Information generation method and device, storage medium and electronic equipment

Abstract

The invention discloses an information generation method and device, a storage medium and electronic equipment. The method comprises the steps that a score interaction object is displayed in a comment interface of a target application, and the score interaction object is used for determining the score of the target application; in response to a first interaction operation executed on the score interaction object, determining that the score of the target application is a first score, and displaying a first group of keywords corresponding to the first score in the comment interface; under the condition that keywords for generating the comment information are a first group of keywords when an automatic generation operation is obtained in the comment interface, in response to the automatic generation operation, displaying first comment information of the target application in the comment interface, the first comment information is comment information generated by an AIGC (Artificial Intelligence Generation Content) model according to the first group of keywords. The technical problem that the process of generating the comment information is high in complexity is solved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method and apparatus for generating information, a storage medium, and an electronic device. Background Art

[0002] The review information of an application can most intuitively reflect the experience of the application. For the development side of the application, the review information of the application is an important basis for version updates and experience optimization of the application. For the application store, obtaining the review information of each application in the application store is beneficial to more accurately push applications that users may need to users.

[0003] Currently, from the user's perspective, the biggest obstacle to preventing users from writing review information is that the process of writing review information is time-consuming and laborious and users cannot receive corresponding rewards. Therefore, in order to obtain more review information of applications from users, the behavior of users writing reviews is usually incentivized. However, on the one hand, it is difficult to control the inclination direction of the incentive resources, and on the other hand, this method may lead to an objective result of the review information. In summary, in the related art, in the case of ensuring the objectivity of the review information, the process of generating the review information is relatively complex, and there are relatively high thresholds and obstacles.

[0004] In response to the above problems, no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of the present invention provide a method and apparatus for generating information, a storage medium, and an electronic device, so as to at least solve the technical problem of relatively high complexity in the process of generating review information.

[0006] According to one aspect of the embodiments of the present invention, a method for generating information is provided, including:

[0007] Display a rating interaction object on a review interface of a target application, where the rating interaction object is used to determine a rating of the target application;

[0008] In response to a first interaction operation performed on the rating interaction object, determine that the rating of the target application is a first rating, and display a first set of keywords corresponding to the first rating on the review interface;

[0009] When the keyword for generating review information obtained during an automatic generation operation on the review interface is the first set of keywords, in response to the automatic generation operation, display a first review information of the target application on the review interface, where the first review information is review information generated by an artificial intelligence generation content AIGC model according to the first set of keywords.

[0010] According to another aspect of the embodiments of the present invention, there is also provided an information generation device, including:

[0011] A first display unit, configured to display a rating interaction object in a comment interface of a target application, where the rating interaction object is used to determine a rating of the target application;

[0012] A determination unit, configured to, in response to a first interaction operation performed on the rating interaction object, determine that the rating of the target application is a first rating, and display a first set of keywords corresponding to the first rating in the comment interface;

[0013] A second display unit, configured to, when keywords for generating comment information obtained during an automatic generation operation in the comment interface are the first set of keywords, in response to the automatic generation operation, display first comment information of the target application in the comment interface, where the first comment information is comment information generated by an artificial intelligence generation content AIGC model according to the first set of keywords.

[0014] Optionally, the device further includes:

[0015] An acquisition unit, configured to, in response to obtaining a keyword adjustment operation in the comment interface, display a second set of keywords in the comment interface, where at least some of the keywords in the second set of keywords are different from the keywords in the first set of keywords;

[0016] A generation unit, configured to, when keywords for generating comment information obtained during the automatic generation operation in the comment interface are the second set of keywords, in response to the automatic generation operation, display second comment information of the target application in the comment interface, where the second comment information is comment information generated by the AIGC model according to the second set of keywords.

[0017] Optionally, the acquisition unit includes at least one of the following:

[0018] An addition module, configured to, in response to obtaining a keyword addition operation in the comment interface, display one or more added keywords in the comment interface, where the second set of keywords includes the one or more keywords, and the keyword adjustment operation includes the keyword addition operation;

[0019] A replacement module, configured to, in response to obtaining a keyword refresh operation in the comment interface, replace the first set of keywords with a new set of keywords in the comment interface, where the second set of keywords includes the new set of keywords, and the keyword adjustment operation includes the keyword refresh operation;

[0020] A deletion module, configured to, in response to obtaining a keyword deletion operation in the comment interface, delete some keywords in the first group of keywords in the comment interface, where the second group of keywords includes the keywords remaining after deleting the some keywords from the first group of keywords, and the keyword adjustment operation includes the keyword refreshing operation.

