Comment information display method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to a comment information display method and device, an electronic device and a storage medium. The method comprises: in response to an information editing operation in a comment editing area, obtaining current content information in the comment editing area; the comment editing area is an area for editing comment information on a to-be-commented object; performing comment information prediction based on the current content information and object association information of the to-be-commented object to obtain at least one piece of candidate comment information for the to-be-commented object; the current content information is semantically associated with each piece of candidate comment information, and the number of semantic elements in each piece of candidate comment information is greater than that in the current content information; and displaying the at least one piece of candidate comment information. The present disclosure can improve the accuracy and scene adaptability of candidate comment information generation.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a method, apparatus, electronic device, and storage medium for displaying comment information. Background Technology

[0002] On platforms such as social media and online forums, users frequently need to comment and reply to convey their views. However, many users may encounter difficulties in expressing themselves or face time constraints when commenting, resulting in unsatisfactory comment quality that fails to accurately convey their intentions; furthermore, a large number of comments and replies usually require a significant amount of time and effort.

[0003] To address the issues of user comments being limited by the user's expression style or requiring a significant amount of time and effort, comment plugin technology has been adopted. This technology allows users to select preset comment content, but these preset comment contents are general and cannot meet the needs of specific comment scenarios. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, and storage medium for displaying comment information, to at least address the problem that comment plugin technology in related technologies cannot meet the needs of specific comment scenarios. The technical solution of this disclosure is as follows:

[0005] According to a first aspect of the present disclosure, a method for displaying comment information is provided, including:

[0006] In response to an information editing operation in the comment editing area, the current content information within the comment editing area is obtained; the comment editing area is an area used to edit the comment information of the object to be commented on;

[0007] Comment information is predicted based on the current content information and the object association information of the object to be commented on, and at least one candidate comment information is obtained for the object to be commented on; the current content information is semantically associated with each candidate comment information, and the semantic elements in each candidate comment information are more than the semantic elements in the current content information;

[0008] Display at least one candidate comment.

[0009] In an exemplary embodiment, when the object to be commented on is a target multimedia resource, the object association information of the object to be commented on includes the content information of the target multimedia resource;

[0010] The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes:

[0011] Based on the current content information and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

[0012] In an exemplary embodiment, when the object to be commented on is existing comment information of the target multimedia resource, the object association information of the object to be commented on includes the existing comment information and the content information of the target multimedia resource;

[0013] The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes:

[0014] Based on the current content information, the existing comment information, and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

[0015] In an exemplary embodiment, the step of predicting comment information based on the current content information and the object association information of the object to be commented, to obtain at least one candidate comment for the object to be commented, includes:

[0016] Obtain the identifier of the target entity that triggered the information editing operation;

[0017] The comment preference information corresponding to the target subject identifier is determined based on the historical comment information corresponding to the target subject identifier; the historical comment information is the existing comment information of the target subject identifier for the object to be commented on.

[0018] Based on the current content information, the object association information of the object to be commented on, and the comment preference information, comment information is predicted to obtain at least one candidate comment information.

[0019] In one exemplary embodiment, the information editing operation includes an information modification operation on existing content information;

[0020] The step of responding to an information editing operation in the comment editing area by obtaining the current content information of the comment editing area includes:

[0021] In response to an information modification operation on existing content information in the comment editing area, the modified content information is determined as the current content information;

[0022] The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes:

[0023] Based on at least one candidate comment corresponding to the existing content information before modification, and at least one candidate comment corresponding to the current content information after modification, multiple candidate comment information for the object to be commented on are determined.

[0024] In an exemplary embodiment, the step of predicting comment information based on the current content information and the object association information of the object to be commented, to obtain at least one candidate comment for the object to be commented, includes:

[0025] Predict various comment intentions based on the current content information;

[0026] Based on the various comment intentions, the current content information, and the object association information of the object to be commented on, comment information is predicted to obtain at least one candidate comment.

[0027] In one exemplary embodiment, displaying the at least one candidate comment information includes:

[0028] The candidate comment display window displays at least one candidate comment; the candidate comment display window is independent of the page where the comment editing area is located.

[0029] In an exemplary embodiment, when the at least one candidate comment information includes multiple candidate comment information, the candidate comment display window includes a candidate comment display area and a comment expansion control;

[0030] The display of the at least one candidate comment information includes:

[0031] The first candidate comment information is displayed in the candidate comment display area;

[0032] After displaying the at least one candidate comment information, the method further includes:

[0033] In response to a touch operation based on the comment expansion control, first candidate comment information and second candidate comment information are displayed in the candidate comment display area; the first candidate comment information and the second candidate comment information are both comment information from the plurality of candidate comment information.

[0034] In one exemplary embodiment, the method further includes:

[0035] In response to a movement operation on the candidate comment display window, the candidate comment display window is moved to the target location.

[0036] In one exemplary embodiment, after displaying the at least one candidate comment information, the method further includes:

[0037] In response to a selection operation for a target comment, the target comment is displayed in the comment editing area; the target comment is any one of the at least one candidate comment.

[0038] In response to the information modification operation of the target comment information in the comment editing area, comment information prediction is performed based on the modified comment information and the object association information of the object to be commented, to obtain at least one associated comment information corresponding to the modified comment information;

[0039] Display at least one related comment.

[0040] According to a second aspect of the present disclosure, a comment information display device is provided, comprising:

[0041] The content information acquisition unit is configured to perform an information editing operation in response to the comment editing area, and acquire the current content information within the comment editing area; the comment editing area is an area used to edit the comment information of the object to be commented on;

[0042] The candidate comment prediction unit is configured to perform comment information prediction based on the current content information and the object association information of the object to be commented, to obtain at least one candidate comment information for the object to be commented; the current content information is semantically associated with each candidate comment information, and the semantic elements in each candidate comment information are more than the semantic elements in the current content information;

[0043] The candidate comment display unit is configured to display the information of at least one candidate comment.

