework that passes the evaluation;

[0035] The copy generation unit is used to generate the required copy in batches according to the copy generation requirements and based on the copy requirement framework.

[0036] A third aspect of the present disclosure provides a copywriting generation device, comprising:

[0037] processor;

[0038] a memory in which executable instructions for the processor are stored;

[0039] The processor is configured to execute the steps of the text generation method provided in the first aspect by executing executable instructions.

[0040] A fourth aspect of the present disclosure provides a computer-readable storage medium for storing a program, which, when executed, implements the steps of the text generation method provided in the first aspect.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] Through the technical solution provided by the present invention, it is possible to utilize the set text demand framework to generate batches of high-quality social media platform delivery copy according to customized needs; in the process of setting the text demand framework, based on the embedding and splicing of content feature information, limited feature information and point of interest information, batch copy can be generated within a limited range to avoid errors. While ensuring that the generated copy is effective, accurate and novel, it greatly saves labor costs. The generated copy can be delivered to social media platforms to realize corresponding promotion, traffic diversion and other functions, and has promotional value. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Other features, objects and advantages of the present disclosure will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following accompanying drawings.

[0044] Figure 1 According to an embodiment of the present disclosure, a flowchart of a copywriting generation method is provided.

[0045] Figure 2a According to an embodiment of the present disclosure, a flow chart of generating a copy evaluation for a copy requirement framework embedded with point of interest information is provided.

[0046] Figure 2b According to an embodiment of the present disclosure, a flow chart of batch generating required documents according to document generation requirements is provided.

[0047] Figure 3 According to an embodiment of the present disclosure, a flow chart of obtaining corresponding defect prediction results according to a service defect prediction model is provided.

[0048] Figure 4 According to an embodiment of the present disclosure, a storage example of specific items in a locally stored copywriting requirement framework is provided.

[0049] Figure 5 According to an embodiment of the present disclosure, a structural schematic diagram of a copywriting generation system is provided.

[0050] Figure 6 According to an embodiment of the present disclosure, a structural schematic diagram of a copywriting generation device is provided.

[0051] Figure 7 According to an embodiment of the present disclosure, a schematic diagram of the structure of a computer-readable storage medium is provided. DETAILED DESCRIPTION

[0052] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the present application. The present application can also be implemented or applied through other different specific implementation methods, and the details in the present application can also be modified or changed in various ways according to different viewpoints and application systems without departing from the spirit of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0053] The following is a detailed description of the embodiments of the present application with reference to the accompanying drawings so that those skilled in the art can easily implement the present application. The present application can be embodied in a variety of different forms and is not limited to the embodiments described herein.

[0054] In the representations of the present application, the representations with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics represented in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the represented specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples represented in the present application and the features of the different embodiments or examples, unless they contradict each other.

[0055] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the representation of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0056] In order to clearly describe the present application, components irrelevant to the description are omitted, and the same reference symbols are given to the same or similar components throughout the specification.

[0057] Throughout the specification, when a device is said to be "connected" to another device, this includes not only the case of "direct connection" but also the case of "indirect connection" by placing other elements therebetween. In addition, when a device is said to "include" a certain component, unless otherwise stated, it does not exclude other components, but means that other components may be included.

[0058] When a device is said to be "on" another device, it may be directly on the other device, but there may also be other devices between it. In contrast, when a device is said to be "directly" on another device, there are no other devices between it.

[0059] Although the terms first, second, etc. are used to represent various elements in some examples, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first interface and the second interface, etc. are represented. Moreover, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate the existence of features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". Only when the combination of elements, functions, steps or operations is inherently mutually exclusive in some way, will there be an exception to this definition.

[0060] The technical terms used herein are only used to refer to specific embodiments and are not intended to limit the present application. The singular form used herein also includes the plural form unless the sentence clearly indicates the contrary meaning. The meaning of "including" used in the specification is to specify specific characteristics, regions, integers, steps, operations, elements and / or components, and does not exclude the existence or addition of other characteristics, regions, integers, steps, operations, elements and / or components.

