Image searching method and device, electronic equipment and storage medium

Abstract

The invention provides an image searching method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the technical field of image searching. According to the specific implementation scheme, image searching demand information is received; performing image search in the target equipment according to the image search demand information to obtain a candidate image set; extracting character information corresponding to the images in the candidate image set, wherein the character information at least comprises at least one of a human face and a character relationship between the human face and the target user; and determining a target image from the candidate image set according to the character information, and displaying the target image on the dialogue interface.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, specifically to the field of image search technology, and more particularly to an image search method, device, electronic device, and storage medium. Background Art

[0002] Since users store a large number of pictures in storage devices such as the cloud, although the cloud is equipped with a search function that allows users to search for images in the cloud, in actual use, users often find it difficult to quickly and accurately find the target picture from the large number of pictures in the cloud. Summary of the Invention

[0003] The present disclosure provides a method, device, electronic device and storage medium for image searching.

[0004] According to one aspect of the present disclosure, a method for searching images is provided, comprising: receiving image search requirement information; performing an image search in a target device according to the image search requirement information to obtain a set of candidate images; extracting character information corresponding to images in the set of candidate images, wherein the character information includes at least one of a face and a character relationship between the face and a target user; determining a target image from the set of candidate images according to the character information, and displaying the target image on a dialogue interface.

[0005] According to another aspect of the present disclosure, there is provided an image search device, comprising: a receiving module for receiving image search requirement information; a search module for performing an image search in a target device according to the image search requirement information to obtain a candidate image set; an extraction module for extracting character information corresponding to images in the candidate image set, wherein the character information includes at least one of a face and a character relationship between the face and a target user; and a determination module for determining a target image from the candidate image set according to the character information, and displaying the target image on a dialogue interface.

[0006] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the image search method described in the above-mentioned embodiment.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, on which a computer program / instructions are stored, and the computer instructions are used to enable the computer to execute the image search method described in the embodiment of the above aspect.

[0008] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instruction, which implements the image search method described in the embodiment of the above aspect when the computer program / instruction is executed by a processor.

[0009] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0011] Figure 1 A flowchart of a method for searching images provided in an embodiment of the present disclosure;

[0012] Figure 2 A flowchart of another image search method provided by an embodiment of the present disclosure;

[0013] Figure 3 A flowchart of another image search method provided by an embodiment of the present disclosure;

[0014] Figure 4 A flowchart of another image search method provided by an embodiment of the present disclosure;

[0015] Figure 5 A schematic diagram of a process for searching for images in a target device according to an embodiment of the present disclosure;

[0016] Figure 6 A schematic diagram of selecting a face provided in an embodiment of the present disclosure;

[0017] Figure 7 A schematic structural diagram of an image search device provided in an embodiment of the present disclosure;

[0018] Figure 8 The present invention is a block diagram of an electronic device for implementing the image search method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0020] The image search method, device, electronic device, and storage medium of the embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0021] Artificial Intelligence (AI) is the study of how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). This discipline encompasses both hardware and software technologies. AI hardware technologies generally include computer vision, speech recognition, natural language processing, as well as deep learning / learning, big data processing, and knowledge graphs.

[0022] Figure 1 A flowchart of a method for searching images provided in an embodiment of the present disclosure is provided.

[0023] like Figure 1 As shown, the image search method may include:

[0024] S101, receiving image search request information.

[0025] It should be noted that the execution subject of the image search method in the embodiment of the present disclosure may be a hardware device with data processing capabilities and / or the necessary software required to drive the hardware device to work. Optionally, the execution subject may include a server, a user terminal and other smart devices. Optionally, the user terminal includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, etc. Optionally, the server includes but is not limited to a network server, an application server, and may also be a server of a distributed system, or a server combined with a blockchain, etc. The embodiment of the present disclosure does not make any specific limitations.

[0026] In some embodiments, the client's input information is obtained and used as the image search requirement information. Optionally, it can be determined whether the input information contains keywords related to image search, and the input information containing the keywords is used as the image search requirement information.

