Artificial intelligence model-based room type video generation method, computing device and computer program product

Abstract

The embodiment of the invention provides a room type video generation method based on an artificial intelligence model, and in the method, because video mirror operation parameters are obtained based on a plurality of position parameters, the video mirror operation parameters can more accurately describe the position relationship of each guest room article in the composition of the room type video and the space size of a hotel room, so that the room type video generation efficiency is improved. The occurrence probability of unreasonable composition in the room type video is reduced, and the probability of abnormal view angle change in the room type video is reduced, so that the success rate of generating the room type video corresponding to the hotel room by calling the artificial intelligence model can be improved, and compared with a traditional video shooting method, the generation cost of the room type video can be reduced, and the generation efficiency of the room type video is improved. And the room type video corresponding to the hotel room is generated based on the video mirror operation parameters, so that the space size of the hotel room, room supplies and other related conditions can be displayed more truly and comprehensively, and the display effect of the room type video on the hotel room can be improved.

Description

Technical Field

[0001] This specification relates to the field of computer application technology, and more specifically, to a method for generating room type videos based on an artificial intelligence model, a computing device, and a computer program product. Background Art

[0002] Travel service applications can provide users with a variety of travel products. For example, travel service applications can provide hotel reservation, ticket reservation and other functions, allowing users to book hotels, tickets and other travel products through travel service applications.

[0003] When users make hotel reservations, they often need to view the layout and facilities of the hotel rooms. Therefore, it is necessary to improve the display effect of hotel rooms. Summary of the Invention

[0004] The embodiments of this specification provide a method, computing device, and computer program product for generating room type videos based on an artificial intelligence model to achieve the purpose of improving the display effect of hotel rooms.

[0005] To achieve the above technical objectives, the embodiments of this specification provide the following technical solutions:

[0006] In a first aspect, one embodiment of this specification provides a method for generating a room type video based on an artificial intelligence model, which is applied to a travel service application. The room type video is used to display the space size and room items of a hotel room. The method for generating a room type video based on the artificial intelligence model includes:

[0007] Acquire a target image of a hotel room, wherein the target image shows a plurality of guest room items in the hotel room;

[0008] Based on the target image, obtaining position parameters corresponding to each of the plurality of guest room items displayed in the target image, wherein the position parameters are used to represent the position of the corresponding guest room items in the hotel room;

[0009] Based on the plurality of position parameters, obtaining video camera movement parameters, wherein the video camera movement parameters are used to describe the viewing angle and composition of the room type video corresponding to the hotel room;

[0010] Based on the video camera parameters, an artificial intelligence model is called to generate a room type video corresponding to the hotel room, and the room type video corresponding to the hotel room is used to be played on the client of the travel service application.

[0011] In a second aspect, an embodiment of the present specification also provides a computing device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the method for generating room type videos based on the artificial intelligence model as described above is implemented.

[0012] On the third aspect, an embodiment of the present specification further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for generating room type videos based on the artificial intelligence model as described above is implemented.

[0013] Fourthly, embodiments of this specification provide a computer program product or computer program, comprising a computer program stored in a computer-readable storage medium; a processor of a computer device reads the computer program from the computer-readable storage medium; and when the processor executes the computer program, implements the steps of the method for generating a room type video based on an artificial intelligence model. Optionally, the computer program may be stored in a computer-readable storage medium or in the cloud; the processor of the computer device reads the computer program from the computer-readable storage medium or in the cloud.

[0014] It can be seen from the above technical solution that the method for generating room type videos based on an artificial intelligence model provided in the embodiment of this specification obtains the target image of the hotel room, and then obtains the position parameters corresponding to the multiple guest room items displayed therein based on the target image, and the position parameters represent the positions of the corresponding guest room items in the hotel room; then, based on the multiple position parameters, the video movement parameters are obtained, and based on the video movement parameters, the artificial intelligence model is called to generate the room type video corresponding to the hotel room. Since the video camera movement parameters are obtained based on multiple position parameters, the video camera movement parameters can more accurately describe the positional relationship of each guest room item in the composition of the room type video and the spatial size of the hotel room, reducing the probability of unreasonable composition (such as abnormal position of guest room items, etc.) appearing in the room type video, and since multiple position parameters can respectively describe the position of the guest room items corresponding to the position parameters in the hotel room, the video camera movement parameters can be more reasonable when describing the perspective changes of the room type video corresponding to the hotel room, reducing the probability of abnormal perspective changes in the room type video. In this way, the success rate of generating the room type video corresponding to the hotel room by calling the artificial intelligence model can be improved. Compared with the traditional video shooting method, the generation cost of the room type video can be reduced, and the room type video corresponding to the hotel room based on the video camera movement parameters can more realistically and comprehensively display the spatial size of the hotel room and related conditions such as guest room supplies, which is conducive to improving the display effect of the room type video on the hotel room. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without any creative work.

