Anchor search method, device, computer equipment and storage medium

By drawing line images by users and generating similar face images, the problem of anchor searches in the prior art requires pre-saving face images, and a more flexible and convenient search method is achieved.

CN113255488BActive Publication Date: 2024-11-12GUANGZHOU FANXING ENTERTAINMENT INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110522185.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-05-13
Publication Date
2024-11-12
Estimated Expiration
2041-05-13

AI Technical Summary

Technical Problem

In the prior art, anchor searches require pre-save facial images, resulting in limited and inflexible search methods.

Method used

By drawing line images by the user, obtaining and generating similar face images, directly searching for face features matching line images, and displaying the corresponding anchor account.

Benefits of technology

It improves the flexibility and convenience of anchor search and avoids the limitation of pre-saving face images. Users can directly search for interested anchors based on their preferences.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113255488B_ABST
    Figure CN113255488B_ABST
Patent Text Reader

Abstract

The embodiments of the present application disclose a method, device, computer equipment and storage medium for searching anchors, and belong to the field of computer technology. The method includes: obtaining a line image drawn in the current interface, the line image is used to indicate the facial features of the anchor to be searched; searching for a first facial image similar to the line image, the first facial image is the facial image of the anchor to be displayed, and the facial features of the first facial image are similar to the facial features indicated by the line image; and displaying the first anchor account corresponding to the first facial image in the current interface. In the anchor search method provided by the present application, the drawn line image can indicate the features of the anchor that the user is interested in, and the search can be performed directly based on the line image without pre-saving the facial image that the user is interested in, thereby avoiding limitations when searching for anchors and improving the flexibility and convenience of the search.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to a method, device, computer equipment and storage medium for searching an anchor. Background Art

[0002] With the widespread popularity of live broadcasting, more and more anchors are starting to broadcast live, and more and more users are watching live broadcasts. Since different users are interested in different anchors, how to accurately search for anchors that users are interested in has become an urgent problem to be solved.

[0003] In the related art, a face image selected by a user is determined from pre-saved face images, and a host matching the face image is displayed, so that the user can watch the live broadcast of the host. However, this search method requires pre-saving face images, which has limitations. Summary of the invention

[0004] The embodiments of the present application provide a method, device, computer equipment and storage medium for searching anchors, which avoid the limitations when searching anchors and improve the flexibility and convenience of searching. The technical solution is as follows:

[0005] On the one hand, a method for searching for an anchor is provided, the method comprising:

[0006] Obtaining a line image drawn in the current interface, where the line image is used to indicate facial features of the anchor to be searched;

[0007] Searching for a first facial image similar to the line image, the first facial image being a facial image of a host to be displayed, and facial features of the first facial image being similar to facial features indicated by the line image;

[0008] The first anchor account corresponding to the first facial image is displayed in the current interface.

[0009] In a possible implementation, searching for a first face image similar to the line image includes:

[0010] generating a second facial image corresponding to the line image, wherein facial features of the second facial image are the same as facial features indicated by the line image;

[0011] The first facial image similar to the second facial image is searched.

[0012] In a possible implementation, the current interface includes a canvas area and a generation control; and obtaining a line image drawn in the current interface includes:

[0013] Acquire the line image drawn in the canvas area;

[0014] The generating a second face image corresponding to the line image comprises:

[0015] In response to a triggering operation on the generating control, the second facial image is generated.

[0016] In a possible implementation, after generating the second face image corresponding to the line image, the method further includes:

[0017] The second facial image is displayed in the current interface.

[0018] In a possible implementation, displaying the second facial image in the current interface includes:

[0019] displaying the second facial image in the canvas area of ​​the current interface; or,

[0020] The second facial image is displayed in a preview area in the current interface, where the preview area is an area in the current interface that is different from the canvas area.

[0021] In a possible implementation, the current interface further includes a search control, and after displaying the second facial image in the current interface, displaying the first anchor account corresponding to the first facial image in the current interface includes:

[0022] In response to a triggering operation on the search control, displaying a search animation in the current interface, wherein the search animation is used to indicate that an image matching the second facial image is currently being searched for;

[0023] In response to finding the first anchor account, the search animation is stopped and the first anchor account is displayed.

[0024] In a possible implementation, the second facial image includes a plurality of facial parts, the current interface includes a sliding control corresponding to each facial part, and the sliding control is used to adjust the corresponding facial part; after displaying the second facial image in the current interface, the method further includes:

[0025] In response to a sliding operation on a sliding control corresponding to any facial part, the any facial part in the second facial image is adjusted to obtain an adjusted second facial image.

[0026] In a possible implementation, in response to a sliding operation on a sliding control corresponding to any facial part, adjusting any facial part in the second facial image to obtain the adjusted second facial image includes:

[0027] In response to a sliding operation on a sliding control corresponding to any one of the facial parts, obtaining an adjustment parameter corresponding to the sliding operation, wherein the adjustment parameter is used to indicate an adjustment range for the any one of the facial parts;

[0028] According to the adjustment parameters, any one facial part is adjusted to obtain the adjusted second facial image.

[0029] In one possible implementation, the method further includes:

[0030] Selecting a first face part from the plurality of face parts, wherein the first face part is adjusted more times than other face parts;

[0031] Selecting, from a plurality of candidate facial images, a third facial image whose second facial part is similar to the first facial part, wherein the second facial part is a facial part of the same type as the first facial part in the third facial image;

[0032] The second anchor account corresponding to the third facial image is displayed in the current interface.

[0033] In a possible implementation, after acquiring the line image drawn in the current interface, the method further includes:

[0034] In response to the second face image corresponding to the line image not being generated, a prompt message is displayed in the current interface, where the prompt message is used to prompt the line image to be redrawn.

[0035] In a possible implementation, in response to failure to generate the second face image corresponding to the line image, displaying prompt information in the current interface includes:

[0036] In response to the fact that a facial image corresponding to the line image is not generated, an effect of the virtual anchor outputting the prompt information is displayed in the current interface.

[0037] In a possible implementation, searching for a first face image similar to the line image includes:

[0038] The first facial image similar to the line image is selected from a plurality of candidate facial images in an image library, wherein the image library includes facial images of a plurality of hosts to be displayed.

[0039] In a possible implementation, selecting the first face image similar to the line image from a plurality of candidate face images in an image library includes:

[0040] Acquire the facial similarity between the line image and the plurality of candidate facial images;

[0041] Based on multiple facial similarities, the first facial image is selected from the multiple candidate facial images, and the facial similarity corresponding to the first facial image is greater than the facial similarities corresponding to other candidate facial images.

[0042] In a possible implementation, the acquiring the facial similarity between the line image and the plurality of candidate facial images includes:

[0043] Performing feature extraction on the line image to obtain a first feature of the line image;

[0044] Extracting features from the plurality of candidate face images respectively to obtain second features of the plurality of candidate face images;

[0045] Based on the first feature and multiple second features, the facial similarity between the line image and each candidate facial image is obtained.

[0046] In a possible implementation, after displaying the first anchor account corresponding to the first facial image in the current interface, the method further includes:

[0047] In response to the triggering operation on the first anchor account, the live broadcast interface corresponding to the live broadcast room of the first anchor account is displayed.

[0048] In a possible implementation, displaying the first anchor account corresponding to the first facial image in the current interface includes:

[0049] Displaying the first anchor account and summary information corresponding to the first anchor account in the current interface; or,

[0050] The first anchor account and the anchor information list corresponding to the first anchor account are displayed in the current interface.

[0051] In a possible implementation, the line image includes a plurality of lines. After acquiring the line image drawn in the current interface, the method further includes:

[0052] According to at least one of the shape or position of each line in the line image, the line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face;

[0053] For any region, searching for a fourth face image whose third face part is similar to the any region, wherein the third face part is the face part in the fourth face image that is the same as the face part indicated by the any region;

[0054] The third anchor account corresponding to the fourth facial image is displayed in the current interface.

