Content flyback method and device, equipment and medium

Abstract

The embodiment of the invention relates to a content flyback method and device, equipment and a medium, and the method comprises the steps: obtaining flyback basic content and a target flyback dimension in response to an input operation and a dimension selection operation on a flyback page; performing flyback in the content library based on the sub-content of the flyback basic content under the target flyback dimension to obtain a flyback result based on user aggregation; and displaying the sub-content of the flyback basic content under the target flyback dimension and the flyback result in a flyback page in a left-right layout mode. Therefore, compared with manual flyback in the related technology, the flyback efficiency is greatly improved, the sub-content and the flyback result aggregated by taking the user as the basic unit are displayed in the flyback page in a left-right layout mode, the sub-content and the flyback result are visually compared and displayed, and the user experience is improved. Potential abnormal users and abnormal contents can be quickly found subsequently, and the abnormal information positioning efficiency is improved from multiple dimensions such as the flyback process and flyback result display.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a content rewinding method, device, equipment and medium. Background Art

[0002] When performing anomaly detection on an application, it is necessary to manually scan back based on known abnormal scenarios to find more abnormal users or abnormal content. However, this method of manually scanning back to locate abnormal information is inefficient. Summary of the invention

[0003] In order to solve the above technical problems, the present disclosure provides a content rewind method, device, equipment and medium.

[0004] The present disclosure provides a content rewinding method, the method comprising:

[0005] In response to an input operation and a dimension selection operation on a retrace page, acquiring a retrace basic content and a target retrace dimension;

[0006] Retrace the content library based on the sub-contents of the retrace basic content under the target retrace dimension to obtain a retrace result based on user aggregation;

[0007] The sub-content of the retrace basic content under the target retrace dimension and the retrace result are displayed in the retrace page in a left-right layout.

[0008] The present disclosure also provides a content rewinding device, the device comprising:

[0009] A first acquisition module, configured to acquire a retrace basic content and a target retrace dimension in response to an input operation and a dimension selection operation on a retrace page;

[0010] A first retrace module, configured to retrace a content library based on the sub-contents of the retrace basic content under the target retrace dimension, and obtain a retrace result based on user aggregation;

[0011] The first display module is used to display the sub-content of the retrace basic content under the target retrace dimension and the retrace result in the retrace page in a left-right layout.

[0012] An embodiment of the present disclosure also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor is used to read the executable instructions from the memory and execute the instructions to implement the content retrace method provided in the embodiment of the present disclosure.

[0013] The embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the content rewind method provided by the embodiment of the present disclosure.

[0014] Compared with the prior art, the technical solution provided by the embodiment of the present disclosure has the following advantages: the content retrace solution provided by the embodiment of the present disclosure obtains the retrace basic content and the target retrace dimension in response to the input operation and dimension selection operation on the retrace page; retrace the content library based on the sub-content of the retrace basic content under the target retrace dimension to obtain the retrace result based on user aggregation; and display the sub-content and retrace result of the retrace basic content under the target retrace dimension in the retrace page in a left-right layout. With the above technical solution, the retrace basic content and the target retrace dimension are efficiently determined in the retrace page in a page interactive manner, the sub-content is determined according to the retrace basic content and the target retrace dimension, and the content library is automatically retraced according to the sub-content. Compared with the manual retrace in the related art, the retrace efficiency is greatly improved, and the sub-content and the retrace result aggregated based on the user are displayed in the retrace page in a left-right layout, and the sub-content is intuitively compared with the retrace result. Potential abnormal users and abnormal content can be quickly discovered later, and the efficiency of locating abnormal information is improved from multiple dimensions such as the retrace process and the display of retrace results. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0016] Figure 1 A flowchart of a content rewinding method provided by an embodiment of the present disclosure;

[0017] Figure 2 A schematic diagram of obtaining basic retrace content and target retrace dimension on a retrace page provided in an embodiment of the present disclosure;

[0018] Figure 3 A flowchart of another content rewinding method provided by an embodiment of the present disclosure;

[0019] Figure 4 A schematic diagram of a retrace basic content including an image provided for an embodiment of the present disclosure;

[0020] Figure 5 A schematic diagram of displaying sub-content and retrace results on a retrace page provided by an embodiment of the present disclosure;

[0021] Figure 6A schematic diagram of determining a target screen provided by an embodiment of the present disclosure;

[0022] Figure 7 A schematic diagram of a retrace result corresponding to a target picture provided by an embodiment of the present disclosure;

[0023] Figure 8 A schematic diagram of a retrace result corresponding to a target voiceprint segment provided in an embodiment of the present disclosure;

[0024] Fig. 9 A schematic diagram of a target card provided in an embodiment of the present disclosure;

[0025] Fig.10 A schematic diagram of a details page provided in an embodiment of the present disclosure;

[0026] Fig.11 A schematic diagram of performing an input operation on a retrace page in a model retrace state provided by an embodiment of the present disclosure;

[0027] Fig.12 A schematic diagram of displaying a retrace result on a retrace page of a model retrace state provided by an embodiment of the present disclosure;

[0028] Fig.13 A schematic diagram of the structure of a content rewinding device provided by an embodiment of the present disclosure;

[0029] Fig.14 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0031] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0032] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0033] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0034] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0035] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0036] In order to solve the above problems, an embodiment of the present disclosure provides a content rewinding method, which is introduced below in conjunction with a specific embodiment.

[0037] Figure 1 The present invention provides a flow chart of a method for scanning content in an embodiment of the present invention. The method can be performed by a content scanning device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method includes:

[0038] Step 101: In response to an input operation and a dimension selection operation on a retrace page, obtain retrace basic content and a target retrace dimension.