[0021] Optionally, the generating unit includes: a generating module, configured to, when the keyword for generating comment information obtained in the comment interface during the automatic generation operation is the second group of keywords, the score of the target application is the first score, and the second group of keywords matches the first score, in response to the automatic generation operation, display the second comment information of the target application in the comment interface, where the second comment information is the comment information generated by the AIGC model according to the second group of keywords and the first score;

[0022] The generating unit further includes: a first display module, configured to, when the keyword for generating comment information obtained in the comment interface during the automatic generation operation is the second group of keywords, the score of the target application is the first score, and at least some keywords in the second group of keywords do not match the first score, in response to the automatic generation operation, display the target comment information of the target application in the comment interface, where the target comment information is the comment information generated by the AIGC model according to the first score, or is the comment information generated by the AIGC model according to the first score and the keywords in the second group of keywords other than the at least some keywords.

[0023] Optionally, the device further includes:

[0024] An adjustment unit, configured to, in response to a second interaction operation performed on the score interaction object, adjust the score of the target application from the first score to a second score, and display a third group of keywords corresponding to the second score in the comment interface;

[0025] A third display unit, configured to, when the keyword for generating comment information obtained in the comment interface during the automatic generation operation is the third group of keywords, in response to the automatic generation operation, display the third comment information of the target application in the comment interface, where the third comment information is the comment information generated by the AIGC model according to the third group of keywords.

[0026] Optionally, the device further includes:

[0027] A fourth display unit, configured to, when the keyword for generating comment information during an information refresh operation in the comment interface is the first set of keywords, in response to the information refresh operation, display fourth comment information of the target application in the comment interface, where the fourth comment information is comment information generated by the AIGC model according to the first set of keywords, and the fourth comment information is different from the first comment information.

[0028] Optionally, the device further includes:

[0029] A fifth display unit, configured to, when the keyword for generating comment information during an auto-generation operation in the comment interface is empty and the score of the target application is the first score, in response to the auto-generation operation, display fifth comment information of the target application in the comment interface, where the fifth comment information is comment information generated by the AIGC model according to the first score.

[0030] Optionally, the device further includes:

[0031] A sending unit, configured to, before a score interaction object is displayed in the comment interface of the target application, when the target account acquires the target application and the target account cannot cancel the acquisition of the target application, send a comment link to the target account, where the comment link is used to display the comment interface; or,

[0032] A sixth display unit, configured to, when the target account acquires the target application and the target account cannot cancel the acquisition of the target application, display a comment link in the target application logged in by the target account, where the comment link is used to display the comment interface.

[0033] Optionally, the second display unit includes:

[0034] A second display module, configured to, in response to the auto-generation operation, display the first comment information of the target application in the comment interface, where the first comment information is comment information generated by the AIGC model according to the first set of keywords and the preset description information of the target application, or the first comment information is comment information generated by the AIGC model according to the first set of keywords, the first score, the description information of the target application, and the generated comment information.

[0035] Optionally, the device further includes:

[0036] A publishing unit, configured to, after displaying the first comment information of the target application in the comment interface, when the comment information to be published obtained in the comment interface during an information publishing operation is the first comment information, in response to the information publishing operation, publish the first comment information.

[0037] Optionally, the device further includes:

[0038] A third display unit, configured to, after publishing the first comment information, display the first comment information in the comment information display interface of the target application, where the first comment information is marked as being generated by the AIGC model or marked as being generated by artificial intelligence.

[0039] According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium storing a computer program, where the computer program is configured to execute the above information generation method when running.

[0040] According to another aspect of the embodiments of the present application, there is provided a computer program product or a computer program, the computer program product or the computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the information generation method as described above.

[0041] According to another aspect of the embodiments of the present invention, there is also provided an electronic device including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to execute the above information generation method through the computer program.

