Comment method, device and equipment, medium and product

Abstract

The invention relates to the technical field of computers, and discloses a comment method and device, equipment, a medium and a product.The method comprises the steps that in response to a comment display operation for a target fragment in a target text, a comment interaction interface corresponding to the target fragment is displayed on a graphical user interface; displaying a formation comment control corresponding to the formation copywriting of the target segment in a comment interaction interface; the formation copywriting is a copywriting determined according to clustering of at least part of historical interaction data of the target fragment; and in response to an interaction operation aiming at the formation comment control, sending comment contents containing the formation copywriting. According to the method, the comments containing the formation copywriting can be generated and published in a one-button mode, manual copying and pasting of the user are not needed, user operation can be greatly simplified, and the participation threshold of following the formation is reduced.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically to a commenting method, apparatus, device, medium, and product. Background Technology

[0002] Comment and interaction features are common in communities and social platforms, such as the comment functions of forums, social media, or document collaboration tools. These features allow users to underline or highlight specific paragraphs of text and add comments, and support interaction between users. Common implementations include reply, like, favorite, or share functions.

[0003] When a user posts a comment, if another user has already posted a similar comment, that user can post the same or similar comment to show agreement or participation, commonly known as "following the crowd." This requires manually copying the original comment text, pasting it into the comment box, and then manually sending it, which is cumbersome for users. Summary of the Invention

[0004] In view of this, this application provides a commenting method, apparatus, device, medium, and product to solve the problem of cumbersome operation when users follow a formation.

[0005] Firstly, this application provides a commenting method, including: In response to a comment display operation targeting a specific segment of the target text, a comment interaction interface corresponding to the target segment is displayed in the graphical user interface; The comment interaction interface displays a formation comment control corresponding to the formation text of the target segment; the formation text is determined by clustering at least part of the historical interaction data of the target segment. In response to an interactive action on the formation comment control, a comment containing the formation text is sent.

[0006] Secondly, this application provides a commenting device, comprising: The display module is used to respond to a comment display operation for a target segment in the target text and display the comment interaction interface corresponding to the target segment in the graphical user interface; The display module is further configured to display a formation comment control corresponding to the formation text of the target segment in the comment interaction interface; the formation text is a text determined by clustering at least a portion of the historical interaction data of the target segment; The processing module is used to send comment content containing the formation text in response to the interactive operation of the formation comment control.

[0007] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the comment method described in the first aspect or any corresponding embodiment.

[0008] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to perform the comment method described in the first aspect or any corresponding embodiment thereof.

[0009] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to perform the comment method described in the first aspect or any corresponding embodiment thereof.

[0010] The commenting method provided in this application, for a target segment with pre-set formation text, will display a formation comment control corresponding to the formation text after entering the comment interaction interface of the target segment; users can generate and publish comments containing the formation text with one click by performing corresponding interactive operations on the formation comment control, without the need for users to manually copy and paste, which can greatly simplify user operations and lower the participation threshold of following the formation; moreover, this quick operation method of following the formation will also attract users to participate more actively, and can encourage users to actively follow the formation, thereby improving the comment interaction experience. Attached Figure Description

[0011] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0012] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic flowchart of a first type of commenting method according to an embodiment of the present invention; Figure 3 This is a first schematic diagram of a comment interaction interface according to an embodiment of the present invention; Figure 4 This is a second schematic diagram of a comment interaction interface according to an embodiment of the present invention; Figure 5 This is a third schematic diagram of a comment interaction interface according to an embodiment of the present invention; Figure 6This is a schematic diagram of a second flowchart of the commenting method according to an embodiment of the present invention; Figure 7 This is a schematic diagram of generating formation text according to an embodiment of the present invention; Figure 8 This is a schematic diagram illustrating the display of target text according to an embodiment of the present invention; Figure 9 This is a fourth schematic diagram of a comment interaction interface according to an embodiment of the present invention; Figure 10 This is a schematic diagram of an interface after sending a comment according to an embodiment of the present invention; Figure 11 This is a detailed process diagram of a commenting method according to an embodiment of the present invention; Figure 12 This is a structural block diagram of a commenting device according to an embodiment of the present invention; Figure 13 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0014] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0015] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0016] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0017] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0018] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0020] As an optional application scenario of this invention, such as Figure 1 As shown, application 101 is installed in terminal device 110, and user 130 can interact with application 101 through terminal device 110 and / or access device of terminal device 110.

[0021] For example, application 101 can be any application that provides social services. For instance, application 101 could be a community or forum application, through which users can publish articles and comment on the content. Figure 1 In the application scenario shown, if application 101 is active, the terminal device 110 can display the interface 102 of application 101. The interface 102 may include various pages that application 101 can provide, such as interactive pages, settings pages, query pages, etc.

[0022] In some embodiments, terminal device 110 is communicatively connected to server 120 to provide services to application 101. Terminal device 110 may be a mobile terminal, fixed terminal, or portable terminal, etc., including but not limited to mobile phones, desktop computers, laptop computers, multimedia tablets, e-book devices, gaming devices, or any combination thereof, including accessories and peripherals of these devices or any combination thereof. In some embodiments, terminal device 110 may also support any type of interface, and server 120 may be various types of computing systems or servers capable of providing computing power, including but not limited to mainframes, edge computing nodes, computing devices in cloud environments, etc.

[0023] It should be noted that, Figure 1 This is merely an example of an application scenario and does not limit the scope of protection of this invention.

