Method, system, equipment and product for generating scenic spot video based on scenic spot picture

Abstract

The invention provides a method, system, equipment and product for generating a scenic spot video based on scenic spot pictures, and the method comprises the steps: receiving at least one scenic spot feature keyword and a plurality of scenic spot pictures; scoring the scenic spot pictures based on a preset picture quality scoring rule, and reserving the scenic spot pictures with scores higher than a preset value as high-quality pictures; classifying the high-quality pictures based on the scenic spot feature keywords to obtain a scenic spot feature picture set corresponding to each scenic spot feature keyword; adding special effects on the basis of high-quality pictures in each scenic spot feature picture set to form a scenic spot feature video; based on the fixed scenes of the preset video template, selecting a scenic spot feature video adapted to each fixed scene, inserting the scenic spot feature video into the fixed scene, and imprinting a corresponding scene text; and adding an audio to the video template to generate a scenic spot video. The scenic spot video production efficiency can be improved, the scenic spot video production standardization degree is increased, and the scenic spot video editability is improved.

Description

Background Art

[0002] With the popularization of digital media and the Internet, video content has become an important means to showcase tourist attractions and enhance user experience. On some tourism platforms, a large number of static scenic spot pictures are often used to form dynamic videos introducing the attractions through simple picture splicing and special effects processing. However, this method of generating videos based on pictures has the following main problems:

[0003] First, the efficiency of scenic spot video production is low. Existing methods of generating videos from pictures often require a lot of manual participation. In actual operation, it is necessary to manually select high-quality pictures that match the characteristics of the scenic spot, and screen and classify the pictures one by one. The entire process not only has many steps, but also relies on the experience and judgment of the operator, resulting in low efficiency in video production and difficulty in meeting the needs of large-scale and rapid updates.

[0004] Second, the production of scenic spot videos is not standardized. As the existing methods are highly dependent on manual operation during the video generation process, different operators are prone to large differences in image selection, special effects addition, text layout and other links, making the final generated video lack uniformity in visual style, content layout and overall effect.

[0005] Third, scenic spot videos are not easy to edit. Videos generated by existing technologies are usually inadequate in post-editing and error correction. Since each link is relatively fixed after the video is generated, if a picture error, text error or inconsistent visual effect is found in a certain frame or scene, it is often necessary to re-produce or adjust the entire video clip on a large scale, resulting in high modification costs and slow response speed. Summary of the invention

[0006] In view of this, the present disclosure provides a method, system, device and product for generating a scenic spot video based on scenic spot pictures, so as to at least solve the problems of low efficiency of scenic spot video production, low degree of standardization of scenic spot video production and poor editability of scenic spot video in the existing method of generating videos based on pictures.

[0007] In one aspect, an embodiment of the present disclosure provides a method for generating a scenic spot video based on a scenic spot picture, comprising:

[0008] Receiving at least one scenic spot feature keyword and a plurality of scenic spot pictures;

[0009] Score scenic spot pictures based on preset picture quality scoring rules, and retain scenic spot pictures with scores higher than the preset value as high-quality pictures;

[0010] Classify high-quality pictures based on scenic spot feature keywords to obtain a set of scenic spot feature pictures corresponding to each scenic spot feature keyword;

[0011] After adding special effects to the high-quality pictures in each scenic spot feature picture set, a scenic spot feature video is formed;

[0012] Based on the fixed scenes of the preset video template, select the scenic spot feature video that is suitable for each fixed scene and insert it into the fixed scene, and print the corresponding scene text;

[0013] Add audio to video templates to generate attraction videos.