[0016] Figure 1 A schematic diagram of the architecture of a travel service system provided for one embodiment of this specification;

[0017] Figure 2 A flowchart of a method for generating room type videos based on an artificial intelligence model provided in accordance with one embodiment of this specification;

[0018] Figure 3 A schematic diagram of a process for calculating the orientation of a target guest room item in a hotel room, provided in accordance with one embodiment of this specification;

[0019] Figure 4 A schematic diagram of a room type video display page provided in one embodiment of this specification;

[0020] Figure 5 A schematic diagram of a room type video display page provided in one embodiment of this specification;

[0021] Figure 6 A schematic diagram of a process for generating a room type video provided in one embodiment of this specification;

[0022] Figure 7 A schematic diagram of a room type video review process provided in accordance with one embodiment of this specification;

[0023] Figure 8 A schematic diagram of the structure of a computing device provided for one embodiment of this specification. DETAILED DESCRIPTION

[0024] Unless otherwise defined, technical or scientific terms used in the embodiments of this specification should have the same ordinary meaning as those understood by persons of ordinary skill in the art to which this specification pertains. The terms "first," "second," and similar terms used in the embodiments of this specification do not denote any order, quantity, or importance, but are provided solely to avoid confusion between constituent elements.

[0025] Unless the context requires otherwise, throughout this specification, the term "plurality" means "at least two," and "including" is to be interpreted as open and inclusive, meaning "including, but not limited to." Throughout this specification, the terms "one embodiment," "some embodiments," "exemplary embodiments," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with the embodiment or example is included in at least one embodiment or example of this specification. The schematic representations of these terms do not necessarily refer to the same embodiment or example.

[0026] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the embodiments described are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this specification.

[0027] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this manual are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0028] System Architecture

[0029] like Figure 1 As shown, Figure 1 This is a schematic diagram of the architecture of a travel service system provided by an exemplary embodiment. Figure 1 As shown, the system may include a server 11, a network 12, and several computing devices, such as a PC (Personal Computer) 13, a mobile phone 14, and the like.

[0030] The server 11 may be a physical server comprising an independent host, or a virtual server hosted by a host cluster. During operation, the server 11 may run a server-side program of an application to implement the relevant functions of the application. For example, the server of a travel service application may run on the server 11 to implement the relevant functions of the travel service application.

[0031] PC 13 and mobile phone 14 are only some types of computing devices that users can use. In fact, users can obviously also use computing devices such as the following types: tablet devices, laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.), etc., and one or more embodiments of this specification do not limit this. During operation, the computing device can run the client-side program of a certain application to implement the relevant functions of the application. For example, the client of a travel service application can run on a computing device to implement the relevant functions of the client of the travel service application. Among them, the client of the above-mentioned travel service application can be a native application installed on the computing device, or the program on the client side can be a small program, a quick application or other similar forms. Of course, when using web page technologies such as HTML5 or similar, the relevant functions can be implemented through the page displayed by the browser. The browser here can be an independent browser application or a browser module embedded in certain applications.

[0032] Regarding the network 12 for interaction between computing devices such as PC 13 and mobile phone 14 and server 11, communication can be achieved using a wired or wireless network based on the communication methods supported by the corresponding computing devices, and this specification does not limit this. For example, if PC 13 supports both wired and wireless communication, then communication can be achieved using either a wired or wireless network as needed, while mobile phone 14 generally only supports wireless communication and thus can achieve communication using a wireless network.

[0033] Travel service applications can provide functions such as hotel reservations. In addition to traditional star-rated hotels and convenient hotels, these hotels can also include homestays, youth hostels, hourly rooms, daily rental rooms, monthly rental rooms and other hotel types in a broader sense.

[0034] Overview

[0035] Traditionally, travel service apps have provided one or more pictures of hotel rooms to help users understand the interior structure and layout of the rooms. However, these pictures often lack visual quality, preventing users from clearly understanding the room's dimensions or the relationship between the items displayed in the pictures. To improve this, travel service apps can provide room layout videos. These videos showcase the room's dimensions and furnishings, helping users more intuitively understand the room's interior.

[0036] However, currently, room layout videos rely on staff using professional filming equipment to shoot, which makes the labor and equipment costs of room layout videos high. If VR (Virtual Reality) type room layout videos need to be shot, the cost of a room layout video is usually over a thousand yuan.

[0037] To reduce the cost of filming room layout videos, related technologies use artificial intelligence models to generate room layout videos. Specifically, they leverage the image-to-video functionality of AI models to generate room layout videos based on images of hotel rooms. However, in practice, AI models have found that their accuracy in spatial calculations, such as the positional relationships between spaces and objects, is low. As a result, room layout videos generated by AI models based on hotel room images struggle to accurately reproduce the room's dimensions and items.

