Information processing method and device, electronic equipment, medium and program product

Abstract

The invention provides an information processing method, which can be applied to the technical fields of big data, artificial intelligence, large models, visual processing and the like, and comprises the following steps: in response to a comment triggering operation, determining an evaluation information set about a to-be-evaluated object, the evaluation information set comprising evaluation information of candidate evaluation roles, the expression mode of the evaluation information is matched with the style of the candidate evaluation role; determining evaluation information of the evaluation roles from the evaluation information set based on the evaluation roles interested by the user; and displaying the evaluation information of the evaluation role. The invention further provides an information processing device, electronic equipment, a storage medium and a program product.

Description

Technical Field

[0001] This disclosure relates to the technical fields of big data, artificial intelligence, large models, and visual processing, and more specifically, to an information processing method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] In existing technologies, user reviews of the object to be evaluated are typically displayed on the application's user interface (UI). Taking a restaurant as an example, user reviews of aspects such as the restaurant's hygiene, service quality, and food taste can be displayed.

[0003] In realizing the present invention, the inventors discovered at least the following problems in the related technology: generally, only user evaluation information is displayed on the user interface, and the information type is limited. Summary of the Invention

[0004] In view of the above, this disclosure provides an information processing method, apparatus, electronic device, storage medium, and program product.

[0005] One aspect of this disclosure provides an information processing method, comprising: in response to a review triggering operation, determining a set of evaluation information about an object to be evaluated, wherein the set of evaluation information includes evaluation information of candidate evaluation roles, the expression of which matches the writing style of the candidate evaluation roles; determining evaluation information of evaluation roles from the set of evaluation information based on evaluation roles that the user is interested in; and displaying the evaluation information of the evaluation roles.

[0006] According to embodiments of this disclosure, the evaluation information in the evaluation information set is determined in the following manner: based on the writing style information of the candidate evaluation role, the original evaluation information for the object to be evaluated is rewritten to obtain evaluation information that matches the writing style of the candidate evaluation role, wherein the writing style information includes at least one of the following: writing style type, writing style description information, and example.

[0007] According to embodiments of this disclosure, the evaluation information in the evaluation information set is determined in the following manner: the writing style information of the candidate evaluation role and multiple original evaluation information for the object to be evaluated are input into a large language model to obtain evaluation information that matches the writing style of the candidate evaluation role, wherein the writing style information includes at least one of the following: writing style type, writing style description information, and example.

[0008] According to embodiments of this disclosure, the information processing method further includes: determining initial original evaluation information from historical interaction behavior data of the object to be evaluated; verifying the authenticity of the initial original evaluation information based on the historical interaction behavior data and the initial original evaluation information to obtain a verification result; and using the initial original evaluation information as the original evaluation information if the verification result indicates that the initial original evaluation information is authentic.

[0009] According to embodiments of this disclosure, the information processing method further includes: performing semantic similarity matching on the evaluation information and the writing style information to obtain an information matching result; and updating the evaluation information to the evaluation information set when the information matching result indicates that the expression mode of the evaluation information matches the writing style of the candidate evaluation role.

[0010] According to embodiments of this disclosure, the information processing method further includes: determining an image of an evaluation role from an image set based on the evaluation role, such that the image of the evaluation role is displayed while the evaluation information of the evaluation role is being displayed, wherein the image set includes image images of candidate evaluation roles, and the character images in the image images match the candidate evaluation roles.

[0011] According to embodiments of this disclosure, the image in the atlas is determined as follows: the character image information of the candidate evaluation character and the original image of the candidate evaluation character are input into a multimodal large model to obtain the image of the candidate evaluation character.

[0012] According to embodiments of this disclosure, the information processing method further includes: performing information matching on the image semantic information of the image and the text semantic information of the character image to obtain an image-text matching result; and updating the image to the image set when the image-text matching result indicates that the image matches the candidate evaluation character.

[0013] According to embodiments of this disclosure, the information processing method further includes: determining the attention level of each of a plurality of candidate evaluation roles based on the user's historical interaction behavior data with respect to the object to be evaluated, wherein the attention level represents the degree of interest of the user in the candidate evaluation roles; and determining the evaluation role that the user is interested in from the plurality of candidate evaluation roles based on the attention level of each of the plurality of candidate evaluation roles.

[0014] According to embodiments of this disclosure, displaying evaluation information of evaluation roles includes: when there are multiple evaluation roles, displaying evaluation information of a target evaluation role, wherein the target evaluation role has a higher attention level than other evaluation roles, and the other evaluation roles include evaluation roles other than the target evaluation role among the multiple evaluation roles.

[0015] According to embodiments of this disclosure, the information processing method further includes: displaying multiple role controls on a user interface while simultaneously displaying the evaluation information of a target evaluation role, the role controls representing evaluation roles; and updating information in response to a triggering operation of a target control, displaying the evaluation information of the evaluation role corresponding to the target control on the user interface.

[0016] Another aspect of this disclosure provides an information processing apparatus, comprising: an operation parsing module, configured to determine a set of evaluation information about an object to be evaluated in response to a comment triggering operation, wherein the set of evaluation information includes evaluation information of candidate evaluation roles, and the expression of the evaluation information matches the writing style of the candidate evaluation roles; an information determination module, configured to determine the evaluation information of evaluation roles from the set of evaluation information based on evaluation roles that the user is interested in; and an information display module, configured to display the evaluation information of the evaluation roles.

[0017] Another aspect of this disclosure provides an electronic device, including: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method described above.

