Video script generation method and device, electronic equipment and storage medium

Abstract

The invention provides a video script generation method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the fields of large models, generative models and the like. According to the specific implementation scheme, the method comprises the following steps: determining a reference video script from a database according to demand information and correlation among video scripts in the database; generating a target video script based on the large model according to the demand information, the reference video script and the tag sequence corresponding to the reference video script; wherein the reference video script comprises a plurality of sub-texts, and each sub-text corresponds to a label; the label sequence comprises a plurality of labels corresponding to the plurality of sub-texts in the reference video script, and the sequence of the plurality of labels in the label sequence is consistent with the sequence of the plurality of sub-texts in the reference video script.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to the fields of large models, generative models, etc. More specifically, the present disclosure provides a video script generation method, device, electronic device, storage medium and computer program product. Background Art

[0002] With the popularity of short videos, the types of content creation have been greatly enriched. Video scripts, as the cornerstone of content creation, can provide inspiration for the video itself and improve creative efficiency. Summary of the invention

[0003] The present disclosure provides a video script generation method, device, electronic device, storage medium and computer program product.

[0004] According to one aspect of the present disclosure, a video script generation method is provided, which determines a reference video script from a database according to demand information and the correlation between each video script in the database; and generates a target video script based on a large model according to the demand information, the reference video script and a label sequence corresponding to the reference video script; wherein the reference video script includes multiple sub-texts, each sub-text corresponds to a label; the label sequence includes multiple labels corresponding to the multiple sub-texts in the reference video script, and the order of the multiple labels in the label sequence is consistent with the order of the multiple sub-texts in the reference video script.

[0005] According to another aspect of the present disclosure, a video script generation device is provided, comprising: a reference video script determination module and a generation module. The reference video script determination module is used to determine the reference video script from the database according to the demand information and the correlation between each video script in the database. The generation module is used to generate a target video script based on a large model according to the demand information, the reference video script and a label sequence corresponding to the reference video script. The reference video script includes multiple subtexts, each of which corresponds to a label; the label sequence includes multiple labels corresponding to the multiple subtexts in the reference video script, and the order of the multiple labels in the label sequence is consistent with the order of the multiple subtexts in the reference video script.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method provided by the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method provided by the present disclosure.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method provided by the present disclosure is implemented.

[0009] It should be understood that the content described in this section 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

[0010] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0011] Figure 1 is a schematic diagram of an application scenario of the video script generation method and device according to an embodiment of the present disclosure;

[0012] Figure 2 is a schematic flow chart of a method for generating a video script according to an embodiment of the present disclosure;

[0013] Figure 3 is a schematic diagram of a method for generating a video script according to an embodiment of the present disclosure;

[0014] Figure 4 is a schematic structural block diagram of a video script generating device according to an embodiment of the present disclosure; and

[0015] Figure 5 It is a structural block diagram of an electronic device used to implement the video script generation method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0016] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0017] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0018] In the technical solution of the present disclosure, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0019] Sometimes users need to create video scripts, and users may be users who need to place advertisements or other users. In some technical solutions, the big model can be fine-tuned based on the original capabilities of the big model or through training data, and then the big model can be used to generate the target video script that needs to be created based on the input content given by the user.

[0020] However, the above technical solution has the following disadvantages: First, if the high-quality reference video script is not used in the process of generating the target video script, the quality of the generated target video script is generally low, resulting in a low click-through rate of the target video script. Second, if the large model lacks a reference video script in the process of generating the target video script, or borrows too much from the content of the reference video script, it is easy to have the problem that the style of the target video script does not match the business scenario of the user's needs. For example, the business scenario is medical rehabilitation, and the style of the reference video script is relatively joyful, so the style of the generated target video script is also prone to be joyful, which is poorly matched with the business scenario of medical rehabilitation. Third, when generating target video scripts in batches, if the referenced high-quality copywriting is relatively single, the generated target video script will be single in content and low in diversity. Fourth, the original ability of the base model and the quality of the fine-tuning data determine the effect of the target video script generation, and the process of iterating the model and constructing the fine-tuning data is relatively complicated. If no iteration is performed, the generated target video script will not adapt to market trends and its attractiveness will decrease.