[0044] In an exemplary embodiment, when the object to be commented on is a target multimedia resource, the object association information of the object to be commented on includes the content information of the target multimedia resource;

[0045] The candidate comment prediction unit is configured to perform:

[0046] Based on the current content information and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

[0047] In an exemplary embodiment, when the object to be commented on is existing comment information of the target multimedia resource, the object association information of the object to be commented on includes the existing comment information and the content information of the target multimedia resource;

[0048] The candidate comment prediction unit is configured to perform:

[0049] Based on the current content information, the existing comment information, and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

[0050] In one exemplary embodiment, the candidate comment prediction unit includes:

[0051] The target entity identifier acquisition unit is configured to acquire the target entity identifier that triggered the information editing operation.

[0052] The preference information determination unit is configured to determine the comment preference information corresponding to the target subject identifier based on the historical comment information corresponding to the target subject identifier; the historical comment information is the existing comment information of the target subject identifier for the object to be commented on;

[0053] The first prediction unit is configured to perform comment information prediction based on the current content information, the object association information of the object to be commented on, and the comment preference information, to obtain the at least one candidate comment information.

[0054] In one exemplary embodiment, the information editing operation includes an information modification operation on existing content information; the content information acquisition unit is configured to perform:

[0055] In response to an information modification operation on existing content information in the comment editing area, the modified content information is determined as the current content information;

[0056] The candidate comment prediction unit is configured to perform:

[0057] Based on at least one candidate comment corresponding to the existing content information before modification, and at least one candidate comment corresponding to the current content information after modification, multiple candidate comment information for the object to be commented on are determined.

[0058] In one exemplary embodiment, the candidate comment prediction unit includes:

[0059] The intent prediction unit is configured to predict various comment intents based on the current content information;

[0060] The second prediction unit is configured to perform comment information prediction based on the multiple comment intentions, the current content information, and the object association information of the object to be commented on, so as to obtain the at least one candidate comment information.

[0061] In one exemplary embodiment, the candidate comment display unit is configured to display the at least one candidate comment in a candidate comment display window; the candidate comment display window is independent of the page where the comment editing area is located.

[0062] In an exemplary embodiment, when the at least one candidate comment information includes multiple candidate comment information, the candidate comment display window includes a candidate comment display area and a comment expansion control;

[0063] The candidate comment display unit is configured to display first candidate comment information in the candidate comment display area;

[0064] The device further includes:

[0065] The touch display unit is configured to perform a touch operation in response to the comment expansion control, displaying first candidate comment information and second candidate comment information in the candidate comment display area; the first candidate comment information and the second candidate comment information are both comment information from the plurality of candidate comment information.

[0066] In one exemplary embodiment, the apparatus further includes:

[0067] The moving unit is configured to perform a moving operation in response to the candidate comment display window, moving the candidate comment display window to a target location.

[0068] In one exemplary embodiment, the apparatus further includes:

[0069] The comment selection unit is configured to perform a selection operation for a target comment information in response to the target comment information, and to display the target comment information in the comment editing area; the target comment information is any one of the at least one candidate comment information.

[0070] The third prediction unit is configured to perform an information modification operation in response to the target comment information in the comment editing area, and to predict comment information based on the modified comment information and the object association information of the object to be commented, so as to obtain at least one associated comment information corresponding to the modified comment information.

[0071] The associated comment display unit is configured to display at least one associated comment.

[0072] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the comment information display method as described above.

[0073] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided that, when instructions in the computer-readable storage medium are executed by a processor of a server, enables the server to perform the comment information display method as described above.

[0074] According to a fifth aspect of the present disclosure, a computer program product is provided, the computer program product including a computer program stored in a readable storage medium, wherein at least one processor of a computer device reads from the readable storage medium and executes the computer program, causing the device to perform the above-described comment information display method.

[0075] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects:

[0076] This disclosure detects information editing operations in the comment editing area in real time. Upon detection of such operations, it acquires the current content information within the comment editing area and predicts comment information based on this information and the object association information of the object to be commented on, thus generating and displaying candidate comment information. On one hand, by responding to information editing operations in the comment editing area in real time, it enables real-time comment information prediction based on the real-time content information in the area, improving the real-time nature of candidate comment information generation. On the other hand, by integrating the current content information within the comment editing area with the object association information of the object to be commented on during comment information prediction, it ensures that the predicted candidate comment information is associated with the user-input keywords and the object to be commented on, improving the accuracy and scenario adaptability of candidate comment information generation. Furthermore, each candidate comment contains more semantic elements than the current content information input by the user; that is, the user can obtain complete candidate comment information with only a few keywords, enhancing the richness and diversity of the semantic content of the candidate comment information.

[0077] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0078] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0079] Figure 1 This is a schematic diagram illustrating an application scenario according to an exemplary embodiment.

[0080] Figure 2 This is a flowchart illustrating a method for displaying comment information according to an exemplary embodiment.

[0081] Figure 3 This is a schematic diagram of a comment editing page according to an exemplary embodiment.

[0082] Figure 4This is a schematic diagram illustrating the first comment display according to an exemplary embodiment.

[0083] Figure 5 This is a flowchart illustrating a method for generating candidate comment information according to an exemplary embodiment.

[0084] Figure 6 This is a schematic diagram illustrating a second comment display according to an exemplary embodiment.

[0085] Figure 7 This is a schematic diagram illustrating a third comment, according to an exemplary embodiment.

[0086] Figure 8 This is a schematic diagram illustrating a fourth comment according to an exemplary embodiment.

[0087] Figure 9 This is a flowchart illustrating a method for generating associated comment information according to an exemplary embodiment.