[0055] In a possible implementation, after searching for the first face image similar to the line image, the method further includes:

[0056] Respectively determining the part similarities between a plurality of face parts in the first face image and corresponding areas in the line image, wherein the line image includes a plurality of areas, and a line in each area is used to indicate a face part;

[0057] Based on the multiple part similarities, selecting a fourth face part from the multiple face parts, the part similarity corresponding to the fourth face part is greater than the part similarities corresponding to the other face parts;

[0058] The displaying the first anchor account corresponding to the first face image in the current interface includes:

[0059] The first anchor account corresponding to the first facial image and the description information corresponding to the fourth facial part are displayed in the current interface, and the description information is used to describe the fourth facial part as a facial part similar to the first facial image and the line image.

[0060] In a possible implementation, the line image includes a plurality of lines. After acquiring the line image drawn in the current interface, the method further includes:

[0061] According to at least one of the shape or position of each line in the line image, the line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face;

[0062] The lines in at least one area of ​​the line image are adjusted to obtain the adjusted line image.

[0063] In a possible implementation, generating a second face image corresponding to the line image includes:

[0064] According to at least one of the shape or position of each line in the line image, the line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face;

[0065] Obtaining line features corresponding to the lines in each area, decoding the obtained line features, and obtaining the face part corresponding to each area;

[0066] The obtained multiple facial parts are synthesized to obtain the second facial image.

[0067] In a possible implementation, generating a second face image corresponding to the line image includes:

[0068] Based on a facial image generation model, the line image is processed to obtain the second facial image corresponding to the line image.

[0069] In another aspect, a host search device is provided, the device comprising:

[0070] A line image acquisition module, used to acquire a line image drawn in the current interface, wherein the line image is used to indicate the facial features of the anchor to be searched;

[0071] An image search module, used to search for a first face image similar to the line image, the first face image being a face image of a host to be displayed, and the face features of the first face image being similar to the face features indicated by the line image;

[0072] An account display module is used to display the first anchor account corresponding to the first facial image in the current interface.

[0073] In a possible implementation, the image search module includes:

[0074] A facial image generating unit, configured to generate a second facial image corresponding to the line image, wherein facial features of the second facial image are the same as those indicated by the line image;

[0075] An image searching unit is used to search for the first facial image similar to the second facial image.

[0076] In a possible implementation, the current interface includes a canvas area and a generation control; the line image acquisition module is used to acquire the line image drawn in the canvas area;

[0077] The facial image generating unit is used to generate the second facial image in response to a triggering operation on the generating control.

[0078] In a possible implementation, the image search module further includes:

[0079] A face image display unit is used to display the second face image in the current interface.

[0080] In a possible implementation, the face image display unit is used to:

[0081] displaying the second facial image in the canvas area of ​​the current interface; or,

[0082] The second facial image is displayed in a preview area in the current interface, where the preview area is an area in the current interface that is different from the canvas area.

[0083] In a possible implementation, the current interface further includes a search control, and the account display module includes:

[0084] a search animation display unit, configured to display a search animation in the current interface in response to a triggering operation on the search control, wherein the search animation is configured to indicate that an image matching the second facial image is currently being searched for;

[0085] An account display unit is used to stop displaying the search animation and display the first anchor account in response to having searched for the first anchor account.

[0086] In a possible implementation, the second face image includes a plurality of face parts, the current interface includes a sliding control corresponding to each face part, and the sliding control is used to adjust the corresponding face part; the image search module further includes:

[0087] The facial image adjustment unit is used to adjust any facial part in the second facial image in response to a sliding operation of a sliding control corresponding to any facial part to obtain the adjusted second facial image.

[0088] In a possible implementation, the face image adjustment unit is used to:

[0089] In response to a sliding operation on a sliding control corresponding to any one of the facial parts, obtaining an adjustment parameter corresponding to the sliding operation, wherein the adjustment parameter is used to indicate an adjustment range for the any one of the facial parts;

[0090] According to the adjustment parameters, any one facial part is adjusted to obtain the adjusted second facial image.

[0091] In a possible implementation, the account display unit is further used to:

[0092] Selecting a first face part from the plurality of face parts, wherein the first face part is adjusted more times than other face parts;

[0093] Selecting, from a plurality of candidate facial images, a third facial image whose second facial part is similar to the first facial part, wherein the second facial part is a facial part of the same type as the first facial part in the third facial image;

[0094] The second anchor account corresponding to the third facial image is displayed in the current interface.

[0095] In a possible implementation, the device further includes:

[0096] The prompt information display module is used to display prompt information in the current interface in response to the second face image corresponding to the line image not being generated, wherein the prompt information is used to prompt the redrawing of the line image.

[0097] In a possible implementation, the prompt information display module is used to display the effect of the prompt information output by the virtual anchor in the current interface in response to the failure to generate a facial image corresponding to the line image.

[0098] In one possible implementation, the image search module is used to select the first facial image that is similar to the line image from a plurality of candidate facial images in an image library, and the image library includes facial images of a plurality of hosts to be displayed.

[0099] In a possible implementation, the image search module is used to:

[0100] Acquire the facial similarity between the line image and the plurality of candidate facial images;

[0101] The first facial image is selected from the multiple candidate facial images based on multiple facial similarities, and the facial similarity corresponding to the first facial image is greater than the facial similarities corresponding to other candidate facial images.

[0102] In a possible implementation, the image search module is used to:

[0103] Performing feature extraction on the line image to obtain a first feature of the line image;

[0104] Extracting features from the plurality of candidate face images respectively to obtain second features of the plurality of candidate face images;

[0105] Based on the first feature and multiple second features, the facial similarity between the line image and each candidate facial image is obtained.

[0106] In a possible implementation, the device further includes:

[0107] The live broadcast interface display module is used to display the live broadcast interface corresponding to the live broadcast room of the first anchor account in response to the trigger operation of the first anchor account.

[0108] In a possible implementation, the account display module is used to:

[0109] Displaying the first anchor account and summary information corresponding to the first anchor account in the current interface; or,

[0110] The first anchor account and the anchor information list corresponding to the first anchor account are displayed in the current interface.

[0111] In a possible implementation, the line image includes a plurality of lines, and the image search module is further configured to:

[0112] According to at least one of the shape or position of each line in the line image, the line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face;

[0113] For any region, searching for a fourth face image whose third face part is similar to the any region, wherein the third face part is the face part in the fourth face image that is the same as the face part indicated by the any region;

[0114] The account display module is also used to display the third anchor account corresponding to the fourth facial image in the current interface.

[0115] In a possible implementation, the image search module is further used to:

[0116] Respectively determining the part similarities between a plurality of face parts in the first face image and corresponding areas in the line image, wherein the line image includes a plurality of areas, and a line in each area is used to indicate a face part;

[0117] Based on the multiple part similarities, selecting a fourth face part from the multiple face parts, the part similarity corresponding to the fourth face part is greater than the part similarities corresponding to the other face parts;

[0118] The account display module is also used to display the first anchor account corresponding to the first facial image and the descriptive information corresponding to the fourth facial part in the current interface, and the descriptive information is used to describe the fourth facial part as a facial part similar to the first facial image and the line image.

[0119] In a possible implementation manner, the line image includes a plurality of lines, and the device further includes:

[0120] A line image adjustment module, used for dividing the line image into a plurality of regions according to at least one of a shape or a position of each line in the line image, wherein the lines in each region are used to indicate a part of a human face;

[0121] The line image adjustment module is further used to adjust the lines in at least one area of ​​the line image to obtain the adjusted line image.

[0122] In a possible implementation, the face image generating unit is used to:

[0123] According to at least one of a shape or a position of each line in the line image, the line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face;

[0124] Obtaining line features corresponding to the lines in each area, decoding the obtained line features, and obtaining the face part corresponding to each area;

[0125] The obtained multiple facial parts are synthesized to obtain the second facial image.

[0126] In a possible implementation, the face image generating unit is used to:

[0127] Based on a facial image generation model, the line image is processed to obtain the second facial image corresponding to the line image.