[0014] On the other hand, an embodiment of the present disclosure further provides a system for generating a scenic spot video based on a scenic spot picture, comprising:

[0015] A scenic spot information receiving module receives at least one scenic spot feature keyword and a plurality of scenic spot pictures;

[0016] The scenic spot picture screening module scores the scenic spot pictures based on the preset picture quality scoring rules, and retains the scenic spot pictures with scores higher than the preset value as high-quality pictures;

[0017] The scenic spot picture classification module classifies high-quality pictures based on the scenic spot feature keywords to obtain a set of scenic spot feature pictures corresponding to each scenic spot feature keyword;

[0018] The scenic spot feature video generation module adds special effects based on the high-quality pictures in each scenic spot feature picture set to form a scenic spot feature video;

[0019] The scenic spot feature video combination module selects the scenic spot feature video that is suitable for each fixed scene based on the fixed scene of the preset video template, inserts it into the fixed scene, and prints the corresponding scene text;

[0020] Audio combination module, adds audio to video templates to generate scenic spot videos.

[0021] In another aspect, an embodiment of the present disclosure further provides a device for generating a scenic spot video based on a scenic spot picture, comprising:

[0022] processor;

[0023] a memory storing computer-readable instructions;

[0024] The processor is configured to perform the above method by executing computer-readable instructions.

[0025] On the other hand, an embodiment of the present disclosure further provides a computer program product, including computer-readable instructions, which implement the above method when executed by a processor.

[0026] The method, system, device and product for generating scenic spot videos based on scenic spot pictures disclosed in the present invention improve the production efficiency of scenic spot videos by adopting an algorithm to replace manual automatic generation of scenic spot videos based on scenic spot pictures; increase the standardization of scenic spot video production by adding special effects, applying video templates and adding background music; and by adopting video templates, various parts of scenic spot videos can be adjusted according to fixed scenes, thereby improving the editability of scenic spot videos and reducing the modification costs of scenic spot videos. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0028] Figure 1 is a flowchart of the steps of a method for generating a scenic spot video based on a scenic spot picture provided by an embodiment of the present disclosure;

[0029] Figure 2 is a flow chart of other steps of a method for generating a scenic spot video based on a scenic spot picture provided by an embodiment of the present disclosure;

[0030] Figure 3 yes Figure 1 A specific step flow chart of step S130;

[0031] Figure 4 yes Figure 1 A specific step flow chart of step S140;

[0032] Figure 5 yes Figure 1 A specific step flow chart of step S150;

[0033] Figure 6 It is a module structure diagram of a system for generating a scenic spot video based on a scenic spot picture provided by an embodiment of the present disclosure;

[0034] Figure 7 It is a structural schematic diagram of a device for generating a scenic spot video based on a scenic spot picture provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that the disclosure will be comprehensive and complete and the concepts of the example embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their repeated description will be omitted.

[0036] The words "first", "second" and similar words used in the specific description do not indicate any order, quantity or importance, but are only used to distinguish different components. In addition, in the description of the present disclosure, the orientation or position relationship indicated by the terms "upper" and "lower" are based on the orientation or position relationship shown in the drawings, which are only for the convenience of description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation of the present disclosure.

[0037] It should be noted that, in the absence of conflict, the embodiments of the present disclosure and the features in different embodiments may be combined with each other.

[0038] like Figure 1 As shown, in one aspect, an embodiment of the present disclosure provides a method for generating a scenic spot video based on a scenic spot picture, comprising:

[0039] S110, receiving at least one scenic spot feature keyword and a plurality of scenic spot pictures;

[0040] S120, scoring the scenic spot pictures based on a preset picture quality scoring rule, and retaining the scenic spot pictures with scores higher than the preset value as high-quality pictures;

[0041] S130, classifying the high-quality pictures based on the scenic spot feature keywords to obtain a scenic spot feature picture set corresponding to each scenic spot feature keyword;

[0042] S140, adding special effects based on the high-quality pictures in each scenic spot feature picture set to form a scenic spot feature video;

[0043] S150, based on the fixed scenes of the preset video template, selecting a scenic spot feature video adapted to each fixed scene to insert into the fixed scene, and imprinting the corresponding scene text;

[0044] S160: Add audio to the video template to generate a scenic spot video.

