Image searching method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides an image searching method and device, electronic equipment, a storage medium and a program product. The method comprises the steps of obtaining target search information in response to an image search operation for a target image library comprising at least one first image; under the condition that the target search information comprises the target keyword, determining a second image corresponding to the target search information from the first image according to the target keyword, and displaying the second image; and under the condition that the target search information does not comprise the target keyword, determining a second image corresponding to the target search information from the first image according to the search semantic feature corresponding to the target search information, and displaying the second image. According to the technical scheme, image search can be carried out according to the keywords so as to ensure higher image search efficiency and more accurate image search results, and the effect of obtaining the image search results according to the search semantic features under the condition that the image search results are not obtained according to the keywords is achieved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to computer application technology, and in particular, to an image search method and device, electronic equipment, storage medium and program product. BACKGROUND

[0002] With the rapid development of the big data era, search engines play an increasingly important role and become a convenient entrance to obtain knowledge and information. In order to continuously improve the search experience, developers continuously improve the functions and technologies of search engines, so that search engines can be used not only to search for text data, but also to search for images and / or videos.

[0003] In related technologies, when an image search is performed on a mobile terminal, if a local search method of the mobile terminal is used for the search, there may be a problem that relevant images of search information cannot be searched. If a search tool of a cloud is used for the image search, images and videos in a local end need to be uploaded to the cloud, and this way increases the transmission time of the images and may affect the security of the data. SUMMARY

[0004] The present disclosure provides an image search method, device, electronic equipment, storage medium and program product, to achieve the effect that in the image search process, not only the image search can be performed according to the keyword to ensure that the image search is more efficient and the image search result is more accurate, but also in the case that the image search result cannot be obtained according to the search keyword, the image search result corresponding to the image search demand can be obtained according to the search semantic feature.

[0005] In a first aspect, the embodiments of the present disclosure provide an image search method, which comprises:

[0006] In response to an image search operation for a target image library, target search information is obtained; wherein the target image library comprises at least one first image;

[0007] In the case that the target search information comprises a target keyword, a second image corresponding to the target search information is determined from the first image of the target image library according to the target keyword, and the second image is displayed;

[0008] In the case that the target search information does not comprise the target keyword, a second image corresponding to the target search information is determined from the first image of the target image library according to a search semantic feature corresponding to the target search information, and the second image is displayed.

[0009] In a second aspect, the embodiments of the present disclosure also provide an image search device, which comprises:

[0010] The search information acquisition module is used to acquire target search information in response to an image search operation targeting a target image library; wherein the target image library includes at least one first image;

[0011] The keyword search module is used to determine, based on the target keywords, a second image corresponding to the target search information from the first image in the target image library, and display the second image when the target search information includes target keywords;

[0012] The semantic feature search module is used to determine, based on the search semantic features corresponding to the target search information, a second image corresponding to the target search information from the first image in the target image library, and display the second image when the target search information does not include the target keyword.

[0013] Thirdly, embodiments of this disclosure also provide an electronic device, the electronic device comprising:

[0014] One or more processors;

[0015] Storage device for storing one or more programs.

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the image search method as described in any of the embodiments of this disclosure.

[0017] Fourthly, embodiments of this disclosure also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the image search method as described in any of the embodiments of this disclosure.

[0018] Fifthly, this disclosure also provides a computer program product, which includes a computer program that, when executed by a processor, implements the image search method described in any embodiment of the present invention.

[0019] The technical solution of this disclosure, in response to an image search operation targeting a target image library including at least one first image, acquires target search information. The acquisition of target search information and the execution of subsequent image search operations can be triggered through a simple interactive operation. Furthermore, when the target search information includes target keywords, a second image corresponding to the target search information is determined from the first image in the target image library based on the target keywords, and the second image is displayed. This achieves the effect of image search based on keywords and improves image search efficiency and accuracy while reducing terminal resource consumption. Furthermore, when the target search information does not include target keywords, a second image corresponding to the target search information is determined from the first image in the target image library based on the search semantic features corresponding to the target search information. The system displays a second image corresponding to the search information, enabling image search based on semantic features of the search information even when keyword searches are unavailable. This solves the problems of low accuracy or failure to find relevant images and data security issues in related technologies. It achieves the effect of first searching for images based on search keywords and then searching for images based on search semantic features. Furthermore, it enables image search based on keywords to ensure higher efficiency and more accurate results, while also providing image search results corresponding to the search needs based on search semantic features even when keyword searches are unavailable. This enhances the intelligence and flexibility of the image search process and improves the overall image search experience. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0021] Figure 1 This is a schematic flowchart of an image search method provided in an embodiment of the present disclosure;

[0022] Figure 2 This is a schematic flowchart of another image search method provided in an embodiment of the present disclosure;

[0023] Figure 3 This is a schematic flowchart of another image search method provided in an embodiment of the present disclosure;

[0024] Figure 4 This is a schematic flowchart of another image search method provided in an embodiment of the present disclosure;

[0025] Figure 5This is a schematic diagram of an image search process provided in an embodiment of the present disclosure;

[0026] Figure 6 This is a schematic diagram of the structure of an image search device provided in an embodiment of the present disclosure;

[0027] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0028] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0029] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0030] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0031] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0032] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0033] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0034] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0035] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0036] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0037] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0038] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0039] Figure 1 This is a flowchart illustrating an image search method provided in an embodiment of the present disclosure. This embodiment is applicable to situations where images in a library are searched based on input search information. The method can be executed by an image search device, which can be implemented in software and / or hardware, or optionally by an electronic device, such as a mobile terminal, a PC, or a server.

[0040] like Figure 1 As shown, the method in this embodiment may specifically include:

[0041] S110. In response to an image search operation targeting a target image library, obtain target search information; wherein the target image library includes at least one first image.

[0042] It should be noted that the technical solutions provided in this disclosure can be applied to local devices or the cloud. However, image searching in the cloud requires uploading images and videos from the local device to the cloud before searching can be performed. This may result in the consumption of cloud resources, increased cloud operating costs, a burden on cloud servers, and an impact on data security. Preferably, when the technical solutions provided in this disclosure are applied to local devices, image searching can be performed directly on the local device without uploading images and videos to the cloud. Therefore, cloud server resources and storage space are saved, and data security is better protected, reducing the risk of privacy leaks. Furthermore, image searching on the local device can be performed directly on the terminal device without relying on network connections and cloud server responses, thereby improving the response speed and real-time performance of image searches. Moreover, image searching on the local device allows for the management and searching of images on the terminal device without relying on specific cloud services or external platforms, thereby enhancing the independence and convenience of image searches and improving the image search experience. Of course, the technical solutions provided in this disclosure can also be applied to the cloud, and this disclosure does not specifically limit the subject of implementation.