[0042] In an embodiment of the present invention, by using an artificial intelligence - generated content AIGC model to generate comment information based on keywords, only the rating interaction object needs to be displayed in the comment interface of the target application. In response to the first interaction operation performed on the rating interaction object, the rating of the target application is determined as the first rating, and the first set of keywords corresponding to the first rating is displayed in the comment interface. By the above - mentioned method, the process of obtaining keywords is simplified. Furthermore, when the keywords used for generating comment information during the automatic generation operation in the comment interface are the first set of keywords, the AIGC model generates the first comment information based on the first set of keywords and displays the first comment information in the comment interface. The above process does not require the user to write comment information. The user only needs to give the rating of the target application, and then the first set of keywords can be automatically generated. Furthermore, the AIGC model can generate comment information based on the first set of keywords, achieving the purpose of simplifying the process of generating comment information, thereby realizing the technical effect of reducing the complexity of the process of generating comment information, and further solving the technical problem of the high complexity of the process of generating comment information. Brief Description of the Drawings

[0043] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention, and do not constitute an improper limitation of the present invention. In the drawings:

[0044] Figure 1 is a schematic diagram of an application environment of an optional information generation method according to an embodiment of the present invention;

[0045] Figure 2 is a flowchart of an optional information generation method according to an embodiment of the present invention;

[0046] Figure 3 is a schematic diagram of an optional initial comment interface according to an embodiment of the present invention;

[0047] Figure 4 is a schematic diagram of an optional comment interface according to an embodiment of the present invention;

[0048] Figure 5 is a schematic diagram of an optional AIGC model generating the first comment information based on the first set of keywords according to an embodiment of the present invention;

[0049] Figure 6 is a schematic diagram of an optional information refresh operation according to an embodiment of the present invention;

[0050] Figure 7 is a schematic diagram of an optional comment information preview interface according to an embodiment of the present invention;

[0051] Figure 8 It is a schematic diagram of an optional comment information publishing interface according to an embodiment of the present invention;

[0052] Figure 9 It is a schematic diagram of an optional information generation process according to an embodiment of the present invention;

[0053] Figure 10 It is a structural block diagram of an information generation device according to an embodiment of the present application;

[0054] Figure 11 It is a schematic structural diagram of an optional electronic device according to an embodiment of the present invention;

[0055] Figure 12 It is a structural block diagram of a computer system of an optional electronic device according to an embodiment of the present invention. Detailed implementation manners

[0056] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0057] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0058] First, some nouns or terms that appear in the process of describing the embodiments of the present application are applicable to the following explanations:

[0059] AIGC: Artificial Intelligence Generated Content, which is a technology that uses artificial intelligence technology to automatically generate content without human intervention;

[0060] GRU: Gated Recurrent Unit, a gating mechanism in recurrent neural networks.

[0061] Transformer model: A deep learning model that uses self-attention mechanism, which can allocate different weights according to the importance of different parts of the input data. This model is mainly used in the fields of natural language processing and computer vision.

[0062] It should be noted that the information generation method has a wide range of application scenarios. Among them, the generated information can be, but is not limited to, comment information. The information generation method can be applied not only to generate comment information for the target application, but also in the shopping scenario to generate comment information for physical products. The object commented on by the comment information can be, but is not limited to, virtual products (such as application software, virtual games, etc.), physical products (such as books, articles, paintings, etc.). Taking the scenario of generating comment information for the target application as an example, the information generation method proposed in this application will be described.

[0063] To better understand the information generation method proposed in this application, the inventive concept of this application is elaborated as follows:

[0064] Taking the game application as an example, according to statistics, the penetration rate of online shopping malls in the game purchase channels has reached more than 80%. For game companies, how to operate the online game store well is crucial for product sales. Similar to e-commerce websites, consumers are very sensitive to the ratings and product reviews of other users when selecting game products. It can be said that if a game product can accumulate enough positive reviews, it is very important for future game operation and life cycle profitability.

[0065] For the game online shopping mall, it is crucial to encourage users to comment on the purchased products after buying games. The accumulated comment data can help the platform accurately push game products, and can also in turn promote user activity and maintain the stickiness of game manufacturers. Therefore, from this perspective, how to encourage users who have purchased games to write effective comments is the main problem faced by the online game mall.

[0066] From the perspective of consumer operation, the biggest obstacle to preventing users from writing comments is that the process of writing comments is time-consuming and laborious and users cannot receive corresponding rewards. If the platform or game manufacturer motivates users' behavior of writing comments, it may lead to unobjective comment results, and it is also difficult to control the inclination direction of incentive resources.