[0039] Among them, the retrace page can be a page that performs retrace processing on anomalies through page interaction, and multiple controls for performing retrace processing can be set on the retrace page. The retrace processing can be understood as a search process based on a specific algorithm. The input operation can be an operation of inputting the basic retrace content in the content input text box of the retrace page. The dimension selection operation can be an operation of selecting the required target retrace dimension in the dimension selection control corresponding to the multiple retrace dimensions displayed on the retrace page. The basic retrace content can be the content based on which the retrace processing is performed, and the basic retrace content can represent an object that is known to have anomalies. The target retrace dimension can be the dimension based on which the retrace processing is performed. The basic retrace content can correspond to the target retrace dimension.

[0040] In some embodiments of the present disclosure, the target retrace dimension includes a target sub-dimension under the target dimension, the target dimension is the dimension corresponding to the dimension selection operation among multiple dimensions, each dimension includes multiple sub-dimensions, and the target sub-dimension is one of the multiple sub-dimensions included in the target dimension. The multiple dimensions can be multiple overall dimensions based on which the retrace processing is selected. The sub-dimensions can be understood as multiple subdivision dimensions under the corresponding overall dimensions. The target dimension can be understood as the dimension selected by the dimension selection operation among multiple dimensions, and the target sub-dimension can be understood as the sub-dimension selected by the dimension selection operation among multiple sub-dimensions under the target dimension. The dimension selection control can be a selection control in the style of a secondary drop-down menu, the main drop-down menu in the dimension selection control is used to display multiple dimensions, and the sub-drop-down menu in the dimension selection control is used to display multiple sub-dimensions under the target dimension.

[0041] In some embodiments of the present disclosure, the target dimension in the anomaly detection scenario is one of personal information, contribution, live broadcast room, comment and group chat. If the target dimension is personal information, the sub-dimension may include one or more of avatar, background image, nickname, and signature. If the target dimension is video contribution, the sub-dimension may include one or more of the video as a whole, video cover, video screen, video recognition characters, and video title. If the target dimension is a live broadcast room, the sub-dimension may include one or more of the live broadcast room screen and the live broadcast room voiceprint. If the target dimension is a comment, the sub-dimension may include one or more of the comment as a whole, comment text, and comment picture. If the target dimension is a group chat, the sub-dimension may include one or more of the group avatar, group announcement, group signature, and group name.

[0042] For example, the target retrace dimension and its corresponding retrace basic content may include at least one of the following: if the target retrace dimension corresponds to one of personal information, contribution, and comment, the retrace basic content may be the identification of the abnormal user; if the target retrace dimension corresponds to a live broadcast room, the retrace basic content may be the identification of the abnormal live broadcast room; if the target retrace dimension corresponds to a group chat, the retrace basic content may be the identification of the existence of an abnormal group chat.

[0043] In an embodiment of the present disclosure, a content input text box and a dimension selection control are configured in the retrace page. The administrator can select a target dimension from the multiple dimensions displayed in the main drop-down menu of the dimension selection control according to his / her own needs, and select a target sub-dimension from the multiple sub-dimensions displayed in the sub-drop-down menu of the dimension selection control. The content retrace device determines the selected target sub-dimension as the target retrace dimension in response to the administrator's dimension selection operation. In addition, the administrator can input text content corresponding to the target retrace dimension in the content input text box according to his / her own needs. The content retrace device obtains the text content in response to the administrator's input operation and determines the text content as the retrace basic content.

[0044] Figure 2 A schematic diagram of obtaining basic retrace content and target retrace dimensions on a retrace page provided by an embodiment of the present disclosure, such as Figure 2 As shown, page 200 is a retrace page, control 201 is the main drop-down menu of the dimension selection control, which may include personal information, contribution, live broadcast room, comments and group chat. Control 202 is a sub-drop-down menu of the dimension selection control, and the sub-drop-down menu under the personal information may include controls of multiple dimensions such as avatar, background image, nickname, signature, etc.

[0045] Step 102: Retrace the content library based on the sub-contents of the retrace basic content under the target retrace dimension to obtain a retrace result based on user aggregation.

[0046] Among them, the sub-content can be the specific content under the target retrace dimension. For example, if the retrace basic content is the identification of the abnormal user and the target retrace dimension is the avatar, the sub-content can include the current avatar and / or historical avatar of the abnormal user; if the retrace basic content is the identification of the abnormal live broadcast room and the target retrace dimension is the live broadcast room screen, the sub-content can include the target screen of the abnormal live broadcast room; if the retrace basic content is the identification of the abnormal group chat and the target retrace dimension is the group avatar, the sub-content can include the current avatar and / or historical avatar of the abnormal group chat.

[0047] The content library can be a collection of user content stored and managed by the application to be retraced. User content can be content generated by the user in the process of using the application, and the acquisition of the user content is authorized by the user. In some embodiments of the present disclosure, each user content includes multimodal content consisting of at least one of text, video, image and audio corresponding to a user. For example, user content may include one or more of the user's avatar, background image, nickname, signature, contributed video, contributed video cover, contributed video screen, contributed video identification characters, contributed video title, live room screen, live room voiceprint, comment text, comment picture, group avatar, group announcement, group signature, and group name.

[0048] The number of applications to be retraceable may be one or more. This embodiment does not limit the type of application to be retraceable. For example, the type of application may be one or more of a short video type, a social type, a game type, and a video editing type. The content library may include content corresponding to one or more of a user's personal profile, contributions, live broadcast room, comments, and group chat. The retrace result may be content that is potentially abnormal as determined by the retrace process.

[0049] In the embodiment of the present disclosure, after obtaining the retrace basic content and the retrace content dimension, the content retrace device determines the sub-content of the retrace basic content under the target retrace dimension, and performs retrace processing on the user content in the content library based on the sub-content to obtain a retrace result based on user aggregation.