[0027] For example, keywords related to image search may be search, query, retrieval, etc. If the client inputs "search for photos of XX location", which includes keyword search, the client's input information can be used as image search requirement information.

[0028] In some embodiments, the client's input information can be obtained by interacting with the client. Optionally, information can be entered in the dialogue interface and used as the image search request information. Optionally, a prompt word can be used to enter the image search request information in a set area. For example, a search box can be set in the dialogue interface, and a prompt word can be displayed in the search box to indicate that the image search request information is entered in the search box.

[0029] S102: Perform an image search in the target device according to the image search requirement information to obtain a set of candidate images.

[0030] In some embodiments, the target device may be a device with a storage function, such as a network disk, a cloud disk, a storage device, etc.

[0031] In some embodiments, an image query term may be obtained from the image search requirement information, and an image search may be performed on the target device based on the image query to obtain candidate images and generate a candidate image set. Optionally, the image query term may be at least one of a person query term, a location query term, a time query term, a type query term, and a format query term.

[0032] In some embodiments, by performing semantic analysis on the image search requirement information, image query terms can be determined, and matching is performed with images in the target device based on the image query terms, and successfully matched images are used as images in the candidate image set.

[0033] Optionally, image information corresponding to the image in the target device can be obtained and matched with the image query term to determine the successfully matched image as an image in the candidate image set. Optionally, the image information includes but is not limited to: time identifier, person identifier, location identifier, type identifier, etc.

[0034] In some embodiments, the image search request information includes at least one image query term, and images that match the at least one image query term can be selected as images in the candidate image set. For example, the image query terms include query terms A, B, and C. Let the image information of image 1 be information A, the image information of image 2 be information A and information B, and the image information of image 3 be information C. If information A matches query term B, and information B matches query term C, it can be determined that the image information of image 2 matches two image query terms, and the image information of image 1 matches one image query term. In this case, images 1 and 2 are selected as images in the candidate image set.

[0035] S103: extracting character information corresponding to the images in the candidate image set, wherein the character information includes at least one of a face and a character relationship between the face and a target user.

[0036] In some embodiments, features are extracted from images in a candidate image set to obtain faces contained in the images, and the character relationship between the faces and the target user is determined based on the faces, and the faces and the character relationship between the faces and the target user can be used as character information corresponding to the image.

[0037] In some embodiments, a character relationship table between a face and a target user may be pre-established in the target device. By extracting a face from an image, the character relationship between the face and the target user may be determined based on the pre-established character relationship table.

[0038] In some embodiments, at least one of a human face and a person relationship between the face and the target user can be determined based on the image information corresponding to the image. Alternatively, if the image does not contain a human face, but the image information contains a person identifier, the face corresponding to the person identifier can be determined from a pre-established correspondence between faces and persons, and the person relationship corresponding to the person identifier can be determined from a person relationship table.

[0039] S104: Determine a target image from the candidate image set based on the person information, and display the target image on the dialogue interface.

[0040] In some embodiments, a target image can be determined from a candidate image set based on the image search requirement information and the person information. Alternatively, a target person to be searched for, or a relationship between target persons to be searched for, can be determined based on the image search requirement information.

[0041] Furthermore, the face of the target person can be determined and matched with the face in the person information to determine an image with a successful face match as the target image. Optionally, the relationship of the target person can also be matched with the relationship of the person in the person information to determine an image with a successful relationship match as the target image.

[0042] In some embodiments, interaction with a client may also be performed based on person information, with the client filtering the person information and then determining a target image from a set of candidate images based on the filtering results received from the client. For example, if the person information includes face A, face B, and face C, as well as person relationships A and person relationship B, and the filtering results indicate that face A and person relationship A should be deleted from the person information, then from the candidate images, images where the face is face B may be determined as the target image, images where the face is face C may be determined as the target image, and images where the person relationship is person relationship B may be determined as the target image.

[0043] In some embodiments, a set number of target images can be displayed on the dialogue interface. If the total number of target images is less than or equal to the set number, all target images can be displayed on the dialogue interface; if the total number of target images is greater than the set number, a set number of target images can be determined and displayed on the dialogue interface.