[0038] To solve this problem, a method for generating room type videos based on an artificial intelligence model is proposed. After obtaining a target image of a hotel room, the method obtains the position parameters corresponding to multiple guest room items displayed in the target image based on the target image. The position parameters represent the positions of the corresponding guest room items in the hotel room. Then, based on the multiple position parameters, the video camera movement parameters are obtained. Based on the video camera movement parameters, the artificial intelligence model is called to generate the room type video corresponding to the hotel room. Since the video camera movement parameters are obtained based on multiple position parameters, the video camera movement parameters can more accurately describe the positional relationship of each guest room item in the composition of the room type video and the spatial size of the hotel room, reducing the probability of unreasonable composition (such as abnormal position of guest room items, etc.) appearing in the room type video, and since multiple position parameters can respectively describe the position of the guest room items corresponding to the position parameters in the hotel room, the video camera movement parameters can be more reasonable when describing the perspective changes of the room type video corresponding to the hotel room, reducing the probability of abnormal perspective changes in the room type video. In this way, the success rate of generating the room type video corresponding to the hotel room by calling the artificial intelligence model can be improved. Compared with the traditional video shooting method, the generation cost of the room type video can be reduced, and the room type video corresponding to the hotel room based on the video camera movement parameters can more realistically and comprehensively display the spatial size of the hotel room and related conditions such as guest room supplies, which is conducive to improving the display effect of the room type video on the hotel room.

[0039] Exemplary Methods

[0040] Taking the application of travel service as an example, some embodiments of this specification exemplify the method for generating room type videos based on the artificial intelligence model, such as Figure 2 As shown, the room type video is used to show the space size and room items of the hotel room. The method for generating the room type video based on the artificial intelligence model includes:

[0041] S201: Acquire a target image of a hotel room, where the target image displays a plurality of guest room items in the hotel room;

[0042] S202: Based on the target image, obtaining position parameters corresponding to each of the plurality of guest room items displayed in the target image, wherein the position parameters are used to represent positions of the corresponding guest room items in the hotel room;

[0043] S203: Obtaining video camera parameters based on the multiple position parameters, where the video camera parameters are used to describe the viewing angle and composition of the room type video corresponding to the hotel room;

[0044] S204: Based on the video camera parameters, an artificial intelligence model is called to generate a room type video corresponding to the hotel room, and the room type video corresponding to the hotel room is used to be played on the client of the travel service application.

[0045] The target image of a hotel room can be selected from images uploaded by the hotel to the travel service application. Guest room items include but are not limited to furniture, soft furnishings, and daily necessities. Furniture may include beds, bedside tables, desks, chairs, etc.; soft furnishings may include curtains, lamps, decorative paintings, etc.; daily necessities may include pillows, quilts, tissues, etc.

[0046] In some embodiments, the video camera movement parameters may include part or all of the basic parameters, camera control parameters, and motion mode parameters.

[0047] Basic parameters may include aspect ratio, frame rate, and video duration. The aspect ratio is used to define the aspect ratio of each frame of the room video, the frame rate is used to define the number of frames displayed per second in the room video, which can be expressed in frames per second (FPS), and the video duration is used to define the duration of the room video.

[0048] Camera control parameters can include pan, tilt, zoom, and rotation. Pan parameters include horizontal and vertical pan, which adjust the camera's horizontal and vertical position. The camera's position determines the viewing angle of the room video. Pan parameters can be used to change the viewing angle and composition of the image. Tilt parameters include left and right tilt and up and down tilt, which simulate camera rotation movements, such as panning left and right or shooting from above or below. This can change the direction and angle of the image and create different visual effects. Zoom parameters adjust the camera's focal length, zooming in and out to highlight the subject or show the scene's breadth. Rotation parameters adjust the camera's rotation angle to alter the horizontal and vertical lines of the image, creating special visual effects such as tilted images or rotated perspectives.

[0049] Motion mode parameters can include parameters such as motion brush and regular action. Among them, the motion brush can be used to specify the movement direction and speed of the characters or objects in the video. By drawing in a specific area of ​​the picture, the object and method of movement can be controlled, making the movement of elements in the video more in line with expectations and natural. It can be used in combination with camera movement; regular action is used to increase or decrease the intensity of motion in the video. The higher the value, the more intense the movement, which can control the overall dynamic level of the video.

[0050] In addition, the video camera movement parameters may also include parameters such as interpolation, video style, and resolution. The type and quantity of parameters included in the video camera movement parameters may be determined according to actual conditions, and this manual does not limit this.

