Method and system for generating copywriting, computing device and medium

Abstract

The embodiment of the invention provides a method and system for generating a copywriting, computing equipment and a medium. The method comprises the steps of receiving prompt words input by a user; obtaining a first keyword from the prompt word; using the vector representation of the cue word to retrieve enhancement information associated with the cue word and a second keyword associated with the enhancement information from a vector index database; generating an enhanced cue word using enhancement information based on a comparison of the first keyword and the second keyword; and providing the enhanced cue word to the language model to generate a copywriting. In this way, the quality of the cue word input into the language model can be improved, and therefore the quality of the generated copywriting is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of information processing technology, and more specifically, to a method, system, computing device, computer-readable storage medium, and computer program product for generating documents. Background Art

[0002] In the short video copywriting scenario, the Large Language Model (LLM) can quickly generate copywriting that meets user requirements based on prompts with a small amount of training data or even no training data due to its advantage in parameter magnitude, greatly reducing the copywriting cost of short videos, especially oral short videos.

[0003] At present, a mainstream process of generating short video copy based on LLM is that users give specific prompt words based on the short video theme, style, etc., and input them into LLM. LLM can return the video copy that meets the requirements under the constraints of the corresponding prompt words. However, due to the limitations of LLM's capabilities, the copy obtained in this way may not meet the diverse needs of users. Summary of the invention

[0004] In view of this, the present disclosure provides a method, system, computing device, computer-readable storage medium and computer program product for generating copy, which can enhance the prompt words input by the user by retrieving and utilizing an existing knowledge base, and then input the enhanced prompt words into a language model to generate a target copy, thereby providing users with higher quality copy.

[0005] According to a first aspect of the present disclosure, a method for generating copy is provided, comprising: receiving a prompt word input by a user; obtaining a first keyword from the prompt word; using a vector representation of the prompt word, retrieving enhanced information associated with the prompt word and a second keyword associated with the enhanced information from a vector index database; based on a comparison between the first keyword and the second keyword, using the enhanced information to generate an enhanced prompt word; and providing the enhanced prompt word to a language model to generate copy.

[0006] According to a second aspect of the present disclosure, a system for generating copy is provided, comprising: a prompt word receiving unit, configured to receive a prompt word input by a user; a keyword extraction unit, configured to obtain a first keyword from the prompt word; an enhanced information acquisition unit, configured to use a vector representation of the prompt word to retrieve enhanced information associated with the prompt word and a second keyword associated with the enhanced information from a vector index database; a prompt word enhancement triggering unit, configured to generate an enhanced prompt word using the enhanced information based on a comparison between the first keyword and the second keyword; and a copy generating unit, configured to provide the enhanced prompt word to a language model to generate copy.

[0007] According to a third aspect of the present disclosure, a computing device is provided, comprising: at least one processing unit; and at least one memory, wherein the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, wherein the instructions, when executed by the at least one processing unit, enable the computing device to execute the method as described in the first aspect of the present disclosure.

[0008] According to a fourth aspect of the present disclosure, a non-transitory computer storage medium is provided, comprising machine executable instructions, which, when executed by a device, cause the device to perform the method as described in the first aspect of the present disclosure.

[0009] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising machine executable instructions, which, when executed by a device, cause the device to perform the method as described in the first aspect of the present disclosure.

[0010] It should be understood that the invention summary is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other objects, features and advantages of the embodiments of the present disclosure will become more easily understood through the following detailed description with reference to the accompanying drawings. In the accompanying drawings, various embodiments of the present disclosure will be described in an exemplary and non-limiting manner, in which:

[0012] Figure 1 A block diagram showing a computing device capable of implementing various embodiments of the present disclosure;

[0013] Figure 2 A schematic block diagram showing a framework of a copywriting generator according to an embodiment of the present disclosure;

[0014] Figure 3A schematic diagram of a process for generating a copy according to an embodiment of the present disclosure is shown;

[0015] Figure 4 A schematic diagram of a prompt word enhancement trigger module according to an embodiment of the present disclosure is shown;

