Method, System, Device and Storage Medium for Generating Image Covers Based on Points of Interest

Abstract

The present invention provides a method, system, device and storage medium for generating an image cover based on points of interest. The method includes: collecting image files of points of interest to establish an image material set and related comment texts, and extracting landmark name keywords and scene information keywords from the comment texts; performing landmark recognition on the image material set to obtain a first image file that matches the landmark name keywords and has the highest network interaction parameters; performing scene information recognition on the image material set to obtain a second image file set that matches the scene information keywords, and inputting the second image file set into a neural network for deep learning; inputting the first image file into the trained neural network, and using the output image as the image cover of the image file of the point of interest. The present invention can automatically collect image materials of points of interest and generate corresponding image covers according to network hotspots, thereby improving the page traffic and conversion rate and optimizing the user experience.

Description

Background Art

[0002] The role of online travel agencies (abbreviated as OTA, full name: online travel agent) has become increasingly important in the hotel industry because they provide customers with a convenient way to compare hotels and book hotels through the Internet, in the comfort of their own homes, or on the go. An online travel agency (OTA) is a website or online service that sells travel-related products to customers. These products may include hotels, flights, travel packages, activities, and car rentals. Importantly, OTAs are third parties that resell these services on behalf of other companies, including those in the hotel industry. Usually, OTAs will offer many of the benefits of using offline travel agencies, increasing convenience and more self-service options. They will also include a built-in booking system that allows for instant booking.

[0003] Currently, OTA platforms increase users' understanding of tourist destinations by providing images or videos of scenic spots or points of interest, in order to improve conversion rates. However, if the aesthetic degrees of the cover images of scenic spots vary unevenly, it will affect the traffic and conversion rates of the page, thus affecting the sales of their travel products.

[0004] Although there is existing technology for performing single-piece AI beautification on landscape pictures (adjusting brightness, saturation, color vividness, and even changing lighting effects, etc.), the simple beautification effect is not good, and the natural scenery in each place is completely different. Using a beautification model trained with the same picture lacks pertinence, resulting in the pictures lacking a sense of reality and being unable to truly attract users to click.

[0005] Therefore, the present invention provides a method, system, device, and storage medium for generating image covers based on points of interest. Summary of the Invention

[0006] Aiming at the problems in the prior art, the purpose of the present invention is to provide a method, system, device, and storage medium for generating image covers based on points of interest, which overcomes the difficulties of the prior art, can automatically collect image materials of points of interest, and generate corresponding image covers according to network hotspots, thereby improving the traffic and conversion rates of the page and optimizing the user experience.

[0007] An embodiment of the present invention provides a method for generating an image cover based on a point of interest, including the following steps:

[0008] Collect image files of points of interest to establish an image material set and related review texts, and extract landmark name keywords and scene information keywords from the review texts;

[0009] Perform landmark recognition on the image material set to obtain a first image file that matches the landmark name keywords and has the highest network interaction parameters;

[0010] Perform scene information recognition on the collection of video materials to obtain a second collection of video files that match the keywords of the scene information, and input the second collection of video files into a neural network for in-depth learning; and

[0011] Input the first video file into the trained neural network, and use the output image as the video cover of the video file of the point of interest.

[0012] Preferably, collecting the video files of the points of interest to establish a collection of video materials and related review texts, and extracting landmark name keywords and scene information keywords from the review texts, including:

[0013] Collect the video files of the points of interest to establish a collection of video materials, and the video files have scene information and network interaction parameters during shooting;

[0014] Collect the review text corresponding to each point of interest; and

[0015] Perform natural language processing on the review text, and extract at least one landmark name keyword and at least one scene information keyword corresponding to the point of interest from the review text.

[0016] Preferably, the video files include images and videos, and the network interaction parameters include the sum of one or several of the number of evaluations, the number of coins, the number of collections, and the number of forwards.

[0017] Preferably, the scene information keywords include scenery information, time information, and / or weather information.