[0051] In this embodiment, an artificial intelligence model is called based on video camera parameters to generate a room type video corresponding to a hotel room. While utilizing the advantage of low cost of generating room type videos by artificial intelligence models, the weakness of low accuracy of the artificial intelligence model when directly processing spatial calculations such as the positional relationship between space and objects is avoided. The adaptability of the room type video generated by the artificial intelligence model to the hotel room is improved, so that the room type video generated by the artificial intelligence model can better restore the spatial size and guest room items of the hotel room, which is conducive to improving the display effect of the room type video. Specifically, in the method for generating room type videos based on the artificial intelligence model, since the video camera movement parameters are obtained based on multiple position parameters, the video camera movement parameters can more accurately describe the positional relationship of each guest room item in the composition of the room type video and the spatial size of the hotel room, reducing the probability of unreasonable composition (such as abnormal position of guest room items, etc.) appearing in the room type video, and since multiple position parameters can respectively describe the position of the guest room items corresponding to the position parameters in the hotel room, the video camera movement parameters can be more reasonable when describing the perspective changes of the room type video corresponding to the hotel room, reducing the probability of abnormal perspective changes in the room type video. In this way, the success rate of generating room type videos corresponding to hotel rooms by calling the artificial intelligence model can be improved. Compared with traditional video shooting methods, the generation cost of room type videos can be reduced, and generating room type videos corresponding to hotel rooms based on video camera movement parameters can more realistically and comprehensively display the spatial size of the hotel room and related conditions such as guest room supplies, which is conducive to improving the display effect of room type videos on hotel rooms.

[0052] In one embodiment, a feasible process for calling an artificial intelligence model to generate a room type video is provided. Specifically, calling the artificial intelligence model to generate a room type video corresponding to the hotel room based on the video camera parameters includes:

[0053] Taking the video camera parameters and the target image of the hotel room as input, the artificial intelligence model is called to generate a room type video corresponding to the hotel room.

[0054] In this embodiment, the AI ​​model's input includes video camera parameters and a target image of a hotel room. As previously mentioned, the video camera parameters enable the AI ​​model to more accurately describe the positional relationships between guest room items and the room's spatial dimensions within the room layout video, reducing the likelihood of inappropriate compositions (e.g., those with unusually positioned guest room items) appearing in the room layout video. The target image of the hotel room ensures that the room layout video generated by the AI ​​model more accurately reflects the original appearance of the hotel room.

[0055] In some embodiments, in addition to step S204 being implemented by calling an artificial intelligence model, steps S201 to S203 can also be implemented by a trained artificial intelligence model. The artificial intelligence model that implements step S204 and the artificial intelligence model that implements steps S201 to S203 can be the same model or different models. This specification does not limit this, and the specific situation depends on the actual situation.

[0056] In order to avoid abnormal situations in the room type video, in one embodiment, after generating the room type video corresponding to the hotel room, the method further includes:

[0057] Reviewing the room type video according to the target image of the hotel room; if the review fails, adjusting the video camera parameters, and returning to the step of calling the artificial intelligence model to generate the room type video corresponding to the hotel room based on the video camera parameters;

[0058] or

[0059] Acquire another image of the hotel room as the target image, and return to the step of acquiring position parameters corresponding to each of the plurality of guest room items displayed in the target image based on the target image;

[0060] or

[0061] Return to the step of calling the artificial intelligence model to generate a room type video corresponding to the hotel room based on the video camera parameters.

[0062] In this embodiment, after the room type video is generated, the room type video can be reviewed to find out whether there are any abnormalities in the room type video. If the room type video passes the review, a prompt message can be set in the room type video. The prompt message is used to indicate that the room type video is generated by artificial intelligence technology and is for reference only, so as to avoid unnecessary disputes caused by users thinking that the room type video is a real-life shot. Optionally, the prompt message can remind the user that the room type video they are watching is a virtual video generated by artificial intelligence technology. The room type video is only used to show the possible layout of the interior of the hotel room and the possible guest room items. The actual hotel room interior layout, structure and guest room items are subject to the actual situation. The prompt message can be displayed in multiple frames of the room type video. The prompt message can be displayed in text at a certain position in the room type video, which can be a corner of the room type video, so as to avoid the prompt message excessively interfering with the user's observation of the interior of the hotel room.

[0063] If the room type video review fails, three feasible handling strategies are provided, as described below:

[0064] Strategy 1: Directly return to the step of generating the room type video corresponding to the hotel room based on the video camera parameters and call the artificial intelligence model to regenerate the room type video. This can eliminate abnormalities in the generated room type video with a certain probability. This is because although the video camera parameters used when regenerating the room type video do not change, the artificial intelligence model will output different results under the same input due to the randomness within the artificial intelligence model. Therefore, the abnormalities may be eliminated in the regenerated room type video to meet the usage requirements. This strategy does not require the regeneration of video camera parameters, which helps reduce the computing resources required to execute the method.