[0128] On the other hand, a computer device is provided, comprising a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the operations performed in the anchor search method described in the above aspects.

[0129] On the other hand, a computer-readable storage medium is provided, in which at least one program code is stored. The at least one program code is loaded and executed by a processor to implement the operations performed in the anchor search method described in the above aspects.

[0130] On the other hand, a computer program product or a computer program is provided, wherein the computer program product or the computer program comprises a computer program code, wherein the computer program code is stored in a computer-readable storage medium, and wherein the computer program code is loaded and executed by a processor to implement the operations performed in the anchor search method as described in the above aspects.

[0131] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0132] The method, apparatus, computer equipment and storage medium provided in the embodiments of the present application can search for a face image matching a line image drawn by the user, and display the anchor account corresponding to the face image. In this new anchor search method, the user can draw a favorite line image according to his or her preferences. The drawn line image can indicate the characteristics of the anchor that the user is interested in. The user can search directly based on the line image without pre-saving the face image that the user is interested in. This avoids the limitations of anchor search and improves the flexibility and convenience of the search. BRIEF DESCRIPTION OF THE DRAWINGS

[0133] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0134] Figure 1 It is a schematic diagram of an implementation environment provided by an embodiment of the present application;

[0135] Figure 2 is a flow chart of a method for searching anchors provided in an embodiment of the present application;

[0136] Figure 3 is a flow chart of another anchor search method provided by an embodiment of the present application;

[0137] Figure 4 is a schematic diagram of a current interface provided by an embodiment of the present application;

[0138] Figure 5 is a flow chart of another anchor search method provided by an embodiment of the present application;

[0139] Figure 6 It is a structural diagram of a host search device provided in an embodiment of the present application;

[0140] Figure 7 is a structural diagram of another anchor search device provided in an embodiment of the present application;

[0141] Figure 8 is a schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0142] Fig. 9 It is a structural diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0143] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0144] It is understood that the terms "first", "second", etc. used in this application can be used in this article to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of this application, the first anchor account can be called the second anchor account, and the second anchor account can be called the first anchor account.

[0145] The terms "at least one", "a plurality of", "each", "any" and the like used in this application include one, two or more than two, a plurality of includes two or more than two, each refers to each of the corresponding plurality, and any refers to any one of the plurality. For example, the plurality of facial images include three facial images, and each facial image refers to each of the three facial images, and any refers to any one of the three facial images, which may be the first, the second, or the third.

[0146] Figure 1 is a schematic diagram of an implementation environment provided by an embodiment of the present application. Figure 1 , the implementation environment includes a terminal 101 and a server 102. The terminal 101 and the server 102 are connected via a wireless or wired network.

[0147] The target application served by the server 102 is installed on the terminal 101, and the terminal 101 can realize functions such as data transmission and message interaction through the target application. Optionally, the terminal 101 is a computer, a mobile phone, a tablet computer or other terminals. Optionally, the target application is a target application in the operating system of the terminal 101, or a target application provided by a third party. For example, the target application is a live broadcast application, which has a live broadcast function. Of course, the content sharing application can also have other functions, such as shopping functions, game functions, etc. Optionally, the server 102 is the background server of the target application or a cloud server that provides cloud computing and cloud storage services.

[0148] The method provided in the embodiment of the present application can be applied to the scenario of searching for anchors.

[0149] For example, if a user wants to search for a host to watch a live broadcast, but the user does not know the host's account, the host search method provided by the present application can be used to draw a line image of interest in the search interface of the live broadcast application. The line image can reflect the characteristics of the host that the user is interested in. Then, the terminal searches for the face image of the host similar to the line image based on the line image, and displays the host account corresponding to the face image in the search interface. The user clicks on the host account to enter the host's live broadcast room and watch the live broadcast.

[0150] Figure 2 1 is a flow chart of a method for searching anchors provided in an embodiment of the present application. The execution subject of the embodiment of the present application is a terminal. Figure 2 , the method comprises the following steps:

[0151] 201. The terminal obtains a line image drawn in the current interface.

[0152] When a user searches for a host that he wants to view, he draws a line image in the current interface. The line image can reflect the characteristics of the host that the user wants to view, that is, the line image is used to indicate the facial features of the host to be searched. The current interface is an interface for searching for the host's host account, and the line image is drawn by the user based on the host that he is interested in.

[0153] 202. The terminal searches for a first face image similar to the line image.

[0154] The first face image is a face image of the anchor to be displayed, and the face features of the first face image are similar to the face features indicated by the line image, that is, the terminal can search for face images similar to the face features according to the face features indicated by the line image, thereby searching for the anchor that the user is interested in. The terminal can search for the first face image according to the face similarity between the line image and the face image, or can use other methods to search, and the embodiment of the present application does not limit this.

[0155] 203. The terminal displays the first anchor account corresponding to the first facial image in the current interface.

[0156] After the terminal searches for the first facial image, it can determine the anchor corresponding to the first facial image, and display the anchor's account in the current interface. The user can click on the anchor account to enter the live broadcast room corresponding to the anchor account to watch the live broadcast.

[0157] The method provided in the embodiment of the present application searches for a face image that matches a line image drawn by the user, and displays the anchor account corresponding to the face image. In this new anchor search method, the user can draw a favorite line image according to his or her preferences. The drawn line image can indicate the characteristics of the anchor that the user is interested in. The user can search directly based on the line image without pre-saving the face image that the user is interested in. This avoids the limitations of anchor search and improves the flexibility and convenience of the search.

[0158] Figure 3 is a flow chart of another anchor search method provided by an embodiment of the present application. The execution subject of the embodiment of the present application is a terminal. Figure 3 , the method comprising:

[0159] 301. The terminal obtains a line image drawn in the current interface.

[0160] In the embodiment of the present application, the terminal displays the current interface, and the user draws a line image in the current interface, and the line image is used to indicate the facial features of the anchor to be searched. For example, the user can directly touch the current interface with a finger to draw the line image, or the user can draw in other ways. The embodiment of the present application does not limit the way in which the user draws the line image.

[0161] In one possible implementation, the current interface includes a canvas area, in which the user draws a line image. Figure 4 In the current interface shown, a line image is drawn in the canvas area. Optionally, the canvas area is a blank area, or a face frame is displayed in the canvas area, and the face frame is used to indicate the position of each facial part in the face. The user can draw lines at the corresponding positions according to the positions of the facial parts indicated by the face frame, so as to avoid the line image drawn being greatly different from the face.

[0162] In a possible implementation, due to the different drawing skills of different users, the line images drawn by some users are difficult to reflect the facial features. In this case, after the terminal obtains the line image drawn in the current interface, it adjusts the line image so that the adjusted line image can reflect the facial features. The terminal recognizes the line image according to the distribution of each facial part in the face, and divides the line image into multiple areas according to at least one of the shape or position of each line in the line image, that is, at least one line in the line image indicating a facial part is divided into one area, and then the terminal adjusts the lines in at least one area to obtain the adjusted line image. Among them, the shape or position of each line can indicate the facial part represented by the line.

[0163] For example, the terminal divides the line image into eye area, nose area, mouth area, eyebrow area, hair area and other areas according to the distribution of various facial parts in the face. When the lines in the nose area are not located on the vertical line where the middle position of the eye area is located, it means that the position of the lines in the nose area is inaccurate, and it is necessary to move the position of the lines in the nose area so that the lines are located on the vertical line where the middle position of the eye area is located, so that the facial parts indicated by the lines in each area of ​​the line image are consistent with the distribution of various facial parts in a real face.

[0164] In a possible implementation, a target application is installed in the terminal, and the terminal draws a line image in the current interface of the target application, wherein the target application is a live broadcast application, a video playback application, and the like.

[0165] Regarding the display of the current interface, in one possible implementation, the terminal starts the target application, the user triggers the search bar in any interface of the target application, and the terminal displays the current interface in response to the triggering operation of the search bar.