[0016] Figure 5 A schematic block diagram showing a framework of a copywriting generator based on creative intent categories according to an embodiment of the present disclosure;

[0017] Fig. 6A A schematic diagram of an initial text input page for generating a copy according to an embodiment of the present disclosure is shown;

[0018] Figure 6B A schematic diagram of an input page of an intelligent copywriting system for generating a copy according to an embodiment of the present disclosure is shown;

[0019] Figure 6C A schematic diagram showing an output result of the intelligent copywriting method for generating copy according to an embodiment of the present disclosure; and

[0020] Figure 7 A schematic block diagram of an apparatus for generating text according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0021] The concept of the present disclosure will now be described with reference to the various exemplary embodiments shown in the accompanying drawings. It should be understood that the description of these embodiments is only to enable those skilled in the art to better understand and further implement the present disclosure, and is not intended to limit the scope of the present disclosure in any way. It should be noted that similar or identical reference numerals may be used in the figures where feasible, and similar or identical reference numerals may represent similar or identical elements. Those skilled in the art will understand from the following description that alternative embodiments of the structures and / or methods described herein may be adopted without departing from the principles and concepts of the present disclosure described.

[0022] In the context of the present disclosure, the term "including" and its various variations may be understood as open terms, which means "including but not limited to"; the term "based on" may be understood as "based at least in part on"; the term "one embodiment" may be understood as "at least one embodiment"; the term "another embodiment" may be understood as "at least one other embodiment". Other terms that may appear but are not mentioned here should not be interpreted or limited in a manner contrary to the concept on which the embodiments of the present disclosure are based, unless explicitly stated.

[0023] Large language model (LLM) can quickly generate text that meets the requirements based on the prompt words input by the user with little or no training data. This greatly reduces the cost of short video copywriting and has great advantages in the short video copywriting scenario. The main method for users to generate short video copywriting through LLM is to input the prompt words into LLM based on the short video theme, style and other requirements, and LLM returns the video copy that meets the requirements. This method has some problems.

[0024] First, LLM cannot remember all knowledge, especially long-tail knowledge. In machine learning, long-tail knowledge refers to knowledge or features that appear less frequently in the data set but still have an important impact on model training and generalization capabilities. This knowledge usually comes from the long-tail distribution in the data set, that is, the number of samples in a few categories in the data set is large, while the number of samples in most categories is small. Limited by the training data and existing learning methods, LLM's ability to accept long-tail knowledge is not very high.

[0025] Second, LLM knowledge is easily outdated and difficult to update. LLM training data usually comes from past corpora, which may have changed or are no longer applicable. In addition, language and culture are constantly evolving over time, which can also cause LLM knowledge to become outdated. For this reason, some researchers fine-tune LLM, that is, only update some parameters of the model instead of retraining the entire model. However, this will result in low model acceptance and slow acceptance, and there is even a risk of losing the original knowledge.

[0026] Third, the output of LLM is difficult to explain and verify. This is because LLM is a black box model. It is impossible to directly view the calculation process and decision basis inside the model. The performance of the model can only be observed through input and output. On the other hand, the final result output may also be interfered by problems such as hallucination.

[0027] In order to solve or alleviate the above problems and / or other potential problems, an embodiment of the present disclosure proposes a method for generating copy. The method uses the vector representation of the prompt word input by the user to retrieve the enhanced information matching the vector representation in the existing knowledge base, and uses the enhanced information to enhance the prompt word input by the user, and then inputs it into the language model, thereby generating a higher quality copy that meets the user's needs. In this way, it is possible to utilize the high real-time information related to the prompt word input by the user in the existing knowledge base, enhance the prompt word and then input it into the language model, thereby avoiding some defects of the language model itself, thereby improving the quality of the output copy.

[0028] The basic principles and implementations of the present disclosure are described below with reference to the accompanying drawings. It should be understood that the exemplary embodiments given are only to enable those skilled in the art to better understand and implement the embodiments of the present disclosure, and are not intended to limit the scope of the present disclosure in any way.