[0088] Figure 10 This is a block diagram illustrating a comment information display device according to an exemplary embodiment.

[0089] Figure 11 This is a block diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0090] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0091] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0092] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0093] Please see Figure 1The illustration shows an implementation environment provided by an embodiment of the present disclosure. The implementation environment may include at least one terminal 110 and a server 120, which can communicate with each other via a network.

[0094] Specifically, terminal 110 can obtain multimedia resources from server 120 and display them on terminal 110. These multimedia resources can include information of various types, such as text, images, videos, and audio. That is, terminal 110 can be a terminal used for displaying comment information. In response to information editing operations in the comment editing area, terminal 110 can predict comment information based on the current content information in the comment editing area and the object association information of the object to be commented on, obtain candidate comment information, and display it.

[0095] Terminal 110 can communicate with server 120 based on browser / server (B / S) or client / server (C / S) mode. Terminal 110 may include physical devices such as smartphones, tablets, laptops, digital assistants, smart wearable devices, and in-vehicle terminals, and may also include software running on the physical device, such as applications. The operating system running on terminal 110 in this embodiment may include, but is not limited to, Android, iOS, Linux, and Windows.

[0096] The server 120 and the terminal 110 can establish a communication connection via wired or wireless means. The server 120 may include a stand-alone server, a distributed server, or a server cluster consisting of multiple servers, wherein the server may be a cloud server.

[0097] To address the issue that pre-defined comment content in related technologies often fails to meet the needs of specific comment scenarios, this disclosure provides a method for displaying comment information. The executing entity of this method can be the aforementioned terminal; please refer to [link / reference] for details. Figure 2 The method may include:

[0098] S210. In response to an information editing operation in the comment editing area, obtain the current content information within the comment editing area; the comment editing area is an area used to edit the comment information of the object to be commented on.

[0099] The terminal can obtain multimedia resources from the server and display them on a resource display page. This page may include comment controls for the multimedia resources. The terminal can respond to touch operations on these controls by displaying a comment editing area, allowing users to comment on the multimedia resources by entering comments within this area. The resource display page may also include comment information for the multimedia resources, each with its own comment control. The terminal can respond to trigger operations on any comment control corresponding to any comment by displaying a comment editing area, allowing users to comment on any comment by entering comments within this area. Therefore, when the object to be commented on is a target multimedia resource, the comment editing area is used to edit comment information on that target multimedia resource; when the object to be commented on is existing comment information on the target multimedia resource, the comment editing area is used to edit comment information on that existing comment information.

[0100] The terminal can detect in real time whether there is any information editing operation in the comment editing area. Upon detection, it can respond to the operation by retrieving the current content information within the comment editing area. As editing operations continue, the corresponding current content information will be updated accordingly. The current content information in the comment editing area can refer to the content that the user has already entered and is currently displayed there. This displayed content information can include text, images, emoticons, or symbols.

[0101] Please see Figure 3 It shows the comment editing page, which includes a comment editing area and a comment publishing control. When the comment editing area is editable, users can edit the information and display the entered comment information. Once the comment information is confirmed to be edited, the comment information can be published by triggering the comment publishing control.

[0102] S220. Based on the current content information and the object association information of the object to be commented, predict the comment information to obtain at least one candidate comment information for the object to be commented; the current content information is semantically associated with each candidate comment information, and the semantic elements in each candidate comment information are more than the semantic elements in the current content information.

[0103] In this embodiment, comment information prediction can be performed based on a language generation model. Specifically, the current content information and the object association information of the object to be commented on can be used as inputs to the language generation model. The language generation model can predict comment information based on the input current content information and the object association information of the object to be commented on, obtaining at least one candidate comment for the object to be commented on. The language generation model can be a GPT (Generative Pre-trained Transformer) model, a BERT (Bidirectional Encoder Representations from Transformers) model, a Transformer-XL model, an XLNet model, etc. Any existing language generation model capable of predicting comment information can be applied to this embodiment, and will not be elaborated further here.

[0104] The object association information of the object to be commented on may include the object information of the object itself, and may further include other information associated with the object. The information contained in the object association information is different for different types of objects to be commented on.

[0105] Since candidate comment information is predicted based on current content information, the predicted candidate comment information is semantically related to the current content information, meaning that the predicted candidate comment information will not deviate from the original meaning of the user's input information. Furthermore, each candidate comment information contains more semantic elements than the current content information. These semantic elements can be sentence components, words, or semantic expressions with sentiment bias, etc. Each candidate comment information contains more sentence components than the current content information. For example, the sentence components in the candidate comment information include subject, predicate, and object, while the sentence components in the current content information include subject and predicate. Each candidate comment information contains more words than the current content information. Each candidate comment information contains more semantic expressions with sentiment bias than the current content information. For example, the candidate comment information includes semantic expressions of agreement and / or disagreement, while the current content information does not include semantic expressions of agreement and / or disagreement. As a result, the semantic elements in the candidate comment information are more than those in the current content information, which allows users to automatically predict candidate comment information with richer and more specific semantic expressions without having to input too much content. This saves users' energy and time while improving the richness of candidate comment information.

[0106] When predicting comment information based on the current content information and the object association information of the object to be commented on, multiple predicted comment information may be obtained. For the multiple predicted comment information generated, a set of predicted comment information can be randomly selected as candidate comment information, or Top-k sampling can be used to determine candidate comment information from multiple predicted comment information, or nucleus sampling can be used to determine candidate comment information from multiple predicted comment information.

[0107] S230. Display the information of at least one candidate comment.