[0043] The target image library can be understood as a storage space capable of storing images and / or videos. The target image library can be any storage space on the terminal device that supports image and / or video storage. For example, the target image library can be the terminal's local photo album or an image library of an application software, etc. The target image library can include at least one first image. The first image can be any image to be searched stored in the target image library. Optionally, the first image can be an image captured by a shooting device associated with the terminal device and stored in the target image library; or, the first image can be an image received from an external device, uploaded, and stored in the target image library; or, the first image can be an image downloaded from application software and stored in the target image library, etc. The image search operation can be understood as the operation of searching for images that meet the corresponding requirements in an image database. The image search operation can be any operation input to the target image library. Optionally, the image search operation can include at least one of the following: triggering a preset image search control; receiving audio information including a wake-up word for the image search operation; receiving an image search instruction, etc. The target search information can be understood as the search conditions used in the image search. Generally, the terminal device can provide corresponding information based on the target search information. The target search information can be semantic information of any form. Optionally, the target search information can be text information or audio information, etc. When the target search information is text information, it can be at least one sentence with complete semantics, which can consist of multiple characters connected by conjunctions; or, it can be text composed of multiple words, without conjunctions between adjacent words; or, it can be other forms of text information, etc. When the target search information is audio information, it can be a complete audio clip; or, it can be composed of multiple audio clips, each of which can include at least one search keyword; or, it can be other forms of audio information, etc. The target search information can be information containing characters from one or more language types. Optionally, the language type can include Chinese, English, or other language types, etc.

[0044] In this embodiment of the disclosure, the method of obtaining target search information may include at least two methods, such as obtaining information entered in the search information editing field as target search information; or, using selected candidate search information as target search information, etc. These two methods of obtaining information will be described below.

[0045] Optionally, in response to an image search operation targeting a target image library, obtaining target search information includes: displaying a search information editing interface in response to an image search operation targeting a target image library, wherein the search information editing interface includes search information editing items; and obtaining the information entered in the search information editing items as target search information in response to an information editing operation input into the search information editing items.

[0046] The search information editing interface can be understood as a visual editing interface that supports editing search information. Search information editing items are used to edit the target search information. Search information editing items can be understood as the entry point for editing image search information. Search information editing items can be editing items that support editing any form of information. Optionally, search information editing items can be text input boxes or voice input boxes, etc.

[0047] As an optional implementation of this disclosure, upon detecting a trigger operation on an image search control associated with a preset target image library, it can be determined that an image search operation targeting the target image library has been detected. Furthermore, in response to this image search operation, a search information editing interface is displayed on the terminal device's display interface, which may include search information editing items. Further, an information editing operation can be performed on the search information editing items to input image search information. Then, upon detecting that the editing is complete, the information input in the search information editing items is used as the target search information.

[0048] Optionally, in response to an image search operation targeting a target image library, obtaining target search information includes: in response to an image search operation targeting a target image library, displaying a search information editing interface, wherein the search information editing interface includes at least one candidate search information; and in response to an information selection operation targeting at least one candidate search information, determining the target search information based on the selected at least one candidate search information.

[0049] Here, candidate search information can be understood as pre-determined descriptive information used to search for a first image stored in the target image library. The number of candidate search information can be one or more. It should be noted that candidate search information can include at least two determination methods, such as determination based on historical editing data; or determination based on candidate search information setting operations, etc. These two determination methods will be explained below.

[0050] As an optional implementation of this embodiment, the candidate search information may be one or more search information used to generate the target search information within a preset time period, i.e., historical editing data of the target search information. Alternatively, the method for determining the candidate search information may include at least one of the following: historical editing data of the target search information by the object initiating the image search operation; historical editing data of the target search information by multiple objects, etc. For example, historical application data of the object initiating the image search operation in the application software can be obtained, and historical editing data of the object on the target search information can be determined based on the historical application data. Furthermore, at least one candidate search information can be determined based on the historical editing data.

[0051] As another optional implementation of this disclosure, the candidate search information may also include multiple pre-set search terms. Specifically, multiple search terms associated with the image search process can be pre-set. To facilitate querying and operation, they can be categorized and displayed according to the type corresponding to the search terms. For example, search terms can be categorized and displayed according to image acquisition time, image acquisition location, and image category.

[0052] As another optional implementation of this disclosure, upon detecting a trigger operation on an image search control associated with a preset target image library, it can be determined that an image search operation targeting the target image library has been detected. Furthermore, in response to the image search operation, a search information editing interface is displayed on the terminal device's display interface, which may include at least one candidate search information. Further, upon detecting an information selection operation on at least one candidate search information, the selected at least one candidate search information can be determined based on the information selection operation. Furthermore, the search information composed of the selected at least one candidate search information can be used as the target search information. The display method of the selected candidate search information on the interface can include various methods; optionally, it can be highlighted among at least one candidate search information; or, the selected candidate search information can be displayed in a pre-set text box, etc.

[0053] S120. If the target search information includes target keywords, determine the second image corresponding to the target search information from the first image in the target image library based on the target keywords, and display the second image.

[0054] The target keywords can be understood as the keywords used in the preset image search. Target keywords can include keywords of any dimension associated with the image, optionally including at least one of time keywords, location keywords, and category keywords. Time keywords indicate the time the image was acquired. Location keywords indicate the location where the image was acquired. Category keywords indicate the information presented by the image, such as image content, image style, image color, and the scene represented by the image. For example, assuming the target search information is "food eaten during the Mid-Autumn Festival," the target search information can be determined to include the target keywords "Mid-Autumn Festival" and "food." The second image can be an image that matches the target search information in the first image, that is, an image that meets the search requirements. It should be noted that the number of second images can be one or more, or zero. In other words, if there is at least one first image in the target image library that matches the target search information, then that at least one matching first image can be used as the second image. If there is no first image in the target image library that matches the target search information, then the number of second images is zero.

[0055] In this embodiment of the disclosure, upon obtaining target search information, the target search information can be segmented to obtain at least one search term corresponding to the target search information. Further, the at least one search term can be analyzed to determine whether it includes a target keyword. Further, if it is determined that the at least one search term includes a target keyword, a search can be performed in a target image library based on the target keyword to identify a first image in the first image library that matches the target search information. Further, if a first image matching the target search information exists in the first image library, the matching first image can be used as a second image and displayed. If no first image matching the target search information exists in the first image library, it can be determined that no second image matching the target search information was found.