[0067] Based on the above aspects, the present application proposes an information generation method, which can not only ensure that the comment information given by the user can objectively reflect the experience of the target application itself, but also greatly reduce the complexity of the comment information generation process. Without the need for the user to write comment information, the user only needs to give a score to the target application, and the first set of keywords can be automatically generated. Furthermore, the comment information can be generated by the artificial intelligence generated content AIGC model according to the first set of keywords. The score given by the user in the above process can objectively and truly reflect the user's usage experience of the target application. Using the AIGC model to directly generate the corresponding comment information according to the keywords corresponding to the score achieves the purpose of simplifying the comment information generation process.

[0068] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between the present system and relevant users or institutions. Before obtaining relevant information, a request for acquisition needs to be sent to the aforementioned users or institutions through the interface, and after receiving the consent information feedback from the aforementioned users or institutions, the relevant information can be obtained.

[0069] According to one aspect of the embodiments of the present invention, an information generation method is provided. Optionally, as an alternative implementation manner, the above information generation method can be applied to, but is not limited to, devices such as terminal devices or servers. Taking the information generation method applied to the terminal device as an example, the explanation and description will be given. Figure 1 It is a schematic diagram of the application environment of an alternative information generation method according to the embodiments of the present invention. As Figure 1 shown, taking "Game A" as the target application as an example, a score interaction object (shown as icon 1-1) is displayed in the comment interface of "Game A". In response to the first interaction operation performed on the score interaction object, the score of the target application is determined as the first score. For example, the selection operation of "five-pointed star" is used as the first interaction operation. Selecting 4 "five-pointed stars" indicates that the first score is 4.0 points. The first set of keywords corresponding to 4.0 points (shown as icon 1-2) is displayed in the comment interface. When the keyword for generating comment information obtained in the comment interface during the automatic generation operation (such as clicking the "Start" button (shown as icon 1-3)) is the first set of keywords, in response to the automatic generation operation, the first comment information of "Game A" (shown as icon 1-4) is displayed in the comment interface, where the first comment information is the comment information generated by the artificial intelligence generated content AIGC model according to the first set of keywords.

[0070] The above first comment information is generated by the AIGC model based on the first set of keywords corresponding to the first score, without the need for the user to manually write. In the process of generating the first comment information, the user only needs to determine the first score for the target application, achieving the purpose of simplifying the process of generating comment information.

[0071] Optionally, in this embodiment, the above terminal device may be a terminal device configured with a target client, and may include but are not limited to at least one of the following: mobile phone (such as Android mobile phone, iOS mobile phone, etc.), laptop computer, tablet computer, handheld computer, MID (Mobile Internet Devices), PAD, desktop computer, smart TV, etc. The target client may be a video client, instant messaging client, browser client, education client, etc. The above network may include but is not limited to: wired network, wireless network, where the wired network includes: local area network, metropolitan area network, and wide area network, and the wireless network includes: Bluetooth, WIFI, and other networks that implement wireless communication. The above server may be a single server, or a server cluster composed of multiple servers, or a cloud server. The above is only an example, and this embodiment does not make any limitations in this regard.

[0072] Optionally, as an alternative implementation Figure 2 is a flowchart of an alternative information generation method according to an embodiment of the present invention, as Figure 2 shown, the above information generation method includes:

[0073] Step S12, display a score interaction object in the comment interface of the target application, where the score interaction object is used to determine the score of the target application;

[0074] Optionally, in this embodiment, the user can give a score through the score interaction object, for example Figure 1 in which 5 "five-pointed stars" represent a full score of 5 points, and selecting 4 of them represents 4 points.

[0075] Optionally, in this embodiment, the comment interface may be the interface of the target application. Through the score interaction object in the comment interface of the target application, the user can feedback the experience of the target application. The higher the score, the better the experience can be indicated. The comment interface may also be the interface of the target application store. The target application can be understood as an application product in the target application store. Through the score interaction object in the comment interface of the target application store, the user can rate all the application products deployed in the target application store.