[0166] 302. The terminal generates a second face image corresponding to the line image.

[0167] The facial features of the second facial image are the same as the facial features indicated by the line image, and the second facial image has the same display effect as the actually captured facial image.

[0168] In one possible implementation, see Figure 4 The current interface includes a generation control. After the terminal obtains the line image drawn in the canvas area, the user triggers the generation control. The terminal generates a second face image corresponding to the line image in response to the triggering operation of the generation control.

[0169] After the terminal generates the second facial image, in one possible implementation, the terminal displays the second facial image in the current interface. Further, the terminal displays the second facial image in the canvas area; or, the terminal displays the second facial image in the preview area in the current interface, and the preview area is an area in the current interface that is different from the canvas area. For example, the preview area is located below the canvas area, or above the canvas area. This application does not limit the positions of the canvas area and the preview area in the current interface.

[0170] In one possible implementation, when there are a canvas area and a preview area in the current interface, the terminal displays the line image in the canvas area and displays the generated second face image in the preview area. The user can then modify the line image again. After the modification, the user triggers the generation control again. The terminal regenerates the second face image corresponding to the modified line image in response to the triggering operation of the generation control, and displays the regenerated second face image in the preview area.

[0171] In another possible implementation, after the terminal generates the second facial image, step 303 is directly executed without displaying the second facial image.

[0172] In the embodiment of the present application, the terminal generates the second face image in the following manner:

[0173] The first method: the terminal processes the line image based on the face image generation model to obtain a second face image corresponding to the line image. The face image generation model is used to convert the line image into a face image, and the face image generation model can be trained by the terminal or sent to the terminal after being trained by other devices.

[0174] The training process of the face image generation model is as follows: obtain a sample line image and a corresponding sample face image, process the sample line image based on the face image generation model to obtain a predicted face image, and adjust the parameters in the face image generation model according to the difference between the sample face image and the predicted face image until the predicted face image and the sample face image are sufficiently similar, indicating that the training of the face image generation model is completed. Among them, it can be determined whether the predicted face image and the sample face image are similar according to the face similarity between the predicted face image and the sample face image.

[0175] The second method: the terminal divides the line image into multiple areas according to at least one of the shape or position of each line in the line image; obtains the line features corresponding to the lines in each area, decodes the obtained line features, and obtains the facial parts corresponding to each area; synthesizes the obtained multiple facial parts to obtain a second facial image. When obtaining the line features, the line features corresponding to the lines in a region are obtained based on all the lines in the region, so that the obtained line features can reflect the features of the facial parts corresponding to the region. When synthesizing the second facial image, the skin color of different facial parts is also adjusted to avoid uneven skin color in the synthesized second facial image.

[0176] For different regions, the line features corresponding to each region are decoded respectively to obtain the face part corresponding to each region. In the case of using a decoder to decode the line features, the corresponding decoders are trained for different regions, and based on the decoder corresponding to each region, the line features corresponding to the region are decoded to obtain the face part corresponding to the region.

[0177] The embodiments of the present application only use the above two methods of generating facial images corresponding to line images as examples for illustration. In another embodiment, other methods may be used to generate facial images corresponding to line images. The embodiments of the present application do not limit the methods of generating facial images.

[0178] In a possible implementation, after the terminal generates the second facial image, the second facial image is displayed. If the generated second facial image is not of interest to the user, the user can further adjust the second facial image. Since the second facial image includes multiple facial parts, for example, the second facial image includes eyes, nose, mouth, eyebrows, ears and other parts, a sliding control corresponding to each facial part is provided in the current interface, and the sliding control is used to adjust the corresponding facial part. Of course, the current interface may also include a sliding control for adjusting skin color and hair color.

[0179] In response to the sliding operation of the sliding control corresponding to any facial part, the terminal adjusts any facial part in the second facial image to obtain the adjusted second facial image. For example, if the user slides the sliding control corresponding to the eyes, the terminal adjusts the size of the eyes based on the final adjustment range of the sliding control; if the user slides the sliding control corresponding to the skin color, the terminal adjusts the color of the facial skin based on the final adjustment range of the sliding control.

[0180] In a possible implementation, the terminal responds to a sliding operation on a sliding control corresponding to any facial part, obtains an adjustment parameter corresponding to the sliding operation, and the adjustment parameter is used to indicate the adjustment range of any facial part. The terminal adjusts any facial part according to the adjustment parameter to obtain an adjusted facial image. For example, the adjustment parameter corresponding to the sliding control corresponding to the eyes is 0-10, and different adjustment parameters correspond to different increase ranges. 0 means no adjustment of the eyes, 10 means increasing the eyes by 10%, and when the adjustment parameter corresponding to the sliding control finally adjusted is 6, the eyes are increased by 6%.

[0181] In addition, in a possible implementation, if the line image drawn by the user is quite different from the face, and the terminal cannot recognize that each area in the line image corresponds to the facial part of the face, then the second facial image corresponding to the line image cannot be generated. In this case, in response to the failure to generate the second facial image corresponding to the line image, the terminal displays a prompt message in the current interface, and the prompt message is used to prompt the user to redraw the line image. For example, the prompt message is "I have everything you like, let's try again, okay!".

[0182] Furthermore, the terminal not only displays the prompt information, but also can display a virtual object, that is, in response to the second face image corresponding to the line image not being generated, the terminal displays the effect of the prompt information output by the virtual object in the current interface. For example, the virtual object is displayed in the current interface, and a dialog box is displayed next to the virtual object, in which the prompt information is displayed, so as to present the effect that the prompt information is spoken by the virtual object.

[0183] The virtual object may be a static virtual object or a dynamic virtual object, and the virtual object may be any virtual object selected from a virtual object library, wherein the virtual object library stores a plurality of virtual objects. In addition, the present application does not limit the image of the virtual object, for example, the virtual object may be a cat, a dog, a child or other images.

[0184] It should be noted that the embodiment of the present application only takes the example of a terminal generating a second facial image corresponding to a line image. In another embodiment, the terminal interacts with a server, and the terminal sends the line image drawn in the current interface to the server. The server generates a second facial image corresponding to the line image based on the received line image.

[0185] 303. The terminal searches for a first facial image similar to the second facial image.

[0186] The first facial image is a facial image actually taken, and the similarity between the first facial image and the second facial image means that facial features in the first facial image are similar to facial features in the second facial image.

[0187] In one possible implementation, see Figure 4 , the current interface also includes a search control. When the second face image is displayed in the current interface, the user triggers the search control after viewing the second face image. In response to the triggering operation of the search control, the terminal displays a search animation in the current interface, and the search animation is used to indicate that an image matching the second face image is currently being searched. The search animation can be any animation, for example, the search animation is a dynamic loop playback of the four words "Searching".

[0188] In a possible implementation, an image library is stored in the terminal, and the image library includes facial images of multiple anchors to be displayed, and there is a corresponding relationship between the facial images in the image library and the anchors. The terminal selects a first facial image similar to a second facial image from multiple candidate facial images in the image library. For example, the image library stores facial images of anchors already in the live broadcast platform, and the terminal searches for the first facial image from the image library, thereby ensuring that the anchor searched is an anchor already in the live broadcast platform.

[0189] In a possible implementation, the terminal obtains the facial similarity between the third facial image and multiple candidate facial images, selects a first facial image from the multiple candidate facial images, and the facial similarity corresponding to the first facial image is greater than the facial similarities corresponding to the other candidate facial images, that is, the candidate facial image with the largest facial similarity among the multiple candidate facial images is determined as the first facial image. The facial similarity is used to indicate the degree of similarity between different facial images.

[0190] Among them, the terminal can determine the face similarity based on the features of the face images. The terminal extracts features from the second face image to obtain the third feature of the second face image; extracts features from multiple candidate face images respectively to obtain the second features of multiple candidate face images; and obtains the face similarity between the second face image and each candidate face image based on the third feature and the multiple second features.