[0024] The embodiments of the present invention will now be described with reference to the accompanying drawings. It should be understood that the pages shown in the drawings are merely examples, and various page designs are possible in practice. The various graphic elements on the page may have different arrangements and different visual representations; one or more elements may be omitted or replaced, and one or more other elements may also be present, without any limitation in the embodiments of the present invention. Furthermore, the embodiments described below primarily pertain to terminal device 110. It should be understood that the actions described relative to terminal device 110 can be performed by application 101 on terminal device 110, or can be performed by application 101 in conjunction with its server (e.g., server 120).

[0025] According to an embodiment of the present invention, a comment method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0026] This embodiment provides a commenting method that can be used in the aforementioned terminal devices, such as mobile terminals like mobile phones and tablets. Figure 2 This is a flowchart of a commenting method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps.

[0027] Step S201: In response to the comment display operation for the target segment in the target text, the comment interaction interface corresponding to the target segment is displayed in the graphical user interface.

[0028] In this embodiment, when a user uses a terminal device, the terminal device may have applications installed that enable interaction with other users, such as forum applications or community applications. After the user opens the application, the terminal device's graphical user interface (GUI) can display various texts provided by the application. These texts may be published to the application platform by the user or other users. Furthermore, the user can open and browse texts that interest them; for ease of description, the text currently being browsed by the user is referred to as the target text.

[0029] The target text can be divided into multiple segments, which are the smallest units for users to comment on. For example, each paragraph of the target text can be considered a segment, or a single word or phrase within the target text can also be considered a segment, depending on the specific circumstances. Users can then post comments on each segment of the target text.

[0030] For example, each paragraph of the target text is a segment, and users can underline or mark the paragraphs they are interested in and add comments.

[0031] Furthermore, users can view the comment information corresponding to each segment of the target text, provided that segment has been commented on by other users. For ease of description, the segment from which users view comment information is referred to as the target segment.

[0032] For example, by clicking on the target fragment, a user can trigger an operation to display comments on that fragment, i.e., a comment display operation; or, for fragments in the target text that have been commented on by users, a specific identifier can be displayed, such as information like the number of comments or the number of comments displayed at the corresponding position of the fragment, and by clicking on the specific identifier, the user can also trigger the comment display operation.

[0033] Once the comment display operation is received, the graphical user interface of the terminal device can be controlled to display the comment interaction interface corresponding to the target segment. This comment interaction interface is used to display the comment information corresponding to the target segment, including previous comments from various users on that segment.

[0034] For example, if the content corresponding to the target segment is: "Congratulations on passing the exam". Figure 3 The comment interface corresponding to the target segment is shown. For example... Figure 3 As shown, the comment interaction interface displays several comments that users have already posted, including "Congratulations!" and "Excellent! Congratulations!!"

[0035] Step S202: Display the formation comment control corresponding to the formation text of the target segment in the comment interaction interface; the formation text is the text determined by clustering at least part of the historical interaction data of the target segment.

[0036] In this embodiment, for the target segment, there is user interaction behavior on the target segment, and the generated interaction data is the historical interaction data; for example, the interaction behavior can be a comment, and correspondingly, the historical interaction data is historical comment data. Figure 3 For example, the historical comment data for this target segment includes: Username 001 commented "Congratulations!", Username 002 commented "Congratulations!", Username 003 commented "Excellent! Congratulations!!", Username 004 commented "Congratulations!!", etc.

[0037] By analyzing the historical interaction data of the target segment, it can be determined whether there is a pattern in the interaction behavior under the target segment, that is, whether there are neat and uniform or highly consistent comment content or comment type. If a pattern exists, relevant copy can be generated based on some or all of the historical interaction data, that is, pattern copy.

[0038] Specifically, at least a portion of the historical interaction data of the target segment can be clustered to identify historical interaction data related to the formation, and then the appropriate formation text can be determined based on this portion of historical interaction data. For example, one historical comment related to the formation can be selected as the formation text (e.g., the historical comment with the most likes can be used as the formation text); or, multiple historical comment data can be combined to generate a more suitable formation text, such as generating formation text based on a large model.

[0039] If the target segment has a formation text, when the comment interaction interface is displayed in the graphical user interface, a formation comment control will be additionally displayed in the comment interaction interface. The formation comment control corresponds to the formation text. For example, the formation comment control contains the text corresponding to the formation text.

[0040] by Figure 3 Taking the example of the comments shown, if there are highly consistent comments, then corresponding formatted text can be generated based on these comments (i.e., historical comment data). For example, if the formatted text is "Congratulations!", then a formatted comment control containing the formatted text "Congratulations!" can be further displayed in the comment interaction interface.

[0041] Figure 4 Another schematic diagram of the comment interaction interface is shown, such as... Figure 4 As shown, if the target segment contains the formation text "Congratulations!", then the formation comment control 301 can be additionally displayed on the comment interaction interface.

[0042] Understandable. Figure 3 This is the comment interaction interface for fragments that do not have a specific text format. Figure 4 This is the comment interaction interface corresponding to the segment with formatted text. For a specific target segment, it can be determined in advance whether it has formatted text, and it will be directly displayed when the comment interaction interface of that target segment is opened. Figure 3 or Figure 4 The corresponding comment interaction interface.

[0043] Step S203: In response to the interactive operation of the formation comment control, send comment content containing the formation text.

[0044] In this embodiment, if a user of the terminal device also wants to post comments with uniform content, i.e., wants to follow the same format, the user can directly initiate an interactive operation on the format comment control. This interactive operation can be, for example, a click or a long press. After the user triggers the interactive operation on the format comment control, content containing the format text will be automatically generated and sent. This eliminates the need for the user to copy comments already posted by other users, enabling one-click operation.

[0045] by Figure 4 As shown in the example, if a user clicks the formation comment control 301, a comment containing "Congratulations!" will be automatically posted. The comment interaction interface after posting this comment can be as follows: Figure 5 As shown in the image. Username 005 is the username corresponding to the user using this terminal device; that is, with a single click, username 005 can post comments in a neat and consistent manner.