[0061] Although not defined differently, all terms, including technical and scientific terms used herein, have the same meaning as those generally understood by those skilled in the art to which this application belongs. Terms defined in commonly used dictionaries are additionally interpreted as having meanings consistent with the relevant technical literature and the contents of the current disclosure, and unless defined, shall not be overly interpreted as ideal or very formal meanings.

[0062] In some embodiments of the present disclosure, Figure 1 According to a process diagram of a copywriting generation method, a method is provided. Figure 1 As shown, the copywriting generation method may specifically include:

[0063] Step 101: Based on the preset copy generation scenario, multiple copy requirement frameworks are set. Specifically, the copy requirement framework includes multiple content feature information and limited feature information. The specific settings of the content feature information and limited feature information will be described in detail later.

[0064] Step 102: In the copy requirement framework, the interest point information corresponding to the copy generation scenario is embedded to limit the scope of the generated content corresponding to the copy requirement framework. It is understandable that in order to overcome the hallucination problem that may occur in the generative artificial intelligence model, it can be circumvented by further limiting the interest point information. The specific settings of the interest points will be further explained later.

[0065] Step 103: Evaluate the generated copywriting requirements framework embedded with the POI information, and select and store the copywriting requirements framework that has passed the evaluation. The specific evaluation of the copywriting requirements framework will be further described later.

[0066] Step 104: According to the copywriting generation requirements, the required copywriting is generated in batches based on the copywriting requirement framework. It can be understood that based on the above steps 101 to 104, the automatic batch generation of high-quality social media platform delivery copywriting can be achieved. The specific implementation of the above steps 101 to 104 will be further explained below:

[0067] In the above embodiment, the content feature information may include at least one or more of the following: copy role setting information, copy generation description information, generation step description information, reverse sensitive word information, and instance information, wherein the copy role setting information is associated with the author and publisher of the generated copy; the copy generation description information includes various requirements for batch generation of copy; the generation step description information sets requirements and limitations on the possible traffic diversion scenarios that may appear in the copy; the reverse sensitive word information is used to remove prohibited publication information of the copy placed on the social media platform; the instance information is a reference example for copy generation, which is not limited here.

[0068] In the above embodiment, specifically, when the copy requirement framework generates copy content for tourism-related products, the content feature information includes at least one variable field, wherein the variable field includes at least one or more combinations of tourism scenes, tourism destination areas, tourism time periods, tourism travel time, and text requirement content; in the process of setting the copy requirement framework, the corresponding text requirement content can be obtained based on the characteristic variable values ​​of one or more of the tourism scenes, tourism destination areas, tourism time periods, and tourism travel time, which are not limited here.

[0069] In the above embodiment, the limiting feature information includes the word limit information corresponding to the required copy and / or the additional information of the generated copy. The limiting feature information is different from the relatively fixed content feature information mentioned above, and can be adaptively adjusted by the user according to the generated copies of different batches, that is, the limiting feature information is associated with the required copies generated in the same batch. By splicing the limiting feature information with the content feature information, the preliminary required copy requirement framework can be obtained.

[0070] In the above embodiment, in the specific implementation of the aforementioned step 102, when the copy demand framework generates copy content for tourism-related products, the point of interest information includes real-time updated strategy route information and / or scenic spot business information associated with the tourist destination area. It is understandable that in order to ensure the authenticity and reliability of the copy content in the subsequent specific generation process of the copy and avoid the illusion problem in the artificial intelligence generation process, the corresponding point of interest information can be embedded in the copy demand framework, thereby giving a specific content generation range, thereby effectively controlling the timeliness and accuracy of the copy generation content. Specifically, in the scenario where the copy demand framework generates copy content for tourism-related products, the point of interest information can include the latest business information of the strategy routes and various scenic spots stored in various countries. In the specific embedding process, the strategy route information and scenic spot business information associated with all tourist destinations can be extracted through the database, and spliced ​​in the copy demand framework as the generated content range limit. It is particularly important to note that the above-mentioned point of interest information is updated in real time and can meet the changes in the routes of tourist destinations in different periods.