[0029] Figure 1 1 is a block diagram of a computing device 100 capable of implementing multiple embodiments of the present disclosure. It should be understood that Figure 1 The computing device 100 shown is merely exemplary and should not be construed as limiting the functionality and scope of the implementations described in the present disclosure. Figure 1 As shown, components of computing device 100 may include, but are not limited to, one or more processors or processing units 110 , memory 120 , storage device 130 , one or more communication units 140 , one or more input devices 150 , and one or more output devices 160 .

[0030] In some implementations, the computing device 100 can be implemented as various user terminals or service terminals with computing capabilities. The service terminal can be a server, a large computing device, etc. provided by various service providers. The user terminal is such as any type of mobile terminal, fixed terminal or portable terminal, including a mobile phone, a site, a unit, a device, a multimedia computer, a multimedia tablet, an Internet node, a communicator, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. It is also foreseeable that the computing device 100 can support any type of interface for the user (such as a "wearable" circuit, etc.).

[0031] Processing unit 110 may be a real or virtual processor and may be capable of performing various processes according to a program stored in memory 120. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to increase the parallel processing capabilities of computing device 100. Processing unit 110 may also be referred to as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor, a controller, or a microcontroller.

[0032] The computing device 100 typically includes a plurality of computer storage media. Such media may be any available media accessible to the computing device 100, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 120 may be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The memory 120 may include a copy generator 122 implemented as a program module, which may be configured as a program module to perform the copy generation functions described herein. The copy generator 122 may be accessed and run by the processing unit 110 to implement the corresponding functions.

[0033] Storage device 130 may be a removable or non-removable medium and may include machine-readable media that can be used to store information and / or data and can be accessed within computing device 100. Computing device 100 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 1 As shown in , a disk drive for reading or writing from a removable, nonvolatile disk and an optical drive for reading or writing from a removable, nonvolatile optical disk can be provided. In these cases, each drive can be connected to a bus (not shown) by one or more data media interfaces.

[0034] The communication unit 140 enables communication with another computing device via a communication medium. Additionally, the functions of the components of the computing device 100 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Therefore, the computing device 100 can operate in a networked environment using a logical connection with one or more other servers, a personal computer (PC), or another general network node.

[0035] Input device 150 may be one or more various input devices, such as a mouse, keyboard, trackball, touch screen, voice input device, etc. Output device 160 may be one or more output devices, such as a display, speaker, printer, etc. Computing device 100 may also communicate with one or more external devices (not shown) through communication unit 140 as needed, such as storage devices, display devices, etc., communicate with one or more devices that allow a user to interact with computing device 100, or communicate with any device that allows computing device 100 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0036] In some implementations, in addition to being integrated on a single device, some or all of the various components of the computing device 100 can also be set in the form of a cloud computing architecture. In a cloud computing architecture, these components can be remotely arranged and can work together to implement the functions described in the present disclosure. In some implementations, cloud computing provides computing, software, data access and storage services, which do not require end users to know the physical location or configuration of the system or hardware that provides these services. In various implementations, cloud computing uses appropriate protocols to provide services through a wide area network (such as the Internet). For example, a cloud computing provider provides applications through a wide area network, and they can be accessed through a web browser or any other computing component. The software or components of the cloud computing architecture and the corresponding data can be stored on a server at a remote location. The computing resources in a cloud computing environment can be merged at a remote data center location or they can be dispersed. Cloud computing infrastructure can provide services through a shared data center, even if they appear as a single access point for users. Therefore, the components and functions described herein can be provided from a service provider at a remote location using a cloud computing architecture. Alternatively, they can also be provided from a traditional server, or they can be installed on a client device directly or otherwise.

[0037] The computing device 100 may generate copywriting according to various implementations of the present disclosure. Figure 1 As shown, the computing device 100 can receive the input prompt word 170 through the input device 150, and the prompt word 170 can be a user's description of the desired short video copy. Alternatively, the computing device 100 can also read the prompt word 170 from the storage device 130 or receive the prompt word 170 from other devices (e.g., mobile phones, tablets, personal computers, etc.) from the communication device 140. The computing device 100 can transmit the prompt word 170 to the copy generator 122. The copy generator 122 generates a corresponding target copy 180 based on the prompt word 170. The target copy 180 can meet the requirements described by the user in the prompt word 170.