[0046] Understandable, such as Figure 4 As shown, the comment interaction interface also includes an input box 302, through which users can manually enter the comments they want to post, which will not be described in detail here.

[0047] The commenting method provided in this embodiment, for a target segment with pre-set formation text, will display a formation comment control corresponding to the formation text after entering the comment interaction interface of the target segment; users can generate and publish a comment containing the formation text with one click by performing the corresponding interactive operation on the formation comment control, without the need for users to manually copy and paste, which can greatly simplify user operation and lower the participation threshold of following the formation; moreover, this quick operation method of following the formation will also attract users to participate more actively, and can attract users to actively follow the formation, thus improving the comment interaction experience.

[0048] This embodiment provides another commenting method, which can be used on the aforementioned terminal devices, such as mobile terminals like mobile phones and tablets. Figure 6 This is a flowchart of a commenting method according to an embodiment of the present invention, such as... Figure 6 As shown, the process includes the following steps.

[0049] Step S601: Determine the formation text corresponding to the target segment.

[0050] In this embodiment, for each segment of the target text, it can be pre-determined whether the corresponding layout text can be determined. Taking a target segment as an example, a suitable layout text can be determined based on at least some of the historical interaction data of the target segment.

[0051] It's understandable that the formation text can be determined by the server or processed and determined by the terminal device itself. Generally, the formation text for each segment is determined uniformly by the server, and the terminal device only needs to obtain the formation text.

[0052] Specifically, step S601 may include steps a1 to a2.

[0053] Step a1: Obtain historical interaction data for the target segment.

[0054] Step a2: Clustering determines the formation interaction data in the historical interaction data.

[0055] Step a3: Determine the corresponding formation text based on the formation interaction data.

[0056] As shown above, users can interact with the target segment, thereby generating historical interaction data for that segment. If this historical interaction data includes formation-related interaction data, this data can be extracted, and the formation text for the target segment can be determined based on this data. This formation interaction data characterizes the formation features of the comment section and can be used to generate formation text.

[0057] It's understandable that for a target segment, if it involves formation behavior, the corresponding historical interaction data needs to reach a certain amount. Therefore, the process of generating formation text for the target segment can only be triggered after the amount of historical interaction data exceeds a certain value. This historical interaction data can be all interaction data before the target segment, or interaction data within a recent period (such as the most recent day, the most recent month, etc.).

[0058] In some alternative implementations, users can cluster the target segment to determine the corresponding interaction data through different interaction methods. As shown above, this historical interaction data may include historical comment data, such as... Figure 3 Comment data, etc., as shown.

[0059] In the process of determining the formation text, the above step a2 "clustering to determine the formation interaction data in the historical interaction data" may specifically include the following steps b1 to b2.

[0060] Step b1 involves performing semantic analysis on each historical comment data set and determining the semantic similarity between them.

[0061] Step b2: Determine the formation interaction data based on multiple historical comment data with semantic similarity exceeding the similarity threshold.

[0062] In this embodiment, if the historical comment data of the target segment exceeds a certain value, all historical comment data can be processed into text vectorization, and then the semantic similarity between each historical comment data can be calculated. If the semantic similarity exceeds a preset similarity threshold, it can be indicated that some of the historical comment data are highly related and can be used as a unified formation. Therefore, these historical comment data can be used as formation interaction data.

[0063] In this process, semantic similarity can be calculated pairwise, and historical comment data can be clustered based on these semantic similarities. If they can be clustered into one category (historical comment data with semantic similarity greater than the similarity threshold are clustered into one category), and the number of historical comment data after clustering exceeds a certain value, it means that there are a sufficient number of semantically similar historical comment data for the target segment. These historical comment data can be used as formation interaction data.

[0064] Optionally, step b2, "determining formation interaction data based on multiple historical comment data with semantic similarity exceeding a similarity threshold," may specifically include steps b21 to b23.

[0065] Step b21: Determine the corresponding comment dataset based on multiple historical comment data whose semantic similarity exceeds the similarity threshold.

[0066] Step b22: Determine the formation confidence of the comment dataset.

[0067] Step b23: Determine the formation interaction data based on the historical comment data in the comment dataset whose formation confidence meets the preset confidence conditions.

[0068] In this embodiment, for multiple historical comment data with semantic similarity exceeding the similarity threshold, a corresponding dataset, namely a comment dataset, can be generated. This comment dataset includes these historical comment data with semantic similarity exceeding the similarity threshold.

[0069] For this comment dataset, determine the confidence level at which the comment dataset is suitable as formation interaction data, i.e., the formation confidence level. The higher the formation confidence level, the more obvious the formation features in the comment dataset are, and the more suitable it is as formation interaction data.

[0070] Specifically, if the formation confidence of the comment dataset meets a preset confidence condition, then the historical comment data in the comment dataset can be used as the subsequent formation interaction data. This confidence condition can be that the formation confidence exceeds a preset confidence threshold; or, if there are multiple comment datasets (e.g., multiple historical comment data can be clustered into multiple classes), then the confidence condition can be: the formation confidence exceeds the preset confidence threshold, and the formation confidence is the highest, meaning that only the data with the highest formation confidence will be used to generate the formation text.

[0071] Optionally, step b22, “determining the formation confidence of the comment dataset”, may include steps b221 to b223.

[0072] Step b221: Determine the time density of the comment dataset based on the publication time of multiple historical comment data in the comment dataset.

[0073] Step b222: Determine the user clustering coefficient based on the user characteristics corresponding to the users in the historical comment data of the comment posting dataset.