[0191] It should be noted that the embodiment of the present application is only described by taking the terminal searching for a first facial image similar to a second facial image as an example. In another embodiment, the terminal interacts with the server, and the terminal sends the generated second facial image to the server, and the server searches for a first facial image similar to the second facial image based on the second facial image; or the terminal sends a line image to the server, and the server generates a second facial image based on the line image and searches for a first facial image similar to the second facial image. In one possible implementation, the terminal displays a search animation while the server is searching for the first facial image.

[0192] Another point that needs to be explained is that the above embodiment is only described by taking the example of searching for a first facial image that matches the second facial image. In another embodiment, multiple first facial images that match the second facial image can be searched. In one possible implementation, the terminal obtains the facial similarity between the second facial image and multiple candidate facial images, and selects a reference number of first facial images from the multiple candidate facial images according to the multiple facial similarities, and the facial similarities corresponding to the reference number of first facial images are greater than the facial similarities corresponding to the other candidate facial images. The reference number is any number, for example, the reference number is 10, 20 or other numbers.

[0193] 304. The terminal displays the first anchor account corresponding to the first facial image in the current interface.

[0194] There is a corresponding relationship between the candidate facial images stored in the terminal and the anchors. After searching for a similar first facial image, the anchor to which the first facial image belongs can be determined based on the corresponding relationship, and the first anchor account corresponding to the anchor can be determined, and the first anchor account can be displayed in the current interface.

[0195] In a possible implementation, after the terminal searches for the first anchor account, it stops displaying the search animation and displays the first anchor account in the current interface.

[0196] In one possible implementation, when the terminal searches for multiple first facial images, the terminal displays the first anchor accounts corresponding to the multiple first facial images in the current interface, and the user can select any first anchor account from the multiple first anchor accounts.

[0197] In a possible implementation, the terminal can display not only the first anchor account but also the anchor information of the first anchor account in the current interface. For example, the first anchor account and the summary information corresponding to the first anchor account are displayed in the current interface, and the summary information is used to introduce the anchor corresponding to the first anchor account; or, the first anchor account and the anchor information list corresponding to the first anchor account are displayed in the current interface, and the anchor information list includes anchor profile, anchor achievements and other information; or, the first anchor account, the avatar corresponding to the first anchor account, and the anchor profile corresponding to the first anchor account and other information can be displayed in the current interface.

[0198] In one possible implementation, the terminal separately determines the part similarities between multiple facial parts in the first facial image and the corresponding areas in the line image, and the part similarities are used to indicate the degree of similarity between the facial parts in the facial image and the corresponding areas in the line image, for example, the degree of similarity between the eyes in the facial image and the eye areas in the line image; based on the multiple part similarities, a fourth facial part is selected from the multiple facial parts, and the part similarity corresponding to the fourth facial part is greater than the part similarities corresponding to other facial parts; the first anchor account corresponding to the first facial image and the description information corresponding to the fourth facial part are displayed in the current interface, and the description information is used to describe the fourth facial part as a similar facial part between the first facial image and the line image.

[0199] For example, the terminal determines that the face image of anchor A is similar to the line image, and determines the part similarity between multiple face parts in the face image of anchor A and the corresponding areas in the line image, and determines that the eyes of anchor A are the most similar to the eyes in the drawn line image. In this case, not only the anchor account of anchor A is displayed in the current interface, but also the description information "She meets the requirements in all aspects, especially the eyes you love". Or, if the mouth of anchor B is the most similar to the mouth in the drawn line image, not only the anchor account of anchor B is displayed in the current interface, but also the description information "She meets the requirements in all aspects, especially the mouth you love".

[0200] In addition, after the terminal displays the first anchor account in the above manner, if the user triggers the first anchor account, it is considered that the anchor that the user is interested in is successfully searched, and the facial features of the first face image are stored in the server. When the target application is started again later, the anchor of interest can be recommended to the user based on the stored facial features.

[0201] It should be noted that the above embodiment is only described by using the second facial image to search for a similar first facial image as an example. In another embodiment, after the second facial image is generated, the user can adjust each facial part in the second facial image, and the adjustment process can reflect the facial part that the user is interested in. Therefore, the terminal can search for facial images based on the adjusted facial part in the second facial image.

[0202] The terminal selects a first facial part from multiple facial parts, and the number of adjustments of the first facial part is greater than the number of adjustments of other facial parts, that is, the facial part with the largest number of adjustments among the multiple facial parts is determined as the first facial part; from multiple candidate facial images, a third facial image is selected whose second facial part is similar to the first facial part, wherein the second facial part is a facial part of the same type as the first facial part in the third facial image; and the second anchor account corresponding to the third facial image is displayed. Among them, the second anchor account and the first anchor account can be the same or different; the same type means that the two facial parts belong to the same type, for example, if the first facial part is an eye, then the second facial part is also an eye. For example, if the user has adjusted the eyes the most times, then a third facial image whose eyes are similar to the eyes in the first facial image is selected from multiple candidate images.

[0203] In one possible implementation, the terminal can select multiple third facial images in which the second facial parts are similar to the first facial parts from multiple candidate facial images, and display the second anchor accounts corresponding to the multiple third facial images, that is, display multiple second anchor accounts in the current interface.

[0204] In a possible implementation, the terminal displays only the at least one first anchor account that is searched; or displays only the at least one second anchor account that is searched; or displays the at least one first anchor account and at least one second anchor account that are searched. When at least one first anchor account and at least one second anchor account are displayed at the same time, this application does not limit the display order. For example, at least one first anchor account may be displayed first, and at least one second anchor account may be displayed below the at least one first anchor account.

[0205] One thing that needs to be explained is that the embodiment of the present application is only explained by taking the example that the terminal first generates a second facial image corresponding to the line image and then searches for the anchor account based on the second facial image. In another embodiment, the terminal can directly search for the anchor account based on the line image, that is, steps 302 and 303 are no longer executed.

[0206] In a possible implementation, the current interface includes a search control. After the user draws a line image in the current interface, the search control is triggered. In response to the triggering operation of the search control, the terminal displays a search animation in the current interface, and the search animation is used to indicate that an image matching the line image is currently being searched. The search animation can be any animation, for example, the search animation is a dynamic loop playback of the four words "Searching".

[0207] In one possible implementation, the terminal performs feature extraction on the line image to obtain a first feature of the line image; performs feature extraction on multiple candidate face images in the image library respectively to obtain second features of the multiple candidate face images; based on the first feature and the second feature, obtains the facial similarity between the line image and each candidate face image, and determines the candidate face image with the greatest corresponding facial similarity among the multiple candidate face images as the first face image.

[0208] Another point that needs to be explained is that Figure 3 In the embodiment shown, a similar first facial image is directly searched based on the complete line image. In another embodiment, the terminal may also divide the line image into multiple areas based on at least one of the shape or position of each line in the line image, and the lines in each area are used to indicate a facial part; for any area, a fourth facial image whose third facial part is similar to any area is searched, wherein the third facial part is the same facial part in the fourth facial image as the facial part indicated by any area; and the third anchor account corresponding to the fourth facial image is displayed in the current interface. In other words, based on each area in the line image, a fourth facial image whose facial part in the facial image is similar to the facial part indicated by the area is searched.

[0209] The method provided in the embodiment of the present application searches for a face image that matches a line image drawn by the user, and displays the anchor account corresponding to the face image. In this new anchor search method, the user can draw a favorite line image according to his or her preferences. The drawn line image can indicate the characteristics of the anchor that the user is interested in. The user can search directly based on the line image without pre-saving the face image that the user is interested in. This avoids the limitations of anchor search and improves the flexibility and convenience of the search.

[0210] Moreover, through the user's adjustment operation on the facial area in the generated second facial image, the first facial part that the user is interested in can be determined, and then based on the first facial part that the user is interested in, a third facial image whose second facial part is similar to the first facial part can be searched, thereby realizing the search for the anchor of interest to the user based on the facial part.

[0211] Furthermore, displaying a search animation during the search process can remind the user that a search is currently in progress, thereby preventing the user from mistakenly believing that the search has not yet started.