[0044] Optionally, when the total number of target images is greater than a set number, a text message indicating that the total number of target images is greater than a set number may also be displayed on the dialogue interface.

[0045] In some embodiments, a thumbnail of the target image may be displayed on the dialogue interface to improve the simplicity of the screen display. The thumbnail is obtained by reducing the image size of the target image and displayed on the dialogue interface.

[0046] According to the image search method provided by the embodiment of the present disclosure, an image search is performed on the target device based on the image search requirement information to obtain a set of candidate images, and character information is extracted from the images in the candidate image set to determine the target image from the candidate image set based on the character information, and the target image is displayed on the dialogue interface. Thus, this solution performs a preliminary screening of the images of the target device based on the image search requirement information to obtain a set of candidate images, and then performs a secondary screening of the candidate image set based on the character information to obtain the target image, thereby improving the accuracy of the image search. By quickly performing image searches based on the image search requirement information, the efficiency and speed of the image search can be improved, saving time and costs.

[0047] Figure 2 A flowchart of a method for searching images provided in an embodiment of the present disclosure is provided.

[0048] like Figure 2 As shown, the image search method may include:

[0049] S201, receiving image search request information.

[0050] S202: Perform an image search in the target device according to the image search requirement information to obtain a set of candidate images.

[0051] S203: Extracting character information corresponding to the images in the candidate image set.

[0052] The relevant contents of steps S201-S203 can be found in the above embodiment and will not be repeated here.

[0053] S204: Determine a candidate first face based on the character information, and display the first face on the dialogue interface.

[0054] In some embodiments, faces included in the character information can be selected as candidate first faces and displayed on the conversation interface. Optionally, a priority for displaying the first faces can be determined based on the number of first faces, so that the first faces are displayed on the conversation interface based on the priority, thereby avoiding information overload caused by displaying a large number of images on the conversation interface and helping to improve information acquisition efficiency.

[0055] In some embodiments, by determining the first number of images associated with the first face, and sorting the first face in descending order according to the first number, the first face can be displayed on the dialogue interface according to the sorting result. Optionally, the sorting result can be used as the display priority. For example, there are first face 1, first face 2, and first face 3. If the first number of images associated with first face 1 is A, the first number of images associated with first face 2 is B, and the first number of images associated with first face 3 is C, where A is greater than C and greater than B, it can be determined that the priority of first face 1 is greater than first face 3 and greater than first face 2, so that the first face can be displayed on the dialogue interface in the order of first face 1-first face 3-first face 2.

[0056] In some embodiments, multiple different first faces can be determined based on the person information. If the first faces are all different, they can be directly displayed on the conversation interface. If there are identical first faces, the identical first faces can be merged to save display space and display more faces.

[0057] In some embodiments, a face merging operation sent by a client can be obtained to merge the same first face according to the face merging operation. That is, by receiving the face merging operation and determining the second face to be merged in the first face according to the face merging operation, the second face to be merged is the face of the same person at a different angle. For example, there are first face 1, first face 2, and first face 3, where first face 2 and first face 3 are the faces of the same person at different angles, then first face 2 and first face 3 can be used as the second face to be merged.

[0058] Furthermore, by merging the second faces, a merged face is obtained as the first face of the same person, thereby replacing the second face on the dialogue interface with the first face of the same person. Optionally, any face can be determined from the second faces as the first face of the same person.

[0059] For example, the dialogue interface displays the first face 1, the first face 2, and the first face 3, wherein the first face 2 and the first face 3 are the second faces that need to be merged. The first face 2 and the first face 3 are merged and the first face 2 or the first face 3 is displayed on the dialogue interface.

[0060] In some embodiments, since the sorting results of the first number of first faces are displayed in order on the dialogue interface, after the faces are merged, the sorting results can be updated and the first face can be displayed according to the updated sorting results, thereby realizing real-time updating of the display order and improving the accuracy of the first face display.