[0074] Step b223: Determine the formation confidence of the comment dataset based on time density, user clustering coefficient, and semantic similarity corresponding to the comment dataset.

[0075] In this embodiment, the confidence level of the formation can be evaluated from multiple perspectives. Specifically, for multiple historical comment data in the comment dataset, the density of published comments, i.e., the time density, can be determined based on the publication time of these historical comment data. The time density can specifically be the density of published historical comment data within a preset time period (e.g., quantity or frequency); for example, it can be required that no fewer than three similar comments appear within a certain time period (e.g., 10 minutes, one hour, etc.).

[0076] Furthermore, since these historical comment data are posted by the respective users, their user characteristics can be identified. Then, based on the similarity of these user characteristics, a corresponding user clustering coefficient can be determined. In other words, the user clustering coefficient represents the degree of feature similarity among the users who posted this historical comment data. For example, corresponding user embedding vectors can be generated based on users' basic information, and the user clustering coefficient can be calculated based on these embedding vectors. The higher the user clustering coefficient, the more likely the users participating in the comments belong to the same interest group.

[0077] By combining the temporal density, user clustering coefficients, and semantic similarity of the comment dataset itself, the formation confidence of the comment dataset can be comprehensively determined. For example, the temporal density, user clustering coefficients, and semantic similarity can be weighted to calculate the formation confidence.

[0078] For example, the formation confidence score is calculated as: semantic similarity × a + temporal density × b + user clustering coefficient × c, where a, b, and c are preset weights, and their sum is 1. If the formation confidence score exceeds a preset threshold (e.g., 0.75), historical comment data from the comment dataset can be used as formation interaction data.

[0079] The semantic similarity of the comment dataset can be determined based on the semantic similarity between various historical comment data. For example, the highest semantic similarity (or the average semantic similarity) can be used as the semantic similarity of the comment dataset. Furthermore, the semantic similarity of the comment dataset can be dynamically adjusted; for instance, the higher the number of likes on a historical comment, the greater the semantic similarity of the comment dataset, and consequently, the higher the formation confidence.

[0080] Optionally, the generated formation text can be updated in real time, and the process of updating the formation text may include: statistically analyzing the interactive operations of the formation comment control, validating the formation text based on the statistical results; and if the formation text fails the validation, regenerating the formation text corresponding to the target segment based on at least some of the historical interaction data of the target segment.

[0081] In this embodiment, during the verification process, user participation data can be collected. Specifically, the interaction operations of each user with the formation comment control can be counted, such as the number of interaction operations, frequency, and whether there are any interaction operations. Based on these statistical results, the formation execution can be verified to realize the verification of the generated formation text.

[0082] Figure 7 This diagram illustrates a method for generating formatted text based on users' historical comment data. For example... Figure 7 As shown, if users can post comments using underlined text, real-time semantic analysis can be performed on the underlined comment data (i.e., historical comment data) to identify and generate corresponding formatted text. The process of formatted text identification and generation specifically includes: text vectorization, similarity calculation, and finally, generating the corresponding formatted text. When generating formatted text, it can be based solely on the interaction data of each format, or it can be further combined with the text of the original paragraph (i.e., the target segment) to comprehensively generate suitable formatted text.

[0083] The generated formation text can be validated for confidence, such as... Figure 7 As shown, the process specifically includes: collecting user engagement data, validating the formation confidence level, and if the current formation text is inappropriate (low confidence level), then the formation text needs to be regenerated to update the formation text. For formation text that passes the validation, formation interaction can be displayed, such as displaying a formation comment control containing the formation text.

[0084] In this embodiment, content understanding and recognition are performed on the historical comment data in the comment section to extract core key semantics. Through similarity calculation, the core viewpoints of the corresponding comment section are summarized. Combined with the thematic context of the specific underlined comment paragraph, corresponding formation text is generated, allowing users to follow the formation with one click.

[0085] In some alternative implementations, when a user interacts with a target segment, they may not post text-containing content but instead express emotional sentiments, such as giving a "like." Based on these emotional expressions, corresponding historical sentiment data can be determined; that is, historical interaction data includes historical sentiment data.

[0086] In the process of determining the formation text, the above step a2 "clustering to determine the formation interaction data in the historical interaction data" may specifically include the following steps c1 to c2.

[0087] Step c1: Determine the sentiment type and the corresponding number of sentiment expressions corresponding to the historical sentiment data.

[0088] Step c2: Determine the formation interaction data based on the historical emotional data corresponding to the emotional types whose emotional expression frequency meets the preset frequency conditions.

[0089] In this embodiment, a user's emotional expression can be categorized into multiple emotional types, and correspondingly, historical emotional data may also correspond to multiple emotional types; for example, the emotional type may include types expressing liking and types expressing disliking. For each emotional type, the corresponding number of emotional expressions can be statistically determined, and this number of emotional expressions is also the number of historical emotional data points under the corresponding emotional type.

[0090] For a given emotion type, if the number of emotional expressions meets a preset threshold, then that emotion type can be considered to possess certain formation characteristics. In other words, the historical emotion data corresponding to that emotion type can be used as formation interaction data for generating formation-based copy. The preset threshold can be greater than a preset number, meaning that the historical emotion data for emotion types with a greater than preset number of emotional expressions can be used to generate formation interaction data.

[0091] Optionally, if the formation interaction data is generated based on historical sentiment data, then step a3 above, "determine the corresponding formation text based on the formation interaction data", may include steps a31 to a32.

[0092] Step a31: Determine the corresponding sentiment level words based on the number of sentiment statements corresponding to the formation interaction data.

[0093] Step a32: Based on the sentiment level words, fill in the copy template corresponding to the sentiment type of the formation interaction data to determine the corresponding formation copy.