[0108] Once candidate comment information is generated through prediction, it can be displayed in real time. It should be noted that in this embodiment, each comment information prediction is triggered by an information editing operation. That is, each time the terminal responds to an information editing operation in the comment editing area, such as entering a character, a word, or deleting a character or word, the content information in the corresponding comment editing area generally changes. Based on this changed content information, comment information prediction is performed, resulting in at least one candidate comment corresponding to this information editing operation. Therefore, displaying at least one candidate comment is a dynamic display of the candidate comment information corresponding to each information editing operation. In other words, responding to an information editing operation allows the acquisition of current content information, which is then used to predict comment information and obtain candidate comment information for that specific information editing operation.

[0109] Please see Figure 4 In the comment editing area, the current content information is "persistence," and the corresponding candidate comment information may include "Persistence is victory, let the results speak for themselves!" As more information is entered into the comment editing area, the current content information may change to "Is persistence useful?" and the corresponding candidate comment information may include "Is persistence useful? Don't think that losing weight will change everything." Therefore, during a commenting process, the current content information and the corresponding candidate comment information are displayed synchronously. Different information is entered into the comment editing area, resulting in different candidate comment information, and consequently, different displayed candidate comment information. In this embodiment, a commenting process begins with the initial triggering of the comment editing area and ends with the triggering of the comment posting control, allowing for one or more information editing operations during a single commenting process.

[0110] This disclosure detects information editing operations in the comment editing area in real time. Upon detection of such operations, it acquires the current content information within the comment editing area and predicts comment information based on this information and the object association information of the object to be commented on, thus generating and displaying candidate comment information. On one hand, by responding to information editing operations in the comment editing area in real time, it enables real-time comment information prediction based on the real-time content information in the area, improving the real-time nature of candidate comment information generation. On the other hand, by integrating the current content information within the comment editing area with the object association information of the object to be commented on during comment information prediction, it ensures that the predicted candidate comment information is associated with the user-input keywords and the object to be commented on, improving the accuracy and scenario adaptability of candidate comment information generation. Furthermore, each candidate comment contains more semantic elements than the current content information input by the user; that is, the user can obtain complete candidate comment information with only a few keywords, enhancing the richness and diversity of the semantic content of the candidate comment information.

[0111] In this embodiment, the object to be commented on can be a target multimedia resource. When the object to be commented on is a target multimedia resource, the object association information of the object to be commented on includes the content information of the target multimedia resource. The content information of the target multimedia resource can be obtained by understanding the content of the target multimedia resource through computer vision technology, such as using a convolutional neural network (CNN) for image feature extraction, or using optical flow to extract motion information of video frames.

[0112] The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes:

[0113] Based on the current content information and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

[0114] Comment information is predicted based on the current content information of the comment editing area and the content information obtained by understanding the target multimedia resource through computer vision technology. At least one candidate comment is obtained for the target multimedia resource. That is, when predicting comment information, the current content information input by the user and the target multimedia resource to be commented are integrated. This makes the predicted comment information related to both the current content information input by the user and the content information of the target multimedia resource, thereby improving the adaptability and accuracy of the candidate comment information to the target multimedia resource.

[0115] In this embodiment, the object to be commented on can be existing comment information of the target multimedia resource. When the object to be commented on is existing comment information of the target multimedia resource, the object association information of the object to be commented on includes the existing comment information and the content information of the target multimedia resource. The content information of the target multimedia resource can be obtained by performing content understanding on the target multimedia resource through computer vision technology, such as using convolutional neural networks (CNN) for image feature extraction, or using optical flow to extract motion information of video frames.

[0116] The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes:

[0117] Based on the current content information, the existing comment information, and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

[0118] When commenting on existing comments of a target multimedia resource, comment information can be predicted by combining current content information, existing comment information, and the content information of the target multimedia resource. This allows the predicted candidate comment information to be associated with the current content information, existing comment information, and the content information of the target multimedia resource, thereby improving the scenario adaptability and accuracy of the candidate comment information.

[0119] In an optional embodiment, comment preference information can also be determined based on the user's historical comment information, and then candidate comment information can be predicted; please refer to [link / reference] for details. Figure 5 It illustrates a method for generating candidate comment information, which may include:

[0120] S510. Obtain the identifier of the target subject that triggered the information editing operation.

[0121] While responding to the information editing operation, the target entity identifier corresponding to the information editing operation can be obtained. The target entity identifier can be the target account corresponding to the information editing operation or the target user identifier corresponding to the information editing operation.

[0122] S520. Determine the comment preference information corresponding to the target subject identifier based on the historical comment information corresponding to the target subject identifier; the historical comment information is the existing comment information of the target subject identifier for the object to be commented.

[0123] The system retrieves historical comment information corresponding to the target entity's identifier and analyzes this information to obtain comment preference information. This preference information may include word choice preferences, sentence structure preferences, and sentiment preferences. For word choice preferences, it may indicate the target entity's habit of using phrases like "in my opinion..." or "my personal suggestion...". For sentence structure preferences, it may indicate the target entity's habit of describing the problem first and then offering suggestions. For sentiment preferences, it may indicate the target entity's habit of maintaining a neutral or positive attitude in their comments.

[0124] S530. Based on the current content information, the object association information of the object to be commented on, and the comment preference information, predict the comment information to obtain the at least one candidate comment information.

[0125] Once the comment preference information corresponding to the target subject's identifier is determined, information prediction can be performed based on the current content information, the object association information of the object to be commented on, and the comment preference information to obtain candidate comment information. This ensures that the candidate comment information contains the comment preference information of the target subject, thus making the candidate comment information compatible with the target subject and realizing the personalized generation of candidate comment information.