[0076] Step S14, in response to a first interaction operation performed on the scoring interaction object, determine that the score of the target application is a first score, and display a first set of keywords corresponding to the first score in the comment interface;

[0077] Optionally, in this embodiment, the first set of keywords is a set of keywords corresponding to the first score. The first score can represent the user's basic feelings about the target application in terms of usage experience, such as excellent experience, poor experience, etc. The first set of keywords needs to be consistent with the basic feelings expressed by the first score. For example, Figure 1 as shown, if the user gives a high score of 4 points, the corresponding first set of keywords is some keywords describing an excellent experience.

[0078] Optionally, in this embodiment, the first set of keywords may include T keyword sets. Among them, the keywords in the same keyword set are used to characterize the element features of the target application that meets the first score on the same application element, and the keywords in different keyword sets are used to characterize the element features of the application that meets the first score on different application elements. The application element is an element that constitutes the target application, and T is a positive integer greater than or equal to 1 and less than or equal to R. For example, the first set of keywords may include 2 keyword sets respectively characterizing the element features of the application that meets the first score on different product elements. Taking game A as the target application, the application elements of game A include plot elements, picture quality elements, and content elements. Among them, the keyword set (smooth, interesting, rich) can characterize the element features of the application that meets the first score on the plot element, the keyword set (high, delicate, gorgeous) characterizes the element features of the application that meets the first score on the plot element, and the keyword set (substantial, interesting, diverse) characterizes the element features of the application that meets the first score on the content element. Different keywords in the same keyword set can characterize different element features of the same application element from different experience dimensions.

[0079] Optionally, in this embodiment, before displaying the scoring interaction object in the comment interface of the target application, the method further includes displaying an "AI Automatic Comment" button in the initial comment interface of the target application. When the user clicks the "AI Automatic Comment" button, the initial comment interface can be switched to the comment interface. Figure 3 is a schematic diagram of an optional initial comment interface according to an embodiment of the present invention, as Figure 3As shown, taking game A as the target application as an example, after the user purchases product game A (including the game body, DLC (Downloadable Content), item products, etc.) in the online game mall and exceeds the maximum allowable return time limit, the system sends an in-site message or push to the user, inviting the user to comment on the purchased game A. When the user clicks on the comment link, they will enter the initial comment interface corresponding to game A. It is possible to Figure 3 In the comment box (shown as icon 3-1), the user can edit the comment content by themselves, and set the attributes of the comment through the comment attribute setting option (shown as icon 3-2). Before clicking the "Comment Publish" button, the user can also choose whether to recommend the game. The above is a way for the user to write comment information. In addition to writing, the user can also click the "AI Automatic Comment" button (shown as icon 3-3) in the gray box slightly below to activate the AI intelligent comment module, and the AI intelligent comment module opens the comment interface that displays the scoring interaction object as described above.

[0080] Optionally, in this embodiment, the comment information generated by the information generation method proposed in this application is not 100% generated by AI. Before the AI intelligently generates text, the user needs to first give the basic sentiment (i.e., the first score) of the target application and some keywords, where the basic sentiment of the target application is a required field, and the keywords are not a required field.

[0081] After the user clicks Figure 3 the "AI Automatic Comment" button in, a floating box pops up on the initial comment interface, and the floating box is modified to the comment interface for AI intelligent generation of comments. Figure 4 This is a schematic diagram of an optional comment interface according to an embodiment of the present invention. As Figure 4 shown, the user inputs and interacts through the comment interface to input necessary information to the AI. First, the user should click on the score in the upper left corner (equivalent to the first interaction operation performed on the scoring interaction object described above) to rate the target application to be commented. The scoring system design here adopts the traditional 5-star system, which is divided into three levels: not recommended (1, 2 stars), average (3 stars), and recommended (4, 5 stars) according to different scores. When the user clicks on the star to give a score, the oval box automatically and real-time displays the user's score.