[0212] In one possible implementation, the above Figure 3 When the anchor search method shown in the figure is applied in the live broadcast scenario, the anchor to be searched is the anchor account. For the anchor account search process, see Figure 5 As shown:

[0213] 501. The terminal obtains a line image drawn in a canvas area in a search interface.

[0214] 502. The terminal adjusts the line image in response to a triggering operation on a generation control in the search interface, and generates a second face image corresponding to the line image based on the adjusted line image.

[0215] 503. The terminal displays the second facial image in a preview area in the search interface.

[0216] 504. The terminal adjusts the second facial image in response to the adjustment operation on the facial image, and determines the first facial part with the largest number of adjustments in the first facial image.

[0217] 505. In response to a triggering operation on a search control in a search interface, the terminal searches for a plurality of first facial images similar to the adjusted second facial image and a plurality of third facial images whose second facial parts are similar to the first facial parts while displaying a search animation in the search interface.

[0218] 506. The terminal stops displaying the search animation, and displays the first anchor account corresponding to the multiple first facial images and the second anchor account corresponding to the multiple third facial images in the search interface.

[0219] In one possible implementation, in a live broadcast scenario, after the terminal searches for the first facial image or the third facial image that is similar to the second facial image, it determines whether the live broadcast room of the second anchor account or the first anchor account is currently broadcasting live. If it is broadcasting live, the anchor account is displayed in the search interface; if it is not broadcasting live, the anchor account is not displayed.

[0220] 507. In response to a triggering operation on any one of the multiple first anchor accounts and the multiple second anchor accounts, the terminal displays a live broadcast interface corresponding to the anchor room of any one of the anchor accounts.

[0221] In the embodiment of the present application, the implementation method of searching for the anchor account is the same as the above Figure 3 The implementation method of searching for anchors in the illustrated embodiment is similar and will not be described in detail here.

[0222] Figure 6is a structural diagram of a host search device provided in an embodiment of the present application. Figure 6 , the device comprises:

[0223] The line image acquisition module 601 is used to acquire the line image drawn in the current interface, where the line image is used to indicate the facial features of the anchor to be searched;

[0224] An image search module 602 is used to search for a first face image similar to the line image, the first face image being a face image of a host to be displayed, and the face features of the first face image being similar to the face features indicated by the line image;

[0225] The account display module 603 is used to display the first anchor account corresponding to the first facial image in the current interface.

[0226] The device provided in the embodiment of the present application searches for a face image that matches a line image drawn by the user, and displays the anchor account corresponding to the face image. In this new anchor search method, the user can draw a favorite line image according to his or her preferences. The drawn line image can indicate the characteristics of the anchor that the user is interested in. The user can search directly based on the line image without pre-saving the face image that the user is interested in. This avoids the limitations of anchor search and improves the flexibility and convenience of the search.

[0227] In one possible implementation, see Figure 7 , the image search module 602 comprises:

[0228] A face image generating unit 6021 is used to generate a second face image corresponding to the line image, and the face features of the second face image are the same as the face features indicated by the line image;

[0229] The image searching unit 6022 is used to search for a first facial image similar to a second facial image.

[0230] In a possible implementation, the current interface includes a canvas area and a generation control; a line image acquisition module 601, used to acquire a line image drawn in the canvas area;

[0231] The face image generating unit 6021 is used to generate a second face image in response to a triggering operation on the generating control.

[0232] In one possible implementation, see Figure 7 , the image search module 602 further includes:

[0233] The face image display unit 6023 is used to display the first face image in the current interface.

[0234] In one possible implementation, see Figure 7 , the face image display unit 6023 is used to:

[0235] Displaying the second face image in the canvas area of ​​the current interface; or,

[0236] The second face image is displayed in a preview area in the current interface, where the preview area is an area in the current interface that is different from the canvas area.

[0237] In one possible implementation, the current interface also includes a search control, see Figure 7 , the account display module 603 includes:

[0238] A search animation display unit 6031 is used to display a search animation in the current interface in response to a trigger operation on the search control, where the search animation is used to indicate that an image matching the first face image is currently being searched for;

[0239] The account display unit 6032 is used to stop displaying the search animation and display the first anchor account in response to the first anchor account having been searched.

[0240] In a possible implementation, the second face image includes multiple face parts, and the current interface includes a sliding control corresponding to each face part, and the sliding control is used to adjust the corresponding face part; see Figure 7 , the image search module 602 further includes:

[0241] The facial image adjustment unit 6024 is used to adjust any facial part in the second facial image in response to a sliding operation on a sliding control corresponding to any facial part to obtain an adjusted second facial image.

[0242] In one possible implementation, see Figure 7 , the face image adjustment unit 6024 is used to:

[0243] In response to a sliding operation on a sliding control corresponding to any facial part, obtaining an adjustment parameter corresponding to the sliding operation, where the adjustment parameter is used to indicate an adjustment range for any facial part;

[0244] According to the adjustment parameters, any facial part is adjusted to obtain an adjusted second facial image.

[0245] In a possible implementation, the account display unit 6032 is further used to:

[0246] Selecting a first face part from a plurality of face parts, wherein the number of times the first face part is adjusted is greater than the number of times the other face parts are adjusted;

[0247] Selecting, from a plurality of candidate facial images, a third facial image in which a second facial part is similar to the first facial part, wherein the second facial part is a facial part of the third facial image of the same type as the first facial part;

[0248] The second anchor account corresponding to the third facial image is displayed in the current interface.

[0249] In one possible implementation, see Figure 7 , the device further comprises:

[0250] The prompt information display module 604 is used to display prompt information in the current interface in response to the first face image corresponding to the line image not being generated, where the prompt information is used to prompt the user to redraw the line image.

[0251] In one possible implementation, see Figure 7 The prompt information display module 604 is used to display the effect of the virtual anchor outputting the prompt information in the current interface in response to the face image corresponding to the line image not being generated.

[0252] In one possible implementation, see Figure 7 The image search module 602 is used to select a first face image similar to the line image from a plurality of candidate face images in an image library, wherein the image library includes face images of a plurality of hosts to be displayed.

[0253] In one possible implementation, see Figure 7 , the image search module 602 is used to:

[0254] Obtaining facial similarities between the first facial image and a plurality of candidate facial images;

[0255] Based on multiple face similarities, a first face image is selected from multiple candidate face images, and the face similarity corresponding to the first face image is greater than the face similarities corresponding to other candidate face images.

[0256] In one possible implementation, see Figure 7 , the image search module 602 is used to:

[0257] Perform feature extraction on the line image to obtain a first feature of the line image;

[0258] Extracting features from the plurality of candidate face images respectively to obtain second features of the plurality of candidate face images;

[0259] Based on the first feature and the plurality of second features, the facial similarity between the line image and each candidate facial image is obtained.

[0260] In one possible implementation, see Figure 7 , the device further comprises:

[0261] The live broadcast interface display module 605 is used to display the live broadcast interface corresponding to the live broadcast room of the first anchor account in response to the trigger operation of the first anchor account.

[0262] In a possible implementation, the account display module 603 is used to:

[0263] Displaying the first anchor account and summary information corresponding to the first anchor account in the current interface; or,

[0264] The first anchor account and the anchor information list corresponding to the first anchor account are displayed in the current interface.

[0265] In a possible implementation, the line image includes a plurality of lines, and the image search module 602 is further configured to:

[0266] According to at least one of the shape or the position of each line in the line image, the line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face;

[0267] For any region, searching for a fourth face image whose third face part is similar to any region, wherein the third face part is the face part in the fourth face image that is the same as the face part indicated by any region;

[0268] The account display module 603 is also used to display the third anchor account corresponding to the fourth facial image in the current interface.