[0065] Strategy 2: After adjusting the video camera parameters, the AI ​​model is re-invoked using the adjusted video camera parameters to generate a room video corresponding to the hotel room. This strategy allows for targeted adjustments to the camera parameters and re-generation of the room video based on any anomalies discovered during the review process. This increases the probability of obtaining a room video that meets the requirements and reduces the number of re-generated room videos.

[0066] Strategy 3: Obtain other images of the hotel room as the target image, and re-execute steps S202 to S204 in sequence to obtain a new room type video. This strategy can avoid the situation where the generated room type video does not meet the requirements due to inappropriate target image selection.

[0067] In one embodiment of the present specification, a feasible strategy for adjusting video camera movement parameters is provided. Specifically, the video camera movement parameters include: camera control parameters, the camera control parameters including at least one of translation, tilt, zoom, and rotation parameters;

[0068] The adjusting of the video camera parameters includes:

[0069] At least one of the translation, tilt, scale, and rotation parameters is reduced.

[0070] As mentioned above, the camera control parameters can define the perspective and composition of the room video. By reducing at least one of the camera control parameters, the probability of abnormal situations such as sudden changes in perspective in the generated room video can be reduced to a certain extent, thereby increasing the probability of generating a room video that meets the requirements.

[0071] In one embodiment, a feasible process for reviewing a room type video is provided. Specifically, reviewing the room type video includes:

[0072] Acquire multiple frames of continuous images in the room video;

[0073] Judging whether there is any abnormality in the room type video according to the target image of the hotel room and the multiple frames of continuous images, if so, the room type video fails the review, and if not, the room type video passes the review;

[0074] The abnormal conditions include: compared with the target image, there are new guest room items, and / or there is an abnormal proportion of at least one of the guest room items, and / or there is a sudden scene change in the multiple frames of continuous images.

[0075] In this embodiment, multiple frames of continuous images in the room video can be used as audit objects. In this way, on the one hand, the amount of data required to be processed during the audit process can be reduced. On the other hand, multiple frames of continuous video can reflect the perspective changes in the room video to a certain extent.

[0076] The target image of the hotel room and the multiple frames of continuous images can then be used to determine whether there are any anomalies. A newly added guest room item may refer to a guest room item that appears in the room layout video but is not present in the target image. For example, if there is a TV in the target image but two TVs appear in the room layout video, the extra TV is a newly added guest room item. In some embodiments, a newly added guest room item may refer to a specific newly added guest room item. These specific guest room items may be larger items, such as TVs, refrigerators, and beds. Smaller items or items whose quantity or location may not be fixed (such as tissues, tissue boxes, and trash cans) may not be included in the review.

[0077] Abnormal proportions of guest room items may refer to abnormal proportions of guest room items relative to other guest room items in the guest room video. For example, under normal circumstances, in the video, the length ratio of the bed and pillow is A. If, in the guest room video, the length ratio of the bed and pillow seriously deviates from the A value (for example, a deviation of 20% or 30% or more, etc.), it can be considered that the proportions of the bed or pillow are abnormal.

[0078] The situation where a sudden scene change exists in multiple frames of continuous images refers to a situation where a sudden jump occurs from one room in the guest room video to another room, or a sudden jump occurs from one position in the guest room video to another position during the guest room video playback.

[0079] By checking the above abnormal situations, it is possible to check abnormal situations with a high probability of occurring in guest room videos, which is helpful to avoid the situation where guest room videos with abnormal situations are put online.

[0080] In one embodiment, a feasible process for obtaining video camera movement parameters based on position parameters is provided. Specifically, the position parameters corresponding to the guest room items include: position coordinates of the guest room items, the position coordinates including coordinates of feature points of the guest room items in a default coordinate system;

[0081] The obtaining of the video camera movement parameters based on the plurality of position parameters includes:

[0082] determining an orientation of the target guest room item within the hotel room based on a position parameter of the target guest room item and a position parameter of at least one associated guest room item; the associated guest room item comprising a guest room item that has a matching relationship with the target guest room item when in use;

[0083] Calculating the space size of the hotel room based on the location parameters of the plurality of guest room items;

[0084] The video camera movement parameters are generated based on the orientation of the target guest room item in the hotel room and the spatial size of the hotel room.

[0085] In this embodiment, a feasible method for determining video motion parameters is provided. First, based on the position parameters of the target guest room item and the position parameters of at least one associated guest room item, the orientation of the target guest room item in the hotel room is determined. The target guest room item can be a large or necessary item in the hotel room (such as a bed). By determining the orientation of the target guest room item in the room, the approximate layout of the items in the hotel room can be basically determined. Then, based on the position parameters of multiple guest room items, the spatial size of the hotel room is calculated. When calculating the spatial size of the hotel room, the position parameters of the two guest room items farthest apart can be used for calculation, or the position parameters of two guest room items with a relatively fixed relative distance (such as the relatively fixed distance between a bed and a nightstand) can be used for calculation. This specification does not limit this. After calculating the orientation of the target guest room item in the hotel room and the spatial size of the hotel room, the spatial size of the hotel room and the layout of the main items are relatively clear, and video motion parameters that can more accurately describe the hotel room can be generated based on this.