[0021] The disclosed embodiment provides a method for generating a video script. The method first determines a reference video script from a database according to the correlation between the demand information and each video script in the database. The reference video script includes multiple subtexts, each subtext corresponds to a label, and the label sequence includes multiple labels corresponding to the multiple subtexts in the reference video script, and the order of the multiple labels in the label sequence is consistent with the order of the multiple subtexts in the reference video script. Then, according to the demand information, the reference video script, and the label sequence corresponding to the reference video script, a target video script is generated based on a large model.

[0022] First, the video script generation method provided by the embodiment of the present disclosure can automatically select a reference video script from a database based on relevance, and then generate a target video script based on the reference video script. The reference video scripts in the database can be high-quality samples, so the high-quality reference video scripts can be used as samples for imitation, thereby improving the quality of the generated target video script and ensuring that the target video script has a high click-through rate.

[0023] Secondly, the video script generation method provided by the embodiment of the present invention imitates the labels and label order of each sub-text in the reference video script, which is equivalent to imitating the structure of the reference video script, while avoiding the large model paying too much attention to the content, style, tone, etc. of the reference video script. Therefore, the content, style, and tone of the reference video script have less influence on the target video script, thereby improving the consistency of the style of the target video script with the business scenario.

[0024] Furthermore, the process of generating the target video script mainly relies on the labels of each sub-text in the reference video script, which belongs to the imitation of the structural level. The large model has a wider range of freedom, so it can avoid generating a large number of target video scripts with similar content, and has better diversity.

[0025] In addition, the embodiments of the present disclosure rely on reference video scripts to generate target video scripts. When the capabilities of the large model meet the standards, the reference video scripts can be updated as needed (for example, resources that are popular with users are screened out based on their online performance, and then the database is updated using video scripts associated with these resources) to make the target video scripts conform to market trends, without the need for manual screening of the corpus to fine-tune the large model.

[0026] The video script generation method provided by the embodiment of the present disclosure is suitable for application scenarios such as product promotion. The technical solution provided by the present disclosure will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0027] Figure 1 It is a schematic diagram of an application scenario of the video script generation method and device according to an embodiment of the present disclosure.

[0028] It should be noted that Figure 1 What is shown is merely an example of a system architecture to which the embodiments of the present disclosure can be applied, in order to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0029] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0030] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptops, desktop computers, etc.

[0031] The server 105 may be a server that provides various services, such as a background management server (only an example) that provides support for websites browsed by users using the terminal devices 101, 102, and 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as the target video script generated according to the demand information input by the user, etc.) to the terminal device.

[0032] It should be noted that the video script generation method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the video script generation device provided in the embodiment of the present disclosure can generally be set in the server 105. The video script generation method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the video script generation device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0033] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0034] Figure 2 It is a schematic flowchart of a method for generating a video script according to an embodiment of the present disclosure.

[0035] like Figure 2 As shown, the video script generation method 200 may include operations S210 to S220.

[0036] In operation S210, a reference video script is determined from the database according to the demand information and the correlation between each video script in the database.

[0037] For example, users can input demand information through the front-end operation page, or users can import the page to be processed, and then parse the page to be processed to obtain demand information. The page to be processed can be the landing page of some entities. The entity can be a product, a brand, a company, etc. For example, the page to be processed is the details page of a product, the promotion page of a company, etc. For example, demand information can include business scenarios, applicable populations, etc. Business scenarios can include medical rehabilitation, dental implants, etc., and applicable populations can include the elderly, children, etc.

[0038] For example, a database can be pre-built. In one example, videos, pictures, or other types of resources that are popular with people can be screened from a large number of resources, and then scripts associated with the resources are added to the database.

[0039] For example, the level of correlation can be determined by at least one of similarity, category, and description dimension. For example, a video script whose correlation meets predetermined conditions can be used as a reference video script. The predetermined conditions may include at least one of the following: the similarity between the demand information and the video script is greater than or equal to a threshold, the demand category in the demand information is the same as the actual category of the video script, and the demand description dimension in the demand information is the same as the description dimension of a descriptive text in the video script.

