Video generation method, system and equipment based on hotel information and storage medium

Abstract

The invention provides a video generation method, system and device based on hotel information and a storage medium, and the method comprises the steps: collecting related information of an object hotel, inputting the related information into preset language scripts, and generating a hotel introduction document through a trained large language model; segmenting the hotel introduction copywriting, and generating a voice broadcast of each copywriting sentence by using a TTS voice synthesis model; collecting a picture set of an object hotel and screening and displaying pictures by using a multi-modal large model; converting the display picture into a video clip on the basis of the duration of each voice broadcast, and synthesizing the voice broadcast and the video clip into a hotel display video; and adding at least one trigger suspension layer in the hotel display video, and if the trigger suspension layer is clicked, skipping to a hotel guest room ordering link. According to the method, an automatic link from script generation, voice synthesis, image screening to video synthesis can be realized, the labor cost can be greatly reduced, hotel content popularization and display are optimized, and the user experience is improved.

Description

Background Art

[0002] In the current Internet environment, images and videos are two important information display media. Compared with images, videos can dynamically reflect the development and change trends of things, contain more information than pictures, and display more vivid content. The OTA platform has a natural advantage in obtaining basic hotel information and the amount of hotel picture data, but using these hotel information and pictures to produce comprehensive hotel content marketing videos requires a lot of labor costs in script copywriting, picture screening, video production, etc. Therefore, as an OTA platform, it can fully screen and use hotel information and image data, and automatically synthesize hotel script marketing videos to comprehensively display hotel key information and enhance user experience. Through the existing hotel information and image data, the hotel script marketing video can be automatically generated, which can not only promote and distribute hotel content, but also reduce the production cost of marketing videos and improve production efficiency, providing consumers with an intuitive and comprehensive display effect of the hotel.

[0003] At present, the manual production cost of hotel script marketing videos is high and the video production takes a long time. The OTA platform has a huge amount of hotel image data. How to use these images more efficiently and conveniently to generate comprehensive hotel content for promotion so that users can intuitively experience the hotel information is a challenging project.

[0004] Therefore, the present invention provides a video generation method, system, device and storage medium based on hotel information. Summary of the invention

[0005] In response to the problems in the prior art, the purpose of the present invention is to provide a video generation method, system, device and storage medium based on hotel information, which overcomes the difficulties of the prior art and can automate the link from script generation, speech synthesis, image screening to video synthesis, which can greatly reduce labor costs, optimize hotel content promotion and display, and enhance user experience.

[0006] An embodiment of the present invention provides a method for generating a video based on hotel information, comprising the following steps:

[0007] S110, collect information about the target hotel and input it into various preset language scripts, and then generate a hotel introduction copy through the trained large language model;

[0008] S120, segmenting the hotel introduction text based on preset sentence lengths, and generating a voice broadcast of each sentence in the text using a TTS speech synthesis model;

[0009] S130, collecting pictures of the target hotel to establish a picture collection and screening the displayed pictures by using a multimodal large model, and establishing a mapping relationship between the copywriting sentences, voice broadcast and displayed pictures;

[0010] S140, converting the display pictures into video clips based on the duration of each of the voice broadcasts, and then synthesizing the voice broadcasts and the video clips into a hotel display video; and

[0011] S150: Add at least one triggering suspension layer in the hotel display video, which jumps to the hotel room ordering link when clicked.

[0012] Preferably, the step S110 includes:

[0013] S111. Collect information about the target hotel;

[0014] S112, inputting the relevant information of the target hotel into various preset language scripts to obtain several introduction texts;

[0015] S113, inputting all the introduction texts into a trained large language model to generate a hotel introduction copy.

[0016] Preferably, the step S120 includes:

[0017] S121, segmenting the hotel introduction text based on a preset sentence length, wherein the preset sentence length is less than 18 words;

[0018] S122. Generate a voice broadcast of each text sentence using a TTS speech synthesis model.

[0019] Preferably, the step S130 includes:

[0020] S131, collect pictures of the target hotel to establish a picture collection;

[0021] S132, filtering the picture collection based on preset size and picture quality;

[0022] S133, using the multimodal large model to calculate the picture with the highest similarity to each sentence in the hotel introduction copy as the display picture;

[0023] S134: Establish a mapping relationship between the text sentence, voice broadcast, and display picture.