[0071] In the above embodiment, in the specific implementation of the above step 103, Figure 2a FIG. 1 shows a flow chart of generating a copywriting evaluation for a copywriting requirement framework embedded with point of interest information. Figure 2a As shown, the following steps may be specifically included:

[0072] Step 103a: According to the preset copy generation requirements, different copy requirement frameworks are called to generate corresponding copies to be evaluated.

[0073] Step 103b: Based on the preset evaluation model, the copy quality of the copy to be evaluated and the similarity between the copy to be evaluated are evaluated to screen multiple one-time screening results. Among them, the copy content generated for different copy requirement frameworks can be scored by the preset evaluation model first, and the scoring includes the copy content quality and the similarity between the copy, wherein the copy content quality includes but is not limited to the fluency of the sentences, the typos, whether there is misleading information, whether there is uncertain information, whether it can attract readers and other multi-dimensional considerations; the similarity is used to judge the similarity between the copy content corresponding to different copy requirement frameworks. In an optional specific implementation of the present disclosure, a copy requirement framework with a copy content quality score greater than a first preset threshold and a similarity score lower than a second preset threshold can be selected as a one-time screening result, which is not limited here.

[0074] Step 103c: Based on the preset screening criteria, a preferred copywriting requirement framework is screened from the first screening results, and the preferred copywriting requirement framework is used as the copywriting requirement framework that has passed the evaluation. It is understandable that in the specific implementation of step 103c, further manual screening can be performed based on the first screening results to obtain the corresponding preferred copywriting requirement framework, wherein the requirements of the preferred copywriting requirement framework include that the copywriting generated by the framework is of high quality, and the difference between the generated copywriting and other copywriting requirement frameworks is large. The preferred copywriting requirement framework that best meets the requirements can be screened from multiple copywriting requirement frameworks based on the above two evaluation criteria based on manual review.

[0075] In the above embodiment, in the specific implementation of the above step 104, Figure 2b A flow chart of batch generating required documents according to document generation requirements is provided, such as Figure 2b As shown, the following steps may be specifically included:

[0076] Step 104a: Provide a configuration interface corresponding to the copywriting requirement framework. Figure 3 A schematic diagram of a configuration interface is provided, such as Figure 3 As shown, the configuration interface includes configuration windows corresponding to multiple variable fields, which respectively correspond to the adjustable variable fields corresponding to the content feature information.

[0077] Step 104b: Based on the copywriting generation requirements received by the configuration interface, the copywriting requirement framework is called to generate corresponding copywriting requirement information. The specific acquisition of the copywriting requirement information will be described in detail later. It can be understood that by Figure 3 The visual configuration interface shown can facilitate users to perform specific configuration of the copywriting requirement framework, avoiding the need for users to manually compile each copywriting requirement information, thereby greatly reducing the required manual workload.

[0078] Step 104c: Based on the copy requirement information, call the preset copy generation model to batch generate the required copy. In an alternative specific implementation of the present disclosure, the GPT-4o model can be selected for copy generation, and the copy generated by it is more complete and in line with expectations. Those skilled in the art can also select other copy generation models according to actual needs, which is not limited here.

[0079] In the above embodiment, further, Figure 3 As shown, the configuration interface includes a randomness adjustment window, namely Figure 3The random horizontal pull-down window in is used to configure the similarity of the required copy generated in batches according to the copy generation requirements. It is understandable that since it is necessary to generate copy in batches according to the copy requirement framework and deliver it on the social media platform, it is required that the copy generated in the same batch have differences. Therefore, the parameter of random adjustment value is introduced in the above specific implementation. The random adjustment value is inversely proportional to the similarity between the required copy. The larger the random adjustment value, the lower the similarity between the generated copy, thereby solving the homogenization problem that may occur when generating copy in batches. The above random adjustment value can be set and adjusted as needed by the user through the random adjustment window of the configuration interface, and is not limited here.