[0045] This embodiment improves the efficiency of scenic spot video production by adopting an algorithm to replace manual automatic generation of scenic spot videos based on scenic spot pictures; increases the standardization of scenic spot video production by adding special effects, applying video templates, and adding background music; and by adopting video templates, various parts of scenic spot videos can be adjusted according to fixed scenes, thereby improving the editability of scenic spot videos and reducing the cost of modifying scenic spot videos.

[0046] It is worth noting that the above S110 to S160 are merely step numbers, which are used to facilitate reference and avoid text duplication. Unless otherwise specified, the above and subsequent step numbers will not limit the order of implementation of the various steps of the method. In other embodiments, the above steps of the method can also be written and implemented in an interchangeable order, and are not limited thereto.

[0047] like Figure 2 As shown, in some embodiments, before step S110, the method for generating a scenic spot video based on the scenic spot picture further includes:

[0048] S101, in response to receiving a scenic spot text and a plurality of scenic spot pictures, extracting at least one scenic spot feature keyword based on the scenic spot text;

[0049] S102, segmenting the scenic spot text based on the scenic spot feature keywords to obtain at least one scenic spot sub-text corresponding to each scenic spot feature keyword;

[0050] S103: Send at least one scenic spot feature keyword, at least one scenic spot subtext, and a plurality of scenic spot pictures.

[0051] For the above step S101, specifically, the system first receives a text describing a certain scenic spot (such as an introduction to the scenic spot, promotional copy) and multiple scenic spot pictures related to the scenic spot. Then the text is cleaned, noise is removed and word segmentation is performed. Using natural language processing (NLP) technology, words with higher frequency or greater semantic weight are extracted from the word segmentation results as candidate keywords. TF-IDF, TextRank and other algorithms can be used to analyze the text and filter out the keywords that best represent the characteristics of the scenic spot. For example, for texts describing "ancient city, lake, picturesque scenery" and other contents, the system will extract "ancient city", "lake" and so on as scenic spot feature keywords.

[0052] For the above step S102, specifically, after extracting the scenic spot feature keywords, the system divides the original scenic spot text according to the positions where the scenic spot feature keywords appear through a text segmentation algorithm. The scenic spot text is encoded with a semantic vector using a deep learning model, and then the sentences semantically related to a certain scenic spot feature keyword are aggregated into a scenic spot sub-text through a clustering algorithm. A mapping relationship between the scenic spot feature keywords and the scenic spot sub-text is established.

[0053] This embodiment automatically generates scenic spot feature keywords through a section of scenic spot text, which can reduce the workload of manual reading and judgment, can quickly and accurately capture the core description information of the scenic spot, and improve the efficiency of scenic spot video production.

[0054] In some embodiments, the scenic spot picture may be a picture containing content represented by the characteristic keywords of the scenic spot. For example, the content of the scenic spot picture may be "temple fair", "ancient city", "lake", "picturesque scenery" and the like.

[0055] In some embodiments, the scene text includes: a scenic spot feature keyword, a scenic spot subtext, or a combination of one or at least two other scenic spot keywords extracted from the scenic spot subtext. That is, while the scenic spot video displays the scenic spot picture, the scene text is also displayed as text description information to assist in describing the scenic spot and improve the integration of the scenic spot video.

[0056] In some embodiments, the audio includes: one or a combination of at least two of preset background music, converted audio of the scenic spot subtext, or converted audio of the abstract of the scenic spot subtext. That is, while the scenic spot video displays the scenic spot picture, the converted audio of the scenic spot subtext or the converted audio of the abstract of the scenic spot subtext can also be added to further introduce the scenic spot, or preset background music can be added to improve the watchability of the scenic spot video. The preset background music can be matched with a suitable song or instrumental music through the scenic spot text or the scenic spot feature keywords.