[0018] Another aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0019] Another aspect of this disclosure provides a computer program product including computer-executable instructions that, when executed, are used to implement the method described above.

[0020] The information processing method provided in this disclosure provides a new way of displaying evaluation information. It can determine the evaluation role that the user is interested in from multiple candidate evaluation roles of different types in response to the user's review request, and display evaluation information that matches the writing style of the evaluation role. This improves the richness, interest and diversity of the displayed evaluation information, while enhancing the user's personalized experience. Attached Figure Description

[0021] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0022] Figure 1 This illustration schematically shows an exemplary system architecture to which information processing methods and apparatus can be applied according to embodiments of the present disclosure;

[0023] Figure 2 A flowchart illustrating an information processing method according to an embodiment of the present disclosure is shown schematically.

[0024] Figure 3A A schematic diagram illustrating the generation of a review request according to an embodiment of this disclosure is shown.

[0025] Figure 3B The illustration shows a schematic diagram of the display evaluation information and image according to an embodiment of the present disclosure;

[0026] Figure 3C A schematic diagram illustrating an updated user interface according to an embodiment of the present disclosure is shown.

[0027] Figure 4 A schematic diagram illustrating the determination of evaluation information according to an embodiment of the present disclosure is shown.

[0028] Figure 5 A schematic diagram illustrating a determination of an image according to an embodiment of the present disclosure is shown.

[0029] Figure 6 A block diagram schematically illustrates an information processing apparatus according to embodiments of the present disclosure; and

[0030] Figure 7 A block diagram of an electronic device suitable for implementing an information processing method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0031] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0032] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0033] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0034] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0035] In the embodiments disclosed herein, the collection, updating, analysis, processing, use, transmission, provision, disclosure, and storage of data (e.g., including but not limited to user personal information) comply with relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. In particular, necessary measures have been taken to prevent unauthorized access to user personal information data and to safeguard user personal information security, network security, and national security.

[0036] This disclosure provides an information processing method, comprising: responding to a review trigger operation, determining a set of evaluation information about the object to be evaluated, wherein the set of evaluation information includes evaluation information of candidate evaluation roles, and the expression of the evaluation information matches the writing style of the candidate evaluation roles; determining the evaluation information of the evaluation roles from the set of evaluation information based on the evaluation roles that the user is interested in; and displaying the evaluation information of the evaluation roles.

[0037] The information processing method provided in this disclosure provides a new way of displaying evaluation information. It can determine the evaluation role that the user is interested in from multiple candidate evaluation roles of different types in response to the user's review request, and display evaluation information that matches the writing style of the evaluation role. This improves the richness, interest and diversity of the displayed evaluation information, while enhancing the user's personalized experience.

[0038] Figure 1 An exemplary system architecture for which information processing methods and apparatus can be applied according to embodiments of this disclosure is illustrated.

[0039] It is important to note that Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0040] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0041] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (for example only).

[0042] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0043] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using terminal devices 101, 102, and 103 (for example only). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0044] It should be noted that the information processing method provided in this embodiment can generally be executed by server 105. Correspondingly, the information processing device provided in this embodiment can generally be located in server 105. The information processing method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the information processing device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Alternatively, the information processing method provided in this embodiment can also be executed by terminal devices 101, 102, or 103, or by other terminal devices different from terminal devices 101, 102, or 103. Correspondingly, the information processing device provided in this embodiment can also be located in terminal devices 101, 102, or 103, or in other terminal devices different from terminal devices 101, 102, or 103.

[0045] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0046] Figure 2 A flowchart illustrating an information processing method according to an embodiment of the present disclosure is shown schematically.

[0047] like Figure 2 As shown, the method includes operations S210~S230.

[0048] In operation S210, in response to the review trigger operation, the set of evaluation information about the object to be evaluated is determined.

[0049] In operation S220, the evaluation information of the evaluation role is determined from the evaluation information set based on the evaluation role that the user is interested in.

[0050] When operating S230, the evaluation information of the evaluated role is displayed.

[0051] A review trigger action can refer to a user's action on the user interface to request review information. For example, a review trigger action could be a user clicking on a review control displayed on the user interface, but it is not limited to this. It can also refer to certain interactive behaviors of the user interface that meet preset conditions, such as double-clicking the interface area that displays user review information.

[0052] The objects to be evaluated can include, but are not limited to, goods, shops, or food. Anything that can be evaluated is acceptable.

[0053] Evaluation information sets can be pre-configured for the objects to be evaluated. These sets can include evaluation information from candidate evaluation roles. The expression style of the evaluation information can match the writing style of the candidate evaluation roles. The writing style of the candidate evaluation roles is not limited and can include different types such as classical Chinese, modern poetry, ancient poetry, and Song Dynasty lyrics. For example, candidate evaluation roles could include ancient poet AA, lyricist BB, modern poet CC, ..., and novelist MM.

[0054] Taking the candidate evaluation character AA as an example, AA's writing style is realistic and humorous, so the evaluation information can be expressed in a realistic and humorous way. AA's image is that of someone with long hair, a beard, thick eyebrows, and big eyes, so the image can be a cartoon character with long hair, a beard, thick eyebrows, and big eyes.

[0055] The system can filter user feedback from a collection of reviews by identifying reviewers who are of interest, and then display their reviews to the user. The reviews are presented in a style that mimics the reviewers' writing, giving the user the feeling that the reviewers are personally evaluating the object being reviewed. This increases the interest and variety of the reviews, thereby improving the user experience.