[0018] Preferably, performing landmark recognition on the collection of video materials to obtain the first video file that matches the landmark name keyword and has the highest network interaction parameter, including:

[0019] Extract frames from the videos in the collection of video materials to obtain images;

[0020] Perform image recognition on all images to obtain the corresponding landmark labels in each image; and

[0021] Sort the images that match the landmark name keyword according to the network interaction parameter, and use the image with the highest network interaction parameter as the first video file.

[0022] Preferably, performing scene information recognition on the collection of video materials to obtain a second collection of video files that match the scene information keywords, and inputting the second collection of video files into a neural network for in-depth learning, including:

[0023] Identify the scene information of the image material set to obtain the scene information of the image file;

[0024] Filter the image material set according to the scene information keywords to obtain a second image file set; and

[0025] Input the images and scene information in the second image file set into a neural network for deep learning.

[0026] Preferably, inputting the first image file into the trained neural network and using the output image as the image cover of the image file of the point of interest includes:

[0027] Input the first image file and the scene information keywords into the trained neural network together; and

[0028] Use the image output by the neural network as the image cover of the image file of the point of interest.

[0029] An embodiment of the present invention also provides a point-of-interest-based image cover generation system for implementing the above-mentioned point-of-interest-based image cover generation method. The point-of-interest-based image cover generation system includes:

[0030] An image acquisition module that acquires image files of points of interest to establish an image material set and related review texts, and extracts landmark name keywords and scene information keywords from the review texts;

[0031] A landmark recognition module that performs landmark recognition on the image material set to obtain the first image file that matches the landmark name keywords and has the highest network interaction parameters;

[0032] A neural network module that performs scene information recognition on the image material set to obtain a second image file set that matches the scene information keywords, and inputs the second image file set into a neural network for deep learning; and

[0033] An image cover module that inputs the first image file into the trained neural network and uses the output image as the image cover of the image file of the point of interest.

[0034] An embodiment of the present invention also provides a point-of-interest-based image cover generation device, including:

[0035] A processor;

[0036] A memory that stores executable instructions of the processor;

[0037] Wherein, the processor is configured to execute the steps of the above-mentioned point-of-interest-based image cover generation method by executing the executable instructions.

[0038] An embodiment of the present invention further provides a computer-readable storage medium for storing a program, which when executed implements the steps of the above method for generating an image cover based on points of interest.

[0039] The purpose of the present invention is to provide a method, system, device and storage medium for generating an image cover based on points of interest, which can automatically collect image materials of points of interest and generate corresponding image covers according to network hotspots, thereby improving the traffic and conversion rate of pages and optimizing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] By reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings, other features, objects and advantages of the present invention will become more apparent.

[0041] Figure 1 is a flowchart of the method for generating an image cover based on points of interest of the present invention.

[0042] Figure 2 is a schematic diagram of the modules of the system for generating an image cover based on points of interest of the present invention.

[0043] Figure 3 is a schematic diagram of the structure of the device for generating an image cover based on points of interest of the present invention.

[0044] Figure 4 is a schematic diagram of the structure of the computer-readable storage medium according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The following specific examples illustrate the embodiments of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in the present application. The present application can also be implemented or applied through other different specific embodiments, and various details in the present application can also be modified or changed according to different viewpoints and application systems without departing from the spirit of the present application. It should be noted that, without conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0046] The following will be described in detail with reference to the accompanying drawings for the embodiments of the present application, so that those skilled in the art in the technical field to which the present application belongs can easily implement it. The present application can be embodied in various different forms and is not limited to the embodiments described herein.

[0047] In the description of the present application, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. mean that the specific features, structures, materials, or characteristics represented in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials, or characteristics represented can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples represented in the present application and the features of different embodiments or examples.

[0048] In addition, the terms "first" and "second" are used only for the purpose of indication and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of such features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0049] In order to clearly illustrate the present application, devices irrelevant to the description are omitted, and the same or similar constituent elements throughout the specification are given the same reference numerals.

[0050] Throughout the specification, when it is said that a certain device is "connected" to another device, this includes not only the case of "direct connection", but also the case of "indirect connection" with other elements placed therebetween. In addition, when it is said that a certain device "includes" a certain constituent element, unless there is a particularly contrary record, it does not exclude other constituent elements, but means that other constituent elements can also be included.