[0086] Specifically, in one embodiment, the target guest room item includes a bed, and the associated guest room items include a pillow and / or a bedside table;

[0087] The characteristic point of the target guest room item includes any point at the end of the bed;

[0088] The determining the orientation of the target guest room item in the hotel room based on the location parameter of the target guest room item and the location parameter of at least one associated guest room item includes:

[0089] determining a target direction according to the position parameter of the target guest room item and the position parameter of at least one of the associated guest room items, wherein the target direction includes a direction in which a feature point of the target guest room item points to the associated guest room item;

[0090] The orientation of the target guest room item in the hotel room is determined according to the target direction.

[0091] For example, reference Figure 3 , Figure 3 The present invention shows a feasible method for determining the orientation of a bed in a hotel room based on the bed and pillow. The target guest room item includes the bed, the associated guest room item includes the pillow, the feature points of the bed include feature point A, and the feature points of the pillow include feature point B. Figure 3 The arrow in the image indicates the target direction. In hotel rooms, the direction from the foot of the bed toward the pillow is generally the direction of the bed's head. Therefore, the bed's orientation within the hotel room can be determined based on the target direction. This method allows for accurate and simple determination of the target room item's orientation within the hotel room, helping to ensure the accuracy of the subsequently generated video camera parameters.

[0092] In order to optimize the interactive experience with users when playing room type videos, in one embodiment, the method for generating room type videos based on an artificial intelligence model further includes:

[0093] In response to a user's gesture operation on the room type video being played, the playback progress of the room type video is adjusted accordingly according to the gesture operation.

[0094] In this embodiment, in addition to the traditional method of dragging the progress bar to adjust the playback progress of the room type video, an interactive method of adjusting the playback progress of the room type video according to the user's gesture operation is added, which is conducive to improving the user's interactive experience when playing the room type video.

[0095] Specifically, in one embodiment, the gesture operation includes: a sliding operation;

[0096] The adjusting the playback progress of the room type video according to the gesture operation includes:

[0097] According to the sliding direction of the sliding operation, the playback progress of the room type video is adjusted so that the room type video displays guest room items in the hotel room in the opposite direction of the sliding direction.

[0098] refer to Figure 4 and Figure 5 , Figure 4 and Figure 5 A display page for displaying the room type video of the superior king-size room of Hotel X is shown. Users can watch the room type video of the hotel room on this page. When the room type video is playing, the user can adjust the playback progress of the room type video by sliding (for example, swiping right) on the playback interface of the room type video. For example, when the user swipes right, the hotel room area and guest room items on the left side of the hotel room area displayed on the current screen can be displayed in the hotel room. In this way, the purpose of adjusting the hotel room area displayed in the video can be achieved through the user's gesture operation, realizing an interactive method similar to VR video, and enriching the interactive method between the room type video and the user. For specific reference Figure 4 When watching a room video, if the user wants to understand the layout and structure on the left side of the room, he can adjust the video progress by swiping right. Figure 5 As shown, when the user swipes right on the room type video, the video progress can be automatically adjusted to show the user the area to the left of the hotel room area currently displayed (for example Figure 5 The area to the left of the sofa is shown to the user).

[0099] In order to improve the success rate of generating a room type video of a hotel room, in one embodiment, obtaining a target image of the hotel room includes:

[0100] Acquire multiple images of a hotel room, and determine a target image of the hotel room based on scores of the multiple images;

[0101] The score of the image is positively correlated with the spatial completeness of the hotel room displayed by the image and / or the clarity of the image.

[0102] In this embodiment, hotel operations and maintenance personnel can upload multiple images of hotel rooms to a travel service application. When generating a room video, each image can be scored based on the spatial completeness of the hotel room and / or the clarity of the image. Based on the scores of each of the multiple images, a target image of the hotel room can be determined. In one embodiment, the highest-scoring image among the multiple images can be selected as the target image. In other embodiments, the top N images can be selected from the multiple images in descending order of score as the target images, where N can be greater than or equal to 2. This means that the number of target images can be one, two, or more, and this specification does not limit this; it depends on the actual situation.

[0103] In one embodiment of this specification, a feasible implementation process of a method for generating room type videos based on an artificial intelligence model is provided, referring to Figure 6 and Figure 7 , the process may include a video generation process and a video review process.