[0056] Compared to displaying the evaluation information of any candidate evaluation role, displaying the evaluation information of evaluation roles that users are interested in can meet users' personalized needs.

[0057] According to embodiments of this disclosure, in response to a user's review request, an evaluation role that the user is interested in is determined from multiple candidate evaluation roles of different types, and evaluation information that matches the writing style of the evaluation role is displayed. This improves the richness, interest, and diversity of the displayed evaluation information while enhancing the user's personalized experience.

[0058] The previous text explained how the comment trigger operation displays the comment information. The following text explains how the comment trigger operation can also display an image.

[0059] According to embodiments of this disclosure, the information processing method may further include: determining an image of an evaluation role from an image set based on the evaluation role, such that the image of the evaluation role is displayed simultaneously with the evaluation information of the evaluation role. The image set includes image images of candidate evaluation roles, wherein the character images in the image sets match the candidate evaluation roles.

[0060] Taking the candidate evaluation character AA as an example, AA's character image is long hair tied up, with a beard, thick eyebrows and big eyes, so the image can be a cartoon image of long hair tied up, with a beard, thick eyebrows and big eyes.

[0061] The following section will explain how to display the evaluation information and image of the evaluated character.

[0062] Figure 3A A schematic diagram illustrating the generation of a review request according to an embodiment of this disclosure is shown.

[0063] like Figure 3A As shown, taking a takeout restaurant as an example, the user interface can display the restaurant's information, such as its name, address, images of its signature dishes, and descriptions of those dishes, including price and name. A review control can also be displayed on the user interface, for example, represented by an elliptical ring with the word "Review" inside. Users can trigger a review by clicking the review control.

[0064] Based on the review trigger operation, a review information retrieval instruction is generated. This review information retrieval instruction may include object information of the object to be reviewed, such as object identification information, but is not limited to this. It may also include user information of the user, such as user identification information, and may also include request information representing "requesting review information of the object to be reviewed".

[0065] In response to the instruction to obtain review information, the information processing method provided in this embodiment is executed to obtain the review information and image of the reviewing character, and then performs the following... Figure 3B The display shown.

[0066] Figure 3B The illustration shows a schematic diagram of the display evaluation information and image according to an embodiment of the present disclosure.

[0067] like Figure 3B As shown, the image can be displayed on the left and the evaluation information on the right side of the user interface, with the evaluation character in the image facing the evaluation information, in accordance with the conventional "left-to-right" reading habit.

[0068] According to an optional embodiment of this disclosure, when there are multiple evaluation roles, the evaluation information of the target evaluation role can be displayed on the user interface. However, this is not the only possibility. The user interface can also display an image of the target evaluation role and its evaluation information. The target evaluation role may have higher attention than other evaluation roles, which may include evaluation roles other than the target evaluation role from among multiple evaluation roles.

[0069] Taking the evaluation characters including Ancient Poet AA, Ancient Poet BB, and Ancient Poet CC as an example, if the user is most interested in Ancient Poet AA, then Ancient Poet AA can be selected as the target evaluation character, and his image and evaluation information can be displayed on the user interface. The expression of the evaluation information, "The aroma of stir-fried pork with chili peppers fills the room... Why not enjoy a cup of wine under the setting sun?" can imitate the writing style of Ancient Poet AA.

[0070] Optionally, the format and display method of the evaluation information can be adaptively adjusted. For example, the number of characters per line can be dynamically calculated based on the width of the user interface of the terminal device (e.g., 25 characters / line for large screens, 18 characters / line for small screens), and the maximum number of lines displayed can be precisely controlled (e.g., a maximum of 5 lines). Once the evaluation information exceeds the limit, an expand button will be automatically displayed to ensure the integrity of the content and visual appeal.

[0071] Optionally, the text color, thickness, wavy underline, and other font formatting of the evaluation information can be adjusted according to different writing styles.

[0072] You can also add jumpable links to the review information. Users can control the safe redirection by triggering the jumpable links to quickly access more information, thus improving the richness and diversity of the review information.

[0073] According to embodiments of this disclosure, multiple evaluation roles are pre-determined to improve the candidate capability. Furthermore, the importance of each role is quantified based on the attention metric representing the user's level of interest, and the user's most interesting role is displayed on the user interface, thereby improving the user experience. This is combined with the display interface of the mobile phone as a terminal device, thereby improving the adaptability to hardware resources.

[0074] The following will be done through, as follows Figure 3C The diagram shown illustrates how to switch between information related to multiple evaluation roles.

[0075] Figure 3C A schematic diagram illustrating an updated user interface according to an embodiment of the present disclosure is shown.

[0076] like Figure 3C As shown, taking the evaluation roles including Ancient Poet AA, Author BB, and Ancient Poet CC as an example, the user interface A displays an image of Ancient Poet AA as the target evaluation role, along with evaluation information, while simultaneously displaying multiple role controls, each representing an evaluation role. For example, there are role controls labeled "Ancient Poet AA," "Author BB," and "Ancient Poet CC" within rectangular boxes.

[0077] like Figure 3C As shown, in response to the triggering operation of the target control, such as the click operation of the target control, information is updated, and the evaluation information and image of the evaluation role "Author BB" corresponding to the target control "Author BB" are displayed on the user interface B.

[0078] Optionally, during the information update process, the image and evaluation information of the evaluation character corresponding to the target control can be updated on the user interface at the same time. However, it is not limited to this; the evaluation information or image of the evaluation character corresponding to the target control can also be updated only on the user interface.