[0038] For example, the prompt word 170 is a text to be processed, which can be a text in various languages, such as English, Chinese, etc. The prompt word 170 can be a description of the requirements of the text to be generated from any user, and the requirements can include but are not limited to celebrity introduction, script writing, seeking solutions, etc. For example, the exemplary prompt word 170 is the text "Introducing Li Bai" input by the user. Accordingly, the target text 180 generated according to the prompt word 170 includes a text introducing Li Bai, a poet of the Tang Dynasty. In the case where the prompt word 170 is other requirement description text, the target text 180 can also meet the user's requirement description of the text to be generated contained in the prompt word 170, and is not limited to the specific input requirement description text.

[0039] The technical solution described above is only used as an example and does not limit the present invention. Figure 2 The process of generating the target text 180 according to the prompt word 170 will be described in more detail.

[0040] Figure 2 Schematic block diagram showing the framework of the copy generator 200 according to an embodiment of the present disclosure. Figure 1 An example implementation of the copywriting generator 122. It should be noted that, Figure 2 The copy generator 200 shown is only illustrative, and the copy generator 200 can also be implemented by a system or framework different from this, for example, some modules can be omitted or changed, and is not limited to Figure 2 The framework shown.

[0041] like Figure 2 As shown, the copy generator 200 can receive the prompt word 170 input by the user. The prompt word 170 can represent the user's required description of the desired copy to be generated, for example, a sentence or a paragraph of text. In some embodiments, the copy generator 200 can use a named entity recognition (NER) model 201 to extract keywords 202 in the prompt word from the input prompt word 170. The extracted keywords may include the names of one or more entities. The keywords 202 can be used for subsequent comparison to determine whether the input prompt word 170 needs to be enhanced.

[0042] The named entity recognition (NER) model is a model in natural language processing (NLP) that is used to identify specific types of entities in text, such as place names, organization names, etc. The NER model can also be used to extract keywords from text. For example, for the text "Company A's headquarters is in Nanjing", the NER model can mark "Company A" as the name of the organization and "Nanjing" as the place name, thus making "Company A" and "Nanjing" the keywords of the text.

[0043] The NER model is obtained after offline training. The offline training process can adopt a supervised learning method, which uses a large amount of labeled data to train the model so that it can accurately identify various types of entities during testing. During the training process, the model recognizes entities in the text by learning the features of the input text, such as word form, word order, grammatical structure, etc.

[0044] As shown in the figure, the input prompt word 170 can also be provided to the vector model 203, and a prompt word vector 204 is generated. The vector model 203 can convert the input text or sentence into a vector form. During the conversion process, the text is regarded as a sequence consisting of a series of words or terms and mapped to a vector in the vector space.

[0045] In some embodiments, the vector model may be a BGE-Large model. The model may map any text into a low-dimensional dense vector for tasks such as retrieval, classification, clustering, or semantic matching. The BGE-Large model uses a bidirectional gated recurrent unit (BGRU) as the network structure, combining forward and backward information flows, so that the model can better capture the semantic information of the text. In addition, the model uses a multi-layer gated recurrent unit (Multi-layer BGRU) to deepen the network structure to increase the ability to capture the deep semantics of the text.

[0046] As shown in the figure, the generated prompt word vector 204 can be provided to a vector index database 205. A vector index database is a special database that is mainly used to process and search vector data. In a vector index database, data is represented as high-dimensional vectors, and these vectors are stored in an index for fast retrieval.

[0047] The distance of the vectors can be used to measure the similarity of two vectors. Optionally, the vector similarity can be obtained by calculating the cosine distance, Euclidean distance or vector inner product between the vectors. In some embodiments, the vector index database 205 can be an elastic index K nearest neighbor database, which determines the enhanced prompt word vector in response to the cosine similarity with the prompt word vector 204 exceeding a threshold through the K nearest neighbor algorithm.