[0094] In this embodiment, for the formation interaction data, the corresponding sentiment intensity words can be determined based on the number of sentiment expressions. The greater the number of sentiment expressions, the stronger the corresponding sentiment intensity word. For example, artificial intelligence can be used to enhance the generation of corresponding intensity words to prevent the intensity words from being too simplistic and avoid the template-based use of intensity words.

[0095] Furthermore, for various emotional types, copywriting templates can be pre-set. The generated emotional intensity words can then be filled into the corresponding templates to produce suitable copywriting. This copywriting template is only a basic template; it can be used to generate copywriting that is essentially the same in format.

[0096] For example, if the emotional types are divided into two categories, sweet and sad, the copy template for the sweet type of interactive data could be: "{degree word} sweet + {emoji}", and the generated copy could be: "So sweet it'll give you cavities!" ”, in which “ "" represents the corresponding emoji. For the torture-themed formation interaction data, the text template can be, for example, "tortured to the point of {reaction}{emoji}", and the generated formation text can be, for example, "tortured to the point of angina".

[0097] It is understandable that the copywriting generated based on historical sentiment data can also be subject to secondary verification, such as confidence verification, which will not be elaborated here.

[0098] Step S602: Display a formation marker at the position corresponding to the target segment; the formation marker is used to indicate that the target segment has a formation text.

[0099] In this embodiment, when a user needs to view target text, they can input an operation to display the target text. For example, by clicking on the area corresponding to the target text in the text list interface, the user can control the terminal device to enter the details page of the target text in the graphical user interface, and thus display the target text.

[0100] When displaying target text, some or all segments can be displayed in the graphical user interface. If a target segment with formation text is displayed, a formation marker can be displayed at the corresponding position of the target segment to indicate that the target segment has formation text.

[0101] Figure 8 This illustrates a diagram of displaying target text, such as... Figure 8 As shown, the target text contains multiple paragraphs (each paragraph is a segment). If the third paragraph, "Congratulations on passing the exam," has a formation tag, then a formation tag 804 can be generated for it. Figure 8The example shown uses a "+1" shape as the formation marker, but other markers can also be used. This embodiment does not limit the specific shape of the formation marker. Furthermore, the formation marker can be static or dynamic, and this embodiment does not limit this as well.

[0102] The formation marker can be just a marker, or it can be a comment identifier (or comment control). That is, the formation marker can include at least one of the following: the comment identifier corresponding to the target segment, the number of comments (e.g., the number of comments is 156, or the number of comments is 1000+, etc.), and the number of emotional expressions (e.g., the number of emotional expressions is 171, or the number of emotional expressions is Max, etc.). The specific details can be determined based on the actual situation.

[0103] Traditional formation comments generally require users to discover them independently, resulting in a high attrition rate. In this embodiment, segments identified as containing "formation-following" comments (i.e., formation text) can display special formation markers after the corresponding segments, creating an atmosphere of following the formation under the corresponding segments and attracting users to actively click and enter.

[0104] Step S603: In response to the comment display operation for the target segment in the target text, the comment interaction interface corresponding to the target segment is displayed in the graphical user interface.

[0105] Please see details Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0106] Optionally, step S603, "in response to the comment display operation for the target segment in the target text, display the comment interaction interface corresponding to the target segment in the graphical user interface", may include steps d1 to d2.

[0107] Step d1: Display the comment identifier corresponding to the target fragment in the target text in the graphical user interface.

[0108] Step d2: In response to the interactive operation for the comment identifier, display the comment interaction interface corresponding to the target fragment in the graphical user interface.

[0109] In this embodiment, the details page of the target text can display comment icons corresponding to at least some segments. These comment icons are controls that respond to user actions. When the user performs a corresponding interactive operation (e.g., a click operation) on the comment icon, the comment interaction interface corresponding to the target segment can be displayed in the graphical user interface, that is, the interface jumps from the details page of the target text to the comment interaction interface corresponding to the target segment.

[0110] Optionally, step d1, "displaying the comment identifier corresponding to the target fragment in the target text in the graphical user interface", may include step d11 and / or step d12.

[0111] Step d11: Display the target fragment and the first comment identifier corresponding to the target fragment in the graphical user interface.

[0112] Step d12, in response to the selection operation of the target fragment in the target text, displays the second comment identifier corresponding to the target fragment in the graphical user interface.

[0113] In this embodiment, the comment identifier corresponding to the target fragment, i.e., the first comment identifier, can be directly displayed on the details page of the target text. Alternatively, the user can select the target fragment and then its corresponding comment identifier, i.e., the second comment identifier, can be displayed.

[0114] like Figure 8 As shown, when a user wants to comment on a paragraph, they can select the paragraph to be commented on, such as paragraph 801. This will bring up the corresponding interactive window 802, which includes various controls such as "Underlined Comment," "So Sweet," "So Heartbreaking," and "Share." One or more of these controls can serve as a secondary comment identifier for paragraph 801. For example, clicking the "Underlined Comment" control will bring up the comment interaction interface or other interfaces where the user can input text. Clicking controls such as "So Sweet" or "So Heartbreaking" will trigger an emotional expression behavior, generating corresponding emotional data for paragraph 801. Here, "So Sweet" means the paragraph is very sweet, and "So Heartbreaking" means the paragraph is very heartbreaking.

[0115] Furthermore, for each paragraph in the target text, if it has been interacted with (with comments or emotional expressions), a corresponding comment identifier, i.e., the first comment identifier, can be generated at the end of that paragraph. For example... Figure 8 As shown, the first paragraph, "The weather is great today," has a corresponding comment tag of 803, indicating that the first paragraph has been commented on as "sweet" 171 times; the second paragraph has 17 comments, the third paragraph has 156 comments, the fourth paragraph has no comments, the fifth paragraph has been commented on as "sweet" more than the preset number of times, and is marked as "sweetness max"; the sixth paragraph, "He cried with excitement," has been commented on as "angst max" more than the preset number of times, and is marked as "angst max".