[0050] Figure 3 A flowchart of another content rewinding method provided by an embodiment of the present disclosure is shown in FIG. Figure 3 As shown, in some embodiments of the present disclosure, based on the sub-contents of the basic content under the target retrace dimension, the content library is retraced to obtain the retrace result based on user aggregation, including:

[0051] Step 301: based on the sub-contents of the retrace basic content under the target retrace dimension, retrace the sub-contents of multiple user contents in the content library under the target retrace dimension, and extract a preset number of result contents ranked high in similarity.

[0052] The similarity may represent the similarity between the sub-content corresponding to the scan-back basic content and the sub-content corresponding to the user content. The result content may be a preset number of sub-contents in the sub-content corresponding to the user content that are ranked first in similarity to the sub-content corresponding to the scan-back basic content. The preset number may be a pre-set number. The preset number may be set according to the needs of the management personnel, etc., and is not limited in this embodiment. For example, the preset number may include any one of 200, 50, and 20.

[0053] In some embodiments of the present disclosure, the scanned base content includes text or image, and the result content includes text or image. Figure 4 A schematic diagram of a retrace basic content including an image provided by an embodiment of the present disclosure, such as Figure 4 As shown, the retrace basic content can be uploaded by any of the following methods: dragging, local uploading, or inputting a link. If the target retrace basic content includes an image, the sub-dimension may be an image-related dimension. For example, if the target dimension is a personal profile, the sub-dimension may be one of an avatar and a background image. If the target dimension is a video contribution, the sub-dimension may be one of a video cover, a video screen, and a video identification character. If the target dimension is a live broadcast room, the sub-dimension may be a live broadcast room screen, etc. If the target dimension is a comment, the sub-dimension may be a comment picture. If the target dimension is a group chat, the sub-dimension may be a group avatar.

[0054] In this implementation, if the basic scan back content includes the target text, the content scan back device can determine the sub-content of the object corresponding to the target text in the content library under the target scan back dimension to obtain the basic sub-content, and the data type of the basic sub-content may include one or more of text, image, and video. If the basic scan back content includes the target image, the content scan back device adds the restriction of the target scan back dimension to the target image to obtain the basic sub-content, and the data type of the basic sub-content includes image or video.

[0055] Further, in the user content of the content library, the sub-content corresponding to the target retrace dimension is determined to obtain the user sub-content. Further, the content retrace device performs retrace processing on the user sub-content according to the basic sub-content, obtains the similarity between each basic sub-content and the user sub-content, and sorts the user sub-content in descending order of similarity, and determines the result content based on the pre-set number of user sub-contents.

[0056] Step 302: Aggregate a preset number of result contents according to the user dimension to obtain multiple user results, and determine the multiple user results as retrace results.

[0057] The user result may be a result obtained by aggregating the result content based on the user. In some embodiments of the present disclosure, each user result includes at least one result content corresponding to a user that is similar to the sub-content of the retrace basic content under the target retrace dimension, and the similarity corresponding to the at least one result content.

[0058] In this embodiment, after determining the result content, the content retracement device can determine the user corresponding to each result content, and aggregate the result content corresponding to the same user and the similarity corresponding to the result content into the same user result, to obtain multiple user results, and determine the multiple user results as the retracement results. Optionally, for each user result, the number of result contents contained in the user result is counted, and the number of contents is subsequently associated with the user result for display, so that the administrator can determine the possibility of abnormality of the user through the number of contents.

[0059] In the above scheme, the sub-content with higher similarity is determined as the result content, and the redundant sub-content with lower similarity is excluded, thus avoiding the influence of the sub-content with lower similarity on the final result. The result content is aggregated by user dimension, which creates a basis for subsequent user-based result display, so that managers can intuitively determine the result content corresponding to different users, and managers can quickly identify abnormal users.

[0060] Step 103: Display the sub-content of the retrace basic content under the target retrace dimension and the retrace result in the retrace page in a left-right layout.

[0061] The left-right layout may be a layout in which the sub-content and the retrace result are respectively located on the left and right sides of the retrace page for comparison. For example, the sub-content may be located on the left side of the retrace page, and the retrace result may be located on the right side of the retrace page.

[0062] In an embodiment of the present disclosure, after determining the sub-content corresponding to the scan-back basic content and determining the scan-back result based on the sub-content, the content scan-back device can display the sub-content on the left side of the scan-back page and display the scan-back result corresponding to the selected sub-content on the right side of the scan-back page.

[0063] In some embodiments of the present disclosure, the sub-content of the basic content of the retrace under the target retrace dimension and the retrace result are displayed in the retrace page in a left-right layout, including: the sub-content of the basic content of the retrace under the target retrace dimension is displayed in the first area of ​​the retrace page, and the retrace result is displayed in the second area of ​​the retrace page, wherein the positional relationship between the first area and the second area is a left-right relationship, and the first area and the second area do not overlap each other.

[0064] The first area may be a partial area pre-set in the retrace page for displaying the sub-content corresponding to the retrace basic content. The second area may be a partial area pre-set in the retrace page for displaying the retrace result. Optionally, the first area may be located on the left side of the second area. The left-right relationship may be that the first area and the second area are arranged relative to each other in the horizontal direction in the retrace page.

[0065] In this embodiment, two areas arranged left and right in the retrace page are pre-divided into a first area and a second area, and there is no overlapping area between the first area and the second area. The content retrace device can display the sub-content corresponding to the retrace basic content in the first area, and display the retrace result obtained based on the retrace of the sub-content in the second area. Optionally, the retrace content displayed in the second area can be the retrace content corresponding to the currently selected sub-content.

[0066] Figure 5 A schematic diagram of displaying sub-content and retrace results on a retrace page provided by an embodiment of the present disclosure, in an optional implementation manner, as Figure 5 As shown, area 501 is the first area, area 502 is the second area, area 502 includes area 503 and area 504, and area 503 is the area in area 502 that specifically displays the retrace results. If there is only one result content corresponding to a user, the retrace result displayed on the retrace page may include the specific result content and the similarity corresponding to the result content. If there are multiple result contents corresponding to a user, the retrace result displayed on the retrace page may include a result content collection consisting of multiple result contents and the similarity ranges corresponding to the multiple result contents.