[0048] In some embodiments, the enhanced prompt word vector can be combined with the associated document information for enhancement and keywords related to the information to form a text entry in the vector index database 205, so that the enhanced information 207 related to the input prompt word 170 and the keywords 206 about the enhanced information 207 can be obtained by retrieving the enhanced prompt word vector.

[0049] The text entries in the vector index database 205 are added during the offline training process, so that the vector index database 205 can be frequently updated. Optionally, the text entries stored in one vector index database 205 can belong to the same category (e.g., organization name, place name, etc.), so that each vector index database 205 has highly real-time vertical category (also called subject or topic) information.

[0050] As shown in the figure, the keyword 202 from the prompt word 170 and the keyword 206 from the vector index database 205 can be provided to the prompt word enhancement trigger module 208. In the prompt word enhancement trigger module 208, the similarity between the keyword 202 and the keyword 206 can be compared, and in response to the similarity exceeding a threshold, an enhanced prompt word 209 is generated by combining the enhanced information 207 and the prompt word 170. In some embodiments, the enhanced prompt word 209 includes two parts, background knowledge and problem description. The enhanced prompt word 209 is generated by splicing the enhanced information 207 as the background knowledge part and the prompt word 170 as the problem description part into one text.

[0051] As shown in the figure, the enhanced prompt words 209 can be provided to the LLM 210. By utilizing the feature that the LLM 210 can quickly generate a copy that meets the requirements based on the prompt words, the target copy 180 can be obtained. Compared with the input prompt words 170, the enhanced prompt words 209 have higher text quality, so some of the inherent defects of the LLM 210 can be avoided, thereby improving the quality of the generated target copy 180.

[0052] Figure 3 1 shows a flow chart of a method 300 for generating a copy according to some embodiments of the present disclosure. In some embodiments, the method 300 may be performed by, for example, Figure 1 More specifically, the method 300 may be implemented by the computing device 100 shown in FIG. Figure 1 It should be understood that the method 300 may also include additional actions not shown and / or may omit the actions shown, and the scope of the present disclosure is not limited in this respect. Figure 2 The framework shown is used to illustrate the method 300 .

[0053] like Figure 3 As shown, in block 310, the computing device 100 receives the prompt word input by the user. In some embodiments, the computing device 100 may be a local device, such as a mobile phone, and the user may operate in an application (APP) to input the prompt word. In some embodiments, the computing device 100 may be a server on the Internet, such as a cloud server, which receives the prompt word transmitted from the user's mobile phone via the network.

[0054] like Figure 3 As shown, at block 320, the computing device 100 obtains the first keyword 202 from the prompt word 170. In some embodiments, reference Figure 2, the computing device 100 uses the named entity recognition NER model 201 to obtain the first keyword 202 from the input prompt word 170. For the structured prompt word 170, the corresponding keyword field is directly used as the first keyword 202. For the unstructured prompt word 170, the NER model 201 is used to extract entities with specific meanings or strong referentiality (for example, organization names, place names, dates and times, proper nouns, etc.) from the prompt word 170 to obtain the first keyword 202.

[0055] return Figure 3 In block 330, the computing device 100 uses the vector representation of the prompt word 170 to retrieve the enhancement information 207 associated with the prompt word 170 and the second keyword 206 associated with the enhancement information 207 from the vector index database 205. The enhancement information 207 is text information stored in the vector index database 205, and the second keyword 206 is used to perform a similarity comparison with the first keyword 202 to determine whether the input prompt word 170 needs to be enhanced.

[0056] refer to Figure 2 The computing device 100 can use the vector model 203 to obtain the prompt word vector 204 from the prompt word 170, and then retrieve the enhanced prompt word vector similar to the prompt word vector 204 in the vector index database 205. Based on the enhanced prompt word vector, the corresponding enhanced information 207 and the second keyword 206 are determined.

[0057] As described above, the vector index database 205 may be a text library, in which each text entry has an associated vector representation, a keyword, and text information for enhancement, and the vector representation is used as an index of the corresponding text entry. Thus, as long as an enhanced prompt word vector similar to the prompt word vector 204 is retrieved, the enhanced information 207 and the second keyword 206 under the same entry can be obtained.