[0104] refer to Figure 6 , the video generation process can include:

[0105] Establish a task to generate hotel room videos;

[0106] Get the hotel room images targeted by the generation task from the data warehouse;

[0107] Using the first model to filter images, exclude small space images, exclude spatially blocked images, and calculate position parameters;

[0108] Store the image screening results, that is, store the target image, and can also store the reason for image selection, srid (Spatial Reference System Identifier, spatial reference identifier) ​​and the link to the target image, where srid is used to uniquely identify the target image;

[0109] Utilizing the first model to calculate information such as the bed's orientation through position parameters, and generating video camera movement parameters based on the calculated information;

[0110] The video camera parameters are uploaded to the second model, and the second model generates the room type video. If the generation is successful, the room type video is uploaded to the first database, and the generation completion is notified, and the room type video enters the pending review state; if the generation fails, the task status is reset.

[0111] In the above process, the first model and the second model can be different artificial intelligence models.

[0112] refer to Figure 7 The video review process can include:

[0113] Display videos of rooms awaiting review in the first database;

[0114] The first model is used to review the room type video. During the review, video frames can be created (i.e., multiple frames of continuous images are obtained from the room type video). The first model is used to review the multiple frames of images to determine whether there are any abnormalities. During the review process, multiple frames of continuous images and the reasons for passing or failing the review can be stored.

[0115] After the review is passed, a secondary review by the operation and maintenance personnel can be carried out, prompt information can be added, and the task status can be changed to completed. The daily task status table is synchronized, and the link to the room type video, srid, hotel logo (shid), and cover link of the room type video are stored. The room type video is synchronized to the second database. The room type video stored in the second database is used for client-side call and display by the travel service application. If the review fails, the video is regenerated based on any of the three strategies described above. As mentioned above, the prompt information added to the room type video can be used to remind the user that the room type video is generated by artificial intelligence technology and is for reference only, avoiding unnecessary disputes caused by users believing that the room type video is a real-life shot. Optionally, the prompt information can remind the user that the room type video they are watching is a virtual video generated by artificial intelligence technology. The room type video is only used to show the possible layout of the hotel room interior and possible guest room items. The actual hotel room interior layout, structure, and guest room items are subject to the actual situation. The prompt information can be displayed in multiple frames of the room video. The prompt information can be displayed in text at a certain position in the room video, which can be a corner of the room video, so as to avoid the prompt information excessively interfering with the user's observation of the interior of the hotel room.

[0116] Exemplary Computing Devices

[0117] Another embodiment of the present application further provides a computing device, see Figure 8As shown, an exemplary embodiment of the present specification also provides a computing device, including: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it executes the steps of the method for generating room type videos based on artificial intelligence models according to various embodiments of the present specification described in the above embodiments of the present specification.

[0118] The internal structure of the computing device can be as follows Figure 8 As shown, the computing device includes a processor, a memory, a network interface, and an input device connected via a system bus. The processor of the computing device is used to provide computing and control capabilities. The memory of the computing device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computing device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps of the method for generating a room type video based on an artificial intelligence model according to various embodiments of the present specification described in the above embodiments of the present specification are performed.

[0119] The processor may include a main processor, and may also include a baseband chip, a modem, etc.

[0120] It is understood that the processor in the embodiments of this specification can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by hardware integrated logic circuits in the processor or software instructions. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of this specification can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this specification can be directly implemented as being executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0121] It will be understood that the memory in the embodiments of this specification may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (Programmable ROM, PROM), an erasable programmable read-only memory (ErasablePROM, EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0122] Input devices may include devices that receive data and information input by a user, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0123] Output devices may include means that allow information to be output to a user, such as display screens, printers, speakers, and the like.

[0124] The communication interface may include any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0125] The computing device may also include a display component and a voice component. The display component may be a liquid crystal display or an electronic ink display. The input device of the computing device may be a touch layer covering the display component, or a button, trackball or touchpad provided on the housing of the computing device, or an external keyboard, touchpad or mouse.

[0126] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of this specification, and does not constitute a limitation on the computing device to which the scheme of this specification is applied. The specific computing device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0127] Exemplary computer program products and storage media

[0128] In addition to the above-mentioned methods and devices, the method for generating room type videos based on artificial intelligence models provided in the embodiments of this specification may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method for generating room type videos based on artificial intelligence models according to various embodiments of this specification described in the above "Exemplary Method" section of this specification.

[0129] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0130] The computer program product may be written in any combination of one or more programming languages ​​to implement the operations of the embodiments of this specification, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0131] In addition, an embodiment of this specification also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the method for generating room type videos based on artificial intelligence models according to various embodiments of this specification described in the above "Exemplary Method" section of this specification.