[0067] The content retracement scheme provided by the embodiment of the present disclosure obtains the retracement basic content and the target retracement dimension in response to the input operation and dimension selection operation on the retracement page; performs retracement on the content library based on the sub-content of the retracement basic content under the target retracement dimension to obtain the retracement result based on user aggregation; and displays the sub-content and retracement result of the retracement basic content under the target retracement dimension in the retracement page in a left-right layout. By adopting the above technical scheme, the retracement basic content and the target retracement dimension are efficiently determined in the retracement page in a page interactive manner, the sub-content is determined according to the retracement basic content and the target retracement dimension, and the content library is automatically retraced according to the sub-content. Compared with the manual retracement in the related art, the retracement efficiency is greatly improved, and the sub-content and the retracement result aggregated based on the user are displayed in the retracement page in a left-right layout, and the sub-content is intuitively compared with the retracement result. Potential abnormal users and abnormal content can be quickly discovered later, and the efficiency of locating abnormal information is improved from multiple dimensions such as the retracement process and the display of retracement results.

[0068] In some embodiments of the present disclosure, when the target sub-dimension is the live broadcast room screen under the live broadcast room, in response to the input operation and dimension selection operation on the retrace page, after obtaining the retrace basic content and the target retrace dimension, the content retrace method also includes: extracting frames of the live video of the live broadcast room corresponding to the retrace basic content to obtain multiple live broadcast room screens to be selected; in response to the selection operation of the multiple live broadcast room screens to be selected, determining at least one target screen.

[0069] Among them, this embodiment does not limit the correspondence between the live broadcast room and the basic content of the retrace. For example, the live broadcast room can be a live broadcast room whose live broadcast room identification is consistent with the basic content of the retrace, or the live broadcast room can be a live broadcast room whose user identification is consistent with the basic content of the retrace. The live broadcast video can be a recorded video of the live broadcast room. The live broadcast room selection screen can be multiple screen frames in the live broadcast video. The target screen can be the selected live broadcast room selection screen.

[0070] In this embodiment, the target sub-dimension is the live room screen under the live room. The content retrace device can obtain the live room video corresponding to the retrace basic content, and perform frame extraction processing on the live video to obtain multiple live room screens to be selected. The live room screen to be selected is displayed on the retrace page. The manager can perform screen selection operation on the live room screen to be selected according to his own needs. In response to the screen selection operation, the content retrace device can determine the live room screen to be selected corresponding to the screen selection operation as the target screen.

[0071] Figure 6 A schematic diagram of determining a target screen provided by an embodiment of the present disclosure is shown in FIG. Figure 6As shown, the retrace page displays multiple live room selection pictures obtained by extracting frames from the live video, such as live room selection picture 1, live room selection picture 2, live room selection picture 3, and live room selection picture 4. If the live room selection picture 1 and the live room selection picture 2 are selected in the selection operation, the live room selection picture 1 and the live room selection picture 2 are determined as the target pictures.

[0072] Correspondingly, the content library is retraced based on the sub-contents of the retracing basic content under the target retracing dimension to obtain a retracing result based on user aggregation, including: the content library is retraced under the target retracing dimension based on at least one target screen of the live broadcast room corresponding to the retracing basic content to obtain a retracing result based on user aggregation.

[0073] In this embodiment, the live videos in the content library are retrace processed according to the live room screen dimension of at least one target screen in the live room, and a preset number of extracted live videos ranked high in similarity are extracted. Furthermore, the content retrace device can determine the user corresponding to each extracted live video, and aggregate the extracted live videos corresponding to the same user and the similarities corresponding to the extracted live room videos into the same user result, so as to obtain multiple user results, and determine the multiple user results as retrace results.

[0074] Figure 7 A schematic diagram of a retrace result corresponding to a target screen provided by an embodiment of the present disclosure, such as Figure 7 As shown, area 701 is the first area, area 702 is the second area, area 702 includes area 703 and area 704, and area 703 is the area in area 702 that specifically displays the retrace results. If there is one result content corresponding to a user, the retrace results displayed on the retrace page may include the specific extracted live video and the similarity corresponding to the live room video. If there are multiple result contents corresponding to a user, the retrace results displayed on the retrace page may include a live video collection composed of multiple extracted live videos and the similarity ranges corresponding to the multiple extracted live videos.

[0075] In the above scheme, the target sub-dimension is the live broadcast room screen under the live broadcast room, which realizes the screen selection of the live video to obtain the target screen, and extracts the live video in the content library according to the target screen to obtain the retracement result based on user aggregation. By selecting the extracted frames, a basis is created for the retracement of the live video, and efficient retracement of longer live videos is achieved.

[0076] In some embodiments of the present disclosure, when the target sub-dimension is the voiceprint of a live broadcast room under the live broadcast room, the content library is retraceable in the sub-content under the target retrace dimension based on the retrace basic content to obtain a retrace result based on user aggregation, including: performing voiceprint analysis and voiceprint extraction on the live video of the live broadcast room corresponding to the retrace basic content to obtain a target voiceprint segment; based on the target voiceprint segment, the content library is retraceable under the target retrace dimension to obtain a retrace result based on user aggregation.

[0077] The target voiceprint segment may be a voiceprint segment in a live video.

[0078] In this embodiment, the target sub-dimension is the voiceprint of the live broadcast room under the live broadcast room. The content retrace device can obtain the live broadcast room video of the live broadcast room corresponding to the retrace basic content, and perform voiceprint analysis on the live broadcast video according to a preset voiceprint analysis algorithm to determine the voiceprint segment. This embodiment does not limit the voiceprint analysis algorithm. For example, the voiceprint analysis algorithm can select a voiceprint segment with a fixed length and the highest volume, or select a voiceprint segment within a preset time period.