[0058] In some embodiments, the vector similarity can be obtained by calculating the cosine distance, Euclidean distance or vector inner product between vectors. In some embodiments, the vector index database 205 is an elastic index K nearest neighbor database, which determines the enhanced prompt word vector in response to the cosine similarity with the prompt word vector 204 exceeding a threshold through the K nearest neighbor algorithm.

[0059] return Figure 3 In block 340, the computing device 100 uses the enhancement information 207 to generate an enhanced prompt word 209 based on the comparison between the first keyword 202 and the second keyword 206. Figure 4 The process of generating the enhanced prompt word 209 will be described in more detail.

[0060] Figure 4 FIG. 2 shows a schematic diagram of a prompt word enhancement trigger module according to an embodiment of the present disclosure. Figure 4 As shown, the computing device 100 can use the word embedding encoder 401 to convert the first keyword 202 into a first embedding vector 402 and the second keyword 206 into a second embedding vector 403, and then compare the first embedding vector 402 and the second embedding vector 403 through the vector similarity calculation module 404 to obtain the vector similarity 405. If the vector similarity 405 exceeds a preset threshold, it indicates that the prompt word 170 needs to be enhanced to obtain an enhanced prompt word 209.

[0061] In some embodiments, the enhanced prompt word 209 includes two parts, background knowledge and problem description. The enhanced prompt word 209 is generated by concatenating the enhanced information 207 as the background knowledge part and the prompt word 170 as the problem description part into a text. Optionally, the word embedding encoder 401 can adopt a transformer-based bidirectional encoder representation technology.

[0062] return Figure 3 In block 350, the computing device 100 provides the enhanced prompt word 209 to the language model to generate the copy. Figure 2 As shown, the language model is LLM 210. By utilizing the characteristic of LLM 210 that it can quickly generate a copy that meets the requirements based on the prompt word, the target copy 180 can be obtained. Compared with directly inputting the prompt word 170, taking the enhanced prompt word 209 as input, it is possible to utilize the high real-time information of topics related to the prompt word 170 in the existing knowledge base, and avoid the shortcomings of LLM 210 itself. The quality of the copy finally generated will also be improved, and it will not be easily disturbed by problems such as hallucinations.

[0063] Figure 5 A schematic block diagram of the framework of a copy generator based on creative intent categories according to an embodiment of the present disclosure is shown. In some embodiments, in order to further utilize high real-time information and improve the efficiency of copy enhancement, it is also possible to select to retrieve enhancement information 207 in the vector index database 205 of the corresponding category based on the creative intent category. The text entries in the vector index database 205 are added during the offline training process. The text entries stored in a vector index database 205 belong to the same category, so that each vector index database 205 has vertical category information with high real-time performance.

[0064] In some embodiments, Figure 5As shown, each vector index database 205-1, 205-2...205-n in the database 205 corresponds to a creative intent category, and the creative intent category can be celebrity introduction, script writing, seeking solutions, etc. Optionally, the creative intent category 502 of the prompt word 170 is obtained by pre-inputting the prompt word 170 into the creative intent classification model 330, and the corresponding vector index database is determined based on the creative intent category 502, and the vector index database contains a large number of pre-input text entries of the same category. By introducing the creative intent classification model 501, each vector index database 205 can only store text entries of the same category, and after the computing device 100 obtains the prompt word vector 204, it can efficiently perform retrieval operations.

[0065] Figure 6A-6C The user interaction process of generating copy based on prompt words according to some embodiments of the present disclosure is shown. Fig. 6A A schematic diagram of an initial text input page 600A for generating a copy according to an embodiment of the present disclosure is shown. The initial text input page 600A includes a copy input box 601, a smart copy writing control 602, and a generate video control 603. In some embodiments, the user can enter a complete video copy in the copy input box 601, and then click the generate video control 603 to generate a video with the copy, or do not enter text in the prompt word input box 601, and directly click the smart copy writing control 602 to enter the input page 600B of the smart copy writing.