[0116] For example, if a user wants to comment on the first or third paragraph, the user clicks... Figure 8 The comment identifier 803 or formation marker 804 shown can trigger the comment display operation of the corresponding segment, and then display the comment interaction interface corresponding to the target segment in the graphical user interface.

[0117] Step S604: If the target segment has a formation text, display the formation comment control corresponding to the formation text in the comment interaction interface.

[0118] Please see details Figure 2Step S202 of the illustrated embodiment will not be described again here.

[0119] Optionally, the method further includes: displaying at least a portion of historical comment data used to determine the formation text on the comment interaction interface.

[0120] In this embodiment, if a user has previously commented on the target segment, there will be a certain amount of historical comment data. If the target segment contains a formatted text, and the formatted text is based on the historical comment data, then at least a portion of the historical comment data used to determine the formatted text can be preferentially displayed in the comment interaction interface of the target segment.

[0121] like Figure 4 As shown, since the graphical user interface can only display a limited amount of content at a time, for target segments with formation text, historical comment data related to the formation text can be displayed first for users to view.

[0122] Optionally, the above step "displaying at least a portion of the historical comment data used to determine the formation text on the comment interaction interface" may specifically include: sorting each historical comment data according to the attribute information of each historical comment data; the attribute information includes whether the historical comment data is used to determine the formation text, and the historical comment data used to determine the formation text is sorted first; and displaying at least a portion of the sorted historical comment data on the comment interaction interface.

[0123] In this embodiment, each historical comment data has certain attribute information. This attribute information includes whether the historical comment data is used to determine the layout text. For example, a flag can be added to the historical comment data to indicate whether it is used to determine the layout text. In addition, the attribute information may also include the number of likes, posting time, etc., of the historical comment data. Based on these attribute information, the historical comment data are sorted.

[0124] Specifically, queuing metrics can be determined based on the attribute information of historical comment data; the higher the queuing metric, the higher the ranking. For example, more likes and earlier posting times result in higher queuing metrics. Furthermore, historical comment data used to determine the ranking of text is more likely to have higher queuing metrics than historical comment data not used for ranking; the higher the ranking, the more likely it is to be prioritized for display. In other words, users are more likely to see the top-ranked historical comment data directly when they open the comment interaction interface.

[0125] Figure 9 This shows a schematic diagram of a comment interaction interface, such as... Figure 9As shown, the comment interaction interface displays the original target segment, as well as some or all of the historical comment data. Furthermore, the comment interaction interface also includes a formation comment control 901, which is similar in principle to the aforementioned formation comment control 301, and will not be described in detail here.

[0126] Step S605: In response to the interactive operation of the formation comment control, send comment content containing the formation text.

[0127] Please see details Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0128] In some alternative implementations, after step S605 "sending comment content containing the formation text", the method may further include steps e1 and / or e2.

[0129] Step e1: Within the preset time window, a send icon will pop up at the position corresponding to the formation comment control.

[0130] Step e2: Feedback vibration command to the terminal device. The vibration command is used to control the vibration of the terminal device.

[0131] Figure 10 This shows a schematic diagram of an interface after a comment is sent. Figure 9 and Figure 10 As shown, after a user clicks the formation comment control 901, a send icon 1001 will pop up in the upper right corner of the formation comment control 901 within a certain time window (e.g., 2 seconds) to highlight the user's behavior of following the formation and increase user engagement. The send icon 1001 is used to indicate the behavior of following the formation.

[0132] Similarly, after a user clicks on the formation comment control, vibration feedback can be introduced in the interaction layer, that is, controlling the terminal device (such as a smartphone) to vibrate, thereby combining the vibration feedback function of the terminal device to give the user a certain sense of participation.

[0133] Figure 11 A detailed process diagram of this commenting method is shown. (See attached diagram.) Figure 11 As shown, for the target paragraph, after triggering the formation function, data can be extracted, specifically historical sentiment data and historical comment data.

[0134] If triggered by sentiment data, such as when the quantity or proportion of sentiment data exceeds a certain value, historical sentiment data for the target paragraph can be collected, processed, and the paragraph corresponding to the target paragraph can be identified. For example, if a user clicks... Figure 8When the "sweet" icon appears, corresponding emotional data can be recorded, including: paragraph ID, emotional type, and number of expressions. The number of expressions can be used to calculate the emotional concentration, so as to generate diverse formation copy based on different emotional concentration values.

[0135] If triggered by comment data, such as when the number of comments exceeds a certain value, historical comment data of the target paragraph can be collected, and the data can be cleaned and semantically understood. Finally, the original content of the target paragraph can be combined to generate the layout copy.

[0136] If both comment data and sentiment data can be used to generate formation copy, one can be chosen to use one of them. For example, the formation copy generated based on comment data can be used first.

[0137] If the target paragraph generates relevant formation text, formation effects (such as adding formation marker 804) and formation text (such as adding formation comment control 901) can be added. After the user participates in the formation and sends it, the corresponding comment will be automatically generated and the formation +1 display effect will be triggered, such as popping up the send icon 1001.