[0024] Preferably, the step S132 includes:

[0025] S1321. Filter out pictures with a resolution less than 800*600 in the picture collection;

[0026] S1322. Obtain a quality score for each image based on a preset image quality model, and filter images with a quality score less than or equal to 40.

[0027] Preferably, the step S140 includes:

[0028] S141, converting the display picture into a silent video clip based on the duration of each voice broadcast;

[0029] S142: Based on the order of the text sentences, the voice broadcast and the silent video clips are combined into a hotel display video.

[0030] Preferably, the step S150 includes:

[0031] S151, adding at least one trigger suspension layer to the hotel display video;

[0032] S152: When the hotel display video is played, when the trigger floating layer is clicked, the hotel room ordering link is jumped.

[0033] An embodiment of the present invention further provides a video generation system based on hotel information, which is used to implement the above-mentioned video generation method based on hotel information. The video generation system based on hotel information includes:

[0034] The hotel copywriting module collects information about the target hotel and inputs it into various preset language scripts, and then generates a hotel introduction copy through the trained large language model;

[0035] The voice broadcast module segments the hotel introduction text based on the preset sentence length and generates the voice broadcast of each sentence using the TTS speech synthesis model;

[0036] A mapping relationship module collects pictures of the target hotel to establish a picture collection and screens and displays the pictures using a multimodal large model, and establishes a mapping relationship between the copywriting sentences, voice broadcasts, and displayed pictures;

[0037] A display video module converts the display pictures into video clips based on the duration of each voice broadcast, and then combines the voice broadcast and the video clips into a hotel display video; and

[0038] The room link module adds at least one trigger suspension layer in the hotel display video, and when clicked, it jumps to the hotel room order link.

[0039] An embodiment of the present invention further provides a video generation device based on hotel information, comprising:

[0040] processor;

[0041] a memory storing executable instructions of the processor;

[0042] The processor is configured to execute the steps of the above-mentioned video generation method based on hotel information by executing the executable instructions.

[0043] An embodiment of the present invention further provides a computer-readable storage medium for storing a program, wherein the program, when executed, implements the steps of the above-mentioned method for generating a video based on hotel information.

[0044] The purpose of the present invention is to provide a video generation method, system, device and storage medium based on hotel information, which can automate the link from script generation, speech synthesis, image screening to video synthesis, which can greatly reduce labor costs, optimize hotel content promotion and display, and improve user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Other features, objectives and advantages of the present invention will become more apparent from a reading of the detailed description of non-limiting embodiments made with reference to the following accompanying drawings.

[0046] Figure 1 It is a flow chart of the video generation method based on hotel information of the present invention.

[0047] Figure 2 It is a schematic diagram of the implementation process of the video generation method based on hotel information of the present invention.

[0048] Figure 3 It is a structural schematic diagram of the video generation system based on hotel information of the present invention.

[0049] Figure 4 It is a structural schematic diagram of a video generation device based on hotel information of the present invention.

[0050] Figure 5 It is a schematic diagram of the structure of a computer-readable storage medium according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the present application. The present application can also be implemented or applied through other different specific implementation methods, and the details in the present application can also be modified or changed in various ways according to different viewpoints and application systems without departing from the spirit of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0052] The following is a detailed description of the embodiments of the present application with reference to the accompanying drawings so that those skilled in the art can easily implement the present application. The present application can be embodied in a variety of different forms and is not limited to the embodiments described herein.

[0053] In the representations of the present application, the representations with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials or characteristics represented in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the represented specific features, structures, materials or characteristics may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples represented in the present application and the features of the different embodiments or examples, unless they contradict each other.

[0054] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the representation of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0055] In order to clearly describe the present application, components irrelevant to the description are omitted, and the same reference symbols are given to the same or similar components throughout the specification.

[0056] Throughout the specification, when a device is said to be "connected" to another device, this includes not only the case of "direct connection" but also the case of "indirect connection" by placing other elements therebetween. In addition, when a device is said to "include" a certain component, unless otherwise stated, it does not exclude other components, but means that other components may be included.

[0057] When a device is said to be "on" another device, it may be directly on the other device, but there may also be other devices between it. In contrast, when a device is said to be "directly" on another device, there are no other devices between it.