[0079] Furthermore, voiceprint extraction is performed on the voiceprint segment to obtain a target voiceprint segment. According to at least one target voiceprint segment, a retrace process is performed on the live videos in the content library in the live room voiceprint dimension to extract a preset number of live videos ranked high in similarity. Furthermore, the content retrace device can determine the user corresponding to each extracted live video, and aggregate the extracted live videos corresponding to the same user and the similarities corresponding to the extracted live room videos into the same user result to obtain multiple user results, and determine the multiple user results as retrace results.

[0080] Figure 8 A schematic diagram of a retrace result corresponding to a target voiceprint segment provided in an embodiment of the present disclosure, such as Figure 8 As shown, area 801 is the first area, area 802 is the second area, area 802 includes area 803 and area 804, and area 803 is the area in area 802 that specifically displays the retrace results. If there is one result content corresponding to a user, the retrace results displayed on the retrace page may include the specific extracted live video and the similarity corresponding to the live room video. If there are multiple result contents corresponding to a user, the retrace results displayed on the retrace page may include a live video collection composed of multiple extracted live videos and the similarity ranges corresponding to the multiple extracted live videos.

[0081] In the above scheme, the target sub-dimension is the voiceprint of the live broadcast room under the live broadcast room, which realizes the automated extraction of the target voiceprint fragment, and determines the live video in the content library based on the target voiceprint fragment to obtain the retracement result based on user aggregation, thereby realizing the automated extraction of voiceprint fragments and the efficient retracement of live videos based on voiceprint fragments.

[0082] In some embodiments of the present disclosure, the content rewinding method further includes: displaying preset sub-content in the corresponding user content for each user result in the rewinding page.

[0083] The preset sub-content may be a part of the user's content that is preset to be displayed in the rewind page, and the preset sub-content may include one or more of user information, signature, background image, account status, region, and update time.

[0084] In this embodiment, in addition to the user results, the preset sub-content of the user corresponding to the user results can also be displayed in the second area of ​​the rewind page. Figure 5 As shown, the preset sub-content displayed in area 504 includes user information, signature, background image, account status, area, and update time. Figure 7 As shown, the preset sub-content displayed in area 704 includes user information, background image, account status, and registration time. Figure 8 As shown, the preset sub-content displayed in area 804 includes user information, background image, account status, and registration time. Thus, the administrator can more intuitively understand the user's relevant information, more quickly understand the user's relevant status, and improve the efficiency of retracement.

[0085] In some embodiments of the present disclosure, the content retrace method further includes: in response to a display operation of a first user result in the retrace result, displaying a first result content among at least one result content included in the first user result in a target card, wherein the target card is suspended at the top layer of the retrace page.

[0086] Among them, the first user result may be a user result that needs to be magnified and displayed, and the first user result may be any user result among the user results. The display operation may be an interactive operation for magnifying and displaying the first user result, and the present embodiment does not limit the type of the display operation. For example, the display operation may include a hover operation or a click operation. The first result content may be one of the multiple result contents of the first user result, and the present embodiment does not limit the first user result. For example, the first result content may be the result content with the greatest similarity among the multiple result contents. The target card may be a floating window for carrying and playing the result content, and the target card may be a bubble-type window.

[0087] In this embodiment, when the administrator browses the retrace results displayed on the retrace page, the administrator can determine the first user result that needs to be magnified and specifically displayed among the multiple user results of the retrace results according to his own needs, and perform a display operation on the first user result. In response to the display operation on the first user result, the content retrace device determines a result content in the first user result as the first result content, and displays the first result content in the target card at the top of the retrace page.

[0088] In the above scheme, the result content in the user results is specifically displayed on the target card floating on the retracement page, and the display of the specific result content is achieved without page jump, thereby improving the convenience of viewing the result content.

[0089] In some embodiments of the present disclosure, the content retracement method further includes: in response to a switching operation on the first result content in the target card, switching the first result content to be displayed as the second result content in the at least one result content included in the first user result.

[0090] The switching operation may be an operation for instructing to switch the result content within the first user result, and the switching operation may be a triggering operation for a switching control. The second result content may be other result content different from the first result content among the multiple result contents corresponding to the first user result.

[0091] In this implementation rate, the administrator can trigger the switch control on the target card displaying the first result content according to their own needs to implement the switch operation of the first result content. In response to the switch operation, the content retracement device determines the switch direction corresponding to the switch operation, switches the result content according to the switch direction based on the first result content, determines the second result content, and displays the second result content on the target card.

[0092] Fig. 9 A schematic diagram of a target card provided by an embodiment of the present disclosure, such as Fig. 9 As shown, floating window 901 is a target card, control 902 is a switch control for switching result content to the left, and control 903 is a switch control for switching result content to the right.

[0093] In the above scheme, the switching of different result contents of the same user result is realized in the target card, and a more flexible and convenient display of result content is realized, so that managers can complete the browsing of user result content in a shorter time, thereby improving the efficiency of identifying abnormal users.

[0094] In some embodiments of the present disclosure, the content retracement method further includes: in response to a detail triggering operation on a second user result in the retracement result, launching a detail page, and displaying at least one result content included in the second user result in a tiled manner in the detail page.

[0095] The second user result may be a user result that needs to display all result contents in detail, and the second user result may be any user result among the multiple user results. The detail trigger operation may be an interactive operation for displaying all result contents in the second user result in detail. The detail page may be a page for displaying detailed result contents, and the detail page may be another page jumped from the retrace page.