[0126] In one specific embodiment, the information editing operation includes an information modification operation on existing content information; thus, when generating candidate comment information, both the content information before and after modification can be fully considered; correspondingly, the step of obtaining the current content information of the comment editing area in response to the information editing operation in the comment editing area includes:

[0127] In response to an information modification operation on existing content information in the comment editing area, the modified content information is determined as the current content information;

[0128] The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes:

[0129] Based on at least one candidate comment corresponding to the existing content information before modification, and at least one candidate comment corresponding to the current content information after modification, multiple candidate comment information for the object to be commented on are determined.

[0130] A single commenting process begins with the initial triggering of the comment editing area and ends with the triggering of the comment posting control. During a single commenting process, one or more information editing operations can be performed. The process of modifying existing content in the comment editing area reflects the user's thought process; both the original and modified content reflect the user's commenting intent. Therefore, during a single commenting process, comment information can be predicted based on both the original and modified content, resulting in at least one candidate comment. Specifically, comment information prediction can be performed based on both the original and modified content and the object association information of the object to be commented on, resulting in at least one candidate comment corresponding to the original content. Similarly, comment information prediction can be performed based on the modified content and the object association information of the object to be commented on, resulting in at least one candidate comment corresponding to the modified content. Combining these candidate comments, multiple candidate comments for the object to be commented on are obtained.

[0131] For example, please see Figure 6 The existing content in the comment editing area before modification is "Persistence is victory," and the corresponding candidate comments displayed may include "Persistence is victory, let the results speak for themselves!" The current content in the comment editing area after modification is "Is persistence useful?" and the corresponding candidate comments displayed may include "Persistence is victory, let the results speak for themselves!" and "Is persistence useful? Don't think that losing weight can change everything." That is, after modifying the content information, the corresponding candidate comments displayed include both the candidate comments corresponding to "Persistence is victory" before modification and the candidate comments corresponding to "Is persistence useful?" after modification, thus making it easier for users to select comment information from a wider range.

[0132] The existing content information before modification and the current content information after modification may correspond to different comment ideas or different sentiment biases. When generating candidate comment information, the content information before and after modification can be taken into account to generate candidate comment information corresponding to the before and after modification respectively, which improves the comprehensiveness of candidate comment information and provides users with a wider range of choices.

[0133] Specifically, the step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes:

[0134] Predict various comment intentions based on the current content information;

[0135] Based on the various comment intentions, the current content information, and the object association information of the object to be commented on, comment information is predicted to obtain at least one candidate comment.

[0136] There may be various different intentions for commenting on a given object. For example, the intentions may include positive, negative, or neutral intentions. Positive intentions may be expressed as "I agree with..." or "I can accept..."; negative intentions may be expressed as "I disagree with..." or "I cannot accept..."; and neutral intentions may be expressed as "I take a neutral stance..." or "I will not comment further...".

[0137] Therefore, given existing content information in the comment editing area, comment intent can be predicted based on the current content information, identifying multiple comment intents. For example, if the current content information is "persistence," the corresponding comment intent could be either positive or negative. Please refer to [link / reference]. Figure 7 When the corresponding comment intention is positive, the generated candidate comment information may include "Persistence is victory. I strongly agree with the viewpoint in this work. As the work says, losing weight will lead to a different life." When the corresponding comment intention is negative, the generated candidate comment information may include "Is persistence useful? I disagree with the viewpoint in this work. Losing weight or not doesn't change anything. To fundamentally change yourself, you need to improve your inner self."

[0138] Furthermore, when displaying candidate comment information, expressions related to intent can be highlighted, such as "strongly agree" and "disagree". The highlighting can be done by highlighting, bolding, changing the font size, or changing the font.

[0139] Therefore, based on the current content information, multiple comment intentions can be predicted to generate candidate comment information corresponding to different intentions, which can enrich the range of candidate comment information, expand users' comment ideas, and provide users with comment information from different dimensions.

[0140] In this embodiment, displaying the at least one candidate comment information includes:

[0141] The candidate comment display window displays at least one candidate comment; the candidate comment display window is independent of the page where the comment editing area is located.

[0142] The page containing the comment editing area is the comment editing page. The comment editing page may also include a keyboard area. The candidate comment display window may be adjacent to the comment editing area, and the candidate comment display window may also cover the keyboard area.

[0143] Therefore, the candidate comment display window is independent of the comment editing page and the comment editing area, allowing operations on the candidate comment display window to be performed freely without being restricted by the comment editing page.

[0144] In an optional embodiment, when the at least one candidate comment information includes multiple candidate comment information, the candidate comment display window includes a candidate comment display area and a comment expansion control;

[0145] The display of the at least one candidate comment information includes:

[0146] The first candidate comment information is displayed in the candidate comment display area;

[0147] After displaying the at least one candidate comment information, the method further includes:

[0148] In response to a touch operation based on the comment expansion control, first candidate comment information and second candidate comment information are displayed in the candidate comment display area; the first candidate comment information and the second candidate comment information are both comment information from the plurality of candidate comment information.

[0149] The first candidate comment information may include one or more candidate comment information. The first candidate comment information may be displayed directly in the candidate comment display area without triggering the comment expansion control. When the comment expansion control is triggered, the second candidate comment information may be displayed. The second candidate comment information may include one or more candidate comment information. Specifically, the first candidate comment information and the second candidate comment information may be displayed in the candidate comment display area in the form of a list.

[0150] Please see Figure 8 It displays a candidate comment window, showing the candidate comment "Persistence is victory, let the results speak for themselves." By triggering the comment expansion control "+", more candidate comments are displayed in the candidate comment display area, including "Just keep going, you can definitely do it." Furthermore, by scrolling the candidate comment display area, users can view and display even more candidate comments.

[0151] By triggering the comment expansion control, more candidate comment information can be displayed, making it easier for users to browse more candidate comments at the same time and providing them with a wider range of choices.

[0152] Furthermore, the method in this embodiment may also include:

[0153] In response to a movement operation on the candidate comment display window, the candidate comment display window is moved to the target location.