[0040] For example, a plurality of video scripts are stored in a database, each of which may include at least one description text, and each description text may include at least one subtext. For example, a certain video script includes 10 sentences, of which 3 sentences describe product functions. The three sentences are a description text, and each sentence may be a subtext. Each subtext corresponds to at least one tag, and the tag indicates the category of the subtext. For example, the tag may include product information, applicable scenarios, applicable population, call to action, user pain points, product highlights, price discounts, etc. For example, the subtext may be classified based on a classification model to determine the tag corresponding to the subtext. Each video script in the database corresponds to a tag sequence. Taking the reference video script as an example, the tag sequence corresponding to the reference video script includes multiple tags, which correspond to multiple subtexts in the reference video script, and the order of the multiple tags in the tag sequence is consistent with the order of the multiple subtexts in the reference video script.

[0041] It should be noted that tags can represent general categories rather than specific categories, so as to avoid the category granularity represented by the tags being too small, causing the imitated target video script to be too similar to the reference video script, and to avoid inconsistency between the style and business scenario of the target video script.

[0042] In operation S220, a target video script is generated based on the large model according to the demand information, the reference video script, and a tag sequence corresponding to the reference video script.

[0043] For example, the demand information, reference video script and prompt information are input into the big model, and the big model is used to generate the target video script. The prompt information can require the big model to imitate the order of each label in the label sequence of the reference video script and the expression content, and can prohibit the target video script from including relevant entity content in the reference video script. For example, if a certain brand of headphones is mentioned in the reference video script, the generated target video script does not include the brand.

[0044] In practical applications, the script in the database may be a text for describing resources such as video, graphics, etc., and this embodiment takes a video script as an example. In some embodiments, the tag sequence of the generated target video script may be the same as the tag sequence of the reference video script.

[0045] Using the video script generation method provided by the embodiment of the present disclosure, first, a reference video script can be automatically selected from a database based on relevance, and then a target video script can be generated based on the reference video script, so that the quality of the generated target video script can be improved and the target video script can be ensured to have a high click-through rate. Secondly, based on the tag sequence, the structure of the reference video script can be imitated instead of the content of the reference video script, so the consistency of the style of the target video script with the business scenario can be improved. Furthermore, there is no need to manually screen the corpus to fine-tune the large model. In addition, it is also possible to avoid generating a large number of target video scripts with similar content, and the diversity is better.

[0046] Next, the process of building a database is described.

[0047] In this embodiment, resources may be obtained first, and the resources may be video resources for introducing entities. Then, based on the historical interaction data of each of the multiple resources, a target resource may be determined from the multiple resources. For example, the historical interaction data includes at least one of the following: click-through rate, completion rate, number of favorites, number of likes, number of comments, and number of shares. The target resources that are popular with users may be screened from a large number of resources through the historical interaction data. These target resources may be called popular resources. Then, the video script associated with the target resource may be used to update the video script in the database.

[0048] In this embodiment, video scripts associated with resources with higher popularity are added to the database, which ensures that the video scripts in the database are in line with market trends and audience preferences, thereby ensuring that the target video script generated based on the reference video script is in line with market trends and audience preferences. In addition, in practical applications, the video scripts in the database can be updated at regular intervals, such as daily or weekly, to further ensure that the video scripts in the database and the target video script are in line with current popular trends.

[0049] Next, the process of determining a reference video script from a database based on the demand information and the correlation between each video script in the database is described.

[0050] In this embodiment, video scripts can be screened from the database based on the demand information and the similarity between each video script in the database, and the screened video script is called the initial video script. It should be noted that the video script in the database includes multiple description texts, and the multiple description texts are used to describe entities associated with the video script from different dimensions. For example, one description text is used to introduce the function of the product, another description text is used to introduce the hardware information of the product, and another description text is used to introduce customer feedback.

[0051] Next, the various description texts in the initial video script may be displayed. If the user is satisfied with the initial video script as a whole, the initial video script may be confirmed, and the initial video script may be used as a reference video script.

[0052] If the user is satisfied with part of the description text in the initial video script, but dissatisfied with another part of the description text, the user can select the dissatisfied part of the description text. At this time, the device executing the video script generation method will detect the selection operation for at least part of the description text in the initial video script, and can determine other video scripts of the same category as the initial video script from the database, and then determine the first description text from the other video scripts, wherein the description dimension of the first description text is the same as the description dimension of at least part of the description text. For example, if the user is dissatisfied with the description text for introducing the function of the headset in a certain video script, the description text can be selected. At this time, the device first determines other video scripts of the same category from the database, such as screening other video scripts for introducing the headset from the database, and then uses the description text for describing the function of the headset in the video script as the first description text.