[0269] In a possible implementation, the image search module 602 is further configured to:

[0270] Respectively determining the part similarities between a plurality of face parts in the first face image and corresponding areas in the line image, wherein the line image includes a plurality of areas, and a line in each area is used to indicate a face part;

[0271] Based on the multiple part similarities, selecting a fourth face part from the multiple face parts, the part similarity corresponding to the fourth face part is greater than the part similarities corresponding to the other face parts;

[0272] The account display module 603 is also used to display the first anchor account corresponding to the first facial image and the description information corresponding to the fourth facial part in the current interface, and the description information is used to describe the fourth facial part as a facial part similar to the first facial image and the line image.

[0273] In one possible implementation, the line image includes a plurality of lines, see Figure 7 , the device further comprises:

[0274] A line image adjustment module 606, configured to divide the line image into a plurality of regions according to at least one of a shape or a position of each line in the line image, wherein the lines in each region are used to indicate a part of a human face;

[0275] The line image adjustment module 606 is further configured to adjust the lines in at least one area of ​​the line image to obtain an adjusted line image.

[0276] In a possible implementation, the face image generating unit 6021 is used to:

[0277] According to at least one of the shape or the position of each line in the line image, the line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face;

[0278] Obtain line features corresponding to the lines in each area, decode the obtained line features, and obtain the face part corresponding to each area;

[0279] The obtained multiple facial parts are synthesized to obtain a second facial image.

[0280] In a possible implementation, the face image generating unit 6021 is used to:

[0281] Based on the facial image generation model, the line image is processed to obtain a second facial image corresponding to the line image.

[0282] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present application, which will not be described one by one here.

[0283] It should be noted that: the anchor search device provided in the above embodiment only uses the division of the above functional modules as an example to illustrate when searching for anchors. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the anchor search device provided in the above embodiment and the anchor search method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0284] An embodiment of the present application also provides a computer device, which includes a processor and a memory, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement the operations performed in the anchor search method of the above embodiment.

[0285] Optionally, the computer device is provided as a terminal. Figure 8800 is a schematic diagram of the structure of a terminal 800 provided in an embodiment of the present application. The terminal 800 may be a portable mobile terminal, such as a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The terminal 800 may also be referred to as a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.

[0286] The terminal 800 includes a processor 801 and a memory 802 .

[0287] The processor 801 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 801 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 801 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 801 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 801 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0288] The memory 802 may include one or more computer-readable storage media, which may be non-transitory. The memory 802 may also include a high-speed random access memory and a non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 802 is used to store at least one computer program, which is used to be executed by the processor 801 to implement the anchor search method provided in the method embodiment of the present application.

[0289] In some embodiments, the terminal 800 may further optionally include: a peripheral device interface 803 and at least one peripheral device. The processor 801, the memory 802 and the peripheral device interface 803 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 803 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 804, a display screen 805, a camera assembly 806, an audio circuit 807, a positioning assembly 808 and a power supply 809.

[0290] The peripheral device interface 803 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 801 and the memory 802. In some embodiments, the processor 801, the memory 802, and the peripheral device interface 803 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 801, the memory 802, and the peripheral device interface 803 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0291] The radio frequency circuit 804 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 804 communicates with communication networks and other communication devices through electromagnetic signals. The radio frequency circuit 804 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 804 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 804 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 804 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0292] The display screen 805 is used to display the UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 805 is a touch display screen, the display screen 805 also has the ability to collect touch signals on the surface or above the surface of the display screen 805. The touch signal can be input to the processor 801 as a control signal for processing. At this time, the display screen 805 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 805 can be one, set on the front panel of the terminal 800; in other embodiments, the display screen 805 can be at least two, respectively set on different surfaces of the terminal 800 or in a folding design; in other embodiments, the display screen 805 can be a flexible display screen, set on the curved surface or folding surface of the terminal 800. Even, the display screen 805 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 805 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).

[0293] The camera assembly 806 is used to capture images or videos. Optionally, the camera assembly 806 includes a front camera and a rear camera. The front camera is arranged on the front panel of the terminal, and the rear camera is arranged on the back of the terminal. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 806 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0294] The audio circuit 807 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 801 for processing, or input them into the radio frequency circuit 804 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the terminal 800. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 801 or the radio frequency circuit 804 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 807 may also include a headphone jack.

[0295] The positioning component 808 is used to locate the current geographical location of the terminal 800 to implement navigation or LBS (Location Based Service). The positioning component 808 can be a positioning component based on the US GPS (Global Positioning System), China's Beidou system, Russia's Grenas positioning system, or the European Union's Galileo positioning system.

[0296] The power supply 809 is used to power various components in the terminal 800. The power supply 809 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 809 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0297] In some embodiments, the terminal 800 further includes one or more sensors 810 , including but not limited to: an acceleration sensor 811 , a gyroscope sensor 812 , a pressure sensor 813 , a fingerprint sensor 814 , an optical sensor 815 , and a proximity sensor 816 .

[0298] The acceleration sensor 811 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal 800. For example, the acceleration sensor 811 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 801 can control the display screen 805 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 811. The acceleration sensor 811 can also be used to collect game or user motion data.

[0299] The gyroscope sensor 812 can detect the body direction and rotation angle of the terminal 800, and the gyroscope sensor 812 can cooperate with the acceleration sensor 811 to collect the user's 3D actions on the terminal 800. The processor 801 can implement the following functions based on the data collected by the gyroscope sensor 812: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0300] The pressure sensor 813 can be set on the side frame of the terminal 800 and / or the lower layer of the display screen 805. When the pressure sensor 813 is set on the side frame of the terminal 800, it can detect the user's holding signal of the terminal 800, and the processor 801 performs left and right hand recognition or shortcut operation according to the holding signal collected by the pressure sensor 813. When the pressure sensor 813 is set on the lower layer of the display screen 805, the processor 801 controls the operability controls on the UI interface according to the user's pressure operation on the display screen 805. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0301] The fingerprint sensor 814 is used to collect the user's fingerprint, and the processor 801 identifies the user's identity based on the fingerprint collected by the fingerprint sensor 814, or the fingerprint sensor 814 identifies the user's identity based on the collected fingerprint. When the user's identity is identified as a trusted identity, the processor 801 authorizes the user to perform relevant sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings. The fingerprint sensor 814 can be set on the front, back, or side of the terminal 800. When a physical button or a manufacturer logo is set on the terminal 800, the fingerprint sensor 814 can be integrated with the physical button or the manufacturer logo.

[0302] The optical sensor 815 is used to collect the ambient light intensity. In one embodiment, the processor 801 can control the display brightness of the display screen 805 according to the ambient light intensity collected by the optical sensor 815. Specifically, when the ambient light intensity is high, the display brightness of the display screen 805 is increased; when the ambient light intensity is low, the display brightness of the display screen 805 is reduced. In another embodiment, the processor 801 can also dynamically adjust the shooting parameters of the camera assembly 806 according to the ambient light intensity collected by the optical sensor 815.

[0303] The proximity sensor 816, also called a distance sensor, is disposed on the front panel of the terminal 800. The proximity sensor 816 is used to collect the distance between the user and the front of the terminal 800. In one embodiment, when the proximity sensor 816 detects that the distance between the user and the front of the terminal 800 is gradually decreasing, the processor 801 controls the display screen 805 to switch from the screen-on state to the screen-off state; when the proximity sensor 816 detects that the distance between the user and the front of the terminal 800 is gradually increasing, the processor 801 controls the display screen 805 to switch from the screen-off state to the screen-on state.

[0304] Those skilled in the art will understand that Figure 8 The structure shown in the figure does not constitute a limitation on the terminal 800, and the terminal 800 may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.

[0305] Optionally, the computer device is provided as a server. Fig. 9 This is a schematic diagram of the structure of a server provided in an embodiment of the present application. The server 900 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 901 and one or more memories 902, wherein the memory 902 stores at least one computer program, which is loaded and executed by the processor 901 to implement the methods provided in the above-mentioned various method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the server may also include other components for implementing device functions, which will not be described in detail here.

[0306] An embodiment of the present application also provides a computer-readable storage medium, in which at least one program code is stored. The at least one program code is loaded and executed by a processor to implement the operations performed in the anchor search method of the above embodiment.