[0058] Although the terms first, second, etc. are used to represent various elements in some examples, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, the first interface and the second interface, etc. are represented. Moreover, as used in this article, the singular forms "one", "one" and "the" are intended to also include plural forms, unless there is an opposite indication in the context. It should be further understood that the terms "comprising" and "including" indicate the existence of features, steps, operations, elements, components, projects, kinds, and / or groups, but do not exclude the existence, occurrence or addition of one or more other features, steps, operations, elements, components, projects, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or mean any one or any combination. Therefore, "A, B or C" or "A, B and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B and C". Only when the combination of elements, functions, steps or operations is inherently mutually exclusive in some way, will there be an exception to this definition.

[0059] The technical terms used herein are only used to refer to specific embodiments and are not intended to limit the present application. The singular form used herein also includes the plural form unless the sentence clearly indicates the contrary meaning. The meaning of "including" used in the specification is to specify specific characteristics, regions, integers, steps, operations, elements and / or components, and does not exclude the existence or addition of other characteristics, regions, integers, steps, operations, elements and / or components.

[0060] Although not defined differently, all terms, including technical and scientific terms used herein, have the same meaning as those generally understood by those skilled in the art to which this application belongs. Terms defined in commonly used dictionaries are additionally interpreted as having meanings consistent with the relevant technical literature and the contents of the current disclosure, and unless defined, shall not be overly interpreted as ideal or very formal meanings.

[0061] Figure 1 Flowchart of the video generation method based on hotel information of the present invention. Figure 1 As shown, the video generation method based on hotel information of the present invention includes:

[0062] S110, collect the relevant information of the target hotel into each preset language script, and then generate a hotel introduction copy through the trained large language model.

[0063] S120, segmenting the hotel introduction text based on preset sentence lengths, and generating a voice broadcast of each text sentence using a TTS speech synthesis model.

[0064] S130, collect pictures of the target hotel to establish a picture collection, and use the multimodal large model to filter and display the pictures, and establish a mapping relationship between the copywriting sentences, voice broadcasts, and displayed pictures.

[0065] S140: Convert the display pictures into video clips based on the duration of each voice broadcast, and then combine the voice broadcast and the video clips into a hotel display video.

[0066] S150: Add at least one triggering floating layer in the hotel display video, which will jump to the hotel room ordering link when clicked.

[0067] Based on the existing massive hotel basic information and hotel picture data on the OTA platform, the present invention establishes an automated hotel script marketing video generation solution, realizing an automated link from script generation, speech synthesis, image screening to video synthesis, which can greatly reduce labor costs, optimize hotel content promotion and display, enhance user experience, and build the brand image of OTA.

[0068] In a preferred embodiment, step S110 includes:

[0069] S111. Collect hotel-related information.

[0070] S112, inputting the relevant information of the target hotel into each preset language script to obtain several introduction texts.

[0071] S113, inputting all the introduction texts into the trained large language model to generate a hotel introduction copy, but not limited to this.

[0072] In a preferred embodiment, step S120 includes:

[0073] S121. Segment the hotel introduction text based on a preset sentence length, where the preset sentence length is less than 18 characters.

[0074] S122. Generate a voice broadcast of each copy sentence using a TTS speech synthesis model, but this is not limited to this.

[0075] In a preferred embodiment, step S130 includes:

[0076] S131, collect pictures of the target hotel to create a picture collection.

[0077] S132: Filter the picture collection based on preset size and picture quality.

[0078] S133. Using the multimodal large model, calculate the image with the highest similarity to each sentence in the hotel introduction copy as the display image.

[0079] S134: Establishing a mapping relationship between text sentences, voice broadcasts, and display pictures, but not limited to this.

[0080] In a preferred embodiment, step S132 includes:

[0081] S1321. Filter out pictures with a resolution smaller than 800*600 in the picture collection.

[0082] S1322. Obtain a quality score for each image based on a preset image quality model, and filter images with a quality score less than or equal to 40, but not limited thereto.

[0083] In a preferred embodiment, step S140 includes:

[0084] S141. Convert the displayed image into a silent video clip based on the duration of each voice broadcast.

[0085] S142. Based on the order of the text sentences, the voice broadcast and the silent video clips are combined into a hotel display video, but the present invention is not limited thereto.