[0061] In some embodiments, a second number of images associated with the second face can be determined, and based on the second number, a third number of images associated with the first face of the same person can be determined. Alternatively, the third number can be obtained by summing the second number. Furthermore, the sorting result can be updated based on the third number. Alternatively, the third number can be compared with the first number of unmerged images associated with the first face to update the sorting result.

[0062] For example, before the update, there are first face 1, first face 2, first face 3, and first face 4. The first number of associated images is 50, 55, 40, and 20, respectively. The corresponding sorting result is: first face 2 - first face 1 - first face 3 - first face 4. If first face 3 and first face 4 are the second faces to be merged, then by merging first face 3 and first face 4, the merged first face 3 is obtained as the merged face. This determines that the third number of images associated with the first face of the same person is 60, and the sorting result can be further updated to: first face 3 - first face 2 - first face 1.

[0063] In some embodiments, to improve the simplicity of the display screen, displayable faces and hidden faces can be determined from the first face, so that the displayable faces are displayed in the dialogue interface and the hidden faces are hidden. Optionally, the hidden faces can be hidden according to the first interactive control for expanding or hiding the hidden faces.

[0064] In some embodiments, by determining a face display limit for the conversation interface, and based on the face display limit and the sorting result, determining which faces can be displayed, and hiding the remaining faces. By designating the remaining faces as hidden faces, the hidden faces can be hidden.

[0065] In some embodiments, based on the face display limit and the sorting result of the dialogue interface, before determining which faces can be displayed, it can be determined whether the total number of first faces is less than the face limit.

[0066] Optionally, if the total number of first faces exceeds the face display limit, the first faces that meet the face limit can be selected from the first faces based on the sorting result as displayable faces, and the remaining faces in the first faces are hidden faces. Optionally, if the total number of first faces is less than or equal to the face display limit, the first face can be displayed as a displayable face on the conversation interface.

[0067] In some embodiments, the dialogue interface may include a first interactive control for expanding or hiding a hidden face. By triggering the first interactive control, the hidden face can be expanded or hidden, thereby realizing dynamic interactive design.

[0068] In some embodiments, in response to a first triggering operation on a first interactive control on the dialogue interface, a hidden face is expanded on the dialogue interface. Alternatively, in response to a second triggering operation on the first interactive control, the hidden face is hidden. That is, the first triggering operation may indicate expanding the hidden face on the dialogue interface, and the second triggering operation may indicate hiding the hidden face on the dialogue interface.

[0069] S205: Determine the person query term in the image search requirement information.

[0070] In some embodiments, semantic analysis is performed on the image search request information to determine the person query term in the image search request information. Optionally, person names, person characteristics, person relationships, and other information can be used as person query terms.

[0071] S206 , determining a target face from the first faces according to the person query word and the first face.

[0072] In some embodiments, the first face corresponding to the person query term can be used as the target face. For example, if the image search requirement information is: search for photos of person A, where person A is the person query term, then the face of person A can be determined from the first face as the target face.

[0073] That is, the target person to be searched can be determined based on the person query term, and the target person can be compared with the first face. The target face can then be determined from the first face based on the comparison result. Performing a face search based on the target person can improve the accuracy of the face search. Optionally, after determining the target person, a correspondence between faces and people can be pre-established in the target device. Based on this correspondence, the face corresponding to the target person can be determined, and then the face can be compared with the first face to obtain a comparison result. The comparison result can indicate a first face that is identical to the face corresponding to the target person, and the target face can be determined from the first face based on the comparison result. In other words, the first face indicated in the comparison result is used as the target face.

[0074] S207: Determine a target image from the candidate image set according to the target face.

[0075] In some embodiments, feature extraction is performed on the target face and images in the candidate image set, and matching is performed based on the extracted features, so that the target image is determined from the candidate image set based on the matching results.

[0076] Optionally, the first facial feature is obtained by extracting the target face, and the facial features of the images in the candidate image set are extracted to obtain the second facial feature, so that the similarity between the first facial feature and the second facial feature can be calculated, and matching can be performed based on the size of the similarity, and the similarity being greater than a set threshold is used as a condition for successful matching, so as to determine the matching result based on the condition for successful matching.