[0053] Next, the remaining description text in the initial video script except for at least part of the description text selected by the user can be used as the second description text. It can be seen that at least part of the description text selected by the user is the description text that the user is not satisfied with, while the second description text is the description text that the user is relatively satisfied with. Then, a reference video script can be determined based on the first description text and the second description text, for example, the first description text and the second description text are combined, and the combined data is used as the reference video script.

[0054] In this embodiment, after the initial video script is screened from the database, if the user is not satisfied with part of the description text in the initial video script, the initial video script can be adjusted based on other video scripts in the database, so that the initial video script can be modified according to actual needs, and the matching degree between the reference video script and the user needs can be improved. In addition, since the user does not need to think about the specific modification method during the modification process, but can refer to other video scripts of the same category in the database for adjustment, the operation is more convenient.

[0055] According to another embodiment of the present disclosure, the process of determining the initial video script from the database according to the similarity between the demand information and each video script in the database may include: recalling multiple video scripts from the database according to the similarity between the demand information and each video script in the database. Then, according to at least one of the selection operation of the object and the demand information, determining the initial video script from the recalled multiple video scripts.

[0056] For example, if the subject performs a selection operation on at least one video script among the recalled multiple video scripts within a first predetermined period of time, the selected at least one video script may be used as the initial video script.

[0057] For another example, if the subject does not perform a selection operation on the recalled multiple video scripts within the first predetermined period of time, and the demand information includes a demand category, then at least one video script can be selected from the recalled multiple video scripts as the initial video script based on the demand category and the actual categories of the multiple video scripts. For example, the video script includes multiple description texts, but the video script can focus on certain description texts. For example, if the number of characters in a certain description text accounts for the highest proportion in the video script, then the video script focuses on embodying the description text. In this way, among the multiple video scripts recalled, some video scripts focus on introducing product functions, other video scripts focus on introducing product hardware, and other video scripts focus on introducing user feedback. For example, you can first filter out video scripts with the same actual category as the demand category from the recalled multiple video scripts. If the number of filtered video scripts is less than or equal to the quantity threshold, the quantity threshold can be 1 or 2, and the filtered video script can be used as the initial video script. If the number of screened video scripts is greater than a quantity threshold, the screened video scripts can be sorted based on popularity indicators, and the initial video script can be selected from the screened video scripts in order. The popularity indicators may include the click rate, completion rate, collection volume, likes volume, comments volume, sharing volume, etc. of the resources associated with the video scripts.

[0058] For another example, if the subject does not perform a selection operation on the recalled multiple video scripts within the first predetermined time period, and the demand information does not include a demand category, at least one video script can be randomly selected from the recalled multiple video scripts as the initial video script.

[0059] This embodiment first recalls multiple video scripts based on similarity, and then prioritizes the selection of the object to determine the initial video script from the recalled multiple video scripts. If the user does not make a selection, the initial video script is prioritized to be determined from the recalled multiple video scripts based on the demand information. If the object does not make a clear demand, the initial video script can be randomly selected from the recalled multiple video scripts. In this way, through multi-level screening, it can be ensured that the correlation between the initial video script and the demand is high and meets the user's needs.

[0060] According to another embodiment of the present disclosure, the number of first description texts is multiple, and the process of determining the reference video script based on the first description texts and the second description texts includes: outputting multiple first description texts, and then in response to receiving a selection operation for at least part of the multiple first description texts, determining the reference video script based on at least part of the first description texts and the second description text.

[0061] For example, if the user is not satisfied with the description text used to introduce the headphone function in the initial video script, the description text can be selected. At this time, the device used to execute the video script generation method first determines other video scripts of the same category from the database, such as screening multiple video scripts for introducing headphones from the database, and then uses the description text used to describe the headphone function in the video script as the first description text, so that there are multiple first description texts. Next, multiple first description texts can be displayed, and the user can select according to personal preferences. For example, if a certain first description text is selected, the first description text selected by the user and the second description text in the initial video script are combined to obtain a reference video script.