[0154] Different users have different usage habits, and users can move the candidate comment display window according to their own habits; or the candidate comment display window may cover the comment editing area, or it may cover the comment editing area when more candidate comment information is displayed after touching the comment expansion control. In this case, in order to avoid affecting the information editing operation in the comment editing area, the candidate comment display window can be moved, thus realizing the flexible movement of the candidate comment display window, which can not only adapt to the usage habits of different users, but also avoid the candidate comment display window covering the comment editing area, thereby improving the user experience.

[0155] After displaying at least one candidate comment for the object to be commented on, the user can select a comment from these candidates and further modify the selected comments; please refer to [link / reference] for details. Figure 9 It illustrates a method for generating related comment information, which may include:

[0156] S910. In response to a selection operation for target comment information, the target comment information is displayed in the comment editing area; the target comment information is any one of the candidate comment information from the at least one candidate comment information.

[0157] Comments can be selected from the displayed candidate comments. The selection can be done by clicking, long-pressing, or dragging the target comment. Once a selection is triggered, the target comment will be displayed in the comment editing area.

[0158] S920. In response to the information modification operation of the target comment information in the comment editing area, perform comment information prediction based on the modified comment information and the object association information of the object to be commented, and obtain at least one associated comment information corresponding to the modified comment information.

[0159] When the target comment information is displayed in the comment editing area, further modification operations can be performed on the target comment information. The corresponding terminal can predict the comment information in real time based on the modified comment information and the object association information of the object to be commented, and obtain at least one related comment information corresponding to the modified comment information. The modification operations on the target comment information can include modifying the wording of the target comment information, or changing the order of sentences, etc.

[0160] S930. Display at least one related comment information.

[0161] When predicting and generating related comment information, the related comment information can be displayed in real time. It's important to note that during the modification of the target comment information, each comment information prediction is triggered by a modification operation. Generally, a modification operation changes the target comment information within the corresponding comment editing area. Based on this changed target comment information, comment information prediction is performed, resulting in at least one related comment corresponding to the current modification operation. Therefore, displaying at least one related comment is a dynamic display of the related comment information corresponding to each modification operation. In other words, in response to a modification operation, the current target comment information is retrieved, and comment information prediction is performed to obtain the related comment information for that modification. This achieves the simultaneous modification of the target comment information and the real-time display of related comment information associated with the modified target comment information, providing more accurate comment information to choose from through user interaction with the target comment information.

[0162] The key point of the comment information display method in this embodiment is:

[0163] 1. Real-time interactivity and continuous optimization: By continuously following user input in real time and combining the order and content of the input, the system continuously recommends the latest selectable comments. This real-time interaction and continuous optimization can more accurately capture user intent and emotional changes, providing users with highly personalized suggestions.

[0164] 2. Multimedia Content Integration: This disclosure combines the understanding of multimedia content such as images and videos with text generation technology to transform multimedia content into text descriptions, thereby generating comment suggestions that match the multimedia content. This integration provides users with a more comprehensive and diverse commenting experience. By integrating speech synthesis and speech recognition technologies, users can input or comment via voice; the system converts the voice content into text and generates appropriate comments. This increases the variety of interactive methods, meets the usage preferences of different users, and improves the flexibility of interaction. 3. Consideration of User Input Order: This disclosure not only focuses on the content of user input but also on the order in which it is input. By analyzing the content entered by the user in sequence, the system can better understand the user's intent, thereby generating more accurate comment content.

[0165] 4. Generation of Multimodal Content: This disclosure is not limited to text content, but can also cover various input modalities such as voice input and voice comments. This multimodal content generation can meet the interaction preferences of different users and provide more flexible and diverse interaction methods. By combining input content from multiple modalities such as text, images, and sound, more diverse and richer comments can be generated, expanding the expressive methods of comment generation and providing a more creative and diverse interactive experience.

[0166] 5. Sentiment Analysis and Emotion-Driven Comment Generation: Introducing sentiment analysis technology to analyze the emotional tendencies of user input and comment subjects, generating sentiment-matched comment content. This enables the generation of comments that better reflect the emotional atmosphere, enhancing the emotional expression and resonance of the comments.

[0167] 6. Continuous User Feedback and Optimization: A user feedback mechanism is introduced, allowing users to adjust and provide feedback on the generated comments. The system continuously optimizes the generation algorithm based on user feedback, making the generated comments more in line with user expectations, enhancing users' sense of control over the generated results, and providing more personalized and satisfactory comment suggestions.

[0168] 7. Enhanced Personalized Recommendations and Sentiment Matching: This disclosure can analyze users' past comments and interaction data, generating comments that match user preferences and emotional inclinations based on users' historical behavior and emotional state, thereby enhancing the personalization and emotional expression of comments. It analyzes users' relationships on social networks, including mutual following and interaction frequency, to generate comment suggestions closely related to these relationships. By generating comments that are more closely aligned with user relationships based on social connections, it enhances the authenticity and human touch of social interactions.

[0169] 8. User Control and Choice: This disclosure grants users greater control, allowing them to choose the most suitable comment from multiple options or adjust them according to their own intentions. This user control and choice can enhance user satisfaction and engagement.

[0170] Through innovations in the key areas mentioned above, this disclosure achieves intelligent comment generation while emphasizing real-time user interaction, diverse expressions, and personalized experiences. This improves the efficiency and quality of comment interaction, making it more adaptable to the needs of different users and scenarios, thereby enhancing user experience and interaction effectiveness.