[0066] Figure 6B A schematic diagram of an input page 600B of the intelligent copywriting for generating copywriting according to an embodiment of the present disclosure is shown. In the input page 600B of the intelligent copywriting, a prompt word input box 604, a prompt word upload control 606 and a keyboard 606 are included. In some embodiments, the user can enter the required description of the target copy, that is, the prompt word, in the prompt word input box 604 through the keyboard 606, and then click the prompt word upload control 606. According to an embodiment of the present disclosure, the input prompt word can be enhanced and input into the LLM to generate a high-quality target copy. Thus, the output result 600C page of the intelligent copywriting is entered.

[0067] Figure 6C A schematic diagram of an output result 600C of the intelligent copywriting for generating copywriting according to an embodiment of the present disclosure is shown. The output result 600C page of the intelligent copywriting includes a copywriting input box 601, an intelligent copywriting control 602, and a generate video control 603, wherein the copywriting input box 601 includes a target copywriting corresponding to the prompt word input in the input page 600B of the intelligent copywriting, and the user can click the generate video control 603 to generate a video including the target copywriting.

[0068] References Figures 2 to 6C An exemplary embodiment of the present disclosure is described. Compared with the existing copywriting generation scheme, the prompt word enhancement scheme of the present disclosure can use the high real-time information related to the prompt word input by the user in the existing knowledge base as the enhancement information, and then input the prompt word into the language model after enhancement, so as to improve the quality of the output copywriting. In some implementations, it is also possible to judge whether the input prompt word needs to be enhanced by comparing the similarity between the keywords from the prompt word and the keywords in the enhancement information, thereby improving the reliability of the enhancement operation. In some implementations, it is also possible to retrieve the knowledge base information of the corresponding category based on the creative intent category of the input prompt word, thereby improving the retrieval efficiency.

[0069] Figure 7 : shows a schematic block diagram of an apparatus 700 for generating a copy according to an embodiment of the present disclosure. The apparatus 700 can be implemented in, for example, Figure 1 At the copy generator 122 in the computing device 100 shown. Figure 7 As shown, the device 700 includes: a prompt word receiving unit 710, a keyword extracting unit 720, an enhanced information acquiring unit 730, a prompt word enhancing unit 740 and a text generating unit 750.

[0070] In some embodiments, the prompt word receiving unit 710 is configured to receive a prompt word input by a user; the keyword extraction unit 720 is configured to obtain a first keyword from the prompt word; the enhancement information acquisition unit 730 is configured to use the vector representation of the prompt word to retrieve the enhancement information associated with the prompt word and the second keyword associated with the enhancement information from the vector index database; the prompt word enhancement trigger unit 740 is configured to use the enhancement information to generate an enhanced prompt word based on a comparison between the first keyword and the second keyword; the copy generation unit 750 is configured to provide the enhanced prompt word to the language model to generate copy.

[0071] It should be noted that the reference Figure 2 Further actions or steps to FIG. 6 may be performed by Figure 7 For example, the device 700 may include more modules or units to implement the actions or steps described above, or Figure 7 Some of the units or modules shown may be further configured to implement the actions or steps described above, which will not be repeated here.

[0072] In some embodiments, the methods and processes described above may be implemented as a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0073] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: 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), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0074] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0075] The computer program instructions for performing the disclosed operation may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, and conventional procedural programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via 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., utilizing an Internet service provider to connect via the Internet). In certain embodiments, by utilizing the state information of a computer-readable program instruction to customize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute a computer-readable program instruction, thereby realizing various aspects of the present disclosure.

[0076] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0077] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0078] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the equipment, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes 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 the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0079] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for generating copywriting, include: Receive prompt words input by the user; Acquire a first keyword from the prompt word; Retrieving, from a vector index database, enhanced information associated with the cue word and a second keyword associated with the enhanced information using the vector representation of the cue word; generating an enhanced prompt word using the enhanced information based on a comparison of the first keyword and the second keyword; as well as The enhanced prompt words are provided to a language model to generate text.