[0082] After the user completes the rating, some comment keywords need to be given. In the solution provided by the embodiments of the present application, in order to simplify the user's keyword input process, corresponding templates are preset according to the user's rating and some optional keywords are given. Taking Game A as the target application as an example, in the solution provided by the embodiments of the present application, at least three comment keyword templates are preset according to the category of the game, the characteristics of the game store (where Game A and other game products are deployed), and the rating with at least three levels, which can but are not limited to three levels. For example, if the application to be commented on is an RPG (Role-Playing Game) type game, the three elements that potential purchasers of this type of application are most concerned about can but are not limited to the plot, picture quality, and content. Then, corresponding keyword templates should be given for these three elements at three score levels respectively, and the number of optional keywords for each element should be no less than three. For example, the comment keyword template for a 5-point review of an RPG game is: plot (smooth, interesting, rich), picture quality (high, delicate, gorgeous), content (substantial, interesting, diverse). In the solution provided by the embodiments of the present application, the set optional keywords should be able to fully reflect the emotion corresponding to the user's rating, and there should be no situation where the keywords are contrary to the rating. For example, the user gives a high score of 4 points, but the keywords given in the keyword template contain negative words, unless the user gives a negative comment on a certain aspect of the product in the custom input. Otherwise, by default, the emotion of the keywords preset in the template is consistent with the user's independent rating.

[0083] Step S16, when the keyword for generating the comment information in the comment interface is the first group of keywords during the automatic generation operation, in response to the automatic generation operation, display the first comment information of the target application in the comment interface, where the first comment information is the comment information generated by the artificial intelligence generated content AIGC model according to the first group of keywords.

[0084] Optionally, in this embodiment, when Figure 4 the "Start" button in is clicked, it can be confirmed that the automatic generation operation is obtained, the current keyword on the initial interface is determined as the first group of keywords, and in response to the automatic generation operation, the first comment information of the target application is displayed in the comment interface.

[0085] Optionally, in this embodiment, the first comment information is the comment information generated by the artificial intelligence generated content AIGC model according to the first group of keywords. The following describes the manner in which the artificial intelligence generated content AIGC model generates the first comment information according to the first group of keywords:

[0086] Figure 5 is a schematic diagram of an optional AIGC model according to an embodiment of the present invention for generating the first comment information according to the first group of keywords, as Figure 5As shown, first, obtain the set of description information of the target application. The set of description information includes one or more description information, and each piece of description information records information about one aspect of the target product. Taking the target application Game A as an example of the target product, Figure 5 6 pieces of description information are shown, which respectively relate to developer information, publisher information, first release time information, category information, product type information, and user rating information. Then, input the set of description information, the first rating, and the first set of keywords into the AIGC model to obtain the comment information output by the AIGC model, and determine the comment information output by the AIGC model as the first comment information. The AIGC model is a model based on the encoder-decoder of transformer and GRU. This AIGC model requires pre-training using a dataset and then deploying the corresponding AIGC model on the cloud. The most important inputs of the AIGC model are the set of description information of the game (developer information, publisher information, first release time information, category information, product type information, user rating information, etc.), the actual user rating (i.e., the first rating), and the prompt keywords given by the user. Among them, the set of description information and the user rating will be encoded using a 6-layer transformer model, and the prompt keywords will be encoded together with the historical comment data of the benchmark game of this game using a GRU, and then the encoded results will be concatenated and decoded using a transformer decoding structure.

[0087] Among them, the step of inputting the set of description information, the first rating, and the first set of keywords into the AIGC model to obtain the comment information output by the AIGC model includes: inputting the set of description information and the first rating into the first encoding model (i.e., the transformer model) in the AIGC model to obtain the product information features of the target product; inputting the first set of keywords into the second encoding model (i.e., the GRU model) in the AIGC model to obtain the initial product comment features of the target product; fusing the product information features and the product comment features to obtain the target product comment features of the target product; generating the target comment information (i.e., the first comment information) of the target product based on the target product comment features.

[0088] Among them, inputting the description information set and the first score into the first encoding model in the AIGC model to obtain the product information features of the target product includes: converting each piece of the description information in the description information set and the first score into a first input information to obtain a first input information sequence; using the first encoding model to perform a first encoding operation on each piece of the first input information in the first input information sequence to obtain a first feature vector corresponding to each piece of the first input information, where each first feature vector is used to characterize the features corresponding to the corresponding first input information, each first feature vector is a vector marked with a feature weight and a position encoding, and each position encoding is used to represent the position of the corresponding first input information in the first input information sequence; constructing the first feature vectors corresponding to each piece of the first input information in the first input information sequence into a first feature vector sequence, where the first feature vector sequence is used to characterize the product information features.