[0056] As an optional implementation of this embodiment, the first image in the target image library may include image keywords. Further, if it is determined that the target search information includes a target search term, a search can be performed on the image keywords of at least one first image based on the target search term to determine image keywords matching the target search term. Further, if it is determined that an image keyword matching the target search term exists among the image keywords of the first image, the first image corresponding to that image keyword can be used as the second image. If it is determined that no image keyword matching the target search term exists among the image keywords of the first image, the search result corresponding to the target search information can be determined as "no image search results".

[0057] In this embodiment of the disclosure, in order to search for the first image in the target image library based on target keywords, corresponding image keywords can be pre-set for the first image. Generally, when the first image is stored in the target image library, the system can automatically set keywords associated with the image acquisition time and location. Category keywords can be determined by performing image analysis on the first image.

[0058] Based on the above technical solutions, before determining the second image corresponding to the target search information from the first image in the target image library according to the target keywords, the method further includes: performing image recognition on the first image in the target image library to determine the category keywords of at least one classification dimension corresponding to the first image.

[0059] The classification dimension can be understood as the category of the image. Optionally, the classification dimension includes at least one of the following: image content, image style, image color, and the scene represented by the image. Category keywords can be understood as keywords associated with the corresponding category. For example, when the classification dimension is image content, the corresponding category keywords can include words associated with image content such as people, animals, buildings, trees, flowers, sky, and sea. When the classification dimension is image style, the corresponding category keywords can include words associated with image style such as comics, sketches, ink paintings, and cyberpunk.

[0060] As an optional implementation of this disclosure, image recognition can be performed on the first image in the target image library beforehand. Then, the category keywords of the first image in the corresponding classification dimension can be determined based on the image recognition results, and the determined category keywords can be associated with the corresponding first image.

[0061] It should be noted that if the second image exists within the first image in the target image library, the second image can be displayed. If the second image does not exist within the first image in the target image library, a message indicating that the image search has yielded no results can be displayed to provide a clear and intuitive understanding of the current image search status through the display interface.

[0062] Optionally, displaying a second image includes: if the number of second images is one or more, displaying the second image according to a preset image display method; if the number of second images is zero, displaying preset search prompt information.

[0063] The image display method can be a pre-set method for displaying images matching the search information. In this embodiment, the image display method can be associated with the number of second images, for example, displaying all or part of the second images. When the number of second images is less than or equal to a preset threshold, the image display method can be to directly display all second images in chronological order of image acquisition time. When the number of second images is greater than the preset threshold, the image display method can be to display only part of the second images. A preset number of second images are selected from the second images according to preset image filtering criteria, and the selected second images are displayed. The image filtering criteria can be based on the chronological order of image acquisition time; or, based on the repetition of image content, etc. The search prompt information can be a prompt indicating that the image search has no results.

[0064] As an optional implementation of this disclosure, if the number of second images is greater than or equal to one and less than or equal to a preset threshold, all second images can be displayed on the interface in the order of their acquisition time.

[0065] As another optional implementation of this disclosure, when the number of second images is greater than or equal to one and exceeds a preset threshold, the second images can be sorted according to the order of image acquisition time, and a preset number of second images at the top of the sorted list can be acquired and displayed on the interface. Alternatively, the image content of the second images can be analyzed, and second images with a content repetition degree greater than or equal to a preset repetition threshold can be filtered out to obtain at least one set of second images. Further, for at least one set of second images, one second image can be selected from the set. Thus, at least one filtered second image can be obtained. Further, the at least one filtered second image and the remaining second images after content repetition filtering can be used as the second images to be displayed, and the second images can be displayed.

[0066] As another optional implementation of this disclosure, when the number of second images is zero, preset search prompts can be displayed on the terminal's display interface.

[0067] S130. If the target search information does not include the target keyword, determine the second image corresponding to the target search information from the first image in the target image library based on the search semantic features corresponding to the target search information, and display the second image.

[0068] Among them, search semantic features can be understood as features that characterize the deeper meaning of search information, and these features are easy for the system to understand and process. Search semantic features can be represented based on any form of representation; optionally, they can be represented based on text vectors to represent the search semantic features corresponding to the target search information.

[0069] In this embodiment of the disclosure, when the target search information does not include the target search term, search semantic features corresponding to the target search information can be determined. Further, the search semantic features can be matched with a first image in the target image library. If it is determined that a first image exists that matches the search semantic features, that first image is used as the second image and displayed. If it is determined that no first image exists that matches the search semantic features, preset search suggestions can be displayed.

[0070] It should be noted that, in order to improve image search efficiency, searching in the target image library based on semantic features can be done through feature matching.

[0071] As an optional implementation of this disclosure, search semantic features corresponding to the target search information can be determined, and image content features corresponding to the first image in the target image library can be determined. Further, the similarity between the search semantic features and the image content features can be determined. If the similarity is greater than or equal to a preset similarity threshold, the first image can be determined to match the search semantic features, and thus, the first image can be used as the second image.

[0072] It should be noted that, in order to ensure that the determined second image meets the preset image review standards, the second image can be reviewed after it is determined and before it is displayed, so as to filter out the second images that do not meet the image review standards.

[0073] Optionally, after determining the second image corresponding to the target search information, before displaying the second image, the method further includes: if the second image meets the preset filtering conditions, filtering out the second image and displaying the remaining second image after filtering.

[0074] The preset filtering conditions can be pre-set conditions used to filter images. In this embodiment, the preset filtering conditions include at least the presence of target content in the second image. Target content can be understood as content that cannot appear in the image to be displayed. Target content can include various types of content, optionally including features of at least one target part of a preset object or scene features corresponding to a preset scene, etc.

[0075] As an optional implementation of this embodiment, after determining the second image corresponding to the target search information, the second image can be filtered according to preset filtering conditions. Furthermore, if it is determined that the second image contains the target content, it can be determined that the second image meets the preset filtering conditions. Then, the second image can be filtered out, and the remaining second images after filtering are displayed. The advantage of this setting is that images that do not meet the review standards can be filtered out during the image search process, ensuring the security of the image search process and thus improving the intelligence of the filtering process.