[0079] Optionally, the images and evaluation information of multiple evaluation roles can be temporarily stored in the cache of the terminal device to quickly switch and display them in response to the user's display request, thereby improving the response speed.

[0080] According to embodiments of this disclosure, by providing multiple evaluation role controls with different writing styles, it is possible to support content presentation from different perspectives and enhance the user's multi-dimensional perception of the evaluation object. Furthermore, by triggering the role controls to update information, the convenience of information switching is improved, thereby enhancing the user's operating experience.

[0081] The preceding text explained how to display evaluation information and images of evaluation characters that users are interested in. The following text will explain how to identify evaluation characters that users are interested in.

[0082] According to embodiments of this disclosure, when performing such Figure 2 Following operation S210 and before operation S220, the information processing method may include the following operations: determining the level of interest for each of multiple candidate evaluation roles based on the user's historical interaction data with the object to be evaluated; and determining the evaluation role that the user is interested in from among the multiple candidate evaluation roles based on the level of interest for each of the multiple candidate evaluation roles.

[0083] Attention level can represent the degree of user interest in candidate evaluation roles.

[0084] Historical interaction data can include action data on the object to be evaluated. For example, at least one of liking, saving, commenting, and sharing. Based on historical interaction data, the degree of user interest in candidate evaluation roles can be determined, and quantifiable attention can be used to measure the attention given to each of the multiple candidate evaluation roles, thereby improving the uniformity of the measurement criteria.

[0085] Optionally, the method for determining attention levels differs depending on the type of historical interaction data. For example, for actions like saving and liking, a predetermined score can be used to determine the attention level. For sharing, the predetermined score can be accumulated based on the number of shares to obtain the attention level. For evaluation information, semantic recognition can be performed on the evaluation information, and the attention level can be determined based on the favorability and mapping relationship of the semantic representation. When historical interaction data includes various types of action data, multiple attention levels can be weighted and summed to obtain the attention level for candidate evaluation roles.

[0086] According to embodiments of this disclosure, the attention level of each candidate evaluation role is determined by the user's level of interest in the candidate evaluation roles, thereby improving the user's personalized experience. Furthermore, determining the user's attention level based on historical interaction data can improve the accuracy and effectiveness of attention level assessment through big data statistical methods.

[0087] The previous section explained the front-end display of evaluation information; the following section will explain how to generate evaluation information sets.

[0088] According to embodiments of this disclosure, the evaluation information in the evaluation information set can be determined in the following way: based on the writing style information of the candidate evaluation role, the original evaluation information for the object to be evaluated is rewritten to obtain evaluation information that matches the writing style of the candidate evaluation role.

[0089] Writing style information may include at least one of the following: writing style type, writing style description, and example. The writing style description may refer to a specific explanation or definition. Examples may include at least one instance to provide further explanation.

[0090] Taking the ancient poet AA as a candidate evaluation role as an example, the writing style could be romantic lyricism. The description of the writing style could include a definition of romantic lyricism: "Romantic lyricism is a mode of expression that centers on emotion, emphasizes subjective experience and imagination, and integrates Romanticism's pursuit of an ideal world with the direct transmission of emotion characteristic of lyrical art." An example could be "a poem by the ancient poet AA."

[0091] Compared to rewriting the original evaluation information by combining one or two of the writing style information, combining the writing style type, writing style description information, and examples as writing style information to rewrite the original evaluation information can increase the richness and diversity of the information referenced in the rewriting, thereby improving the degree of matching between the evaluation information and the writing style of the candidate evaluation role and the success rate of rewriting.

[0092] There are no restrictions on how the original evaluation information is obtained; for example, it can be user evaluation information from other users regarding the object being evaluated, obtained from an open-source database. There is no limit to the amount of original evaluation information.

[0093] Optionally, deep learning models, such as encoders and decoders (Transformers), can be used to rewrite the original evaluation information based on the writing style information to obtain the evaluation information. For example, the writing style information and the original evaluation information can be input into the encoder and decoder for rewriting to obtain the evaluation information of Artificial Intelligence Generated Content (AIGC).

[0094] Alternatively, a Large Language Model (LLM) can be used to rewrite the original evaluation information based on writing style information to obtain the evaluation information. For example, the writing style information of the evaluator and the original evaluation information for the object to be evaluated can be input into the Large Language Model to obtain evaluation information that matches the writing style of the candidate evaluator.

[0095] Optionally, the large language model can use an encoder-decoder as the basic network framework, with multiple encoders-decoders combined to form a larger network. This leverages the strong text processing capabilities of the encoders-decoders to encode the original evaluation information and stylistic information, and then rewrites and decodes based on the encoded features to obtain the evaluation information.

[0096] According to embodiments of this disclosure, original evaluation information can be rewritten using artificial intelligence generation methods to obtain evaluation information that matches the writing style of the candidate evaluation role, thereby improving rewriting efficiency. Furthermore, using writing style information as a reference during rewriting can increase the success rate of rewriting, thus improving the quality of rewriting.

[0097] According to another embodiment of this disclosure, the type of evaluation information may further include a summary type. When the type of evaluation information is a summary type, the evaluation information in the evaluation information set can be determined in the following manner.

[0098] For example, the writing style information of the candidate evaluation role and multiple original evaluation information for the object to be evaluated are input into the large language model to obtain evaluation information that matches the writing style of the candidate evaluation role.