[0062] In this embodiment, multiple first description texts can be selected from a database, and the video scripts to which these first description texts belong are of the same category as the initial video script, and the description dimensions of these first description texts are the same as the description texts of the parts of the initial video script that the user is not satisfied with. Then the user can flexibly select according to personal preferences, and then obtain a reference video script that meets the user's needs, so that the reference video script can better meet the user's personal needs and improve the user experience.

[0063] According to another embodiment of the present disclosure, the video script generation method in this embodiment may include the following operations: determining whether the object selects a reference video script from the database within a second predetermined period of time. If so, the video script selected by the user is used as the initial video script or directly as the reference video script. If not, the reference video script is determined from the database based on the demand information and the correlation between the various video scripts in the database, and then the target video script is generated based on the large model according to the demand information, the reference video script and the tag sequence corresponding to the reference video script.

[0064] In this embodiment, if the user actively selects, the video script selected by the user is preferentially used as the initial video script, and then the reference video script is determined based on the initial video script, or the video script selected by the user can be directly used as the reference video script. If the user does not actively select, the reference video script can also be automatically screened from the database, which can provide a reference for generating the target video script.

[0065] Next, the process of determining the demand information is described.

[0066] If the user can input information through the front-end page, the information input by the user can be used as the demand information. If the above input information is not input, but the page to be processed is uploaded through the front-end page, in this case, the page to be processed can be parsed, for example, characters in the page to be processed can be extracted by means of text extraction, optical character recognition, etc., and the summary can also be extracted by the summary generation model to obtain multiple fields, which can include business, highlights, applicable population, summary, etc. Next, these fields can be used as demand information.

[0067] In this embodiment, when the user does not input clear requirements through the front-end page, but uploads a page to be processed, the requirement information can be determined based on the page to be processed, which is more convenient for user operation and improves user experience. In addition, first extracting fields from the page to be processed and then determining the requirement information based on the fields can ensure the accuracy of the requirement information.

[0068] In the process of determining the demand information, for each of the multiple fields, it can be determined whether the field is a key field according to the business scenario of the object associated with the page to be processed, and then the demand information can be determined according to the key fields in the multiple fields. For example, the page to be processed is uploaded by the first object. According to the pre-established information library, it can be known that the first object mainly develops headphone products, and the business scenario is headphones. It can be determined whether the fields in the page to be processed are associated with headphones. If not, the field can be deleted. If relevant, the field can be determined as a key field. In this way, in the process of determining the demand information, it can be generated according to the key fields that are more related to the business scenario, rather than generated according to all fields, so that the demand information can highlight the content related to the business scenario and ignore irrelevant content.

[0069] It is understandable that in other embodiments, fields irrelevant to the business scenario may not be filtered, but the demand information may be determined based on all the fields.

[0070] Figure 3 It is a schematic diagram of a video script generation method according to an embodiment of the present disclosure.

[0071] In this embodiment, based on the popularity indexes such as click-through rate, completion rate, number of favorites, number of likes, number of comments, and number of shares, a target resource 302 with a wide audience can be screened from a large number of online resources 301. The target resource 302 can be a video resource, and then a video script 303 associated with the target resource 302 is added to the database 304. The video scripts in the database 304 can be updated regularly, and the update cycle can be 1 day, 3 days, etc., which is not limited in this embodiment.

[0072] Next, the user's demand information 305 can be obtained. This embodiment provides two input forms for the user. In the first input form, the user can directly input the demand information 305 through the front-end operation page. In the second input form, the user can upload the page to be processed through the front-end operation page, and the page to be processed can be parsed to obtain the demand information 305.

[0073] Next, the reference video script 307 can be determined from the database 304. For example, the initial video script can be first recalled from the database 304 based on the similarity between the demand information 305 and each video script in the database 304, and then the initial video script can be displayed. If the user is not satisfied with part of the description text in the initial video script, the user can select the part of the description text. From other video scripts in the database 304 with the same category as the initial video script, several first description texts with the same description dimension as the part of the description text selected by the user can be determined. Next, the first description text can be displayed for the user to select, and the reference video script 307 can be determined based on the first description text selected by the user and the second description text in the initial description text that the user is satisfied with.