[0307] The embodiment of the present application further provides a computer program product or a computer program, which includes a computer program code stored in a computer-readable storage medium. The computer program code is loaded and executed by a processor to implement the operations performed in the anchor search method of the above embodiment.

[0308] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0309] The above are only optional embodiments of the embodiments of the present application and are not intended to limit the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the protection scope of the present application.

Claims

1. A method for searching anchors, characterized in that: The method comprises: Obtaining a line image drawn in the current interface, where the line image is used to indicate facial features of the anchor to be searched; In the case where the drawn line image cannot reflect the facial features, the drawn line image is divided into a plurality of regions according to at least one of the shape or position of each line in the drawn line image, and the lines in each region are used to indicate a facial part; the lines in at least one region of the drawn line image are adjusted to obtain an adjusted line image, so that the adjusted line image can reflect the facial features; Based on the adjusted line image, generating a second facial image corresponding to the adjusted line image, wherein facial features of the second facial image are the same as the facial features indicated by the adjusted line image, and the second facial image has the same display effect as the actually captured facial image; searching for a first facial image similar to the second facial image, the first facial image being a facial image of a host to be displayed, facial features of the first facial image being similar to facial features indicated by the adjusted line image, the first facial image being an actually photographed facial image, and the first facial image being similar to the second facial image means that facial features in the first facial image are similar to facial features in the second facial image; The first anchor account corresponding to the first facial image is displayed in the current interface.

2. The method according to claim 1, characterized in that The current interface includes a canvas area and a generation control; the obtaining of a line image drawn in the current interface includes: Get the line image drawn in the canvas area; The step of generating a second face image corresponding to the adjusted line image includes: In response to a triggering operation on the generating control, the second facial image is generated.

3. The method according to claim 1, characterized in that After generating the second face image corresponding to the adjusted line image, the method further includes: The second facial image is displayed in the current interface.

4. The method according to claim 3, characterized in that: The displaying the second facial image in the current interface includes: displaying the second facial image in the canvas area of ​​the current interface; or, The second facial image is displayed in a preview area in the current interface, where the preview area is an area in the current interface that is different from the canvas area.

5. The method according to claim 3, characterized in that: The current interface also includes a search control, and after displaying the second face image in the current interface, displaying the first anchor account corresponding to the first face image in the current interface includes: In response to a triggering operation on the search control, displaying a search animation in the current interface, wherein the search animation is used to indicate that an image matching the second facial image is currently being searched for; In response to finding the first anchor account, the search animation is stopped and the first anchor account is displayed.

6. The method according to claim 3, characterized in that The second face image includes a plurality of face parts, the current interface includes a sliding control corresponding to each face part, and the sliding control is used to adjust the corresponding face part; after the second face image is displayed in the current interface, the method further includes: In response to a sliding operation on a sliding control corresponding to any facial part, the any facial part in the second facial image is adjusted to obtain an adjusted second facial image.

7. The method according to claim 6, characterized in that The method of adjusting any facial part in the second facial image in response to a sliding operation of a sliding control corresponding to any facial part to obtain the adjusted second facial image includes: In response to a sliding operation on a sliding control corresponding to any one of the facial parts, acquiring an adjustment parameter corresponding to the sliding operation, wherein the adjustment parameter is used to indicate an adjustment amplitude of the any one of the facial parts; According to the adjustment parameters, any one facial part is adjusted to obtain the adjusted second facial image.

8. The method according to claim 6, characterized in that The method further comprises: Selecting a first face part from the plurality of face parts, wherein the first face part is adjusted more times than other face parts; Selecting, from a plurality of candidate facial images, a third facial image whose second facial part is similar to the first facial part, wherein the second facial part is a facial part of the same type as the first facial part in the third facial image; The second anchor account corresponding to the third facial image is displayed in the current interface.

9. The method according to claim 1, characterized in that: The method further comprises: In response to the second face image corresponding to the adjusted line image not being generated, a prompt message is displayed in the current interface, where the prompt message is used to prompt the redrawing of the line image.

10. The method according to claim 9, characterized in that In response to the second face image corresponding to the adjusted line image not being generated, displaying a prompt message in the current interface includes: In response to the fact that a facial image corresponding to the adjusted line image is not generated, an effect of the virtual anchor outputting the prompt information is displayed in the current interface.

11. The method according to claim 1, characterized in that: After the first anchor account corresponding to the first facial image is displayed in the current interface, the method further includes: In response to the triggering operation on the first anchor account, the live broadcast interface corresponding to the live broadcast room of the first anchor account is displayed.

12. The method according to claim 1, characterized in that The displaying the first anchor account corresponding to the first face image in the current interface includes: Displaying the first anchor account and summary information corresponding to the first anchor account in the current interface; or, The first anchor account and the anchor information list corresponding to the first anchor account are displayed in the current interface.

13. The method according to claim 1, characterized in that The adjusted line image includes a plurality of lines, and the method further includes: According to at least one of the shape or position of each line in the adjusted line image, the adjusted line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face; For any region, searching for a fourth face image whose third face part is similar to the any region, wherein the third face part is the face part in the fourth face image that is the same as the face part indicated by the any region; The third anchor account corresponding to the fourth facial image is displayed in the current interface.

14. The method according to claim 1, characterized in that The method further comprises: Respectively determining the part similarities between a plurality of face parts in the first face image and corresponding areas in the adjusted line image, wherein the adjusted line image includes a plurality of areas, and a line in each area is used to indicate a face part; Based on the multiple part similarities, selecting a fourth face part from the multiple face parts, the part similarity corresponding to the fourth face part is greater than the part similarities corresponding to the other face parts; The displaying the first anchor account corresponding to the first face image in the current interface includes: The first anchor account corresponding to the first facial image and the descriptive information corresponding to the fourth facial part are displayed in the current interface, and the descriptive information is used to describe the fourth facial part as a facial part similar to the first facial image and the adjusted line image.

15. The method according to claim 1, characterized in that The step of generating a second face image corresponding to the adjusted line image includes: According to at least one of the shape or position of each line in the adjusted line image, the adjusted line image is divided into a plurality of regions, wherein the lines in each region are used to indicate a part of a human face; Obtaining line features corresponding to the lines in each area, decoding the obtained line features, and obtaining the face part corresponding to each area; The obtained multiple facial parts are synthesized to obtain the second facial image.

16. The method according to claim 1, characterized in that The step of generating a second face image corresponding to the adjusted line image includes: Based on the facial image generation model, the adjusted line image is processed to obtain the second facial image corresponding to the adjusted line image.

17. A host search device, characterized in that: The device comprises: A line image acquisition module, used to acquire a line image drawn in the current interface, wherein the line image is used to indicate the facial features of the anchor to be searched; A line image adjustment module, used for dividing the drawn line image into a plurality of regions according to at least one of the shape or position of each line in the drawn line image when the drawn line image cannot reflect the facial features, wherein the lines in each region are used to indicate a facial part; and adjusting the lines in at least one region of the drawn line image to obtain an adjusted line image so that the adjusted line image can reflect the facial features; The image search module includes a face image generation unit and an image search unit; The facial image generating unit is used to generate a second facial image corresponding to the adjusted line image based on the adjusted line image, wherein facial features of the second facial image are the same as the facial features indicated by the adjusted line image, and the second facial image has the same display effect as the actually captured facial image; The image search unit is used to search for a first facial image similar to the second facial image, the first facial image is a facial image of a host to be displayed, facial features of the first facial image are similar to facial features indicated by the adjusted line image, the first facial image is an actually photographed facial image, and the first facial image is similar to the second facial image in that facial features in the first facial image are similar to facial features in the second facial image; An account display module is used to display the first anchor account corresponding to the first facial image in the current interface.

18. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the operations performed in the anchor search method according to any one of claims 1 to 16.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one program code, and the at least one program code is loaded and executed by the processor to implement the operations performed in the anchor search method according to any one of claims 1 to 16.