[0099] When there are multiple pieces of original evaluation information, the large language model can perform multiple information processing operations such as summarizing and rewriting, without specifying the order in which summarizing and rewriting are performed. For example, multiple pieces of original evaluation information can be summarized to obtain summarized evaluation information. The summarized evaluation information can then be rewritten to obtain evaluation information that matches the writing style of the candidate evaluation role. Alternatively, multiple pieces of original evaluation information can be rewritten separately to obtain multiple rewritten evaluation information. These rewritten evaluation information can then be summarized to obtain evaluation information that matches the writing style of the candidate evaluation role.

[0100] By utilizing a large language model to process multiple raw evaluation messages for the object to be evaluated based on the writing style information of candidate evaluators, prompts for the large language model can be constructed. For example, the writing style information of candidate evaluators can be added to a text prompt template to generate text prompts. By inputting multiple raw evaluation messages and text prompts for the object to be evaluated into the large language model, evaluation messages matching the writing style of the candidate evaluators can be obtained. The text prompt template can include prompts instructing the large language model to perform a "summarize + rewrite" thought chain task.

[0101] According to embodiments of this disclosure, multiple operations, such as "summarizing and rewriting the writing style," are performed on multiple original evaluation information using artificial intelligence generation methods to obtain evaluation information that matches the writing style of the candidate evaluation role. This fully leverages the high processing power of large language models, improving the processing efficiency of combining rewriting and summarizing. Furthermore, by using writing style information as a reference, summarizing and rewriting multiple original evaluation information can achieve multi-styled summary expressions, further enhancing user satisfaction.

[0102] For example, an open-source large language model can be used to obtain sample evaluation information as labels based on the original evaluation information of multiple samples and the sample writing style information of the sample evaluation roles. The original evaluation information and sample writing style information of multiple samples are used as input data, and the sample evaluation information is used as reference output data, combined to form training data. A pre-trained large language model is trained using the training data to obtain the large language model provided in the above embodiment, which has a lighter network structure compared to the open-source large language model.

[0103] Therefore, by utilizing the large language model provided in the above embodiments, evaluation information for multiple candidate evaluation roles can be generated, reducing generation costs and resource consumption.

[0104] Optionally, the original evaluation information can be determined from historical interaction data of the object to be evaluated. Historical interaction data can be input by multiple different users through human-computer interaction, and can include one or more of the following: text, images, and data representing interactive operations, thereby increasing the diversity of the original evaluation information. Text can be evaluation text expressing feelings. Images can be photographs of the object to be evaluated. Interactive operations can include, but are not limited to, liking, saving, and sharing.

[0105] Due to the diversity of content and data sources of historical interaction behavior data, it is difficult to guarantee that all of it is authentic and valid. In the process of determining original evaluation information based on historical interaction behavior data, authenticity verification can be performed to improve the validity and accuracy of the evaluation information for the identified candidate evaluation roles.

[0106] According to embodiments of this disclosure, the original evaluation information can be determined in the following manner.

[0107] For example, initial evaluation information is determined from historical interaction data of the object to be evaluated. Based on the historical interaction data and the initial evaluation information, the authenticity of the initial evaluation information is verified, and a verification result is obtained. If the verification result indicates that the initial evaluation information is authentic, the initial evaluation information is used as the original evaluation information.

[0108] Text and images can be extracted from historical interaction data. Text can be preprocessed, such as removing invalid characters, extra spaces, and other invalid content, as well as masking sensitive information. Images can also undergo semantic recognition to obtain image-text representing the image's intent. The preprocessed text and image-text are then combined as initial raw evaluation information.

[0109] The authenticity of initial original evaluation information can be verified by combining other data from historical interaction behavior data, excluding "text and images related to the evaluation." For example, verification can include at least one of the following: identity verification, verification of the authenticity of other interaction behavior data, and verification of the evaluation information's authenticity. The identity of the user making the evaluation can be determined based on user login data, login address, and other data from historical interaction behavior data, thus obtaining an identity authenticity verification result. Multiple historical interaction behavior data entered by the same user at different times can be compared and analyzed to determine the authenticity of other interaction behavior data, thus obtaining verification results for the authenticity of other interaction behavior data. For example, other interaction behavior data includes "purchasing vouchers" and "purchasing this dish." The authenticity of initial original evaluation information can also be verified by combining other interaction behavior data, resulting in a verification result for the authenticity of the evaluation information. For example, to verify whether or not to purchase dish A from the restaurant, the authenticity of the image including dish A can be verified, resulting in a verification result for the authenticity of the evaluation information.

[0110] According to embodiments of this disclosure, verifying the authenticity of initial, original evaluation information can improve the authenticity and effectiveness of the evaluation information displayed to users, preventing the spread of false information. Furthermore, performing verification in different ways and from different dimensions further improves the effectiveness and accuracy of the verification results, enhancing the verification effect and avoiding errors in the verification results.

[0111] The above text explained how to ensure the validity of information before processing; the following text will combine... Figure 4 Explain how to ensure the validity of the processed information.

[0112] Figure 4 A schematic diagram illustrating the determination of evaluation information according to an embodiment of the present disclosure is shown.

[0113] like Figure 4 As shown, historical interaction data for the object to be evaluated can be obtained from an open-source database, and initial original evaluation information can be determined from this data. The authenticity of the initial original evaluation information is verified; if the verification result indicates that the initial original evaluation information is authentic, it is used as the original evaluation information.

[0114] like Figure 4 As shown, multiple original evaluation information and the writing style information of candidate evaluation roles are input into the large language model to obtain evaluation information.