[0074] It should be noted that the reference video script 307 includes multiple sub-texts, and a label set 306 can be pre-configured. The set can be a closed set. The sub-texts in the reference video script 307 can be classified to determine the label of each sub-text, thereby obtaining a label sequence 308 of the reference video script 307. The order of the multiple labels in the label sequence 308 is consistent with the order of the multiple sub-texts in the reference video script 307.

[0075] After obtaining the reference video script 307, the demand information 305, the reference video script 307 and the label sequence 308 of the reference video script 307 can be input into the big model 309, so that based on the big model 309, an attractive and influential target video script 310 can be generated according to market trends and user needs.

[0076] Figure 4 It is a schematic structural block diagram of a video script generating device according to an embodiment of the present disclosure.

[0077] like Figure 4 As shown, the video script generating device 400 may include a reference video script determining module 410 and a generating module 420 .

[0078] The reference video script determination module 410 is used to determine the reference video script from the database according to the demand information and the correlation between each video script in the database. The reference video script includes multiple subtexts, each subtext corresponds to a label; the label sequence includes multiple labels corresponding to the multiple subtexts in the reference video script, and the order of the multiple labels in the label sequence is consistent with the order of the multiple subtexts in the reference video script.

[0079] The generation module 420 is used to generate a target video script based on the large model according to the demand information, the reference video script and the label sequence corresponding to the reference video script.

[0080] According to another embodiment of the present disclosure, the reference video script determination module includes: an initial video script determination submodule, a first description text determination submodule and a reference video script determination submodule. The initial video script determination submodule is used to determine the initial video script from the database according to the demand information and the similarity between each video script in the database; wherein the video script in the database includes multiple description texts, and the multiple description texts are used to describe the entity associated with the video script from different dimensions. The first description text determination submodule is used to determine the first description text from other video scripts of the same category as the initial video script in the database in response to detecting a selection operation for at least part of the description text in the initial video script, wherein the description dimension of the first description text is the same as the description dimension of at least part of the description text. The reference video script determination submodule is used to determine the reference video script according to the first description text and the second description text; wherein the second description text is the remaining description text in the initial video script except at least part of the description text.

[0081] According to another embodiment of the present disclosure, the initial video script determination submodule includes: a recall unit and an initial video script determination unit. The recall unit is used to recall multiple video scripts from the database according to the demand information and the similarity between each video script in the database. The initial video script determination unit is used to determine the initial video script from the recalled multiple video scripts according to at least one of the selection operation of the object and the demand information.

[0082] According to another embodiment of the present disclosure, the initial video script determination unit includes: a first subunit, a second subunit, and a third subunit. The first subunit is used to respond to the detection that the object performs a selection operation on at least one of the recalled multiple video scripts within a first predetermined period of time, and the selected at least one video script is used as the initial video script. The second subunit is used to respond to the detection that the object does not perform a selection operation on the recalled multiple video scripts within the first predetermined period of time, and the demand information includes a demand category, and selects at least one video script from the recalled multiple video scripts according to the demand category and the actual categories of the multiple video scripts as the initial video script. The third subunit is used to respond to the detection that the object does not perform a selection operation on the recalled multiple video scripts within the first predetermined period of time, and the demand information does not include a demand category, and randomly selects at least one video script from the recalled multiple video scripts as the initial video script.

[0083] According to another embodiment of the present disclosure, the number of first description texts is multiple; the reference video script determination submodule includes: an output unit and a reference video script determination unit. The output unit is used to output multiple first description texts. The reference video script determination unit is used to determine the reference video script according to at least part of the first description text and the second description text in response to receiving a selection operation for at least part of the first description texts among the multiple first description texts.

[0084] According to another embodiment of the present disclosure, it further includes: a parsing module and a demand information determination module. The parsing module is used to parse the page to be processed in response to receiving the page to be processed to obtain multiple fields. The demand information determination module is used to determine the demand information according to the multiple fields.

[0085] According to another embodiment of the present disclosure, the demand information determination module includes: a determination submodule and a demand information determination submodule. The determination submodule is used to determine, for each of a plurality of fields, whether the field is a key field according to a business scenario of an object associated with a page to be processed. The demand information determination submodule is used to determine demand information according to a key field in a plurality of fields.

[0086] According to another embodiment of the present disclosure, it also includes: a trigger module for triggering an operation of determining a reference video script from a database based on the correlation between demand information and each video script in the database in response to detecting that the object has not selected a reference video script from the database within a second predetermined time period.