[0138] The commenting method provided in this embodiment utilizes the semantic recognition capabilities of users' emotional expression behaviors (such as expressions of sweetness or sadness) during text browsing and the corresponding segment comment content. Through extraction, recognition, and processing, it ultimately generates frequently occurring comment content in the corresponding comment section, which serves as follow-along text for the corresponding paragraph. By increasing the interactive nature of the follow-along text, the operation of following the pattern can be simplified, and users can be encouraged to spontaneously participate in the interactive gameplay of following the pattern, i.e., participate in the comment section pattern, thereby improving the atmosphere of the comment section for the corresponding paragraph. Extracting low-threshold interactive behaviors from the paragraph, aggregating emotional expressions, and generating corresponding follow-along text can effectively improve the coverage of follow-along text. This method can help users actively discover the follow-along phenomenon in the corresponding paragraph, increase the dwell time in the target text, and help improve user activity; through the interactive gameplay of following the pattern, community cultural symbols can be formed, which can enhance users' sense of belonging.

[0139] This embodiment also provides a commenting device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0140] This embodiment provides a commenting device, such as Figure 12 As shown, the device includes: Display module 1201 is used to display the comment interaction interface corresponding to the target segment in the graphical user interface in response to the comment display operation for the target segment in the target text; The display module 1201 is further configured to display a formation comment control corresponding to the formation text of the target segment in the comment interaction interface; the formation text is a text determined by clustering at least a portion of the historical interaction data of the target segment; The processing module 1202 is used to send comment content containing the formation text in response to the interactive operation of the formation comment control.

[0141] In some alternative implementations, the formation text is determined based on the following: Obtain the historical interaction data of the target segment; Clustering identifies the formation interaction data in the historical interaction data, and the corresponding formation text is determined based on the formation interaction data.

[0142] In some alternative implementations, the historical interaction data includes historical comment data; The clustering process determines the formation interaction data in the historical interaction data, including: Semantic analysis is performed on each of the historical comment data, and the semantic similarity between the historical comment data is determined; Based on multiple historical comment data with semantic similarity exceeding the similarity threshold, the formation interaction data is determined.

[0143] In some optional implementations, determining the formation interaction data based on multiple historical comment data whose semantic similarity exceeds a similarity threshold includes: Based on multiple historical comment data with semantic similarity exceeding the similarity threshold, the corresponding comment dataset is determined; Determine the formation confidence of the comment dataset; Based on historical comment data in the comment dataset where the formation confidence level meets the preset confidence level conditions, the formation interaction data is determined.

[0144] In some optional implementations, determining the formation confidence of the comment dataset includes: The time density of the comment dataset is determined based on the publication time of multiple historical comment data in the comment dataset; Determine the user clustering coefficient based on the user characteristics corresponding to the users who published historical comments in the aforementioned comment dataset; The formation confidence of the comment dataset is determined based on the time density, the user clustering coefficient, and the semantic similarity corresponding to the comment dataset.

[0145] In some alternative implementations, the historical interaction data includes historical sentiment data; The clustering process determines the formation interaction data in the historical interaction data, including: Determine the sentiment type and the corresponding number of sentiment expressions corresponding to the historical sentiment data; Based on the historical emotional data corresponding to the emotional types whose emotional expression frequency meets the preset frequency conditions, the formation interaction data is determined.

[0146] In some optional implementations, determining the corresponding formation text based on the formation interaction data includes: The corresponding sentiment level words are determined based on the number of sentiment expressions corresponding to the formation interaction data. Based on the emotional level words, fill in the copy template corresponding to the emotional type of the formation interaction data to determine the corresponding formation copy.

[0147] In some alternative implementations, after sending the comment content containing the formation text, the processing module 1202 is further configured to: Within the preset time window, a send icon will pop up at the position corresponding to the formation comment control; And / or, to feed back vibration commands to the terminal device, the vibration commands being used to control the vibration of the terminal device.

[0148] In some alternative implementations, the process of updating the formation text includes: The interactive operations of the formation comment control are statistically analyzed, and the formation text is validated based on the statistical results. If the formation text fails the validation, the formation text corresponding to the target segment is re-determined based on at least part of the historical interaction data of the target segment.

[0149] In some optional implementations, the step of displaying a comment interaction interface corresponding to the target segment in a graphical user interface in response to a comment display operation for a target segment in the target text includes: Display the comment identifier corresponding to the target fragment in the target text in the graphical user interface; In response to an interactive operation on the comment identifier, the comment interaction interface corresponding to the target segment is displayed in the graphical user interface.

[0150] In some optional implementations, displaying the comment identifier corresponding to the target fragment in the target text in the graphical user interface includes: The target segment and the first comment identifier corresponding to the target segment are displayed in the graphical user interface; And / or, In response to a selection operation on a target segment in the target text, a second comment identifier corresponding to the target segment is displayed in the graphical user interface.

[0151] In some optional embodiments, the processing module 1202 is further configured to: The comment interaction interface displays at least a portion of historical comment data used to determine the formation text.

[0152] In some optional implementations, displaying at least a portion of historical comment data for determining the formation text on the comment interaction interface includes: The historical comment data are sorted according to their attribute information; the attribute information includes whether the historical comment data is used to determine the formation text, and the historical comment data used to determine the formation text is sorted first. The comment interaction interface displays at least a portion of the historical comment data in sorted order.

[0153] In some optional embodiments, the processing module 1202 is further configured to: A formation marker is displayed at the position corresponding to the target segment; the formation marker is used to indicate that the target segment has a formation text.

[0154] In some optional implementations, the formation marker includes at least one of the following: comment identifier corresponding to the target segment, comment quantity information, and sentiment expression frequency information.

[0155] The commenting apparatus provided in this disclosure can execute the commenting method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0156] Figure 13 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0157] The following is a detailed reference. Figure 13This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 1301, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1302 or a program loaded from memory 1308 into random access memory (RAM) 1303. The RAM 1303 also stores various programs and data required for the operation of the electronic device. The processor 1301, ROM 1302, and RAM 1303 are interconnected via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0158] Typically, the following devices can be connected to I / O interface 1305: input devices 1306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 1308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1309. Communication device 1309 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 13 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0159] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 1309, or installed from memory 1308, or installed from ROM 1302. When the computer program is executed by processor 1301, it performs the functions defined in the commentary method of the embodiments of the present invention.