[0115] like Figure 4 As shown, semantic similarity matching is performed between evaluation information and writing style information to obtain information matching results. When the information matching results indicate that the expression style of the evaluation information matches the writing style of the candidate evaluation role, the evaluation information is updated in the evaluation information set.

[0116] Optionally, feature vectors for evaluation information and writing style information can be extracted separately, and the information matching result can be obtained by comparing vector similarity. However, this is not the only option. The semantics of evaluation information and writing style information can also be identified separately to obtain two semantic information sets. The information matching result is determined based on the matching degree between the two semantic information sets.

[0117] Optionally, the matching degree can be compared with a matching degree threshold. If the matching degree is greater than or equal to the matching degree threshold, it is determined that the information matching result indicates that the evaluation information matches the writing style of the candidate evaluation role. Conversely, if the matching degree is less than the matching degree threshold, it is determined that the information matching result indicates that the evaluation information does not match the writing style of the candidate evaluation role. If the information matching result indicates that the evaluation information matches the writing style of the candidate evaluation role, it can be determined that the quality of the obtained evaluation information meets the standard, and the evaluation information can be updated to the evaluation information set. If the information matching result indicates that the evaluation information does not match the writing style of the candidate evaluation role, it can be determined that the quality of the obtained evaluation information does not meet the standard, and it can be deleted. Alternatively, the information matching result, the writing style information of the candidate evaluation role, and multiple original evaluation information can be re-input into the large language model to obtain evaluation information, and the quality of the evaluation information can be re-verified until the expression of the obtained evaluation information matches the writing style of the candidate evaluation role.

[0118] According to embodiments of this disclosure, after obtaining the evaluation information of candidate evaluation roles, by performing a semantic matching operation on the evaluation information and writing style information, it can be ensured that the expression of the evaluation information in the evaluation information set matches the writing style of the candidate evaluation roles, thereby improving the expression of the evaluation information displayed to the user and its fit with the evaluation roles, improving the user's reading experience, and thus improving the user experience.

[0119] The preceding text explained how to determine the evaluation information in the evaluation information set. The following text will explain how to determine the visual images in the image set.

[0120] According to embodiments of this disclosure, the images in the atlas can be determined in the following manner.

[0121] The character image information and original image of the candidate evaluation character are input into a multimodal large language model (MLLMs) to perform denoising processing and obtain the image of the candidate evaluation character.

[0122] Character image information can be expressed through language descriptions of the candidate character's appearance, clothing, and other characteristics. The original image can be an image that partially matches the character image information of the candidate character. The semantic information of the original image can be extracted, and this semantic information can be matched with the textual semantic information of the character image to obtain an initial image-text matching result. If the initial image-text matching result indicates that the original image matches the character image information, the original image can be directly used as the character image. However, in general, the original image contains limited image information, with coarse-grained characterization or missing some image information. Therefore, a multimodal large model is used to enrich the image information based on the original image, resulting in a more vivid and richer character image.

[0123] Optionally, the multimodal large model can use a diffusion model as the basic network framework and employ image denoising principles for processing. For example, character image information can be used as constraint text, and the multimodal large model can be used to denoise the original image to obtain image images of candidate evaluation characters.

[0124] The output obtained after noise reduction can be directly used as the character image. However, it is not limited to this. The output can also be evaluated, and if it is determined that the output matches the character image information, it can be used as the character image and updated in the image set.

[0125] The following will combine Figure 5 This section explains how to determine the image.

[0126] Figure 5 The illustration shows a schematic diagram of a determination image according to an embodiment of the present disclosure.

[0127] like Figure 5 As shown, the original image can be a silhouette or a simple line drawing of a human figure. The character image information and the original image of the candidate evaluation character are input into a multimodal large model for denoising, yielding the final image of the candidate evaluation character. The image can be a near-realistic human portrait with texture, color, and other image details.

[0128] like Figure 5 As shown, information matching is performed on the image semantic information of the image and the text semantic information of the character image to obtain the image-text matching result. If the image-text matching result indicates that the image matches the candidate evaluation character, the image is updated to the image set.

[0129] According to embodiments of this disclosure, when the image matching result represents a match between the image and the candidate evaluation role, the image is updated to the image set.

[0130] Optionally, the image semantic information of the image and the text semantic information of the character image can be extracted separately, and the image-text matching result can be obtained by comparing vector similarity. However, this is not the only option. The matching degree between semantic information can also be used directly to determine the image-text matching result.

[0131] Optionally, the image-text matching degree can be compared with a matching degree threshold. If the image-text matching degree is greater than or equal to the matching degree threshold, it is determined that the image representing the image in the image-text matching result matches the candidate evaluation role. Conversely, if the image-text matching degree is less than the matching degree threshold, it is determined that the image representing the image in the image-text matching result does not match the candidate evaluation role. If the image representing the image in the image-text matching result matches the candidate evaluation role, it can be determined that the quality of the obtained image meets the standard, and the image can be updated to the image set. If the image does not match the candidate evaluation role, it can be determined that the quality of the obtained image does not meet the standard, and it can be deleted. Alternatively, the image-text matching result, the role image information of the candidate evaluation role, and the original image can be re-input into the multimodal large model to obtain an image, and the quality of the image can be re-verified until the obtained image matches the candidate evaluation role.