[0051] When it is said that a certain device is "above" another device, this may be directly above the other device, but there may also be other devices therebetween. When it is said that a certain device is "directly" "above" another device, there are no other devices therebetween.

[0052] Although, in some instances, the terms first, second, etc. are used herein to denote various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first interface and a second interface, etc. are indicated. Furthermore, as used herein, the singular forms "a", "an", and "the" are also intended to include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprising", "including" indicate the presence of the features, steps, operations, elements, components, items, kinds, and / or groups, but do not preclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" used herein are to be construed as inclusive, or meaning any one or any combination. Thus, "A, B, or C" or "A, B, and / or C" means "any of the following: A; B; C; A and B; A and C; B and C; A, B, and C". An exception to this definition occurs only when the combination of elements, functions, steps, or operations are mutually exclusive in some manner.

[0053] The technical terms used herein are only for referring to specific embodiments and are not intended to limit the present application. The singular forms used herein also include the plural forms as long as the statements do not clearly indicate the contrary meaning. The meaning of "including" used in the specification is to embody specific characteristics, regions, integers, steps, operations, elements, and / or components, and does not exclude the existence or addition of other characteristics, regions, integers, steps, operations, elements, and / or components.

[0054] Although not defined differently, including the technical terms and scientific terms used herein, all terms have the same meaning as generally understood by those skilled in the technical field to which the present application belongs. The terms defined in the commonly used dictionary are additionally interpreted to have a meaning consistent with the relevant technical literature and the content currently presented. As long as they are not defined, they should not be over-interpreted as ideal or very formulaic meanings.

[0055] Figure 1 is a flowchart of the method for generating an image cover based on points of interest of the present invention. As Figure 1 shown, the method for generating an image cover based on points of interest of the present invention includes:

[0056] S110. Collect image files of points of interest to establish an image material set and relevant review texts, and extract landmark name keywords and scene information keywords from the review texts.

[0057] S120. Perform landmark recognition on the image material set to obtain the first image file with the highest matching landmark name keywords and network interaction parameters.

[0058] S130. Identify the scene information of the image material set to obtain a second image file set that matches the scene information keywords, and input the second image file set into a neural network for deep learning.

[0059] and

[0060] S140. Input the first image file into the trained neural network, and use the output image as the image cover of the image file of the point of interest.

[0061] The present invention provides a process for automatically beautifying pictures, automatically selecting suitable pictures, performing picture beautification processing such as sky replacement and brightening through an adaptive algorithm, and storing and distributing them through an exclusive picture storage scheme. In addition, this technical process can be applied to all picture scenarios except scenic spots in the future, including restaurants, shopping, hotels, etc.

[0062] In a preferred embodiment, step S110 includes:

[0063] S111. Collect the image files of the points of interest to establish an image material set. The image files have scene information and network interaction parameters at the time of shooting.

[0064] S112. Collect the review text corresponding to each point of interest. And

[0065] S113. Perform natural language processing on the review text, and extract at least one landmark name keyword and at least one scene information keyword corresponding to the point of interest from the review text. In this embodiment, an existing natural language processing model is used to process the review text, and an existing high-frequency word extraction algorithm or keyword extraction algorithm is used to extract the landmark name keyword and scene information keyword corresponding to the point of interest, but it is not limited thereto.

[0066] In a preferred embodiment, in step S111, the image files include images and videos, and the network interaction parameters include the sum of one or more of the number of evaluations, the number of coins, the number of collections, and the number of forwards, but it is not limited thereto.

[0067] In a preferred embodiment, in step S113, the scene information keywords include scenery information, scenery information, time information, and / or weather information, but it is not limited thereto.

[0068] In a preferred embodiment, step S120 includes:

[0069] S121. Extract frames from the videos in the image material set to obtain images, and segment the videos for frame extraction to reduce the computing power cost of image recognition for the videos..

[0070] S122. Perform image recognition on all images to obtain the corresponding landmark labels in each image. And

[0071] S123. Sort the images that match the landmark name keywords according to the network interaction parameters, and use the image with the highest network interaction parameter as the first image file, but not limited thereto.