[0057] In some embodiments, the picture quality scoring rules include: the number of picture pixels, the size of the picture, the exposure of the picture, or whether it contains one or at least two combinations of scenic spot features. The picture quality scoring rules are a set of pre-set quantitative standards for automatically evaluating and screening the quality of input scenic spot pictures. The core purpose is to ensure that the pictures entering the scenic spot video generation process meet high standards, thereby improving the overall quality and user experience of the final video product. Specifically, a minimum number of pixels (such as 1080p or higher standards) is set, and scenic spot pictures below this standard will be considered low quality. If the overall brightness offset or contrast of the scenic spot picture is inappropriate, the score will be reduced accordingly. A deep learning model (such as a convolutional neural network CNN) is used to extract features from the scenic spot pictures to detect whether the pictures contain feature elements related to the scenic spot feature keywords. Match the scenic spot feature keywords with the descriptive tags identified by the scenic spot pictures. If the tags identified in the scenic spot pictures match the preset scenic spot feature keywords, it means that the picture can better reflect the characteristics of the scenic spot, thereby obtaining a higher score. Finally, the above indicators (number of pixels, file size, exposure, and degree of matching of scenic spot features) can be weighted and calculated according to preset weights to obtain a comprehensive score.

[0058] like Figure 3 As shown, in some embodiments, step S130 includes:

[0059] S131, selecting any one from metadata, file name, or descriptive keywords extracted by image recognition technology of each high-quality image as the image keyword of the high-quality image;

[0060] S132, aggregating the vectors of the picture keywords of each high-quality picture to form a picture feature vector of the high-quality picture;

[0061] S133. For each scenic spot feature keyword, high-quality pictures corresponding to picture feature vectors whose difference with the vector of the scenic spot feature keyword is less than a preset value form a scenic spot feature picture set.

[0062] For the above step S131, specifically, the metadata may obtain picture keywords through descriptive information that may be contained in EXIF ​​information, GPS data, shooting time, etc. The file name may obtain picture keywords through the place, scenic spot or feature description that may be contained in the high-quality picture file name. For example, "West Lake Sunset.jpg" can directly extract "West Lake" and "Sunset". A deep learning algorithm (such as a convolutional neural network, target detection or image classification model) is used to automatically analyze high-quality pictures, and object or scene descriptive keywords are extracted as picture keywords.

[0063] For the above step S132, specifically, for each image keyword obtained in step S131, a pre-trained word vector model (such as Word2Vec, GloVe or BERT, etc.) can be used to convert it into a fixed-dimensional image feature vector representation. If a picture corresponds to more than one keyword, multiple word vectors can be integrated into an overall image feature vector by simple averaging, weighted averaging or other aggregation methods. The image feature vector can capture the semantic information and visual features contained in the image.

[0064] For the above step S133, specifically, the "attraction feature keywords" extracted from the attraction description text are also vectorized to obtain the corresponding attraction feature vector (also using a pre-trained language model). For each attraction feature keyword, the distance between its vector and the picture feature vector of each high-quality picture is calculated (commonly used measurement methods include Euclidean distance or cosine similarity). When the distance (or difference) between the two is less than a preset threshold, it means that the high-quality picture is highly semantically matched with the attraction feature keyword, and the picture is included in the attraction feature picture set. The threshold can be adjusted according to actual needs and experimental results to ensure that a certain semantic difference can be tolerated and the accuracy of the match can be guaranteed.

[0065] like Figure 4 As shown, in some embodiments, step S140 includes:

[0066] S141, sorting the high-quality pictures in the characteristic picture set of each scenic spot;

[0067] S142, applying visual effects to each high-quality image through an image processing algorithm;

[0068] S143, using the high-quality picture with visual effects as a frame of the scenic spot feature video, and setting the display duration of each frame to form a scenic spot feature video clip;

[0069] S144, splicing each scenic spot feature video clip in a predetermined sorting order to form a scenic spot feature video.

[0070] For the above step S141, specifically, if the high-quality pictures contain information such as shooting time and geographical location, they can be sorted in chronological order or scene relevance. Alternatively, the high-quality pictures can be sorted according to the semantic matching between the picture keywords of the high-quality pictures and the scenic spot feature keywords, so that the high-quality pictures that best match the current display scene are placed in the front.