[0132] According to embodiments of this disclosure, after obtaining the image of a candidate evaluation character, a verification operation is performed to check whether the image matches the candidate evaluation character. This ensures that the image in the image set matches the character image information of the candidate evaluation character, thereby improving the fit between the image displayed to the user and the evaluation character, enhancing the user's intuitive understanding of the evaluation information, and increasing the richness and interest of the recommended information, thus improving the user experience.

[0133] The information processing method provided in this disclosure enables intelligent and personalized display of evaluation information, enhancing the user's personalized experience when browsing evaluation information. By providing evaluation controls for multiple evaluation roles with different writing styles, the fun and diversity of evaluation information are enhanced.

[0134] Figure 6 A block diagram of an information processing apparatus according to an embodiment of the present disclosure is shown schematically.

[0135] like Figure 6 As shown, the information processing device 600 of the present disclosure includes an operation parsing module 610, an information determination module 620, and an information display module 630.

[0136] The operation parsing module 610 is used to respond to a received review request and, based on the object to be evaluated included in the review request, determine a set of evaluation information about the object to be evaluated. The evaluation information set includes evaluation information from candidate evaluators, and the expression style of the evaluation information matches the writing style of the candidate evaluators. In one embodiment, the operation parsing module 610 can be used to execute the operation S210 described above, which will not be repeated here.

[0137] The information determination module 620 is used to determine the evaluation information of an evaluation role from the evaluation information set based on the evaluation role that the user is interested in. In one embodiment, the information determination module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0138] The information display module 630 is used to display the evaluation information of the evaluation role. In one embodiment, the information display module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0139] According to embodiments of this disclosure, the evaluation information in the evaluation information set is determined through the following modules.

[0140] The rewriting module is used to rewrite the original evaluation information for the object to be evaluated based on the writing style information of the candidate evaluation role, so as to obtain evaluation information that matches the writing style of the candidate evaluation role. The writing style information includes at least one of the following: writing style type, writing style description information, and example.

[0141] According to embodiments of this disclosure, the evaluation information in the evaluation information set is determined through the following modules.

[0142] The summary rewriting module is used to input the writing style information of the candidate evaluation roles and multiple original evaluation information for the object to be evaluated into the large language model to obtain evaluation information that matches the writing style of the candidate evaluation roles. The writing style information includes at least one of the following: writing style type, writing style description information, and example.

[0143] According to embodiments of this disclosure, determining the evaluation information in the evaluation information set further includes the following modules.

[0144] The first determination module is used to determine the initial original evaluation information from the historical interaction behavior data of the object to be evaluated.

[0145] The verification module is used to verify the authenticity of the initial original evaluation information based on historical interaction behavior data and initial original evaluation information, and obtain the verification result.

[0146] The second determining module is used to use the initial original evaluation information as the original evaluation information if the verification result indicates that the initial original evaluation information is true.

[0147] According to embodiments of this disclosure, determining the evaluation information in the evaluation information set further includes the following modules.

[0148] The information matching module is used to perform semantic similarity matching between evaluation information and writing style information to obtain information matching results.

[0149] The information update module is used to update the evaluation information to the evaluation information set when the expression of the evaluation information in the information matching result matches the writing style of the candidate evaluation role.

[0150] According to embodiments of this disclosure, the information processing apparatus further includes an image determination module.

[0151] The image determination module is used to determine the image of the evaluation role from the image set based on the evaluation role, so that the image of the evaluation role is displayed at the same time as the evaluation information of the evaluation role. The image set includes image images of candidate evaluation roles, and the character images in the image set are matched with the candidate evaluation roles.

[0152] According to embodiments of this disclosure, the illustrations in the atlas are determined by the following modules.

[0153] The denoising module is used to input the character image information and the original image of the candidate evaluation character into the multimodal large model to obtain the image of the candidate evaluation character.

[0154] According to embodiments of this disclosure, determining the image in the atlas further includes the following modules.

[0155] The image-text matching module is used to match the image semantic information of the image and the text semantic information of the character image to obtain the image-text matching result.

[0156] The image update module is used to update the image in the image set when the image matching result matches the candidate evaluation role.

[0157] According to embodiments of this disclosure, the information processing apparatus further includes: a focus determination module and a role determination module.

[0158] The attention determination module is used to determine the attention level of multiple candidate evaluation roles based on the user's historical interaction behavior data with the object to be evaluated. The attention level represents the degree of user interest in the candidate evaluation roles.

[0159] The role determination module is used to determine the evaluation role that the user is interested in from multiple candidate evaluation roles based on the attention level of each candidate evaluation role.

[0160] According to embodiments of this disclosure, the information display module includes a target information display submodule.

[0161] The target information display submodule is used to display the evaluation information of the target evaluation role when there are multiple evaluation roles. The target evaluation role has a higher attention level than other evaluation roles, and other evaluation roles include all evaluation roles other than the target evaluation role.

[0162] According to embodiments of this disclosure, the information processing apparatus further includes a control display module and an interface update module.

[0163] The control display module is used to display the evaluation information of the target evaluation role on the user interface, while also displaying multiple role controls, each representing an evaluation role.

[0164] The interface update module is used to update information in response to the trigger operation of the target control and display the evaluation information of the evaluation role corresponding to the target control on the user interface.

[0165] Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as hardware circuitry, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-a-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0166] For example, any plurality of the operation parsing module 610, information determination module 620, and information display module 630 can be combined into one module / unit / subunit, or any one of these modules / units / subunits can be split into multiple modules / units / subunits. Alternatively, at least part of the functionality of one or more of these modules / units / subunits can be combined with at least part of the functionality of other modules / units / subunits and implemented in one module / unit / subunit. According to embodiments of this disclosure, at least one of the operation parsing module 610, information determination module 620, and information display module 630 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the operation parsing module 610, information determination module 620, and information display module 630 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0167] It should be noted that the data processing device part in the embodiments of this disclosure corresponds to the data processing method part in the embodiments of this disclosure. The specific description of the data processing device part is referred to in the data processing method part, and will not be repeated here.