[0077] Optionally, if the matching result indicates a second facial feature that successfully matches the first facial feature, the image corresponding to the second facial feature may be used as the target image.

[0078] S208: Display the target image on the dialogue interface.

[0079] The relevant contents of step S208 can be found in the above embodiment and will not be repeated here.

[0080] In some embodiments, in order to enhance the interactivity with the user, information for interacting with the user can be added during the execution of the image search request information to improve the user's experience. Optionally, the interactive information can be displayed on the dialogue interface.

[0081] Optionally, during the execution of the image search requirement information, the current execution stage can be determined, and text information of the current execution stage can be generated as interactive information, so that the text information can be displayed on the dialogue interface.

[0082] According to the image search method provided by the embodiment of the present disclosure, by determining a candidate first face and determining a target face from the first face based on a person query term, and then determining a target image from a candidate image set based on the target face, accurate matching of the image search requirement information and the target image can be achieved, thereby improving the accuracy and efficiency of the image search.

[0083] Figure 3 A flowchart of a method for searching images provided in an embodiment of the present disclosure is provided.

[0084] like Figure 3 As shown, the image search method may include:

[0085] S301, receiving image search request information.

[0086] S302: Perform an image search in the target device according to the image search requirement information to obtain a set of candidate images.

[0087] S303: Extracting character information corresponding to the images in the candidate image set.

[0088] S304: Determine a candidate first face based on the character information, and display the first face on the dialogue interface.

[0089] S305: Determine the person query term in the image search requirement information.

[0090] The relevant contents of steps S301-S305 can be found in the above embodiment and will not be repeated here.

[0091] S306: Determine the character relationship between the first face and the target user based on the character information.

[0092] S307: Determine the target person relationship to be searched based on the person query word.

[0093] S308 , determining a target face from the first faces based on the target person relationship and the person relationship corresponding to the first face.

[0094] In some embodiments, if the character information includes a character relationship between a face and a target user, the target face can be determined from the first face based on the character relationship. Alternatively, the character relationship between the first face and the target user can be determined from the character information, and the target character relationship to be searched can be determined based on a character query term included in the image search request information. For example, if the search request information is "Find photos of my mother," where the character query term is "mother," the target character relationship determined based on the character query term is "mother-child relationship."

[0095] Furthermore, a person relationship that is the same as the target person relationship can be determined from the person relationship corresponding to the first face, and the first face corresponding to the person relationship can be used as the target face. For example, if the target person relationship is relationship A, the person relationship corresponding to first face 1 is relationship 1, the person relationship corresponding to first face 2 is relationship 2, and the person relationship corresponding to first face 3 is relationship 3, where relationship 1 and relationship 3 are the same as relationship A, then first face 1 and first face 3 can be used as the target faces.

[0096] S309: Determine a target image from the candidate image set according to the target face.

[0097] S310: Display the target image on the dialogue interface.

[0098] The relevant contents of steps S309-S310 can be found in the above embodiment and will not be repeated here.

[0099] According to the image search method provided by the embodiment of the present disclosure, based on the target person relationship indicated in the image search requirement information, the first face corresponding to the target person relationship is determined from the multiple person relationships contained in the person information. As the target face, it is possible to quickly search for the target face among the multiple first faces. By selecting faces based on the person relationships, the accuracy of the face search can be improved, and it is possible to search for target faces of the same face at different face angles.

[0100] Figure 4A flowchart of a method for searching images provided in an embodiment of the present disclosure is provided.

[0101] like Figure 4 As shown, the image search method may include:

[0102] S401, receiving image search request information.

[0103] S402: Perform an image search in the target device according to the image search requirement information to obtain a set of candidate images.

[0104] S403: Extracting character information corresponding to the images in the candidate image set.

[0105] S404: Determine a candidate first face according to the character information, and display the first face on the dialogue interface.

[0106] The relevant contents of steps S401-S404 can be found in the above embodiment and will not be repeated here.