[0080] The following is an exemplary description of the training of the copywriting requirement framework and the process of batch generating the required copywriting in combination with a specific embodiment:

[0081] In a specific embodiment of the present disclosure, during the setting stage of the copywriting requirement framework, the fixed content feature information in the copywriting requirement framework can be configured into the following five parts, namely, copywriting role setting information, copywriting generation description information, generation step description information, reverse sensitive word information, and instance information. Figure 3 In the configuration interface shown, if the scene is selected as "Special Forces", the country is "China", the time is "3" days, and the season is "Dragon Boat Festival", the generated copywriting requirement framework can be as follows:

[0082] Among them, the copy role setting information may include "as a travel blogger on XX social media platform, I publish travel-related guide information on a daily basis"; the copy generation instruction information may include "the copy style on XX social media platform requires vivid descriptive details and emotional resonance, concise and clear in form, and the use of different emoticons to make the content readable; currently it is necessary to generate a copy in the style of XX social media platform, the content shows users the nearest travel routes from Shanghai, ensures smooth sentences, and does not fabricate information"; the generation step instruction information may include "in the generated copy, guide users to go to the business travel platform to search for 'special forces' or 'special forces travel'"; the reverse sensitive word information may include "the word 'search' should not appear in the copy, it can be replaced by 'Sou' or a magnifying glass emoticon; no specific travel train information should appear; the number of emoticons used in each copy should be controlled in the range of 2 to 4; no specific city names or scenic spot names should appear; no politically sensitive topics should appear; no unverified uncertain information should appear"; the example information may provide a specific reference example. In order to train different copywriting demand frameworks for variable fields such as travel scenarios, travel destinations, and travel periods, a statement similar to "It is the Dragon Boat Festival travel season now, please reflect the time of the Dragon Boat Festival travel and recommend a suitable place for the Dragon Boat Festival travel" can be added to the generated copywriting demand framework to highlight the differences between the copywriting demand frameworks corresponding to different variable fields. The above copywriting demand framework is configured to be able to pass the generated copywriting evaluation, which will not be repeated here.

[0083] In order to ensure the timeliness and accuracy of the relevant guide routes in the copy generation, it is necessary to integrate the guide route information and / or scenic spot business information related to the tourist destination area as point of interest information into the copy demand framework, and update these point of interest information in real time to ensure timeliness and accuracy, thereby reducing the illusion problems that may occur in the process of artificial intelligence copy generation. Exemplarily, in the copy demand framework for recommending guide routes, guide routes with a comprehensive score greater than 70 points in different countries and different number of days of play can be selected from the information table corresponding to the point of interest information set, and these real-time updated guide routes are added to the corresponding copy demand framework instructions, so that in the subsequent copy generation process, only these guide routes can be screened for corresponding copy generation, and the attractions in the screened guide routes are highlighted. Exemplarily, the code implementation for accessing the point of interest information and splicing it with the copy demand framework can be as follows:

[0084] Select 'Travel' as scene,

[0085] countrynames,

[0086] ”As festival,

[0087] play_days,

[0088] CONCAT(route_describe,char(10),prompt,char(10),requirement,char(10),reference)

[0089]

[0090] regexp_replace(requirement,'·',char(10))asrequirement,

[0091] regexp_replace(reference,'·',char(10))as reference

[0092] from prompt_fix

[0093] )a2

[0094] on a1.countrynames=a2.country )

[0096] When the available copywriting requirement framework and its corresponding content are finally determined, the copywriting requirement framework and its corresponding content can be stored in a local HIVE table. For example, Figure 4 The following figure shows an example of storing specific items in a locally stored copywriting requirement framework. In the process of generating copywriting according to the copywriting requirement framework, the content can be transmitted to the development in the form of QMQ to achieve efficient inter-process communication. Subsequent users can directly use Figure 3 In the configuration interface shown, the copywriting requirement framework is retrieved according to the circled variable content and the corresponding copywriting generation requirements are generated. Then, the GPT-4o model is called according to the copywriting generation requirements to generate batches of copywriting and publish them on social media platforms. Specifically, the code implementation of the copywriting requirement framework transmission can be as follows:

[0097] -querys"select json from aiprompt"\

[0098] -tar qmq\

[0099] -writer_subject"generate.prompt"\

[0100] In some embodiments of the present disclosure, Figure 5A structural diagram of a copywriting generation system is provided. Figure 5 As shown, the document generation system is used to implement the document generation method provided in the above embodiment, which may specifically include:

[0101] The copy requirement framework configuration unit 501 is used to set multiple copy requirement frameworks based on preset copy generation scenarios, wherein the copy requirement framework includes multiple content feature information and limited feature information, which will not be described in detail here.

[0102] The copy limitation configuration unit 502 is used to embed the interest point information corresponding to the copy generation scenario in the copy requirement framework to limit the generation content scope corresponding to the copy requirement framework.

[0103] The copy requirement framework evaluation unit 503 is used to generate a copy evaluation for the copy requirement framework embedded with the point of interest information, so as to select and store the copy requirement framework that passes the evaluation.

[0104] The copywriting generating unit 504 is used to generate required copies in batches according to copywriting generation requirements and based on a copywriting requirement framework.

[0105] It can be understood that the functions implemented by the copy requirement framework configuration unit 501 to the copy generation unit 504 in the above functional modules correspond one-to-one to the actions performed in the above steps 101 to 104, and will not be described in detail here.

[0106] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0107] Specifically, Figure 6 According to an embodiment of the present disclosure, a schematic diagram of the structure of a copywriting generation device is shown. Figure 6 The electronic device 600 according to this embodiment of the present disclosure is described. Figure 6 The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0108] like Figure 6 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0109] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present disclosure. For example, the processing unit 610 can perform the following steps: Figure 1 The relevant steps of the copy generation method shown in .

[0110] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 6201 and / or a cache storage unit 6202 , and may further include a read-only storage unit (ROM) 6203 .

[0111] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0112] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0113] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0114] The embodiment of the present disclosure also provides a computer-readable storage medium for storing a program, and the steps of the text generation method are implemented when the program is executed. In some possible implementations, various aspects of the present disclosure can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above text generation method section of this specification.

[0115] Specifically, Figure 7 According to an embodiment of the present disclosure, a schematic diagram of the structure of a computer-readable storage medium is shown. Figure 7 As shown, a program product 800 for implementing the above-mentioned copywriting generation method according to an embodiment of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0116] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The 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 thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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 thereof.

[0117] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, in which readable program codes are carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0118] The program code for executing the specific implementation operations of the copywriting generation method provided by the aforementioned embodiments of the present disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0119] To sum up, through the technical solution provided by the present invention, it is possible to utilize the set text demand framework to generate batches of high-quality social media platform delivery copy according to customized needs; in the process of setting the text demand framework, based on the embedding and splicing of content feature information, limited feature information and point of interest information, batch copy can be generated within a limited range to avoid errors. While ensuring that the generated copy is effective, accurate and novel, it greatly saves labor costs. The generated copy can be delivered to social media platforms to realize corresponding promotion, traffic diversion and other functions, and has promotional value.

[0120] The above content is a further detailed description of the present disclosure in combination with specific preferred implementation modes, and it cannot be determined that the specific implementation of the present disclosure is limited to these descriptions. For ordinary technicians in the technical field to which the present disclosure belongs, several simple deductions or substitutions can be made without departing from the concept of the present disclosure, which should be regarded as falling within the scope of protection of the present disclosure.