[0086] In a preferred embodiment, step S150 includes:

[0087] S151. Add at least one trigger suspension layer to the hotel display video.

[0088] S152. When the hotel display video is played, when the trigger floating layer is clicked, the hotel room ordering link is jumped, but not limited to this.

[0089] The present invention first automatically generates a script copy of the hotel introduction through a large language model based on the basic information of the hotel; then uses the existing multimodal large model to filter out the hotel pictures that best match the script copy; then uses the existing speech synthesis model and the image generation video method to generate the script copy oral broadcast and short video; finally uses the marketing video template to synthesize all the short videos and oral broadcasts into a complete hotel marketing video, reducing labor costs in an automated way. In recent years, multimodal large models have developed rapidly. This article introduces how to use multimodal large models to generate hotel script marketing videos.

[0090] A specific implementation of the present invention is as follows:

[0091] In view of the current situation that the manual production cost of hotel script marketing videos is high and the video production is time-consuming, the present invention establishes an automated process system, utilizes the capabilities of a multimodal large model and related hotel images to synthesize hotel script marketing videos, thereby reducing the production cost of marketing videos, improving the efficiency of hotel content promotion, and enhancing user experience.

[0092] Figure 2FIG. 1 is a schematic diagram of the implementation process of the video generation method based on hotel information of the present invention. Figure 2 As shown, the implementation process of the video generation method based on hotel information of the present invention is as follows:

[0093] First of all, in the implementation of this case, we first need to obtain basic information such as the hotel name, hotel introduction, hotel evaluation, hotel special facilities, hotel special theme, hotel surroundings, etc., and organize and package the basic hotel information into the input prompt required by the model according to different types of script design, and generate a real and attractive hotel introduction script copy through the large language model. The implementation flow chart is as follows Figure 2 shown.

[0094] Then, because 18 words are the optimal word limit for screen display under the conditions of font style design and video display size, the generated hotel script copy is segmented according to the requirement that each sentence does not exceed 18 words, and the existing TTS speech synthesis model is used to select a suitable tone to generate the oral broadcast of each sentence.

[0095] Next, we first calculate the quality scores of hotel pictures through the existing picture quality score model, and then select high-quality pictures based on the two conditions of picture resolution and quality score. Then, we calculate the similarity between each copy and the selected hotel pictures through the existing multimodal large model, and filter out the picture data that best matches the copy and has the highest quality. The implementation flow chart is shown in the attached figure. Figure 3 Specifically, the following steps are included:

[0096] Step 1: Filter image data that meets the conditions

[0097] First, you need to calculate the quality score of each image, and then filter out image data that is too small or too poor in quality based on the two conditions of resolution greater than or equal to 800*600 and quality score less than or equal to 40.

[0098] Step 2: Calculate the similarity between the image and the text

[0099] Using the existing multimodal model, the similarity between the screened pictures and each sentence in the hotel copywriting script is calculated, and the similarities are sorted from high to low. Finally, the number of pictures required to generate the video is determined based on the length of the oral broadcast of this sentence, and the pictures with the highest similarity are selected as the video data to be generated.

[0100] In addition, the existing multimodal big model is first used to generate a detailed description of the screened pictures, and then the picture description and the picture are input into the existing picture-to-video big model to convert the pictures into video clips, and finally all the video clips that match the hotel script copy are obtained.

[0101] Finally, you can design a template for generating hotel script marketing videos, determine the type of transition effects and background music added between video clips, and use the video template to synthesize the final hotel script marketing video. For example: add at least one trigger suspension layer to the hotel display video. When the hotel display video is played, when the trigger suspension layer is clicked, it will jump to the hotel room order link.

[0102] Based on the massive hotel basic information and hotel image data of Ctrip online, the present invention realizes a hotel script marketing video automatic generation system based on a multimodal model. The hotel introduction script copy and copy oral broadcast can be automatically generated, the most matching hotel pictures are screened out through the multimodal large model, and the pictures are used to generate videos, and finally the hotel script marketing video is synthesized according to the marketing video template. It effectively optimizes the promotion and display of hotel content, greatly reduces labor costs, and improves user experience.