[0107] S405: Monitor the face selection operation.

[0108] S406: Select a target face from the first faces according to the monitored face selection operation.

[0109] In some embodiments, if the character information does not include a character relationship between the face and the target user, the target face may be selected from the first face based on a face selection operation performed by the client on the first face. In other words, the face selection operation may be monitored to select the first face indicated by the face selection operation as the target face.

[0110] In some embodiments, after determining the target face, the target person relationship to be searched can be determined based on the person query term included in the image search requirement information, and the person relationship between the target face and the target user can be marked as the target person relationship. In other words, the person relationship between the target face and the target user is the same as the target person relationship indicated by the person query term.

[0111] In some embodiments, in order to improve the efficiency of face search, after determining the character relationship between the target face and the target user, the character relationship can be stored, so that the target face can be queried based on the stored character relationship.

[0112] Optionally, the character relationships between different faces contained in the target device and the target user can be stored in a character relationship table. After obtaining the first face based on the candidate image set, the character relationship between the first face and the target user can be determined by querying the character relationship table.

[0113] In some embodiments, if the character relationship between the target face and the target user does not exist in the character relationship table, the character relationship corresponding to the target face can be marked and updated to the character relationship table of the target device.

[0114] S407: Determine a target image from the candidate image set according to the target face.

[0115] S408: Display the target image on the dialogue interface.

[0116] The relevant contents of steps S407-S408 can be found in the above embodiment and will not be repeated here.

[0117] According to the image search method provided by the embodiment of the present disclosure, by monitoring the face selection operation and, after detecting the face selection operation, selecting the target face from the first face according to the face selection operation, the accuracy of searching for the target face can be improved and the interactivity of the image search can be enhanced.

[0118] Figure 5 The figure shows a flow chart of searching for images in a target device. Figure 5 The image search process can be displayed in the dialogue interface, and the copywriting information of the current execution stage can be displayed at each execution stage. Figure 6 As shown, the character relationship corresponding to the target face can be marked in advance, for example: pre-mark based on a photo of a girlfriend, and after uploading other photos, the other photos of the girlfriend can be automatically marked based on face recognition, by inputting: Help me find photos of me and my girlfriend traveling to location A in 2023. By analyzing the input information, it is determined that the image search requirement information is to search for photos of me and my girlfriend traveling to location A in 2023, then the following can be displayed on the dialogue interface: 1. Find all photos in the target device; 2. Search all photos for photos with a time of 2023, a target character relationship of yourself, your girlfriend, and a location of location A. In this way, you can search in the target device and display the target image obtained by the search on the dialogue interface: According to your needs, photos of you and your girlfriend traveling to location A in 2023 have been found in the target device. As Figure 5 As shown, a thumbnail of the target image is displayed on the dialogue interface according to the set display position.

[0119] Optionally, during the execution of the image search request information, if the character information of the image in the searched candidate image set does not contain the character relationship between the face and the target user, the user can select the first face found in the target device to generate a face selection operation, and determine the target face from the first faces by monitoring the face selection operation and based on the monitored face selection operation. Figure 6As shown, by displaying on the dialogue interface: Search for people in the photo, please select the face of the person whose relationship is yourself and your girlfriend, and monitoring the face selection operation to determine the target face. Further, after determining the target face, the target image can be determined from the candidate image set based on the target face, and the target image can be displayed on the dialogue interface, such as Figure 6 As shown, the thumbnail of the target image can be displayed on the dialogue interface according to the set display position.

[0120] Corresponding to the image search methods provided in the above-mentioned embodiments, an embodiment of the present disclosure also provides an image search device. Since the image search device provided in the embodiment of the present disclosure corresponds to the image search methods provided in the above-mentioned embodiments, the implementation methods of the above-mentioned image search methods are also applicable to the image search device provided in the embodiment of the present disclosure and will not be described in detail in the following embodiments.

[0121] Figure 7 A schematic structural diagram of an image search device provided in an embodiment of the present disclosure.