[0076] The technical solution of this disclosure, in response to an image search operation targeting a target image library including at least one first image, acquires target search information. The acquisition of target search information and the execution of subsequent image search operations can be triggered through a simple interactive operation. Furthermore, when the target search information includes target keywords, a second image corresponding to the target search information is determined from the first image in the target image library based on the target keywords, and the second image is displayed. This achieves the effect of image search based on keywords and improves image search efficiency and accuracy while reducing terminal resource consumption. Furthermore, when the target search information does not include target keywords, a second image corresponding to the target search information is determined from the first image in the target image library based on the search semantic features corresponding to the target search information. The system displays a second image corresponding to the search information, enabling image search based on semantic features of the search information even when keyword searches are unavailable. This solves the problems of low accuracy or failure to find relevant images and data security issues in related technologies. It achieves the effect of first searching for images based on search keywords and then searching for images based on search semantic features. Furthermore, it enables image search based on keywords to ensure higher efficiency and more accurate results, while also providing image search results corresponding to the search needs based on search semantic features even when keyword searches are unavailable. This enhances the intelligence and flexibility of the image search process and improves the overall image search experience.

[0077] Figure 2 This is a schematic flowchart illustrating another image search method provided in this embodiment. Based on the above embodiments, the technical solution of this embodiment includes a first image with image keywords of at least two search dimensions; and a second image corresponding to the target search information is determined from the first images in the target image library based on the target keywords and the image keywords of at least one first image. Detailed implementation can be found in the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here.

[0078] like Figure 2 As shown, the method in this embodiment may specifically include:

[0079] S210. In response to an image search operation targeting a target image library, obtain target search information; wherein the target image library includes at least one first image; the first image is set with image keywords of at least two search dimensions.

[0080] In this context, search dimensions can be understood as the search categories applied during the image search process. Search dimensions can include any dimension associated with the image search process, optionally including at least one of the following: image acquisition time, image acquisition location, and image category. Image acquisition time can include image capture time, image upload time, or image download time, etc. Image acquisition location can be understood as the location of the terminal device to which the image belongs when it is acquired. Optionally, image acquisition location can include image capture location, image upload location, or image download location, etc. Image category can be understood as the classification criteria used when classifying images. Image category can include image content, image style, image color, and the scene represented by the image, etc. Image keywords can be keywords associated with search dimensions used to identify images. For example, image keywords corresponding to image acquisition time can be "XX year XX month XX day". Image keywords corresponding to image category can include people, animals, buildings, trees, flowers, sky, sea, food, etc.

[0081] As an optional implementation of this disclosure, after storing the first image in the target image library, the image acquisition time and image acquisition location of the first image can be obtained. Furthermore, given the existence of the image acquisition location and the image acquisition location of the first image, image keywords corresponding to the image acquisition time and image keywords corresponding to the image acquisition location can be determined, and the determined image keywords can be associated with the first image. Further, image recognition can be performed on the first image to determine image keywords corresponding to the image category, and the determined image keywords can be associated with the first image.

[0082] S220. If the target search information includes target keywords, determine the second image corresponding to the target search information from the first images in the target image library based on the target keywords and the image keywords of at least one first image, and display the second image.

[0083] In this embodiment of the disclosure, when the target search information includes a target search term, matching can be performed between the target search term and the image keywords set on the first image. Furthermore, if it is determined that the image keywords match the target keywords, the first image corresponding to the image keywords can be used as the second image, and the second image can be displayed.

[0084] It should be noted that the first image has image keywords set with at least two search dimensions. The target keywords included in the target search information can be target keywords of a single search dimension or target keywords of multiple search dimensions. The method for determining the second image also varies depending on the situation, and these two situations will be explained separately below.

[0085] Optionally, if the target search information includes multiple target keywords under a single search dimension, a first image set corresponding to each target keyword is determined; the union of the first image sets of multiple target keywords is determined, and a second image corresponding to the target search information is determined based on the first image in the union.

[0086] Here, a target keyword under a single search dimension can be understood as the target search information including only the target keyword of one search dimension. Optionally, the target search information may only include the target keyword of image acquisition time; or, the target search information may only include the target keyword of image acquisition location; or, the target search information may only include the target keyword of image category, etc. The first image set is the set of first images in the target image library that correspond to the target keywords. That is, the first images in the first image set match the target keywords included in the target search information.

[0087] As an optional implementation of this embodiment, when the target search information includes multiple target keywords under a single search dimension, for each target keyword, the target keyword can be matched with the image keywords of the corresponding search dimension of the first image in the target image library. Furthermore, if it is determined that the target keyword matches the image keywords of the first image, an image set can be constructed based on at least one matched first image to obtain a first image set corresponding to the target keyword. Furthermore, a first image set corresponding to multiple target keywords can be obtained. Further, the multiple first image sets can be processed by union to obtain the union of the multiple first image sets. Then, the first images included in the union can be used as the second image corresponding to the target search information. The advantage of this setup is that determining the second image corresponding to the target search information based on the union of multiple first image sets ensures the completeness and comprehensiveness of the image search results, thereby improving the accuracy of the image search results and enhancing the image search experience.

[0088] Optionally, if the target search information includes target keywords under multiple search dimensions, a third image corresponding to each search dimension is obtained based on the target keywords under each search dimension, and a set of second images corresponding to each search dimension is constructed based on the third images; the intersection of the second image sets corresponding to multiple search dimensions is determined, and the second image corresponding to the target search information is determined based on the third images in the intersection.

[0089] In this embodiment, the target keywords under multiple search dimensions may include one target keyword corresponding to each search dimension; or, at least one search dimension may correspond to multiple target keywords. Correspondingly, the second image set may be a single image set; or, it may be the union of multiple image sets.

[0090] As an optional implementation of this embodiment, when the target search information includes target keywords under multiple search dimensions, and each search dimension corresponds to one target keyword, for each search dimension, the target keyword under the search dimension can be matched with the image keywords of the first image in the target image library under the corresponding search dimension. Furthermore, if it is determined that the target keyword matches the image keywords of the first image under the corresponding dimension, the matched first image can be used as the third image, and a second image set corresponding to the search dimension can be constructed based on the third image. Thus, a second image set corresponding to each search dimension can be obtained. Further, the intersection of multiple second image sets can be processed to obtain the intersection corresponding to the multiple second image sets. Further, the third image included in the intersection can be used as the second image corresponding to the target search information.

[0091] As another optional implementation of this disclosure, when the target search information includes target keywords under multiple search dimensions, and at least one search dimension corresponds to multiple target keywords, a first image set corresponding to each target keyword is determined for each search dimension corresponding to the multiple target keywords. Then, the multiple first image sets are subjected to union processing, and the resulting union is used as a second image set corresponding to the search dimension. For at least one search dimension corresponding to a target keyword, the target keyword under the search dimension can be matched with the image keywords of the first image in the target image library under the corresponding search dimension. Furthermore, if it is determined that the target keyword matches the image keywords of the first image under the corresponding dimension, the matched first image can be used as a third image, and a second image set corresponding to the search dimension can be constructed based on the third image. Further, the multiple second image sets can be subjected to intersection processing to obtain an intersection corresponding to the multiple second image sets. Further, the third image included in the intersection can be used as a second image corresponding to the target search information.