[0103] Figure 3 Schematic diagram of the structure of the video generation system based on hotel information of the present invention. Figure 3 As shown, an embodiment of the present invention further provides a video generation system based on hotel information, which is used to implement the above-mentioned video generation method based on hotel information. The video generation system based on hotel information 5 includes:

[0104] The hotel copywriting module 51 collects the relevant information of the target hotel and inputs it into various preset language scripts, and then generates a hotel introduction copywriting through the trained large language model;

[0105] The voice broadcast module 52 segments the hotel introduction text based on the preset sentence length and generates a voice broadcast of each sentence of the text using a TTS speech synthesis model;

[0106] A mapping relationship module 53 collects pictures of the target hotel to establish a picture collection and screens and displays the pictures using a multimodal large model, and establishes a mapping relationship between the copywriting sentences, voice broadcasts, and displayed pictures;

[0107] A display video module 54 converts the display pictures into video clips based on the duration of each voice broadcast, and then combines the voice broadcast and the video clips into a hotel display video; and

[0108] The room link module 55 adds at least one trigger suspension layer in the hotel display video, and when clicked, it jumps to the hotel room order link.

[0109] In a preferred embodiment, the hotel copywriting module 51 is configured to collect information related to the target hotel, input the information related to the target hotel into various preset language scripts, obtain several introduction texts, and input all the introduction texts into a trained large language model to generate a hotel introduction copy, but not limited to this.

[0110] In a preferred embodiment, the voice broadcast module 52 is configured to segment the hotel introduction text based on a preset sentence length, which is less than 18 words, and use a TTS speech synthesis model to generate a voice broadcast of each sentence in the text, but is not limited to this.

[0111] In a preferred embodiment, the mapping relationship module 53 is configured to collect pictures of the target hotel to establish a picture collection, filter the picture collection based on preset size and picture quality, use the multimodal large model to calculate the picture with the highest similarity to each copy sentence in the hotel introduction copy as the display picture, and establish a mapping relationship between the copy sentences, voice broadcast and display pictures, but not limited to this.

[0112] In a preferred embodiment, the mapping relationship module 53 is also configured to filter out pictures with a resolution less than 800*600 in the picture collection, obtain the quality score of each picture based on a preset picture quality model, and filter out pictures with a quality score less than or equal to 40, but not limited to this.

[0113] In a preferred embodiment, the display video module 54 is configured to convert the display pictures into silent video clips based on the duration of each voice broadcast, and to synthesize the voice broadcasts and silent video clips into a hotel display video based on the order of the text sentences, but is not limited to this.

[0114] In a preferred embodiment, the room link module 55 is configured to add at least one trigger suspension layer in the hotel display video. When the hotel display video is played, when the trigger suspension layer is clicked, the hotel room order link is jumped, but not limited to this.

[0115] The hotel information-based video generation system of the present invention can automate the links from script generation, speech synthesis, image screening to video synthesis, which can significantly reduce labor costs, optimize hotel content promotion and display, and improve user experience.

[0116] The embodiment of the present invention further provides a video generation device based on hotel information, comprising a processor and a memory in which executable instructions of the processor are stored, wherein the processor is configured to execute the steps of the video generation method based on hotel information by executing the executable instructions.

[0117] As shown above, the video generation device based on hotel information of this embodiment of the present invention can automate the link from script generation, speech synthesis, image screening to video synthesis, which can greatly reduce labor costs, optimize hotel content promotion and display, and improve user experience.

[0118] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0119] Figure 4 This is a schematic diagram of the structure of the video generation device based on hotel information of the present invention. Figure 4 The electronic device 600 according to this embodiment of the present invention is described. Figure 4 The electronic device 600 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0120] like Figure 4 As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0121] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0122] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202 , and may further include a read-only storage unit (ROM) 6203 .

[0123] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0124] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0125] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0126] The embodiment of the present invention also provides a computer-readable storage medium for storing a program, and the steps of the video generation method based on hotel information are implemented when the program is executed. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of various exemplary embodiments of the present invention described in the above method part of this specification.

[0127] As shown above, the video generation system based on hotel information of this embodiment of the present invention can automate the links from script generation, speech synthesis, image screening to video synthesis, which can greatly reduce labor costs, optimize hotel content promotion and display, and improve user experience.