[0168] Figure 7 A block diagram of an electronic device suitable for implementing an information processing method according to an embodiment of the present disclosure is shown schematically.

[0169] Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0170] like Figure 7 As shown, an electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage portion 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0171] RAM 703 stores various programs and data required for the operation of electronic device 700. Processor 701, ROM 702, and RAM 703 are interconnected via bus 704. Processor 701 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 702 and / or RAM 703. It should be noted that programs may also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in one or more memories.

[0172] According to embodiments of this disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to a bus 704. The system 700 may also include one or more of the following components connected to the input / output (I / O) interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0173] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 709, and / or installed from removable medium 711. When the computer program is executed by processor 701, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0174] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0175] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0176] For example, according to embodiments of this disclosure, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0177] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the methods provided in the embodiments of this disclosure.

[0178] When the computer program is executed by the processor 701, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0179] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 709, and / or installed from a removable medium 711. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0180] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0181] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features recited in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not expressly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0182] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. An information processing method, characterized in that, The method includes: In response to a comment trigger operation, a set of evaluation information about the object to be evaluated is determined, wherein the set of evaluation information includes evaluation information of candidate evaluation roles, and the expression of the evaluation information matches the writing style of the candidate evaluation roles; Based on the evaluation roles that the user is interested in, determine the evaluation information of the evaluation roles from the evaluation information set; and Display the evaluation information of the evaluated role.

2. The method according to claim 1, characterized in that, The evaluation information in the evaluation information set is determined in the following way: Based on the writing style information of the candidate evaluation roles, the original evaluation information for the object to be evaluated is rewritten to obtain evaluation information that matches the writing style of the candidate evaluation roles. The writing style information includes at least one of the following: writing style type, writing style description information, and example.

3. The method according to claim 1, characterized in that, The evaluation information in the evaluation information set is determined in the following way: The writing style information of the candidate evaluation role and multiple original evaluation information for the object to be evaluated are input into the large language model to obtain the evaluation information that matches the writing style of the candidate evaluation role. The writing style information includes at least one of the following: writing style type, writing style description information, and example.

4. The method according to claim 2 or 3, characterized in that, The method further includes: Initial raw evaluation information is determined from the historical interaction behavior data of the object to be evaluated; Based on the historical interaction behavior data and the initial original evaluation information, the authenticity of the initial original evaluation information is verified to obtain the verification result; and If the verification result indicates that the initial original evaluation information is true, the initial original evaluation information shall be used as the original evaluation information.

5. The method according to claim 2 or 3, characterized in that, The method further includes: The evaluation information and the writing style information are semantically similar to obtain the information matching result; and If the information matching result indicates that the expression method of the evaluation information matches the writing style of the candidate evaluation role, the evaluation information is updated to the evaluation information set.

6. The method according to claim 1, characterized in that, The method further includes: Based on the evaluation role, an image of the evaluation role is determined from the image set, so that the evaluation information of the evaluation role is displayed at the same time as the image of the evaluation role. The image set includes image images of the candidate evaluation roles, and the character images in the image images match the candidate evaluation roles.

7. The method according to claim 6, characterized in that, The images in the atlas are determined in the following way: The character image information and the original image of the candidate evaluation character are input into the multimodal large model to obtain the image of the candidate evaluation character.

8. The method according to claim 6, characterized in that, The method further includes: Information matching is performed on the image semantic information of the image and the text semantic information of the character image to obtain the image-text matching result; and If the image matching result indicates that the image matches the candidate evaluation role, the image will be updated in the image set.

9. The method according to claim 1, characterized in that, The method further includes: Based on the user's historical interaction data with the object to be evaluated, the attention level of each of the multiple candidate evaluation roles is determined, wherein the attention level represents the degree of interest the user has in the candidate evaluation role; and Based on the attention levels of each of the multiple candidate evaluation roles, the evaluation role that the user is interested in is determined from the multiple candidate evaluation roles.

10. The method according to claim 1, characterized in that, The display of evaluation information for the evaluated role includes: When there are multiple evaluation roles, the evaluation information of the target evaluation role is displayed, wherein the target evaluation role has a higher attention level than the other evaluation roles, and the other evaluation roles include the evaluation roles other than the target evaluation role among the multiple evaluation roles.

11. The method according to claim 10, characterized in that, The method further includes: While displaying the evaluation information of the target evaluation role on the user interface, multiple role controls are also displayed, each representing the evaluation role; and In response to the triggering operation of the target control, information is updated, and the evaluation information of the evaluation role corresponding to the target control is displayed on the user interface.

12. An information processing apparatus, comprising: The operation parsing module is used to respond to the comment trigger operation and determine the evaluation information set about the object to be evaluated. The evaluation information set includes the evaluation information of the candidate evaluation roles, and the expression mode of the evaluation information matches the writing style of the candidate evaluation roles. The information determination module is used to determine the evaluation information of the evaluation role from the evaluation information set based on the evaluation role that the user is interested in; and The information display module is used to display the evaluation information of the evaluation role.

13. An electronic device, comprising: One or more processors; Memory, used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 11.

14. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 11.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 11.

Images