Claims

1. A copywriting generation method, characterized in that: The steps include: Based on a preset copywriting generation scenario, a plurality of copywriting requirement frameworks are set, wherein the copywriting requirement frameworks include a plurality of content feature information and limiting feature information; In the copy requirement framework, the point of interest information corresponding to the copy generation scenario is embedded to limit the scope of generated content corresponding to the copy requirement framework; Performing a copy generation evaluation on the copy requirement framework embedded with the point of interest information, so as to select and store a copy requirement framework that passes the evaluation; According to the copy generation requirements, the required copy is generated in batches based on the copy requirement framework.

2. The method for generating a copywriting according to claim 1, wherein: The content feature information includes at least one or a combination of multiple items of copywriter role setting information, copywriting generation description information, generation step description information, reverse sensitive word information, and instance information; In the case where the copy requirement framework generates copy content for tourism-related products, the content feature information includes at least one variable field; The variable field includes at least one or a combination of multiple items of the following: tourism scene, tourism destination area, tourism time period, tourism travel time, and text demand content; In the process of setting the text requirement framework, the corresponding text requirement content is obtained according to one or more characteristic variable values ​​of the travel scene, the travel destination area, the travel time period, and the travel time.

3. The method for generating a copywriting according to claim 1, wherein: The limiting feature information includes the word limit information corresponding to the required copy and / or the additional information of the generated copy; and The limiting characteristic information is associated with the required documents generated in the same batch; The limiting feature information is combined with the content feature information to generate the copywriting requirement framework.

4. The method for generating a copywriting according to claim 2, wherein: In the case where the copy demand framework generates copy content for tourism-related products, the point of interest information includes real-time updated strategy route information and / or scenic spot business information associated with the tourism destination area; In the process of embedding the POI information corresponding to the text generation scenario, the strategy route information and the scenic spot business information associated with all the tourist destination areas are extracted from the database as the generated content scope.

5. The method for generating a copywriting according to claim 1, wherein: The step of generating a copy evaluation for the copy requirement framework embedded with the point of interest information comprises the following steps: According to the preset copy generation requirements, different copy requirement frameworks are called to generate corresponding copies to be evaluated; Based on a preset evaluation model, the quality of the documents to be evaluated and the degree of similarity between the documents to be evaluated are evaluated to screen multiple primary screening results; Based on the preset screening criteria, a preferred copywriting requirement framework is screened out from the first screening results, and the preferred copywriting requirement framework is used as the copywriting requirement framework that has passed the evaluation.

6. The method for generating a copywriting according to claim 2, wherein: The process of batch generating the required documents according to the document generation requirements includes the following steps: Providing a configuration interface corresponding to the copywriting requirement framework, the configuration interface including multiple variable field configuration windows; According to the copy generation requirement received by the configuration interface, calling the copy requirement framework to generate corresponding copy requirement information; According to the copy requirement information, a preset copy generation model is called to batch generate the required copy.

7. The method for generating a copywriting according to claim 6, wherein: The configuration interface includes a randomness adjustment window for configuring the required similarity of the batch-generated documents according to the document generation requirements; The randomness adjustment value corresponding to the randomness adjustment window is inversely proportional to the similarity between the required documents.

8. A document generation system, used to implement the document generation method described in any one of claims 1 to 7, characterized in that: include: A copy requirement framework configuration unit, used to set a plurality of copy requirement frameworks based on a preset copy generation scenario, wherein the copy requirement frameworks include a plurality of content feature information and limiting feature information; A copy limit configuration unit, used to embed the interest point information corresponding to the copy generation scenario in the copy requirement framework to limit the generated content scope corresponding to the copy requirement framework; A copy requirement framework evaluation unit, used to generate a copy evaluation for the copy requirement framework embedded with the interest point information, so as to select and store the copy requirement framework that passes the evaluation; The copywriting generation unit is used to generate required copies in batches according to copywriting generation requirements and based on the copywriting requirement framework.

9. A copywriting generation device, characterized in that: include: processor; a memory storing executable instructions of the processor; Wherein, the processor is configured to execute the steps of the text generation method described in any one of claims 1 to claim 7 by executing the executable instructions.

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

Images