[0128] Figure 5 Schematic diagram of the structure of the computer-readable storage medium of the present invention. Figure 5 As shown, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0129] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0130] Computer readable storage media may include data signals propagated in baseband or as part of a carrier wave, wherein readable program codes are carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0131] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0132] In summary, the purpose of the present invention is to provide a video generation method, system, device and storage medium based on hotel information, which can automate the link from script generation, speech synthesis, image screening to video synthesis, which can greatly reduce labor costs, optimize hotel content promotion and display, and enhance user experience.

[0133] The above contents are further detailed descriptions of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is limited to these descriptions. For ordinary technicians in the technical field to which the present invention belongs, several simple deductions or substitutions can be made without departing from the concept of the present invention, which should be regarded as falling within the protection scope of the present invention.

Claims

1. A video generation method based on hotel information, characterized in that: The following steps are involved: S110, collect information about the target hotel and input it into various preset language scripts, and then generate a hotel introduction copy through the trained large language model; S120, segmenting the hotel introduction text based on preset sentence lengths, and generating a voice broadcast of each sentence in the text using a TTS speech synthesis model; S130, collecting pictures of the target hotel to establish a picture collection and screening the displayed pictures by using a multimodal large model, and establishing a mapping relationship between the copywriting sentences, voice broadcast and displayed pictures; S140, converting the display pictures into video clips based on the duration of each of the voice broadcasts, and then synthesizing the voice broadcasts and the video clips into a hotel display video; as well as S150: Add at least one triggering suspension layer in the hotel display video, which jumps to the hotel room ordering link when clicked.

2. The video generation method based on hotel information as claimed in claim 1, characterized in that: The step S110 includes: S111. Collect information about the target hotel; S112, inputting the relevant information of the target hotel into various preset language scripts to obtain several introduction texts; S113, inputting all the introduction texts into a trained large language model to generate a hotel introduction copy.

3. The video generation method based on hotel information as claimed in claim 1, characterized in that: The step S120 includes: S121, segmenting the hotel introduction text based on a preset sentence length, wherein the preset sentence length is less than 18 words; S122. Generate a voice broadcast of each copy sentence using a TTS speech synthesis model.

4. The video generation method based on hotel information as claimed in claim 1, characterized in that: The step S130 includes: S131, collect pictures of the target hotel to establish a picture collection; S132, filtering the picture collection based on preset size and picture quality; S133, using the multimodal large model to calculate the picture with the highest similarity to each sentence in the hotel introduction copy as the display picture; S134: Establish a mapping relationship between the text sentence, voice broadcast, and display picture.

5. The video generation method based on hotel information as claimed in claim 4, characterized in that: The step S132 includes: S1321. Filter out pictures with a resolution less than 800*600 in the picture collection; S1322. Obtain a quality score for each image based on a preset image quality model, and filter images with a quality score less than or equal to 40.

6. The video generation method based on hotel information as claimed in claim 1, characterized in that: The step S140 includes: S141, converting the display picture into a silent video clip based on the duration of each voice broadcast; S142: Based on the order of the text sentences, the voice broadcast and the silent video clips are combined into a hotel display video.

7. The video generation method based on hotel information as claimed in claim 1, characterized in that: The step S150 includes: S151, adding at least one trigger suspension layer to the hotel display video; S152: When the hotel display video is played, when the trigger floating layer is clicked, the hotel room ordering link is jumped.

8. A video generation system based on hotel information, used to implement the video generation method based on hotel information according to claim 1, characterized in that: include: The hotel copywriting module collects information about the target hotel and inputs it into various preset language scripts, and then generates a hotel introduction copy through the trained large language model; The voice broadcast module segments the hotel introduction text based on the preset sentence length and generates the voice broadcast of each sentence using the TTS speech synthesis model; A mapping relationship module collects pictures of the target hotel to establish a picture collection and screens and displays the pictures using a multimodal large model, and establishes a mapping relationship between the copywriting sentences, voice broadcasts, and displayed pictures; A display video module converts the display pictures into video clips based on the duration of each voice broadcast, and then combines the voice broadcast and the video clips into a hotel display video; as well as The room link module adds at least one trigger suspension layer in the hotel display video, and when clicked, it jumps to the hotel room order link.

9. A video generation device based on hotel information, characterized in that: include: processor; a memory storing executable instructions of the processor; The processor is configured to execute the steps of the video generation method based on hotel information according to any one of claims 1 to 7 by executing the executable instructions.

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

Images