2. The method according to claim 1, wherein the enhanced information is used to generate an enhanced prompt word include: Obtain a first embedding vector from the first keyword and a second embedding vector from the second keyword using a word embedding encoder; Determining a similarity between the first embedding vector and the second embedding vector; and In response to the similarity exceeding a threshold, the enhanced cue word is generated by combining the cue word and the enhanced information.

3. The method according to claim 1, wherein the first keyword is obtained from the input prompt word include: The first keyword is obtained from the prompt word using a named entity recognition model.

4. The method according to claim 1, wherein the enhanced information related to the prompt word and the second keyword related to the enhanced information are retrieved from a vector index database. include: Using a vector model to obtain a prompt word vector from the prompt word; Retrieving, in the vector index database, an enhanced prompt word vector similar to the prompt word vector; as well as Based on the enhanced prompt word vector, a corresponding text entry is determined as the enhanced information and the second keyword.

5. The method according to claim 4, wherein the vector index database comprises a text library, each text entry in the text library has an associated vector representation and a keyword, the vector representation being used as an index of the corresponding text entry in the vector index database.

6. The method according to claim 4, wherein the vector index database comprises an elastic index K nearest neighbor database, and the enhanced prompt word vector similar to the prompt word vector is retrieved. include: Based on the K nearest neighbor algorithm, in response to the cosine similarity with the prompt word vector exceeding a threshold, the enhanced prompt word vector is determined.

7. The method according to claim 1, further comprising: include: Determine the creative intent category from the prompt word using a creative intent classification model; as well as Based on the creative intent category, the vector index database to be searched of the same category is determined.

8. A system for generating copywriting, include: A prompt word receiving unit, configured to receive a prompt word input by a user; A keyword extraction unit, configured to obtain a first keyword from the prompt word; an enhanced information acquisition unit, configured to retrieve enhanced information associated with the prompt word and a second keyword associated with the enhanced information from a vector index database using the vector representation of the prompt word; a prompt word enhancement trigger unit configured to generate an enhanced prompt word using the enhancement information based on a comparison between the first keyword and the second keyword; as well as The text generation unit is configured to provide the enhanced prompt words to a language model to generate text.

9. The system according to claim 8, wherein the prompt word enhancement trigger unit is further configured to: Obtain a first embedding vector from the first keyword and a second embedding vector from the second keyword using a word embedding encoder; Determining a similarity between the first embedding vector and the second embedding vector; and In response to the similarity exceeding a threshold, the enhanced cue word is generated by combining the cue word and the enhanced information.

10. The system according to claim 8, wherein the keyword extraction unit is further configured to: The first keyword is obtained from the prompt word using a named entity recognition model.

11. The system according to claim 8, wherein the enhanced information acquisition unit is further configured to: Using a vector model to obtain a prompt word vector from the prompt word; Retrieving an enhanced prompt word vector similar to the prompt word vector in the vector index database; and Based on the enhanced prompt word vector, the corresponding enhanced information and the second keyword are determined.

12. The system according to claim 11, wherein the vector index database includes a text library, each text entry in the text library has an associated vector representation, a keyword, and text information for enhancement, the vector representation being used as an index for the corresponding text entry.

13. The system according to claim 11, wherein the vector index database comprises an elastic index K nearest neighbor database, and the enhanced information acquisition unit is further configured to: Based on the K nearest neighbor algorithm, in response to the cosine similarity with the prompt word vector exceeding a threshold, the enhanced prompt word vector is determined.

14. The system according to claim 8, further comprising a database determination unit, wherein the database determination unit is configured to: Determining a creative intent category from the prompt word using a creative intent classification model; and Based on the creative intent category, the vector index database to be searched is determined.

15. A computing device, include: at least one processing unit; At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, causing the computing device to perform the method as claimed in any one of claims 1 to 7.

16. A non-transitory computer storage medium comprising machine executable instructions which, when executed by a device, cause the device to perform the method of any one of claims 1 to 7.

17. A computer program product comprising machine executable instructions which, when executed by a device, cause the device to perform the method of any one of claims 1 to 7.

Images