[0071] For the above step S142, specifically, for static images, a variety of visual effects technologies can be used, such as filter processing, motion effects, transition effects, and artistic style transfer. Artistic style transfer can use deep learning algorithms to transfer styles and convert high-quality images into style images with specific artistic effects. Use image processing libraries (such as OpenCV, Adobe After Effects plug-ins, or special effects processing frameworks based on deep learning) to perform special effects processing on each high-quality image.

[0072] For the above step S143, specifically, the high-quality picture after applying the visual effects is regarded as a video frame, and each frame can directly correspond to a high-quality picture. According to the high-quality picture content and the preset template requirements, the display time (for example, 2-3 seconds) is set for each frame to ensure that the overall rhythm of the video is moderate. Use video editing or processing tools (such as FFmpeg, Premiere Pro's automatic script function) to arrange the continuous picture frames in order to form a short scenic feature video clip.

[0073] For the above step S144, specifically, the previously generated video clips of the scenic spot features are spliced ​​according to the sorting order determined in step S141. Video editing software or programming tools (such as FFmpeg, Adobe Premiere Pro automation script) are used to seamlessly splice the video clips of the scenic spot features. Transition effects (such as fade in and fade out, cross dissolve) can be added between the video clips of the scenic spot features to ensure the overall visual smoothness of the scenic spot feature video.

[0074] like Figure 5As shown, in some embodiments, step S150 includes:

[0075] S151: Obtain a preset video template, where the preset video template includes at least one fixed scene, and the fixed scene is used to display at least a video element and a text element;

[0076] S152, using an algorithm to automatically match the fixed scene and the scenic spot feature video, and inserting the successfully matched scenic spot feature video into the fixed scene;

[0077] S153: Imprint the scene text corresponding to the scenic spot feature video into the fixed scene, and display the scene text and the scenic spot feature video synchronously.

[0078] For the above step S151, specifically, the system pre-builds and stores a series of preset video templates, which contain at least one fixed scene. The fixed scene pre-defines the functions of each area in the picture, for example: the video display area is used to insert the subsequently generated scenic spot feature video clips; the text display area is used to print or overlay the scene text and other related text information.

[0079] For the above step S152, specifically, in the preceding step S140, a plurality of scenic spot feature videos have been generated. At this point, the visual and semantic features of each scenic spot feature video can be extracted using image processing and video content analysis techniques (such as frame feature extraction, color histogram, scene classification or deep learning model). According to the design requirements of the fixed scene in the preset template (for example, scene style, color tone, content layout), a matching algorithm is designed to compare the similarity between the features of the scenic spot feature video and the template requirements. After the match is successful, the system automatically embeds the corresponding scenic spot feature video into the video element area of ​​the specified fixed scene in the preset template to form a dynamic display part in the scenic spot video.

[0080] For the above step S153, specifically, use image / video editing technology (such as FFmpeg, OpenCV or professional video synthesis software) to imprint the corresponding scene text in the preset text element area of ​​the fixed scene.

[0081] The method for generating a scenic spot video based on scenic spot pictures disclosed in the present invention improves the efficiency of scenic spot video production by adopting an algorithm to replace manual automatic generation of scenic spot videos based on scenic spot pictures; increases the degree of standardization of scenic spot video production by adding special effects, applying video templates, and adding background music; and by adopting video templates, various parts of the scenic spot video can be adjusted according to fixed scenes, thereby improving the editability of the scenic spot video and reducing the modification cost of the scenic spot video.

[0082] like Figure 6 As shown, on the other hand, an embodiment of the present disclosure further provides a system for generating a scenic spot video based on a scenic spot picture, including:

[0083] A scenic spot information receiving module receives at least one scenic spot feature keyword and a plurality of scenic spot pictures;

[0084] The scenic spot picture screening module scores the scenic spot pictures based on the preset picture quality scoring rules, and retains the scenic spot pictures with scores higher than the preset value as high-quality pictures;

[0085] The scenic spot picture classification module classifies high-quality pictures based on the scenic spot feature keywords to obtain a set of scenic spot feature pictures corresponding to each scenic spot feature keyword;

[0086] The scenic spot feature video generation module adds special effects based on the high-quality pictures in each scenic spot feature picture set to form a scenic spot feature video;

[0087] The scenic spot feature video combination module selects the scenic spot feature video that is suitable for each fixed scene based on the fixed scene of the preset video template, inserts it into the fixed scene, and prints the corresponding scene text;

[0088] Audio combination module, adds audio to video templates to generate scenic spot videos.