[0171] The comment display method provided in this embodiment can bring many beneficial effects to users' comment interactions on platforms such as social media and online forums, including:

[0172] Improved Comment Quality: Users can receive high-quality, fluent comments without worrying about language expression. Real-time generated comments more accurately convey user intent, thus improving comment quality and effectiveness. Increased Interaction Efficiency: Users can quickly access suitable comment options without spending significant time thinking about or crafting comment content. This greatly improves the efficiency of user comment interaction and promotes active interaction on the social platform. Personalized Comment Experience: By analyzing user input and context, the system can generate personalized comment suggestions based on each user's interests and preferences, making the comment experience more personalized and satisfying. Promotes Positive Interaction: By providing appropriate and rational comment suggestions, this disclosed technology helps promote positive, rational, and constructive interaction, reducing conflict and controversy. Lowered User Barrier: Even users without rich expressive abilities can receive high-quality comments, lowering the barrier to participation and enabling more users to actively participate in comment interactions. Enhanced User Engagement: Users are more willing to participate in comment interactions when using this technology because they know they can easily obtain valuable comments, thereby enhancing user engagement on the social platform. Increased User Satisfaction: By receiving high-quality, personalized comments, users can participate in interactions with greater satisfaction, increasing their satisfaction and loyalty to the social platform. Data-driven optimization: By leveraging user satisfaction feedback and interaction data, the system can continuously optimize its comment generation algorithm, providing more accurate and user-oriented comment suggestions. This disclosed technology will significantly improve the user commenting experience on social media platforms, promote positive interaction and communication, and simultaneously increase platform activity and user loyalty.

[0173] Figure 10 This is a block diagram illustrating a comment information display device according to an exemplary embodiment. (Refer to...) Figure 10 The device includes:

[0174] The content information acquisition unit 1010 is configured to perform an information editing operation in response to the comment editing area, and acquire the current content information within the comment editing area; the comment editing area is an area used to edit the comment information of the object to be commented on;

[0175] The candidate comment prediction unit 1020 is configured to perform comment information prediction based on the current content information and the object association information of the object to be commented, to obtain at least one candidate comment information for the object to be commented; the current content information is semantically associated with each candidate comment information, and the semantic elements in each candidate comment information are more than the semantic elements in the current content information;

[0176] The candidate comment display unit 1030 is configured to display the information of at least one candidate comment.

[0177] In an exemplary embodiment, when the object to be commented on is a target multimedia resource, the object association information of the object to be commented on includes the content information of the target multimedia resource;

[0178] The candidate comment prediction unit is configured to perform:

[0179] Based on the current content information and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

[0180] In an exemplary embodiment, when the object to be commented on is existing comment information of the target multimedia resource, the object association information of the object to be commented on includes the existing comment information and the content information of the target multimedia resource;

[0181] The candidate comment prediction unit is configured to perform:

[0182] Based on the current content information, the existing comment information, and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

[0183] In one exemplary embodiment, the candidate comment prediction unit includes:

[0184] The target entity identifier acquisition unit is configured to acquire the target entity identifier that triggered the information editing operation.

[0185] The preference information determination unit is configured to determine the comment preference information corresponding to the target subject identifier based on the historical comment information corresponding to the target subject identifier; the historical comment information is the existing comment information of the target subject identifier for the object to be commented on;

[0186] The first prediction unit is configured to perform comment information prediction based on the current content information, the object association information of the object to be commented on, and the comment preference information, to obtain the at least one candidate comment information.

[0187] In one exemplary embodiment, the information editing operation includes an information modification operation on existing content information; the content information acquisition unit is configured to perform:

[0188] In response to an information modification operation on existing content information in the comment editing area, the modified content information is determined as the current content information;

[0189] The candidate comment prediction unit is configured to perform:

[0190] Based on at least one candidate comment corresponding to the existing content information before modification, and at least one candidate comment corresponding to the current content information after modification, multiple candidate comment information for the object to be commented on are determined.

[0191] In one exemplary embodiment, the candidate comment prediction unit includes:

[0192] The intent prediction unit is configured to predict various comment intents based on the current content information;

[0193] The second prediction unit is configured to perform comment information prediction based on the multiple comment intentions, the current content information, and the object association information of the object to be commented on, so as to obtain the at least one candidate comment information.

[0194] In one exemplary embodiment, the candidate comment display unit is configured to display the at least one candidate comment in a candidate comment display window; the candidate comment display window is independent of the page where the comment editing area is located.

[0195] In an exemplary embodiment, when the at least one candidate comment information includes multiple candidate comment information, the candidate comment display window includes a candidate comment display area and a comment expansion control;

[0196] The candidate comment display unit is configured to display first candidate comment information in the candidate comment display area;

[0197] The device further includes:

[0198] The touch display unit is configured to perform a touch operation in response to the comment expansion control, displaying first candidate comment information and second candidate comment information in the candidate comment display area; the first candidate comment information and the second candidate comment information are both comment information from the plurality of candidate comment information.

[0199] In one exemplary embodiment, the apparatus further includes:

[0200] The moving unit is configured to perform a moving operation in response to the candidate comment display window, moving the candidate comment display window to a target location.

[0201] In one exemplary embodiment, the apparatus further includes:

[0202] The comment selection unit is configured to perform a selection operation for a target comment information in response to the target comment information, and to display the target comment information in the comment editing area; the target comment information is any one of the at least one candidate comment information.

[0203] The third prediction unit is configured to perform an information modification operation in response to the target comment information in the comment editing area, and to predict comment information based on the modified comment information and the object association information of the object to be commented, so as to obtain at least one associated comment information corresponding to the modified comment information.

[0204] The associated comment display unit is configured to display at least one associated comment.

[0205] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0206] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided. Optionally, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is able to perform any of the methods described above.

[0207] In an exemplary embodiment, a computer program product is also provided, the computer program product including a computer program stored in a readable storage medium, wherein at least one processor of a computer device reads from the readable storage medium and executes the computer program, causing the device to perform any of the methods described above.