[0072] In a preferred embodiment, step S130 includes:

[0073] S131. Identify the scene information of the video material set to obtain the scene information of the video file.

[0074] S132. Filter the video material set according to the scene information keywords to obtain a second set of video files. And

[0075] S133. Input the images and scene information in the second set of video files into a neural network for deep learning, but not limited thereto.

[0076] In a preferred embodiment, step S140 includes:

[0077] S141. Input the first image file and the scene information keywords into the trained neural network. In this embodiment, an existing neural network for generating images is used, but not limited thereto. And

[0078] S141. Use the image output by the neural network as the image cover of the video file of the point of interest, but not limited thereto.

[0079] The present invention aims to build an automated picture special effect beautification process to greatly improve the quality and aesthetic degree of associated pictures of POIs such as scenic spots, restaurants, shopping, etc., so as to increase the traffic and conversion rate of relevant pages, thereby increasing the sales of relevant commercial products and enhancing the overall user experience.

[0080] The specific implementation process of the present invention is as follows:

[0081] First, collect the video files of the point of interest "XX Beach" to establish a video material set A. The video files have the scene information and network interaction parameters at the time of shooting. The video files include images and videos. And the network interaction parameters include the sum of the number of evaluations, the number of coins, the number of collections, and the number of forwards. Use an existing natural language processing model to process the review text, and extract a landmark name keyword "YY Lighthouse" and scene information keywords "sunset glow", "sunny day", "sunset" corresponding to the point of interest through an existing high-frequency word extraction algorithm or keyword extraction algorithm.

[0082] Then, extract frames from the videos in the image material set A to obtain images. Perform image recognition on the extracted images and the original images in the image material set A respectively to obtain the corresponding landmark labels included in each image. Sort the images that match the landmark name keywords according to the network interaction parameters, and use the image with the highest network interaction parameter as the first image file B.

[0083] Next, perform scene information recognition on the image material set A to obtain the scene information of the image files; filter the image material set A according to the scene information keywords "sunset glow", "sunny day", and "sunset", and leave the images that simultaneously meet the scene information keywords "sunset glow", "sunny day", and "sunset" to establish the second image file set C. Input the images and scene information in the second image file set C into the image generation neural network D for deep learning. It should be noted that since the second image file set C is completely composed of real photos or videos corresponding to the interest point "XX Beach" and the keywords "sunset glow", "sunny day", and "sunset", the image generation neural network D trained by the second image file set C can more vividly and accurately depict the images of the interest point "XX Beach". The realism of the images in this mode will far exceed that of the simple massive training models in the prior art. Moreover, in the process, not only the visual effect of the images is improved, but also the computing power required for training the neural network is greatly reduced, the efficiency is improved, and the cost is saved.

[0084] Finally, input the first image file B and the scene information keywords into the trained image generation neural network D, and use the beautified final image E output by the image generation neural network D (render and beautify the relevant elements of the first image file B matched according to the keywords "sunset glow", "sunny day", and "sunset") as the image cover of the image file of the interest point.

[0085] Figure 2 It is a schematic diagram of the modules of the image cover generation system based on interest points of the present invention. As Figure 2 shown, an embodiment of the present invention also provides an image cover generation system based on interest points for implementing the above-mentioned image cover generation method based on interest points. The image cover generation system 5 based on interest points includes:

[0086] An image acquisition module 51 that acquires the image files of the interest point to establish an image material set and related review texts, and extracts landmark name keywords and scene information keywords from the review texts.

[0087] A landmark recognition module 52 that performs landmark recognition on the image material set to obtain the first image file that matches the landmark name keywords and has the highest network interaction parameter.

[0088] The neural network module 53 identifies scene information in the collection of video materials to obtain a second collection of video files that match the scene information keywords, and inputs the second collection of video files into the neural network for in-depth learning. And

[0089] The video cover module 54 inputs the first video file into the trained neural network, and uses the output image as the video cover of the video file of the point of interest.

[0090] In a preferred embodiment, the video acquisition module 51 is configured to acquire video files of points of interest to establish a collection of video materials. The video files have scene information and network interaction parameters at the time of shooting. Collect the review text corresponding to each point of interest. Perform natural language processing on the review text, and extract at least one landmark name keyword and at least one scene information keyword corresponding to the point of interest from the review text, but not limited thereto.