[0087] According to another embodiment of the present disclosure, it also includes: a target resource determination module and a video script determination module. The target resource determination module is used to determine the target resource from multiple resources based on the historical interaction data of each of the multiple resources. The video script determination module is used to determine the video script in the database based on the video script associated with the target resource. The historical interaction data includes at least one of the following: click-through rate, completion rate, number of favorites, number of likes, number of comments, and number of shares.

[0088] According to another embodiment of the present disclosure, the resource is a video resource for introducing the entity.

[0089] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned video script generation method.

[0090] According to an embodiment of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the above-mentioned video script generation method.

[0091] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, including a computer program, which implements the above-mentioned video script generation method when executed by a processor.

[0092] Figure 5 1 is a block diagram of an electronic device for implementing the video script generation method of an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0093] like Figure 5As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0094] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0095] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the video script generation method. For example, in some embodiments, the video script generation method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the video script generation method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the video script generation method in any other appropriate manner (e.g., by means of firmware).

[0096] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0098] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0099] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0100] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0101] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0102] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0103] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a video script, comprising: Determine a reference video script from the database according to the correlation between the demand information and each video script in the database; as well as Generate a target video script based on a large model according to the demand information, the reference video script, and a tag sequence corresponding to the reference video script; Among them, the reference video script includes multiple sub-texts, each sub-text corresponds to a label; the label sequence includes multiple labels corresponding to the multiple sub-texts in the reference video script, and the order of the multiple labels in the label sequence is consistent with the order of the multiple sub-texts in the reference video script.

2. The method according to claim 1, wherein: Determining the reference video script from the database according to the correlation between the demand information and each video script in the database includes: Determine an initial video script from the database according to the similarity between the demand information and each video script in the database; wherein the video script in the database includes a plurality of description texts, and the plurality of description texts are used to describe entities associated with the video script from different dimensions; In response to detecting a selection operation on at least part of the description text in the initial video script, determining a first description text from other video scripts in the database of the same category as the initial video script, wherein a description dimension of the first description text is the same as a description dimension of the at least part of the description text; and The reference video script is determined according to the first description text and the second description text; wherein the second description text is the remaining description text in the initial video script except for the at least part of the description text.

3. The method according to claim 2, wherein: Determining the initial video script from the database according to the demand information and the similarity between each video script in the database comprises: Recalling a plurality of video scripts from the database according to the similarity between the demand information and each video script in the database; and The initial video script is determined from a plurality of recalled video scripts according to at least one of the selection operation of the object and the requirement information.

4. The method according to claim 3, wherein: The determining the initial video script from the recalled multiple video scripts according to at least one of the selection operation of the object and the demand information comprises: In response to detecting that the subject performs a selection operation on at least one video script among the recalled multiple video scripts within a first predetermined time period, taking the selected at least one video script as the initial video script; In response to detecting that the subject does not perform a selection operation on the recalled multiple video scripts within the first predetermined period, and the demand information includes a demand category, selecting at least one video script from the recalled multiple video scripts as the initial video script according to the demand category and the actual categories of each of the multiple video scripts; and In response to detecting that the object has not performed a selection operation on the recalled multiple video scripts within the first predetermined time period, and the demand information does not include the demand category, at least one video script is randomly selected from the recalled multiple video scripts as the initial video script.

5. The method according to claim 2, wherein: The number of the first description texts is multiple; and the determining the reference video script according to the first description text and the second description text comprises: outputting a plurality of first description texts; and In response to receiving a selection operation on at least part of the first description texts among the plurality of first description texts, the reference video script is determined according to the at least part of the first description texts and the second description text.

6. The method according to claim 1, further comprising: In response to receiving a page to be processed, parsing the page to be processed to obtain a plurality of fields; as well as The requirement information is determined according to the multiple fields.

7. The method according to claim 6, wherein: The determining, according to the multiple fields, the requirement information comprises: For each of the multiple fields, determining whether the field is a key field according to a business scenario of an object associated with the page to be processed; and The requirement information is determined according to the key field in the multiple fields.

8. The method according to claim 1, further comprising: In response to detecting that the subject does not select a reference video script from the database within a second predetermined period of time, an operation of determining the reference video script from the database according to the correlation between the demand information and each video script in the database is triggered.