[0122] like Figure 7 As shown, the image search device 700 of the embodiment of the present disclosure includes a receiving module 701, a searching module 702, an extracting module 703 and a determining module 704.

[0123] Receiving module 701, used to receive image search request information;

[0124] Search module 702, configured to search for images in a target device according to image search requirement information to obtain a set of candidate images;

[0125] An extraction module 703 is configured to extract character information corresponding to an image in the candidate image set, wherein the character information includes at least one of a face and a character relationship between the face and a target user;

[0126] The determination module 704 is configured to determine a target image from the candidate image set based on the person information and display the target image on the dialogue interface.

[0127] In one embodiment of the present disclosure, the determination module 704 is further configured to: determine a candidate first face based on the character information and display the first face on the dialogue interface; determine a character query term in the image search requirement information;

[0128] According to the person query word and the first face, a target face is determined from the first faces; and according to the target face, a target image is determined from the candidate image set.

[0129] In one embodiment of the present disclosure, the determination module 704 is further configured to: determine a target person to be searched based on a person query term; compare the target person with the first face, and determine the target face from the first face based on the comparison result.

[0130] In one embodiment of the present disclosure, the determination module 704 is further used to: determine the character relationship between the first face and the target user based on the character information; determine the target character relationship to be searched based on the character query term; and determine the target face from the first face based on the target character relationship and the character relationship corresponding to the first face.

[0131] In one embodiment of the present disclosure, the determination module 704 is further used to: monitor the face selection operation; select a target face from the first faces based on the monitored face selection operation; wherein the character relationship between the target face and the target user is the same as the target character relationship indicated by the character query term.

[0132] In one embodiment of the present disclosure, the determination module 704 is further used to: determine the character relationship between the target face and the target user; mark the character relationship corresponding to the target face, and update it to the character relationship table of the target device.

[0133] In one embodiment of the present disclosure, the determination module 704 is further used to: determine a first number of images associated with the first face; sort the first faces in descending order according to the first number; and display the first face on the dialogue interface according to the sorting result.

[0134] In one embodiment of the present disclosure, the determination module 704 is further used to: receive a face merging operation; determine, based on the face merging operation, a second face that needs to be merged in the first face, wherein the second face that needs to be merged is a face of the same person at a different angle; merge the second face to obtain a merged face as the first face of the same person; and replace the second face on the dialogue interface with the first face of the same person.

[0135] In one embodiment of the present disclosure, the determination module 704 is further used to: determine a second number of images associated with the second face; determine a third number of images associated with the first face of the same person based on the second number; and update the sorting result based on the third number.

[0136] In one embodiment of the present disclosure, the determination module 704 is further used to: determine the displayable faces based on the face display limit and the sorting result of the dialogue interface, and hide the remaining faces; expand the hidden faces on the dialogue interface in response to a first trigger operation of the first interactive control on the dialogue interface; or hide the hidden faces in response to a second trigger operation of the first interactive control.

[0137] In one embodiment of the present disclosure, the device further includes: determining the current execution stage during the execution of the image search requirement information; generating text information of the current execution stage; and displaying the text information on the dialogue interface.

[0138] According to the image search device provided by the embodiment of the present disclosure, an image search is performed on the target device based on the image search requirement information to obtain a candidate image set, and character information is extracted from the images in the candidate image set to determine the target image from the candidate image set based on the character information, and the target image is displayed on the dialogue interface. Thus, this solution performs a preliminary screening of the images of the target device based on the image search requirement information to obtain a candidate image set, and then performs a secondary screening of the candidate image set based on the character information to obtain the target image, thereby improving the accuracy of the image search. By quickly performing image searches based on the image search requirement information, the efficiency and speed of the image search can be improved, saving time and costs.