[0091] In a preferred embodiment, in step S111, the video files include images and videos, and the network interaction parameters include the sum of one or more of the number of evaluations, the number of coins, the number of collections, and the number of forwards, but not limited thereto.

[0092] In a preferred embodiment, in step S113, the scene information keywords include scenery information, time information, and / or weather information, but not limited thereto.

[0093] In a preferred embodiment, step S120 includes:

[0094] S121. Extract frames from the videos in the collection of video materials to obtain images.

[0095] S122. Perform image recognition on all the images to obtain the corresponding landmark labels in each image. And

[0096] S123. Sort the images that match the landmark name keywords according to the network interaction parameters, and use the image with the highest network interaction parameter as the first video file, but not limited thereto.

[0097] In a preferred embodiment, step S130 includes:

[0098] S131. Identify the scene information in the collection of video materials to obtain the scene information of the video files.

[0099] S132. Filter the collection of video materials according to the scene information keywords to obtain a second collection of video files. And

[0100] S133. Input the images and scene information in the second collection of video files into the neural network for in-depth learning, but not limited thereto.

[0101] In a preferred embodiment, step S140 includes:

[0102] S141. Input the first image file and the keywords of the scene information into the trained neural network. And

[0103] S142. Use the image output by the neural network as the image cover of the image file of the point of interest, but not limited thereto.

[0104] The image cover generation system based on points of interest of the present invention can automatically collect image materials of points of interest and generate corresponding image covers according to network hotspots, thereby increasing the traffic and conversion rate of the page and optimizing the user experience.

[0105] An embodiment of the present invention also provides an image cover generation device based on points of interest, including a processor and a memory in which executable instructions of the processor are stored. Wherein, the processor is configured to execute the steps of the image cover generation method based on points of interest by executing the executable instructions.

[0106] As shown above, the image cover generation system based on points of interest of the present invention can automatically collect image materials of points of interest and generate corresponding image covers according to network hotspots, thereby increasing the traffic and conversion rate of the page and optimizing the user experience.

[0107] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, a method, or a program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuitry", "module", or "platform" here.

[0108] Figure 3 is a schematic structural diagram of the image cover generation device based on points of interest of the present invention. The following will refer to Figure 3 to describe the electronic device 600 according to this embodiment of the present invention. Figure 3 The electronic device 600 shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0109] As Figure 3 shown, the electronic device 600 is presented in the form of a general-purpose 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.

[0110] Among them, the storage unit stores program code that can be executed by the processing unit 610, enabling the processing unit 610 to execute the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription transfer processing method section of this specification. For example, the processing unit 610 can execute steps such as Figure 1 as shown in

[0111] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0112] The storage unit 620 may also include a program / utilities 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0113] The bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0114] The electronic device 600 can also communicate with one or more external devices 700 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and can 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 (such as a router, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 650. Moreover, the electronic device 600 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 660. The network adapter 660 can communicate with other modules of the electronic device 600 through the bus 630. It should be understood that although not shown in the figure, other hardware and / or software modules can 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.

[0115] An embodiment of the present invention further provides a computer-readable storage medium for storing a program, and the steps of the method for generating an image cover based on points of interest are implemented when the program is executed. In some possible implementation manners, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription transfer processing method section of this specification.

[0116] As shown above, the system for generating an image cover based on points of interest according to the embodiment of the present invention can automatically collect image materials of points of interest and generate corresponding image covers according to network hotspots, thereby increasing the traffic and conversion rate of the page and optimizing the user experience.

[0117] Figure 4 It is a schematic structural diagram of the computer-readable storage medium of the present invention. Refer to Figure 4 As shown, a program product 800 for implementing the above method according to an embodiment of the present invention is described. It can be a portable compact disc read-only memory (CD-ROM) and includes program code, and can run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited to this. In this document, a readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device.