[0132] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this specification can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0133] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0134] The above-described embodiments merely represent several implementation methods of this specification. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the solutions provided by the embodiments of this specification. It should be noted that a person skilled in the art can make several variations and improvements without departing from the scope of this specification, and these variations and improvements fall within the scope of protection of this specification. Therefore, the scope of protection of the patent in this specification shall be based on the appended claims.

Claims

1. A method for generating room type videos based on an artificial intelligence model, characterized in that: Applied to travel service applications, the room type video is used to display the size of the hotel room and the items in the room. The method for generating the room type video includes: Acquire a target image of a hotel room, wherein the target image shows a plurality of guest room items in the hotel room; Based on the target image, obtaining position parameters corresponding to each of the plurality of guest room items displayed in the target image, wherein the position parameters are used to represent the position of the corresponding guest room items in the hotel room; Based on the plurality of position parameters, obtaining video camera movement parameters, wherein the video camera movement parameters are used to describe the viewing angle and composition of the room type video corresponding to the hotel room; Based on the video camera parameters, an artificial intelligence model is called to generate a room type video corresponding to the hotel room, and the room type video corresponding to the hotel room is used to be played on the client of the travel service application.

2. The method according to claim 1, characterized in that After generating the room type video corresponding to the hotel room, the method further includes: Reviewing the room type video according to the target image of the hotel room; if the review fails, adjusting the video camera parameters, and returning to the step of calling the artificial intelligence model to generate the room type video corresponding to the hotel room based on the video camera parameters; or Acquire another image of the hotel room as the target image, and return to the step of acquiring position parameters corresponding to each of the plurality of guest room items displayed in the target image based on the target image; or Return to the step of calling the artificial intelligence model to generate a room type video corresponding to the hotel room based on the video camera parameters.

3. The method according to claim 2, characterized in that The video camera movement parameters include: camera control parameters, the camera control parameters including at least one of translation, tilt, zoom and rotation parameters; The adjusting of the video camera parameters includes: At least one of the translation, tilt, scale, and rotation parameters is reduced.

4. The method according to claim 2, characterized in that The review of the room type video includes: Acquire multiple frames of continuous images in the room video; Judging whether there is any abnormality in the room type video according to the target image of the hotel room and the multiple frames of continuous images, if so, the room type video fails the review, and if not, the room type video passes the review; The abnormal conditions include: compared with the target image, there are new guest room items, and / or there is an abnormal proportion of at least one of the guest room items, and / or there is a sudden scene change in the multiple frames of continuous images.

5. The method according to claim 1, wherein The location parameters corresponding to the guest room items include: location coordinates of the guest room items, the location coordinates including coordinates of feature points of the guest room items in a default coordinate system; The obtaining of the video camera movement parameters based on the plurality of position parameters includes: determining an orientation of the target guest room item within the hotel room based on a position parameter of the target guest room item and a position parameter of at least one associated guest room item; the associated guest room item comprising a guest room item that has a matching relationship with the target guest room item when in use; Calculating the space size of the hotel room based on the location parameters of the plurality of guest room items; The video camera movement parameters are generated based on the orientation of the target guest room item in the hotel room and the spatial size of the hotel room.

6. The method according to claim 5, characterized in that The target guest room item includes a bed, and the associated guest room items include a pillow and / or a bedside table; The characteristic point of the target guest room item includes any point at the end of the bed; The determining the orientation of the target guest room item in the hotel room based on the location parameter of the target guest room item and the location parameter of at least one associated guest room item includes: determining a target direction according to the position parameter of the target guest room item and the position parameter of at least one of the associated guest room items, wherein the target direction includes a direction in which a feature point of the target guest room item points to the associated guest room item; The orientation of the target guest room item in the hotel room is determined according to the target direction.

7. The method according to claim 1, characterized in that Also includes: In response to a user's gesture operation on the room type video being played, adjusting the playback progress of the room type video according to the gesture operation; The gesture operation includes: sliding operation; The adjusting the playback progress of the room type video according to the gesture operation includes: According to the sliding direction of the sliding operation, the playback progress of the room type video is adjusted so that the room type video displays guest room items in the hotel room in the opposite direction of the sliding direction.

8. The method according to claim 1, characterized in that The calling of the artificial intelligence model to generate a room type video corresponding to the hotel room based on the video camera parameters includes: Taking the video camera parameters and the target image of the hotel room as input, the artificial intelligence model is called to generate a room type video corresponding to the hotel room.

9. The method according to any one of claims 1 to 8, characterized in that Acquiring a target image of a hotel room includes: Acquire multiple images of a hotel room, and determine a target image of the hotel room based on scores of the multiple images; The score of the image is positively correlated with the spatial completeness of the hotel room displayed by the image and / or the clarity of the image.

10. A computer program product, characterized in that It includes computer instructions for implementing the method for generating room type videos based on an artificial intelligence model as described in any one of claims 1 to 9.

Images