[0092] It should be noted that the advantage of determining the second image corresponding to the target search information based on the intersection of multiple sets of second images is that it improves the matching degree between the second image and the target search information, improves the accuracy of image search results, and enhances the intelligence of the image search process.

[0093] S230. If the target search information does not include the target keyword, determine the second image corresponding to the target search information from the first image in the target image library based on the search semantic features corresponding to the target search information, and display the second image.

[0094] The technical solution of this disclosure embodiment obtains target search information in response to an image search operation targeting a target image library. The target image library includes at least one first image. The first image is provided with image keywords of at least two search dimensions. Further, based on the target keywords and the image keywords of the at least one first image, a second image corresponding to the target search information is determined from the first images in the target image library. This achieves the effect of determining image search results based on keyword matching, thereby improving the matching degree between the second image and the target search information, increasing the accuracy of image search results, and enhancing the intelligence of the image search process.

[0095] Figure 3 This is a flowchart illustrating another image search method provided in this embodiment. Based on the above embodiments, after obtaining target search information, the technical solution of this embodiment performs word segmentation on the target search information to obtain search keywords corresponding to the target search information; if the search keywords include time identifier information, a time search field is determined in the search keywords based on the time identifier information; if the time represented by the time search field is a valid time, the target keywords based on the time dimension are determined based on the time search field. For detailed implementation, please refer to the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here.

[0096] like Figure 3 As shown, the method in this embodiment may specifically include:

[0097] S310, in response to an image search operation targeting a target image library, obtain target search information; wherein the target image library includes at least one first image.

[0098] S310. Perform word segmentation on the target search information to obtain search keywords corresponding to the target search information.

[0099] Search keywords can be words with actual meaning included in the target search information. The types of words used in search keywords can include nouns, verbs, quantifiers, and adjectives.

[0100] In this embodiment, the target search information can be segmented according to a preset segmentation method to divide it into at least one word or phrase with actual meaning. Then, the segmented words or phrases can be used as search keywords corresponding to the target search information. The preset segmentation method can be any method capable of segmentation; optionally, it can be segmentation based on segmentation rules, statistical models, or deep learning models, etc.

[0101] S330. If the search keywords include time identifier information, determine the time search field in the search keywords based on the time identifier information.

[0102] The time identifier information can be understood as information used to represent time. Time identifier information may include holiday keywords and / or time segmentation information. Holiday keywords can be understood as characters representing holidays. For example, holiday keywords could be "Mid-Autumn Festival," "Dragon Boat Festival," and "Spring Festival," etc. Time segmentation information can be understood as information used to separate different time units within a time representation. Time segmentation information can be of any type; optionally, it can be a separator, such as a period (.), hyphen (-), forward slash ( / ), or colon (:); or it can be text separator information, such as year, month, day, hour, minute, second, etc.; or it can be a space, etc. The time search field can be understood as a field in the search keywords that is associated with time, and this field can execute the image search process. The time search field can be understood as a time field that can be recognized by the system and applied to the image search process.

[0103] Generally, there is a difference between the time information input and the time information that the system can recognize. Furthermore, the input time information may include not only information explicitly representing a specific time, but also information that uses holidays to represent the time. In this case, the system cannot recognize the input time information to determine the specific time, thus preventing image search based on the input time information.

[0104] In response to the above situation, in this embodiment of the disclosure, determining the time search field in the search keywords based on the time identifier information includes: when the time identifier information includes holiday keywords, mapping the holiday keywords to the image acquisition date based on the calendar information, and generating the time search field based on the image acquisition date.

[0105] The image acquisition date can be a date that matches a holiday and can be recognized by the system.

[0106] As an optional implementation of this embodiment, when the time identifier information includes a holiday keyword, the date corresponding to the holiday keyword can be determined based on calendar information. Furthermore, the holiday keyword can be converted into its corresponding date to determine the image acquisition date. Further, a time search field capable of executing an image search process can be generated based on the image acquisition date. The advantage of this setup is that it maps holidays in the target search information to corresponding dates, and then generates a time search field capable of executing an image search process based on the date, thus improving the flexibility and intelligence of image search.

[0107] S340. If the time represented by the time search field is a valid time, determine the target keywords for the time dimension of image acquisition based on the time search field.

[0108] It should be noted that the generated time search field may contain invalid times. Therefore, given the time search field, its validity can be checked according to preset validity rules. The validity check process can be explained below from three dimensions: year, month, and day (or number).

[0109] For example, if the time search field represents a year, it can be determined whether the field representing the year is a 4-digit or 2-digit number greater than 0. If so, the year represented in the time search field can be identified as a valid year (e.g., 2024). If the time search field represents a month, it can be determined whether the field representing the month is a 2-digit number greater than 0 and less than or equal to 12. If so, the month represented in the time search field can be identified as a valid month (e.g., December). If the time search field represents a day (or number), it can be determined whether the field representing the day is a 2-digit number greater than 0 and less than or equal to 31. If so, the day represented in the time search field can be identified as a valid day (e.g., the 30th).

[0110] In this embodiment of the disclosure, if it is determined that the year, month, and / or day represented by the time search field are all valid, the time represented by the time search field can be determined as a valid time. Further, the target keyword corresponding to the time search field is determined based on the time search field.

[0111] S350. If the target search information includes target keywords, determine the second image corresponding to the target search information from the first image in the target image library based on the target keywords, and display the second image.

[0112] S360. If the target search information does not include the target keywords, determine the second image corresponding to the target search information from the first image in the target image library based on the search semantic features corresponding to the target search information, and display the second image.

[0113] The technical solution of this disclosure embodiment obtains search keywords corresponding to the target search information by performing word segmentation processing on the target search information. Further, when the search keywords include time identifier information, a time search field is determined in the search keywords based on the time identifier information. Furthermore, when the time represented by the time search field is a valid time, the target keywords for the image acquisition time dimension are determined based on the time search field. This achieves the effect of converting time identifier information into a time search field when the search keywords obtained after word segmentation include time identifier information. Moreover, by detecting the validity of the time represented by the time search field, the flexibility and intelligence of image search are improved, thereby increasing the accuracy of image search results.