[0208] Furthermore, Figure 11 A schematic diagram of a hardware structure for implementing the methods provided in embodiments of this disclosure is shown. This device may constitute or include the apparatus provided in embodiments of this disclosure. Figure 11 As shown, device 10 may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 11 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, device 10 may also include a... Figure 11 The more or fewer components shown, or having the same Figure 11 The different configurations shown.

[0209] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuitry are generally referred to herein as "data processing circuitry". This data processing circuitry may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within device 10 (or mobile device). As involved in embodiments of this disclosure, the data processing circuitry serves as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0210] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method described in the embodiments of this disclosure. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the aforementioned player preloading method or player running method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the device 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0211] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of device 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0212] The display may be, for example, a touchscreen liquid crystal display (LCD) that allows a user to interact with the user interface of device 10 (or a mobile device).

[0213] Any of the methods described above in this embodiment can be based on Figure 11 The equipment shown is used for implementation.

[0214] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0215] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for displaying comment information, characterized in that, include: In response to an information editing operation in the comment editing area, obtain the current content information within the comment editing area; The comment editing area is a region used to edit comment information for the object to be commented on; the current content information is the keyword information that the user has entered and is currently displayed in the comment editing area; the current content information is updated accordingly as the information editing operation is continuously executed; the information editing operation includes information modification operations on existing content information; The step of obtaining the current content information in the comment editing area in response to an information editing operation in the comment editing area includes: in response to an information modification operation on existing content information in the comment editing area, determining the modified content information as the current content information; Comment information is predicted based on the current content information and the object association information of the object to be commented on, resulting in at least one candidate comment for the object to be commented on; the current content information is semantically associated with each candidate comment, and each candidate comment contains more semantic elements than the current content information; the at least one candidate comment changes dynamically as the current content information changes; the at least one candidate comment is the comment corresponding to the information modification operation; Display at least one candidate comment.

2. The method according to claim 1, characterized in that, When the object to be commented on is a target multimedia resource, the object association information of the object to be commented on includes the content information of the target multimedia resource; The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes: Based on the current content information and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

3. The method according to claim 1, characterized in that, When the object to be commented on is existing comment information of the target multimedia resource, the object association information of the object to be commented on includes the existing comment information and the content information of the target multimedia resource; The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes: Based on the current content information, the existing comment information, and the content information of the target multimedia resource, comment information is predicted to obtain at least one candidate comment.

4. The method according to claim 1, characterized in that, The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes: Obtain the identifier of the target entity that triggered the information editing operation; The comment preference information corresponding to the target subject identifier is determined based on the historical comment information corresponding to the target subject identifier; the historical comment information is the existing comment information of the target subject identifier for the object to be commented on. Based on the current content information, the object association information of the object to be commented on, and the comment preference information, comment information is predicted to obtain at least one candidate comment information.

5. The method according to claim 1, characterized in that, The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes: Based on at least one candidate comment corresponding to the existing content information before modification, and at least one candidate comment corresponding to the current content information after modification, multiple candidate comment information for the object to be commented on are determined.

6. The method according to claim 1, characterized in that, The step of predicting comment information based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on, includes: Predict various comment intentions based on the current content information; Based on the various comment intentions, the current content information, and the object association information of the object to be commented on, comment information is predicted to obtain at least one candidate comment.

7. The method according to claim 1, characterized in that, The display of the at least one candidate comment information includes: The candidate comment display window displays at least one candidate comment; the candidate comment display window is independent of the page where the comment editing area is located.

8. The method according to claim 7, characterized in that, When the at least one candidate comment includes multiple candidate comment information, the candidate comment display window includes a candidate comment display area and a comment expansion control; The display of the at least one candidate comment information includes: The first candidate comment information is displayed in the candidate comment display area; After displaying the at least one candidate comment information, the method further includes: In response to a touch operation based on the comment expansion control, first candidate comment information and second candidate comment information are displayed in the candidate comment display area; the first candidate comment information and the second candidate comment information are both comment information from the plurality of candidate comment information.

9. The method according to claim 7, characterized in that, The method further includes: In response to a movement operation on the candidate comment display window, the candidate comment display window is moved to the target location.

10. The method according to any one of claims 1-9, characterized in that, After displaying the at least one candidate comment information, the method further includes: In response to a selection operation for a target comment information, the target comment information is displayed in the comment editing area; the target comment information is any one of the at least one candidate comment information. In response to the information modification operation of the target comment information in the comment editing area, comment information prediction is performed based on the modified comment information and the object association information of the object to be commented, to obtain at least one associated comment information corresponding to the modified comment information; Display at least one related comment.

11. A device for displaying comment information, characterized in that, include: The content information acquisition unit is configured to perform an action in response to an information editing operation in the comment editing area, and acquire the current content information in the comment editing area. The comment editing area is a region used to edit comment information for the object to be commented on; the current content information is the keyword information that the user has entered and is currently displayed in the comment editing area; the current content information is updated accordingly as the information editing operation is continuously executed; the information editing operation includes information modification operations on existing content information; The step of obtaining the current content information in the comment editing area in response to an information editing operation in the comment editing area includes: in response to an information modification operation on existing content information in the comment editing area, determining the modified content information as the current content information; The candidate comment prediction unit is configured to perform comment information prediction based on the current content information and the object association information of the object to be commented on, to obtain at least one candidate comment for the object to be commented on; the current content information is semantically associated with each candidate comment, and the semantic elements in each candidate comment are more than the semantic elements in the current content information; the at least one candidate comment changes dynamically as the current content information changes; the at least one candidate comment is the comment corresponding to the information modification operation; The candidate comment display unit is configured to display the information of at least one candidate comment.

12. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the comment information display method as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the comment information display method as described in any one of claims 1 to 10.

Images