[0160] Figure 13 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0161] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium after being downloaded via a network. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods described in the above embodiments.

[0162] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0163] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A commenting method, characterized in that, The method includes: In response to a comment display operation targeting a specific segment of the target text, a comment interaction interface corresponding to the target segment is displayed in the graphical user interface; The comment interaction interface displays a formation comment control corresponding to the formation text of the target segment; the formation text is determined by clustering at least part of the historical interaction data of the target segment. In response to an interactive action on the formation comment control, a comment containing the formation text is sent.

2. The method according to claim 1, characterized in that, The formation text was determined based on the following method: Obtain the historical interaction data of the target segment; Clustering identifies the formation interaction data in the historical interaction data, and the corresponding formation text is determined based on the formation interaction data.

3. The method according to claim 2, characterized in that, The historical interaction data includes historical comment data; The clustering process determines the formation interaction data in the historical interaction data, including: Semantic analysis is performed on each of the historical comment data, and the semantic similarity between the historical comment data is determined; Based on multiple historical comment data with semantic similarity exceeding the similarity threshold, the formation interaction data is determined.

4. The method according to claim 3, characterized in that, The process of determining formation interaction data based on multiple historical comment data points whose semantic similarity exceeds a similarity threshold includes: Based on multiple historical comment data with semantic similarity exceeding the similarity threshold, the corresponding comment dataset is determined; Determine the formation confidence of the comment dataset; Based on historical comment data in the comment dataset where the formation confidence level meets the preset confidence level conditions, the formation interaction data is determined.

5. The method according to claim 4, characterized in that, Determining the formation confidence of the comment dataset includes: The time density of the comment dataset is determined based on the publication time of multiple historical comment data in the comment dataset; Determine the user clustering coefficient based on the user characteristics corresponding to the users who published historical comments in the aforementioned comment dataset; The formation confidence of the comment dataset is determined based on the time density, the user clustering coefficient, and the semantic similarity corresponding to the comment dataset.

6. The method according to claim 2, characterized in that, The historical interaction data includes historical sentiment data; The clustering process determines the formation interaction data in the historical interaction data, including: Determine the sentiment type and the corresponding number of sentiment expressions corresponding to the historical sentiment data; Based on the historical emotional data corresponding to the emotional types whose emotional expression frequency meets the preset frequency conditions, the formation interaction data is determined.

7. The method according to claim 6, characterized in that, The step of determining the corresponding formation text based on the formation interaction data includes: The corresponding sentiment level words are determined based on the number of sentiment expressions corresponding to the formation interaction data. Based on the emotional level words, fill in the copy template corresponding to the emotional type of the formation interaction data to determine the corresponding formation copy.

8. The method according to claim 1, characterized in that, After sending the comment containing the formation text, the method further includes: Within the preset time window, a send icon will pop up at the position corresponding to the formation comment control; And / or, to feed back vibration commands to the terminal device, the vibration commands being used to control the vibration of the terminal device.

9. The method according to claim 1, characterized in that, The process of updating the aforementioned formation text includes: The interactive operations of the formation comment control are statistically analyzed, and the formation text is validated based on the statistical results. If the formation text fails the validation, the formation text corresponding to the target segment is re-determined based on at least part of the historical interaction data of the target segment.

10. The method according to claim 1, characterized in that, The step of displaying a comment interaction interface corresponding to the target segment in a graphical user interface in response to a comment display operation for a target segment in a target text includes: Display the comment identifier corresponding to the target fragment in the target text in the graphical user interface; In response to an interactive operation on the comment identifier, the comment interaction interface corresponding to the target segment is displayed in the graphical user interface.

11. The method according to claim 9, characterized in that, The step of displaying the comment identifier corresponding to the target fragment in the target text in the graphical user interface includes: The target segment and the first comment identifier corresponding to the target segment are displayed in the graphical user interface; And / or, In response to a selection operation on a target segment in the target text, a second comment identifier corresponding to the target segment is displayed in the graphical user interface.

12. The method according to claim 1, characterized in that, The method further includes: The comment interaction interface displays at least a portion of historical comment data used to determine the formation text.

13. The method according to claim 12, characterized in that, The display of at least a portion of historical comment data used to determine the formation text on the comment interaction interface includes: The historical comment data are sorted according to their attribute information; the attribute information includes whether the historical comment data is used to determine the formation text, and the historical comment data used to determine the formation text is sorted first. The comment interaction interface displays at least a portion of the historical comment data in sorted order.

14. The method according to claim 1, characterized in that, The method further includes: A formation marker is displayed at the position corresponding to the target segment; the formation marker is used to indicate that the target segment has a formation text.

15. The method according to claim 14, characterized in that, The formation markers include at least one of the following: the comment identifier corresponding to the target segment, the number of comments, and the number of emotional expressions.

16. A commenting device, characterized in that, The device includes: The display module is used to respond to a comment display operation for a target segment in the target text and display the comment interaction interface corresponding to the target segment in the graphical user interface; The display module is further configured to display a formation comment control corresponding to the formation text of the target segment in the comment interaction interface; the formation text is a text determined by clustering at least a portion of the historical interaction data of the target segment; The processing module is used to send comment content containing the formation text in response to the interactive operation of the formation comment control.

17. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the comment method according to any one of claims 1 to 15.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the commenting method according to any one of claims 1 to 15.

19. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the commenting method according to any one of claims 1 to 15.

Images