[0114] Figure 4 This is a flowchart illustrating another image search method provided in this embodiment. Based on the above embodiments, the technical solution of this embodiment determines the search semantic features corresponding to the target search information and obtains the image content features of a first image in the target image library; determines the similarity between the search semantic features and the image content features, and determines a second image corresponding to the search information from the first image in the target image library based on the similarity. For detailed implementation, please refer to the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here.

[0115] like Figure 4 As shown, the method in this embodiment may specifically include:

[0116] S410. In response to an image search operation targeting a target image library, obtain target search information; wherein the target image library includes at least one first image.

[0117] S420. If the target search information includes target keywords, determine the second image corresponding to the target search information from the first image in the target image library based on the target keywords, and display the second image.

[0118] S430. If the target search information does not include the target keywords, determine the search semantic features corresponding to the target search information and obtain the image content features of the first image in the target image library.

[0119] Image content features can be understood as data or attributes that characterize the deep feature information of an image, making it easier for the system to understand and process. Image content features can be represented in any form; optionally, they can be represented by vectors, meaning image content features can be determined based on image content vectors. Generally, the information in an image can be converted into a series of numerical values. These values ​​can characterize various features of the image, such as color, texture, and shape, allowing for the description and recognition of the image content. These numerical values ​​can then be used as image content features.

[0120] In this embodiment of the disclosure, when the first image is stored in the target image library, content recognition and feature processing can be performed on the first image to obtain image content features, and the image content features are then associated with and stored with the first image. Furthermore, if the target search information does not include target keywords, image search can be performed based on features. Feature processing can be performed on the target search information to obtain search semantic features corresponding to the target search information. Furthermore, the image content features of the first image in the target image library can be obtained. Subsequently, image search can be performed based on the search semantic features and the image content features.

[0121] S440. Determine the similarity between the search semantic features and the image content features, determine the second image corresponding to the target search information from the first image in the target image library based on the similarity, and display the second image.

[0122] In this embodiment of the disclosure, given the search semantic features and the image content features of a first image in the target image library, the similarity between the search semantic features and at least one image content feature can be determined. Further, if the similarity is greater than a preset similarity threshold, the first image corresponding to that similarity can be used as a second image corresponding to the target search information, and the second image can be displayed. If the similarity is less than or equal to the preset similarity threshold, it can be determined that the first image corresponding to that similarity does not match the target search information. The preset similarity threshold can be any value, optionally 0.265, etc.

[0123] The technical solution of this disclosure, when the target search information does not include target keywords, determines the search semantic features corresponding to the target search information, obtains the image content features of the first image in the target image library, further determines the similarity between the search semantic features and the image content features, determines the second image corresponding to the target search information from the first image in the target image library based on the similarity, and displays the second image. This achieves the effect of image search based on feature matching when image search cannot be performed based on search keywords, enriches the image search method, and thus improves the intelligence of image search, achieving the effect of accurately searching for relevant images when the target search information is a vague description.

[0124] Figure 5 This is a schematic diagram of an image search process provided by an embodiment of this disclosure. This embodiment is an optional embodiment of the above-described embodiments. Figure 5 As shown, the method in this embodiment may specifically include:

[0125] First, the target search information is obtained. Then, the target search information is segmented to obtain search keywords. Next, the search dimensions included in the search keywords are determined. Then, based on the search dimensions, location, time, and / or category searches are performed on the images. Further, if no matching image is found, feature search can be performed on the images. Then, if a second image matching the target search information is obtained, image filtering can be performed on the second image. Finally, the remaining second images after filtering can be merged using intersection and / or union operations to obtain the final image search results.

[0126] The technical solution of this disclosure addresses the problems of low accuracy or failure to find relevant images and data security issues in related technologies. It achieves the effect of first performing image search based on search keywords and then performing image search based on search semantic features. Furthermore, it enables image search to be performed based on keywords to ensure higher efficiency and more accurate image search results, and also enables image search results corresponding to the image search needs to be obtained based on search semantic features when no image search results are obtained based on search keywords. This improves the intelligence and flexibility of the image search process and enhances the image search experience.

[0127] Figure 6 This is a schematic diagram of the structure of an image search device provided in an embodiment of the present disclosure, as shown below. Figure 6As shown, the device includes: a search information acquisition module 510, a keyword search module 520, and a semantic feature search module 530. The search information acquisition module 510 is used to acquire target search information in response to an image search operation targeting a target image library; wherein the target image library includes at least one first image; the keyword search module 520 is used to, when the target search information includes a target keyword, determine a second image corresponding to the target search information from the first image in the target image library based on the target keyword, and display the second image; the semantic feature search module 530 is used to, when the target search information does not include the target keyword, determine a second image corresponding to the target search information from the first image in the target image library based on the search semantic features corresponding to the target search information, and display the second image.

[0128] The technical solution of this embodiment, through the search information acquisition module 510, responds to an image search operation targeting a target image library including at least one first image, acquires target search information. The acquisition of target search information and the execution of subsequent image search operations can be triggered through simple interactive operations. Furthermore, when the target search information includes target keywords, the keyword search module 520 determines and displays a second image corresponding to the target search information from the first image in the target image library based on the target keywords, achieving the effect of image search based on keywords. This also improves image search efficiency and accuracy while reducing terminal resource consumption. Furthermore, when the target search information does not include target keywords, the semantic feature search module 530 retrieves the target image from the target image library based on the search semantic features corresponding to the target search information. The system identifies and displays a second image corresponding to the target search information from the first image in the image library. This enables image search based on the semantic features of the search information when keyword search is not possible. It addresses the issues of low accuracy or failure to find relevant images and data security concerns in related technologies. The system achieves the effect of first searching for images based on search keywords and then searching based on semantic features. Furthermore, it enables image search based on keywords to ensure higher efficiency and more accurate results, while also providing image search results corresponding to the search needs based on semantic features when keyword search fails. This enhances the intelligence and flexibility of the image search process and improves the overall image search experience.

[0129] Based on any of the above optional technical solutions, optionally, the first image is provided with image keywords of at least two search dimensions; the search dimensions include at least one of image acquisition time, image acquisition location, and image category; the keyword search module 520 is specifically used to determine a second image corresponding to the target search information from the first image in the target image library based on the target keywords and the image keywords of at least one of the first images.

[0130] Based on any of the above optional technical solutions, the keyword search module 520 optionally includes: an image set determination unit and a set union determination unit. The image set determination unit is used to determine a first image set corresponding to each of the target keywords when the target search information includes multiple target keywords under a single search dimension; wherein the first image set is a set of first images corresponding to the target keywords in the target image library; the set union determination unit is used to determine the union of the first image sets of multiple target keywords, and determine a second image corresponding to the target search information based on the first images in the union.