[0096] In this embodiment, each user result in the retrace page has a corresponding detail jump link. When the administrator browses the user results displayed on the retrace page, the administrator can determine the second user result that needs to be displayed in detail among the multiple user results according to his / her own needs, and perform a detail trigger operation on the detail jump link corresponding to the second user result. In response to the detail trigger operation on the second user result, the content retrace device jumps from the retrace page to the detail page, and displays all the result contents in the second user result in a tiled manner on the detail page.

[0097] like Figure 5 As shown, link 505 is a detail jump link, and the administrator can trigger the detail jump link. Fig.10 A schematic diagram of a details page provided in an embodiment of the present disclosure, such as Fig.10 As shown, after the administrator triggers the detail jump link corresponding to user ID3, the page jumps to the detail page, and the result content corresponding to user ID3 is displayed on the detail page.

[0098] In the above scheme, the entire result content of a user result is displayed in a tiled manner in the detail page outside the retrace page, so that the manager can understand the entire content of the user result in detail, creating a basis for the manager to fully understand the user's situation under the corresponding target sub-dimension.

[0099] In some embodiments of the present disclosure, the content retrace method further includes: in response to an input operation in a retrace page in a model retrace state, obtaining a keyword or a user identifier, inputting the keyword or the user identifier into a retrace model, and obtaining a retrace result based on user aggregation, and displaying the retrace result in the retrace page.

[0100] The model retrace state may be a retrace state based on a neural network model. Keywords may be words or phrases that represent the focus of the retrace. The user identifier may be a unique identifier of a known abnormal user. The retrace model may be a neural network model with a retrace function.

[0101] In this embodiment, the administrator can trigger the model retrace control in the retrace page. In response to the trigger operation, the content retrace device adjusts the state of the retrace page to the model retrace state. The administrator performs input operations in the content input text box in the retrace page in the model retrace state. The content retrace device obtains the keyword or user ID corresponding to the input operation, and inputs the keyword or user ID into the retrace model. The retrace model performs a neural network-based retrace processing on the content library according to the keyword or user ID, obtains the user-aggregated retrace result, and displays the retrace result to the administrator in the retrace page.

[0102] Fig.11 A schematic diagram of performing an input operation on a retrace page in a model retrace state provided by an embodiment of the present disclosure, such as Fig.11 As shown, control 1101 is a model retrace control, and control 1102 is a content input text box for inputting keywords or user identifiers. Fig.12 A schematic diagram of displaying a retrace result on a retrace page of a model retrace state provided by an embodiment of the present disclosure, such as Fig.12 As shown, the retrace results are displayed based on users as basic units, and each user has a corresponding abnormal label, which records the reason why the user is identified as abnormal.

[0103] In the above scheme, the retrace result is determined by a model retrace method, and richer retrace results are obtained based on a working principle different from that of conventional retrace.

[0104] In some embodiments of the present disclosure, after displaying the sub-content of the scan-back basic content under the target scan-back dimension and the scan-back result in a left-right layout on the scan-back page, the content scan-back method further includes: in response to a switching operation of switching the target sub-dimension to another sub-dimension, scanning the content library based on the sub-content of the scan-back basic content under another sub-dimension to obtain a new scan-back result based on user aggregation; switching and displaying the sub-content of the scan-back basic content under another sub-dimension and the new scan-back result in a left-right layout on the scan-back page.

[0105] The other sub-dimension may be another sub-dimension different from the target sub-dimension. The switching operation may be an interactive operation of switching from the target sub-dimension to another sub-dimension.

[0106] In this embodiment, a sub-dimension switching control for another sub-dimension may be provided on the retrace page, and the administrator may trigger the sub-dimension switching control according to his or her own needs. In response to the switching operation of switching the target sub-dimension to another sub-dimension, the content retrace device maintains the retrace basic content corresponding to the previous target sub-dimension, determines the sub-content of the retrace basic content under another sub-dimension, and performs retrace processing on the user content in the content library according to the new sub-content to obtain a new retrace result based on user aggregation. Furthermore, the content retrace device may display the new sub-content on the left side of the retrace page, and display the new retrace result corresponding to the selected new sub-content on the right side of the retrace page. Figure 5 As shown, the target retrace dimension may be the avatar corresponding to the control 506 , and another sub-dimension may be the background image corresponding to the control 507 .

[0107] In the above scheme, flexible switching between the target sub-dimension and another sub-dimension is achieved, so that the management personnel can quickly obtain the retracement results under the corresponding sub-dimension, thereby improving the efficiency of the retracement processing.

[0108] The content retrace method provided by the embodiment of the present disclosure determines the sub-content as an abnormal sample based on which the retrace is performed by retracing the basic content and the target retrace dimension, and quickly retraces the retrace results based on user aggregation, thereby realizing the rapid location of abnormal users. The left-right layout allows managers to more intuitively view the sub-content as abnormal samples and their corresponding retrace results, and quickly compare the similarity between abnormal samples and retrace results. Focusing on the similarity of the result content of different sub-dimensions, the determination of abnormal users and abnormal content is realized. In addition, two states, a conventional retrace state and a model retrace state, are designed to realize a more comprehensive retrace.

[0109] Fig.13 This is a schematic diagram of the structure of a content rewinding device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device. Fig.13 As shown, the device comprises:

[0110] The first acquisition module 1301 is used to acquire the retrace basic content and the target retrace dimension in response to the input operation and the dimension selection operation on the retrace page;

[0111] A first retrace module 1302, configured to retrace the content library based on the sub-contents of the retrace basic content under the target retrace dimension, and obtain a retrace result based on user aggregation;

[0112] The first display module 1303 is used to display the sub-content of the retrace basic content under the target retrace dimension and the retrace result in the retrace page in a left-right layout.

[0113] In some embodiments of the present disclosure, the first retrace module 1302 is used to:

[0114] Based on the sub-contents of the retrace basic content under the target retrace dimension, retrace the sub-contents of multiple user contents in the content library under the target retrace dimension, and extract a preset number of result contents ranked top in similarity;

[0115] The preset number of result contents are aggregated according to the user dimension to obtain a plurality of user results, and the plurality of user results are determined as retrace results.