[0118] The program product can adopt any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0119] A computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable storage medium may also be any readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0120] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, executed 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. In the case of a remote computing device, the remote computing device may be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0121] In summary, the object of the present invention is to provide a method, system, device, and storage medium for generating an image cover based on points of interest, which can automatically collect image materials of points of interest and generate corresponding image covers according to network hotspots, thereby improving the traffic and conversion rate of pages and optimizing the user experience.

[0122] The above content is a further detailed description of the present invention in combination with specific preferred embodiments, and it cannot be determined that the specific implementation of the present invention is only limited to these descriptions. For those of ordinary skill in the technical field to which the present invention pertains, without departing from the concept of the present invention, several simple deductions or substitutions can still be made, and all should be regarded as belonging to the protection scope of the present invention.

Claims

1. A method for generating an image cover based on points of interest, characterized in that It includes the following steps: Collect image files of points of interest to establish an image material set and related review texts, and extract landmark name keywords and scene information keywords from the review texts; Perform landmark recognition on the image material set to obtain the first image file that matches the landmark name keywords and has the highest network interaction parameters; Perform scene information recognition on the image material set to obtain a second set of image files that match the scene information keywords, and input the second set of image files into a neural network for deep learning; And Input the first image file into the trained neural network, and use the output image as the image cover of the image file of the point of interest.

2. The method for generating an image cover based on points of interest according to claim 1, wherein The step of collecting image files of points of interest to establish an image material set and related review texts, and extracting landmark name keywords and scene information keywords from the review texts includes: Collect image files of points of interest to establish an image material set, where the image files have scene information and network interaction parameters at the time of shooting; Collect the review text corresponding to each point of interest; and Perform natural language processing on the review text, and extract at least one landmark name keyword and at least one scene information keyword corresponding to the point of interest from the review text.

3. The method for generating an image cover based on points of interest according to claim 2, wherein The image files include images and videos, and the network interaction parameters include the sum of one or several of the number of evaluations, the number of coins, the number of collections, and the number of forwards.

4. The method for generating an image cover based on points of interest according to claim 2, wherein The scene information keywords include scenery information, time information, and / or weather information.

5. The method for generating an image cover based on points of interest according to claim 1, wherein The step of performing landmark recognition on the image material set to obtain the first image file that matches the landmark name keywords and has the highest network interaction parameters includes: Extract frames from the videos in the image material set to obtain images; Perform image recognition on all images to obtain the corresponding landmark labels in each image; and Sort the images that match the landmark name keywords according to the network interaction parameters, and use the image with the highest network interaction parameters as the first image file.

6. The method for generating an image cover based on points of interest according to claim 1, wherein The step of performing scene information recognition on the image material set to obtain a second set of image files that match the scene information keywords, and inputting the second set of image files into a neural network for deep learning includes: Perform scene information recognition on the image material set to obtain the scene information of the image files; Filter the image material set according to the scene information keywords to obtain a second set of image files; and Input the images and scene information in the second set of image files into a neural network for deep learning.

7. The method for generating an image cover based on points of interest according to claim 1, wherein The step of inputting the first image file into the trained neural network and using the output image as the image cover of the image file of the point of interest includes: Input the first image file and the scene information keywords into the trained neural network together; and Use the image output by the neural network as the image cover of the image file of the point of interest.

8. A point-of-interest-based video cover generation system for implementing the point-of-interest-based video cover generation method according to claim 1, characterized in that, It includes: An image acquisition module that collects image files of points of interest to establish an image material set and related review texts, and extracts landmark name keywords and scene information keywords from the review texts; A landmark recognition module that performs landmark recognition on the set of video material to obtain a first video file that matches the landmark name keyword and has the highest network interaction parameter; A neural network module that performs scene information recognition on the set of video material to obtain a second set of video files that match the scene information keyword, and inputs the second set of video files into a neural network for deep learning; And A video cover module that inputs the first video file into the trained neural network and uses the output image as the video cover of the video file of the point of interest.

9. An image cover generation device based on points of interest, characterized in that, Including: A processor; A memory that stores executable instructions of the processor; Wherein, the processor is configured to execute the steps of the method for generating a video cover based on a point of interest according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium for storing a program, characterized in that, When the program is executed by the processor, it implements the steps of the method for generating a video cover based on a point of interest according to any one of claims 1 to 7.

Images