[0131] Based on any of the above optional technical solutions, the keyword search module 520 optionally includes: an image set construction unit and a set intersection determination unit. The image set construction unit is used to, when the target search information includes target keywords under multiple search dimensions, obtain a third image corresponding to each search dimension based on the target keywords under each search dimension, and construct a second image set corresponding to each search dimension based on the third images. The set intersection determination unit is used to determine the intersection of the second image sets corresponding to multiple search dimensions, and determine the second image corresponding to the target search information based on the third images in the intersection.

[0132] Optionally, based on any of the above-mentioned optional technical solutions, the device further includes: a search keyword acquisition module, a search field determination module, and a keyword determination module. The search keyword acquisition module is used to perform word segmentation processing on the target search information after acquiring the target search information to obtain search keywords corresponding to the target search information; the search field determination module is used to determine a time search field in the search keywords based on the time identifier information, where the search keywords include time identifier information; wherein the time identifier information includes holiday keywords and / or time segmentation information; the keyword determination module is used to determine target keywords for the image acquisition time dimension based on the time search field, where the time represented by the time search field is a valid time.

[0133] Based on any of the above optional technical solutions, the search field determination module is specifically used to map the holiday keyword to the image acquisition date according to the calendar information when the time identification information includes a holiday keyword, and generate a time search field according to the image acquisition date.

[0134] Optionally, based on any of the above-mentioned optional technical solutions, the device further includes: an image recognition module. The image recognition module is configured to perform image recognition on the first image of the target image library before determining the second image corresponding to the target search information from the first image of the target image library based on the target keywords, to determine category keywords of at least one classification dimension corresponding to the first image; wherein the classification dimension includes at least one dimension among image content, image style, image color, and the scene represented by the image.

[0135] Based on any of the above-mentioned optional technical solutions, optionally, the semantic feature search module 530 includes: a semantic feature determination unit and a semantic feature search unit. The semantic feature determination unit is used to determine the search semantic features corresponding to the target search information and to obtain the image content features of the first image in the target image library; the semantic feature search unit is used to determine the similarity between the search semantic features and the image content features, and to determine the second image corresponding to the target search information from the first image in the target image library based on the similarity.

[0136] Optionally, based on any of the above-mentioned optional technical solutions, the device further includes: an image filtering module. The image filtering module is configured to, after determining the second image corresponding to the target search information and before displaying the second image, filter out the second image if the second image meets preset filtering conditions, and display the remaining second image after filtering; wherein the preset filtering conditions at least include that the second image contains target content.

[0137] The image search device provided in this disclosure can execute the image search method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of executing the method.

[0138] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of this disclosure.

[0139] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Reference is made below. Figure 7It illustrates an electronic device suitable for implementing embodiments of the present disclosure (e.g., Figure 7 The diagram below shows the structure of the terminal device or server 500. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0140] like Figure 7 As shown, electronic device 500 may include a processing unit (e.g., central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An edit / output (I / O) interface 505 is also connected to bus 504.

[0141] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0142] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0143] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0144] The electronic device provided in this embodiment and the image search method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0145] This disclosure provides a computer storage medium storing a computer program that, when executed by a processor, implements the image search method provided in the above embodiments.

[0146] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-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 thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave; wherein computer-readable program code is carried. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a 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 computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0147] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0148] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0149] The aforementioned computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: in response to an image search operation targeting a target image library, acquire target search information; wherein the target image library includes at least one first image; if the target search information includes target keywords, determine a second image corresponding to the target search information from the first image in the target image library based on the target keywords, and display the second image; if the target search information does not include the target keywords, determine a second image corresponding to the target search information from the first image in the target image library based on the search semantic features corresponding to the target search information, and display the second image.

[0150] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0151] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0152] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The names of the units are not necessarily limiting in certain circumstances; for example, a search information acquisition module can also be described as a "module for acquiring target search information".

[0153] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0154] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0155] According to one or more embodiments of this disclosure, [Example 1] provides an image search method, comprising: in response to an image search operation targeting a target image library, acquiring target search information; wherein the target image library includes at least one first image; if the target search information includes target keywords, determining a second image corresponding to the target search information from the first image in the target image library based on the target keywords, and displaying the second image; if the target search information does not include the target keywords, determining a second image corresponding to the target search information from the first image in the target image library based on search semantic features corresponding to the target search information, and displaying the second image.

[0156] According to one or more embodiments of this disclosure, [Example 2] provides the method of Example 1, which further includes: optionally, the first image is provided with image keywords of at least two search dimensions; the search dimensions include at least one of image acquisition time, image acquisition location, and image category; the step of determining the second image corresponding to the target search information from the first image in the target image library according to the target keywords includes: determining the second image corresponding to the target search information from the first image in the target image library according to the target keywords and the image keywords of at least one first image.

[0157] According to one or more embodiments of this disclosure, [Example 3] provides the method of Example 2, which further includes: Optionally, determining the second image corresponding to the target search information from the first images in the target image library based on the target keyword and the image keyword of at least one first image includes: when the target search information includes multiple target keywords under a single search dimension, determining a first image set corresponding to each target keyword; wherein the first image set is a set of first images in the target image library corresponding to the target keyword; determining the union of the first image sets of multiple target keywords, and determining the second image corresponding to the target search information based on the first images in the union.

[0158] According to one or more embodiments of this disclosure, Example 4 provides the method of Example 2, which further includes: Optionally, determining the second image corresponding to the target search information from the first images in the target image library based on the target keywords and the image keywords of at least one first image includes: when the target search information includes target keywords under multiple search dimensions, obtaining a third image corresponding to each search dimension based on the target keywords under each search dimension, and constructing a set of second images corresponding to each search dimension based on the third images; determining the intersection of the second image sets corresponding to multiple search dimensions, and determining the second image corresponding to the target search information based on the third images in the intersection.

[0159] According to one or more embodiments of this disclosure, Example 5 provides the method of Example 1, which further includes: optionally, after obtaining the target search information, the method further includes: performing word segmentation on the target search information to obtain search keywords corresponding to the target search information; if the search keywords include time identifier information, determining a time search field in the search keywords based on the time identifier information; wherein the time identifier information includes holiday keywords and / or time segmentation information; if the time represented by the time search field is a valid time, determining target keywords for the image acquisition time dimension based on the time search field.