[0116] In some embodiments of the present disclosure, the content rewinding device further includes:

[0117] The first display module is used to display the preset sub-content in the corresponding user content for each of the user results in the retrace page.

[0118] In some embodiments of the present disclosure, the retrace basic content includes text or images, and the result content includes text or images; each of the user results includes at least one result content corresponding to a user that is similar to the sub-content of the retrace basic content under the target retrace dimension, and the similarity corresponding to the at least one result content.

[0119] In some embodiments of the present disclosure, each of the user contents includes multimodal content consisting of at least one of text, video, image, and audio corresponding to a user.

[0120] In some embodiments of the present disclosure, the first display module 1303 is used to:

[0121] The sub-content of the retrace basic content under the target retrace dimension is displayed in the first area of ​​the retrace page, and the retrace result is displayed in the second area of ​​the retrace page, wherein the positional relationship between the first area and the second area is a left-right relationship, and the first area and the second area do not overlap each other.

[0122] In some embodiments of the present disclosure, the content rewinding device further includes:

[0123] The second display module is used to display the first result content of at least one result content included in the first user result in a target card in response to the display operation of the first user result in the retrace result, wherein the target card is suspended on the top layer of the retrace page.

[0124] In some embodiments of the present disclosure, the content rewinding device further includes:

[0125] A switching module is used to switch and display the first result content to a second result content among at least one result content included in the first user result in response to a switching operation on the first result content in the target card.

[0126] In some embodiments of the present disclosure, the content rewinding device further includes:

[0127] The detail triggering module is used to start a detail page in response to a detail triggering operation on a second user result in the retrace result, and to tile and display at least one result content included in the second user result in the detail page.

[0128] In some embodiments of the present disclosure, the content rewinding device further includes:

[0129] A second acquisition module, configured to acquire a keyword or a user identifier in response to an input operation when the retrace page is in a model retrace state;

[0130] An input module, used for inputting the keyword or user identifier into a retracement model to obtain a retracement result based on user aggregation;

[0131] The third display module is used to display the retrace result in the retrace page.

[0132] In some embodiments of the present disclosure, the target retrace dimension includes a target sub-dimension under the target dimension, the target dimension is a dimension corresponding to the dimension selection operation among multiple dimensions, each of the dimension includes multiple sub-dimensions, and the target sub-dimension is one of the multiple sub-dimensions included in the target dimension.

[0133] In some embodiments of the present disclosure, the content rewinding device further includes:

[0134] A second retrace module is configured to, after displaying the sub-content of the retrace basic content under the target retrace dimension and the retrace result in the retrace page in a left-right layout, perform retrace on the content library based on the sub-content of the retrace basic content under the other sub-dimension in response to a switching operation of switching the target sub-dimension to another sub-dimension, and obtain a new retrace result based on user aggregation;

[0135] The fourth display module is used to switch and display the sub-content of the retrace basic content under another sub-dimension and the new retrace result in the retrace page in a left-right layout.

[0136] In some embodiments of the present disclosure, the target dimension in an anomaly detection scenario is one of personal data, contribution, live broadcast room, comment and group chat.

[0137] In some embodiments of the present disclosure, the content rewinding device further includes:

[0138] A frame extraction module is used for, when the target sub-dimension is a live room screen under the live room, in response to an input operation and a dimension selection operation on a retrace page, after acquiring retrace basic content and a target retrace dimension, extracting frames of a live video of the live room corresponding to the retrace basic content to obtain a plurality of live room screens to be selected;

[0139] A picture determination module, configured to determine at least one target picture in response to a selection operation on the plurality of live broadcast room to-be-selected pictures;

[0140] Then, the first retrace module 1302 is used to:

[0141] Based on at least one target screen of the live broadcast room corresponding to the retrace basic content, the content library is retraced under the target retrace dimension to obtain a retrace result based on user aggregation.

[0142] In some embodiments of the present disclosure, when the target sub-dimension is the live broadcast room voiceprint under the live broadcast room, the first retrace module 1302 is used to:

[0143] Perform voiceprint analysis and voiceprint extraction on the live video of the live broadcast room corresponding to the retrace basic content to obtain a target voiceprint segment; based on the target voiceprint segment, retrace the content library under the target retrace dimension to obtain a retrace result based on user aggregation.

[0144] The content rewinding device provided in the embodiments of the present disclosure can execute the content rewinding method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0145] A computer program product comprises a computer program / instruction, which implements the steps of the above-mentioned content retrace method when executed by a processor.

[0146] Fig.14 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

[0147] The following specific reference Fig.14 , which shows a schematic diagram of the structure of an electronic device 1400 suitable for implementing the embodiment of the present disclosure. The electronic device 1400 in the embodiment of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.14The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0148] like Fig.14 As shown, the electronic device 1400 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 1401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1402 or a program loaded from a storage device 1408 to a random access memory (RAM) 1403. In the RAM 1403, various programs and data required for the operation of the electronic device 1400 are also stored. The processing device 1401, the ROM 1402, and the RAM 1403 are connected to each other via a bus 1404. An input / output (I / O) interface 1405 is also connected to the bus 1404.

[0149] Typically, the following devices may be connected to the I / O interface 1405: an input device 1406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1409. The communication device 1409 may allow the electronic device 1400 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.14 The electronic device 1400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0150] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device 1409, or installed from a storage device 1408, or installed from a ROM 1402. When the computer program is executed by the processing device 1401, the above-mentioned functions defined in the content retrace method of the embodiment of the present disclosure are executed.

[0151] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0152] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0153] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0154] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the basic content of the retrace and the target retrace dimension in response to the input operation and dimension selection operation on the retrace page; retrace the content library based on the sub-content of the basic content of the retrace under the target retrace dimension, and obtains the retrace result based on user aggregation; and displays the sub-content of the basic content of the retrace under the target retrace dimension and the retrace result in the retrace page in a left-right layout.