9. The method according to claim 1, further comprising: Determine a target resource from the multiple resources based on the historical interaction data of each of the multiple resources; as well as Determine the video script in the database according to the video script associated with the target resource; The historical interaction data includes at least one of the following: click rate, completion rate, number of favorites, number of likes, number of comments, and number of shares.

10. The method according to claim 9, wherein: The resource is a video resource used to introduce the entity.

11. A video script generating device, comprising: A reference video script determination module, used to determine a reference video script from the database according to the demand information and the correlation between each video script in the database; as well as A generating module, configured to generate a target video script based on a large model according to the demand information, the reference video script and a tag sequence corresponding to the reference video script; Among them, the reference video script includes multiple sub-texts, each sub-text corresponds to a label; the label sequence includes multiple labels corresponding to the multiple sub-texts in the reference video script, and the order of the multiple labels in the label sequence is consistent with the order of the multiple sub-texts in the reference video script.

12. The device according to claim 11, wherein The reference video script determination module includes: An initial video script determination submodule, used to determine an initial video script from the database according to the demand information and the similarity between each video script in the database; wherein the video script in the database includes a plurality of description texts, and the plurality of description texts are used to describe entities associated with the video script from different dimensions; A first description text determination submodule is configured to, in response to detecting a selection operation on at least part of the description text in the initial video script, determine a first description text from other video scripts of the same category as the initial video script in the database, wherein a description dimension of the first description text is the same as a description dimension of the at least part of the description text; and The reference video script determination submodule is used to determine the reference video script based on the first description text and the second description text; wherein the second description text is the remaining description text in the initial video script except for the at least part of the description text.

13. The device according to claim 12, wherein: The initial video script determination submodule includes: a recall unit, configured to recall a plurality of video scripts from the database according to the demand information and the similarity between each video script in the database; and An initial video script determining unit is used to determine the initial video script from multiple recalled video scripts based on the object selection operation and at least one of the demand information.

14. The device according to claim 13, wherein: The initial video script determination unit comprises: A first subunit is configured to, in response to detecting that the subject performs a selection operation on at least one video script among the recalled multiple video scripts within a first predetermined time period, use the selected at least one video script as the initial video script; a second subunit, configured to select at least one video script from the recalled multiple video scripts as the initial video script in response to detecting that the subject has not performed a selection operation on the recalled multiple video scripts within the first predetermined period of time, and the demand information includes a demand category, according to the demand category and the actual categories of each of the multiple video scripts; and The third subunit is used to randomly select at least one video script from the recalled multiple video scripts as the initial video script in response to detecting that the object has not performed a selection operation on the recalled multiple video scripts within the first predetermined time period and the demand information does not include the demand category.

15. The device according to claim 12, wherein: The number of the first description texts is multiple; The reference video script determination submodule includes: An output unit, used for outputting a plurality of first description texts; as well as A reference video script determining unit is used to determine the reference video script according to the at least part of the first description text and the second description text in response to receiving a selection operation for at least part of the first description text among the multiple first description texts.

16. The apparatus according to claim 11, further comprising: A parsing module, configured to parse the page to be processed in response to receiving the page to be processed, and obtain a plurality of fields; as well as The requirement information determining module is used to determine the requirement information according to the multiple fields.

17. The device according to claim 16, wherein: The demand information determination module includes: a determination submodule, configured to determine, for each of the plurality of fields, whether the field is a key field according to a business scenario of an object associated with the page to be processed; and The requirement information determination submodule is used to determine the requirement information according to the key field in the multiple fields.

18. The apparatus according to claim 11, further comprising: A trigger module is used to trigger the operation of determining the reference video script from the database according to the correlation between the demand information and each video script in the database in response to detecting that the object has not selected a reference video script from the database within a second predetermined time period.

19. The apparatus according to claim 11, further comprising: A target resource determination module, used for determining a target resource from a plurality of resources based on respective historical interaction data of the plurality of resources; as well as A video script determination module, used to determine the video script in the database according to the video script associated with the target resource; The historical interaction data includes at least one of the following: click rate, completion rate, number of favorites, number of likes, number of comments, and number of shares.

20. The device according to claim 19, wherein The resource is a video resource used to introduce the entity.

21. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 10.

23. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images