[0089] The specific technical solutions and technical effects of the system for generating scenic spot videos based on scenic spot pictures disclosed in the present invention can be referred to the aforementioned method embodiment for generating scenic spot videos based on scenic spot pictures, which will not be repeated here.

[0090] like Figure 7 As shown, in another aspect, an embodiment of the present disclosure further provides a device for generating a scenic spot video based on a scenic spot picture, comprising: a processor; a memory storing computer-readable instructions. The processor is configured to execute the method for generating a scenic spot video based on a scenic spot picture by executing the computer-readable instructions.

[0091] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0092] Refer to the following Figure 7 The electronic device 600 according to this embodiment of the present disclosure is described. Figure 7 The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0093] like Figure 7As 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.

[0094] The storage unit 620 stores computer-readable instructions, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps described in the above method section of this specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0095] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0096] 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.

[0097] 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.

[0098] 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.

[0099] The specific technical solutions and technical effects of the device for generating a scenic spot video based on a scenic spot picture disclosed in the present invention can be referred to the aforementioned method embodiment for generating a scenic spot video based on a scenic spot picture, which will not be described in detail here.

[0100] In another aspect, an embodiment of the present disclosure further provides a computer program product, the computer program product including computer-readable instructions, the computer-readable instructions stored in a computer-readable storage medium. A processor of a computing device can read the computer-readable instructions from the computer-readable storage medium, and the processor executes the computer-readable instructions, so that the computing device executes the method for generating a scenic spot video based on a scenic spot picture described in each of the above embodiments.

[0101] The computer-readable storage medium includes computer-readable instructions that can be written in any combination of one or more programming languages. Programming languages ​​include object-oriented programming languages, such as Java, C++, etc., and also include conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0102] The specific technical solutions and technical effects of the computer program product disclosed in the present invention can be referred to the aforementioned method embodiment for generating a scenic spot video based on a scenic spot picture, which will not be described in detail here.

[0103] The above contents are further detailed descriptions of the present disclosure in combination with specific optional implementation methods, and it cannot be determined that the specific implementation of the present disclosure is limited to these descriptions. For ordinary technicians in the technical field to which the present disclosure belongs, several simple deductions or substitutions can be made without departing from the concept of the present disclosure, which should be regarded as falling within the scope of protection of the present disclosure.

Claims

1. A method for generating a scenic spot video based on a scenic spot picture, characterized in that: include: Receiving at least one scenic spot feature keyword and a plurality of scenic spot pictures; Scoring the scenic spot pictures based on a preset picture quality scoring rule, and retaining the scenic spot pictures with scores higher than a preset value as high-quality pictures; Classifying the high-quality pictures based on the scenic spot feature keywords to obtain a set of scenic spot feature pictures corresponding to each of the scenic spot feature keywords; After adding special effects based on the high-quality pictures in each of the scenic spot feature picture sets, a scenic spot feature video is formed; Based on the fixed scenes of the preset video template, the scenic spot feature video adapted to each fixed scene is selected and inserted into the fixed scene, and the corresponding scene text is printed; Audio is added to the video template to generate a scenic spot video.

2. The method for generating a scenic spot video based on a scenic spot picture according to claim 1, characterized in that: Before receiving at least one scenic spot feature keyword and a plurality of scenic spot pictures, the method further includes: In response to receiving a section of scenic spot text and a plurality of the scenic spot pictures, extracting at least one scenic spot feature keyword based on the scenic spot text; Segmenting the scenic spot text based on the scenic spot feature keywords to obtain at least one scenic spot sub-text corresponding to each of the scenic spot feature keywords; At least one of the scenic spot feature keywords, at least one of the scenic spot subtexts, and a plurality of the scenic spot pictures are sent.