[0155] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0156] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0157] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, constitute a limitation on the unit itself.

[0158] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0159] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0160] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0161] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0162] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0163] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A content rewinding method, characterized in that: include: In response to an input operation and a dimension selection operation on a retrace page, acquiring a retrace basic content and a target retrace dimension; Retrace the content library based on the sub-contents of the retrace basic content under the target retrace dimension to obtain a retrace result based on user aggregation; The sub-content of the retrace basic content under the target retrace dimension and the retrace result are displayed in the retrace page in a left-right layout.

2. The method according to claim 1, characterized in that Based on the sub-contents of the retrace basic content under the target retrace dimension, a content library is retraced to obtain a retrace result based on user aggregation, including: Based on the sub-contents of the retrace basic content under the target retrace dimension, retrace the sub-contents of multiple user contents in the content library under the target retrace dimension, and extract a preset number of result contents ranked top in similarity; The preset number of result contents are aggregated according to the user dimension to obtain a plurality of user results, and the plurality of user results are determined as retrace results.

3. The method according to claim 2, characterized in that The method further comprises: For each of the user results, a preset sub-content in the corresponding user content is displayed in the retracement page.

4. The method according to claim 2, characterized in that: The retrace base content includes text or image, and the result content includes text or image; Each of the user results includes at least one result content corresponding to a user that is similar to the sub-content of the retrace basic content under the target retrace dimension, and the similarity corresponding to the at least one result content.

5. The method according to claim 2, characterized in that: Each of the user contents includes multimodal content consisting of at least one of text, video, image and audio corresponding to a user.

6. The method according to claim 1, characterized in that Displaying the sub-content of the retrace basic content under the target retrace dimension and the retrace result on the retrace page in a left-right layout, including: The sub-content of the retrace basic content under the target retrace dimension is displayed in the first area of ​​the retrace page, and the retrace result is displayed in the second area of ​​the retrace page, wherein the positional relationship between the first area and the second area is a left-right relationship, and the first area and the second area do not overlap each other.

7. The method according to claim 1, characterized in that The method further comprises: In response to a display operation on a first user result in the retrace result, a first result content among at least one result content included in the first user result is displayed in a target card, wherein the target card is suspended at the top layer of the retrace page.

8. The method according to claim 7, characterized in that The method further comprises: In response to a switching operation on the first result content in the target card, the first result content is switched and displayed as a second result content in the at least one result content included in the first user result.

9. The method according to claim 1, characterized in that: The method further comprises: In response to a trigger operation on the details of the second user result in the retrace result, a detail page is started, and at least one result content included in the second user result is tiled and displayed in the detail page.

10. The method according to claim 1, characterized in that The method further comprises: In response to an input operation in which the retrace page is in a model retrace state, acquiring a keyword or a user identifier; Inputting the keyword or user identifier into a retrace model to obtain a retrace result based on user aggregation; The retrace result is displayed in the retrace page.

11. The method according to claim 1, characterized in that The target retrace dimension includes a target sub-dimension under a target dimension, wherein the target dimension is a dimension corresponding to the dimension selection operation among multiple dimensions, each of the dimensions includes multiple sub-dimensions, and the target sub-dimension is one of the multiple sub-dimensions included in the target dimension.

12. The method according to claim 11, characterized in that After displaying the sub-content of the retrace basic content under the target retrace dimension and the retrace result in the retrace page in a left-right layout, the method further includes: In response to a switching operation of switching the target sub-dimension to another sub-dimension, a content library is retraceed based on the sub-contents of the retracement basic content under the another sub-dimension to obtain a new retracement result based on user aggregation; The sub-content of the retrace basic content under another sub-dimension and the new retrace result are switched and displayed in the retrace page in a left-right layout.

13. The method according to claim 11, characterized in that The target dimension in the anomaly detection scenario is one of personal profile, contribution, live broadcast room, comment and group chat.

14. The method according to claim 13, characterized in that When the target sub-dimension is a live broadcast room screen under the live broadcast room, in response to an input operation and a dimension selection operation on a retrace page, after acquiring retrace basic content and a target retrace dimension, the method further includes: Extract frames of the live video of the live room corresponding to the retrace basic content to obtain multiple live room selection pictures; In response to a selection operation on the plurality of live broadcast room to-be-selected pictures, determining at least one target picture; Then, based on the sub-contents of the retrace basic content under the target retrace dimension, the content library is retraced to obtain a retrace result based on user aggregation, including: Based on at least one target screen of the live broadcast room corresponding to the retrace basic content, the content library is retraced under the target retrace dimension to obtain a retrace result based on user aggregation.

15. The method according to claim 13, characterized in that When the target sub-dimension is the live broadcast room voiceprint under the live broadcast room, a content library is retraceable in the sub-content under the target retrace dimension based on the retrace basic content to obtain a retrace result based on user aggregation, including: Performing voiceprint analysis and voiceprint extraction on the live video of the live broadcast room corresponding to the retrace basic content to obtain a target voiceprint segment; Based on the target voiceprint segment, a content library is retraced in the target retrace dimension to obtain a retrace result based on user aggregation.

16. A content rewinding device, characterized in that: include: A first acquisition module, configured to acquire a retrace basic content and a target retrace dimension in response to an input operation and a dimension selection operation on a retrace page; A first retrace module, configured to retrace a content library based on the sub-contents of the retrace basic content under the target retrace dimension, and obtain a retrace result based on user aggregation; The first display module is used to display the sub-content of the retrace basic content under the target retrace dimension and the retrace result in the retrace page in a left-right layout.

17. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the content retrace method described in any one of claims 1-15.

18. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the content rewind method described in any one of claims 1-15.

Images