[0139] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0140] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0141] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0142] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to computer programs / instructions stored in a read-only memory (ROM) 802 or computer programs / instructions loaded from a storage unit 806 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0143] Various components in device 800 are connected to I / O interface 805, including: an input unit 806 such as a keyboard, mouse, etc.; an output unit 807 such as various types of displays, speakers, etc.; a storage unit 808 such as a magnetic disk, optical disk, etc.; and a communication unit 809 such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0144] The computing unit 801 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the image search method. For example, in some embodiments, the image search method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit 806. In some embodiments, part or all of the computer program / instructions can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program / instructions are loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the image search method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the image search method in any other appropriate manner (e.g., by means of firmware).

[0145] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs / instructions that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0147] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0148] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0149] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0150] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. The client-server relationship arises through computer programs / instructions running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0151] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0152] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for searching an image, characterized in that: The method comprises: Receive image search request information; Performing an image search in the target device according to the image search requirement information to obtain a set of candidate images; Extracting character information corresponding to the images in the candidate image set, wherein the character information includes at least one of a face and a character relationship between the face and a target user; A target image is determined from the candidate image set according to the character information, and the target image is displayed on a dialogue interface.

2. The method according to claim 1, wherein Determining a target image from the candidate image set according to the person information includes: Determining a candidate first face based on the character information, and displaying the first face on the dialogue interface; Determining a person query term in the image search requirement information; determining a target face from the first faces according to the person query word and the first face; According to the target face, the target image is determined from the candidate image set.

3. The method according to claim 2, wherein: The determining a target face from the first face according to the person query word and the first face includes: Determining a target person to be searched based on the person query term; The target person is compared with the first face, and the target face is determined from the first faces based on the comparison result.

4. The method according to claim 2, wherein: The determining a target face from the first face according to the person query word and the first face includes: Determining a character relationship between the first face and a target user based on the character information; Determining the target person relationship to be searched based on the person query term; A target face is determined from the first faces based on the target person relationship and the person relationship corresponding to the first face.

5. The method according to claim 2, wherein: The method further comprises: Monitor face selection operations; selecting the target face from the first faces according to the monitored face selection operation; The character relationship between the target face and the target user is the same as the target character relationship indicated by the character query term.

6. The method according to any one of claims 2 to 5, wherein: After determining a target face from the first face according to the person query word and the first face, the method further includes: Determining a relationship between the target face and the target user; The character relationship corresponding to the target face is marked and updated to the character relationship table of the target device.

7. The method according to any one of claims 2 to 5, wherein: Displaying the first face on the dialogue interface includes: determining a first number of images associated with the first face; sorting the first faces in descending order of the first quantities; The first face is displayed on the dialogue interface according to the sorting result.

8. The method according to claim 7, wherein: Before selecting the target face from the first faces according to the monitored face selection operation, the method further includes: Receive face merging operation; Determining, according to the face merging operation, a second face to be merged in the first face, wherein the second face to be merged is a face of the same person from a different angle; Merging the second faces to obtain a merged face as the first face of the same person; The second face on the dialogue interface is replaced with the first face of the same person.

9. The method according to claim 8, wherein The method further comprises: determining a second number of images associated with the second face; Determining a third number of images associated with the first face of the same person based on the second number; The sorting result is updated according to the third quantity.

10. The method according to claim 8, wherein Displaying the first face on the dialogue interface includes: Determining the displayable faces based on the face display limit of the dialogue interface and the sorting result, and hiding the remaining faces; In response to a first trigger operation of a first interactive control on the dialogue interface, the hidden face is expanded on the dialogue interface; or, in response to a second trigger operation of the first interactive control, the hidden face is hidden.

11. The method according to any one of claims 1 to 6, wherein: The method further comprises: During the execution of the image search requirement information, determining a current execution stage; Generate copy information for the current execution stage; The text information is displayed on the dialogue interface.

12. A picture search device, characterized in that: The device comprises: A receiving module, used for receiving image search request information; A search module, configured to search for images in a target device according to the image search requirement information to obtain a set of candidate images; an extraction module, configured to extract character information corresponding to the images in the candidate image set, wherein the character information includes at least one of a face and a character relationship between the face and a target user; The determination module is used to determine a target image from the candidate image set according to the character information, and display the target image on the dialogue interface.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 11.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-11.

15. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 11 is implemented.

Images