[0160] According to one or more embodiments of this disclosure, Example Six provides the method of Example Five, which further includes: Optionally, determining the time search field in the search keyword based on the time identifier information includes: when the time identifier information includes a holiday keyword, mapping the holiday keyword to the image acquisition date based on calendar information, and generating the time search field based on the image acquisition date.

[0161] According to one or more embodiments of this disclosure, Example 7 provides the method of Example 1, which further includes: Optionally, before determining the second image corresponding to the target search information from the first image of the target image library based on the target keyword, the method further includes: performing image recognition on the first image of the target image library to determine category keywords of at least one classification dimension corresponding to the first image; wherein the classification dimension includes at least one dimension among image content, image style, image color, and scene represented by the image.

[0162] According to one or more embodiments of this disclosure, Example 8 provides the method of Example 1, which further includes: Optionally, determining the second image corresponding to the target search information from the first image of the target image library based on the search semantic features corresponding to the target search information includes: determining the search semantic features corresponding to the target search information and obtaining the image content features of the first image of the target image library; determining the similarity between the search semantic features and the image content features, and determining the second image corresponding to the target search information from the first image of the target image library based on the similarity.

[0163] According to one or more embodiments of this disclosure, Example 9 provides the method of Example 1, which further includes: optionally, after determining the second image corresponding to the target search information and before displaying the second image, the method further includes: if the second image satisfies a preset filtering condition, filtering out the second image and displaying the remaining second image after filtering; wherein the preset filtering condition includes at least the second image containing target content.

[0164] According to one or more embodiments of this disclosure, [Example 10] provides an image search device, comprising: a search information acquisition module, configured to acquire target search information in response to an image search operation targeting a target image library; wherein the target image library includes at least one first image; a keyword search module, configured to, when the target search information includes a target keyword, determine a second image corresponding to the target search information from the first image in the target image library based on the target keyword, and display the second image; and a semantic feature search module, configured to, when the target search information does not include the target keyword, determine a second image corresponding to the target search information from the first image in the target image library based on search semantic features corresponding to the target search information, and display the second image.

[0165] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0166] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0167] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An image search method characterized by, The method comprises the following steps: In response to an image search operation for a target gallery, target search information is acquired; wherein the target gallery comprises at least one first image; If the target search information comprises a target keyword, a second image corresponding to the target search information is determined from the first image of the target gallery according to the target keyword, and the second image is displayed; If the target search information does not comprise the target keyword, a second image corresponding to the target search information is determined from the first image of the target gallery according to a search semantic feature corresponding to the target search information, and the second image is displayed.

2. The image search method according to claim 1, characterized by, The first image is provided with image keywords of at least two search dimensions; the search dimensions comprise at least one of image acquisition time, image acquisition location and image category; The method comprises the following steps: According to the target keyword and the image keywords of at least one first image, a second image corresponding to the target search information is determined from the first image in the target gallery.

3. The image search method according to claim 2, characterized by, The method comprises the following steps: If the target search information comprises multiple target keywords under a single search dimension, a first image set corresponding to each target keyword is determined respectively; wherein the first image set is a set of first images corresponding to the target keyword in the target gallery; The union set of the first image sets of multiple target keywords is determined, and a second image corresponding to the target search information is determined according to the first image in the union set.

4. The image search method according to claim 2, characterized by, The method comprises the following steps: If the target search information comprises target keywords under multiple search dimensions, a third image corresponding to each search dimension is acquired according to the target keyword under each search dimension respectively, and a second image set corresponding to each search dimension is constructed according to the third image; The intersection of the second image sets corresponding to multiple search dimensions is determined, and a second image corresponding to the target search information is determined according to the third image in the intersection.

5. The image search method according to claim 1, characterized by, After the target search information is acquired, the method further comprises the following steps: The target search information is subjected to word segmentation processing to obtain a search keyword corresponding to the target search information; If the search keyword comprises time identification information, a time search field in the search keyword is determined according to the time identification information; wherein the time identification information comprises a festival keyword and / or time segmentation information; If the search keyword comprises time identification information, a time search field in the search keyword is determined according to the time identification information; wherein the time identification information comprises a festival keyword and / or time segmentation information; In a case that the time represented by the time search field is a valid time, a target keyword of an image acquisition time dimension is determined according to the time search field.

6. The image search method according to claim 5, characterized by, The determining the time search field in the search keyword according to the time identification information comprises: In a case that the time identification information comprises a festival keyword, the festival keyword is mapped to an image acquisition date according to calendar information, and a time search field is generated according to the image acquisition date.

7. The image search method according to claim 1, characterized by, Before the determining the second image corresponding to the target search information from the first image of the target gallery according to the target keyword, the method further comprises: performing image recognition on the first image of the target gallery to determine a category keyword of at least one classification dimension corresponding to the first image, wherein the classification dimension comprises at least one of image content, image style, image color, and scene represented by the image.

8. The image search method according to claim 1, characterized by, The determining the second image corresponding to the target search information from the first image of the target gallery according to the search semantic feature corresponding to the target search information comprises: determining a search semantic feature corresponding to the target search information, and obtaining an image content feature of the first image of the target gallery; determining a similarity between the search semantic feature and the image content feature, and determining the second image corresponding to the target search information from the first image of the target gallery according to the similarity.

9. The image search method according to claim 1, characterized by, After the determining the second image corresponding to the target search information, before the displaying the second image, the method further comprises: in a case that the second image satisfies a preset filtering condition, filtering out the second image, and displaying the second image remaining after the filtering; wherein the preset filtering condition at least comprises that the second image contains target content.

10. An image search apparatus characterized by comprising: comprises: a search information acquisition module configured to, in response to an image search operation on a target gallery, acquire target search information; wherein the target gallery comprises at least one first image; a keyword search module configured to, in a case that the target search information comprises a target keyword, determine a second image corresponding to the target search information from the first image of the target gallery according to the target keyword, and display the second image; a semantic feature search module configured to, in a case that the target search information does not comprise the target keyword, determine a second image corresponding to the target search information from the first image of the target gallery according to a search semantic feature corresponding to the target search information, and display the second image.

11. An electronic device, comprising: The electronic device comprises: one or more processors; a storage device configured to store one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the image search method according to any one of claims 1-9.

12. A storage medium containing computer-executable instructions, wherein: The computer executable instructions, when executed by a computer processor, are used to perform the image search method according to any one of claims 1-9.

13. A computer program product, characterised in that, The computer program product comprises a computer program which, when executed by a processor, implements the image search method according to any one of claims 1-9.

Images