3. The method for generating a scenic spot video based on a scenic spot picture according to claim 2, characterized in that: The scene text includes: the scenic spot feature keyword, the scenic spot subtext, or one or a combination of at least two of other scenic spot keywords extracted from the scenic spot subtext; The audio includes: preset background music, the converted audio of the scenic spot sub-text, or the converted audio of the summary of the scenic spot sub-text, or a combination of at least two of them.

4. The method for generating a scenic spot video based on a scenic spot picture according to claim 1, characterized in that: The image quality scoring rules include: the number of image pixels, image size, image exposure, or whether the image contains one or a combination of at least two of the scenic spot features.

5. The method for generating a scenic spot video based on a scenic spot picture according to claim 1, characterized in that: The step of classifying the high-quality pictures based on the scenic spot feature keywords to obtain a set of scenic spot feature pictures corresponding to each of the scenic spot feature keywords includes: Selecting any one of the metadata, file name or descriptive keywords extracted by image recognition technology of each of the high-quality pictures as the picture keyword of the high-quality pictures; Aggregating the vectors of the picture keywords of each of the high-quality pictures to form a picture feature vector of the high-quality pictures; For each of the scenic spot feature keywords, the high-quality pictures corresponding to the picture feature vectors whose difference with the vector of the scenic spot feature keyword is less than a preset value form the scenic spot feature picture set.

6. The method for generating a scenic spot video based on a scenic spot picture according to claim 1, characterized in that: The adding of special effects based on the high-quality pictures in each of the scenic spot feature picture sets to form a scenic spot feature video includes: Sorting the high-quality pictures in each of the scenic spot feature picture sets; Applying visual effects to each of the high-quality images through an image processing algorithm; Using the high-quality picture with visual effects as a frame of the scenic spot feature video, and setting the display duration of each frame to form a scenic spot feature video clip; Each of the scenic spot feature video clips is spliced ​​in a predetermined sorting order to form the scenic spot feature video.

7. The method for generating a scenic spot video based on a scenic spot picture according to claim 1, characterized in that: The fixed scene based on the preset video template, selecting the scenic spot feature video adapted to each fixed scene to insert into the fixed scene, and imprinting the corresponding scene text, comprises: Acquire the preset video template, where the preset video template includes at least one fixed scene, and the fixed scene is used to display at least a video element and a text element; Automatically match the fixed scene and the scenic spot feature video using an algorithm, and insert the successfully matched scenic spot feature video into the fixed scene; The scene text corresponding to the scenic spot feature video is imprinted into the fixed scene, and the scene text is displayed synchronously with the scenic spot feature video.

8. A system for generating scenic spot videos based on scenic spot pictures, characterized in that: include: A scenic spot information receiving module receives at least one scenic spot feature keyword and a plurality of scenic spot pictures; A scenic spot picture screening module is used to score the scenic spot pictures based on a preset picture quality scoring rule, and to retain the scenic spot pictures with a score higher than a preset value as high-quality pictures; A scenic spot picture classification module, classifying the high-quality pictures based on the scenic spot feature keywords, and obtaining a scenic spot feature picture set corresponding to each of the scenic spot feature keywords; A scenic spot feature video generation module, which adds special effects based on each of the high-quality pictures in the scenic spot feature picture set to form a scenic spot feature video; The scenic spot feature video combination module selects the scenic spot feature video adapted to each fixed scene based on the fixed scene of the preset video template, inserts it into the fixed scene, and prints the corresponding scene text; The audio combination module adds audio to the video template to generate a scenic spot video.

9. A device for generating a scenic spot video based on a scenic spot picture, characterized in that: include: processor; a memory storing computer-readable instructions; The processor is configured to perform the method according to any one of claims 1 to 7 by executing the computer readable instructions.

10. A computer program product comprising computer readable instructions, characterized in that: When the computer-readable instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images