[0089] Among them, inputting the first group of keywords into the second encoding model in the AIGC model to obtain the initial product review features of the target product includes: converting each keyword in the first group of keywords into a second input information to obtain a second input information sequence; using the second encoding model to perform a second encoding operation on each piece of the second input information in the second input information sequence to obtain a second feature vector corresponding to each piece of the second input information, where each second feature vector is used to characterize the features corresponding to the corresponding second input information, the second encoding model includes a plurality of sub-encoding modules, and each sub-encoding module is used to perform a second encoding operation on a piece of the second input information in the second input information sequence; constructing the second feature vectors corresponding to each piece of the second input information in the second input information sequence into a second feature vector sequence, where the second feature vector sequence is used to characterize the initial product review features.

[0090] Among them, the fusion of the product information features and the product review features to obtain the target product review features of the target product includes: splicing the first feature vector sequence output by the first encoding model and the second feature vector sequence output by the second encoding model to obtain a target feature vector sequence. The first feature vector sequence includes first feature vectors corresponding to each first input information in the first input information sequence, and each first feature vector is used to represent the features corresponding to the corresponding first input information. The first input information sequence is obtained by converting each product information and the first score in the description information set into a first input information, and the first feature vector sequence is used to represent the product information features; the second feature vector sequence includes second feature vectors corresponding to each second input information in the second input information sequence, and each second feature vector is used to represent the features corresponding to the corresponding second input information. The second input information sequence is obtained by converting each target keyword in the group of target keywords into a second input information, and the second feature vector sequence is used to represent the initial product review features; the target feature vector sequence is used to represent the target product review features of the target product.

[0091] Among them, generating the target review information of the target product based on the target product review features includes: using the target decoding model (i.e., Transformer Decoder) in the AIGC model to decode the target feature vector sequence, and obtaining the review information output by the target decoding model as the first review information.

[0092] Specifically, the first encoding model (i.e., the transformer model) is a 6-layer encoding structure TransformerEncoder. This encoder generates input embeddings and positional encodings for each description information in the description information set, and creates new description information expressions based on self-attention and multi-head attention. Convert each description information and the first score in the description information set into a first input information to obtain a first input information sequence. For each input first input information C i , the corresponding Transformer Encoder performs a first encoding operation on the first input information C i and outputs a first feature vector t i , and a multi-head self-attention mechanism attn i , and this calculation logic can be expressed as:

[0093] t i , attn i = Transformer Encoder(C i)

[0094] Wherein indicates that the dimension of the first feature vector is C i represents the i-th first input information in the first input information sequence, represents the sequence length of the input first input information sequence, H t is the hidden size of the Transformer.

[0095] The second encoding model (i.e., the GRU model) is an encoding model composed of n sub-encoding modules (sorted from 1 to n), and each sub-encoding module processes the comment corresponding to the serial number in the comment dataset R i in the comment dataset R i is equivalent to the above-mentioned second input information, is the j-th second input information in the second input information sequence. If the serial number exceeds n, the corresponding sub-module cannot process the corresponding comment. Here, n is a value set by the user of the present invention, mainly determined according to the capacity of its computing power. The larger n is, the more computing power is consumed. Each available sub-module will return a hidden state This calculation logic can be expressed as:

[0096]

[0097] where j is the serial number of the sub-encoder (from 1 to n), is the j-th second input information in the second input information sequence, is the second feature vector corresponding to the j-th second input information, GRU SubEncoder j represents the j-th sub-encoder, indicates the second feature vector whose dimension is l is the number of layers of the GRU, H g represents the dimension of the hidden state of each sub-encoder. In the present invention, the number of layers of each sub-encoder can be customized by the user according to the actual situation. Similarly, this index is restricted by the computing power.

[0098] The first feature vector sequence output by the first encoding model and the second feature vector sequence output by the second encoding model are concatenated to obtain a target feature vector sequence. The decoding process of the Transformer is similar to that of the RNN, which is a process of decoding word by word from left to right. For a given target feature vector sequence r i , the s-th target feature vector in the target feature vector sequence r i is labeled as the s-th target feature vector Obtained through Transformer decoding And then Converted into part of the text in the comment information, and the entire target feature vector sequence r i Through Transformer decoding, the first comment information is obtained. Among them, the entire process of Transformer decoding can be expressed as:

[0099]

[0100] Among them,

[0101] As an alternative solution, it further includes:

[0102] S21, in response to obtaining a keyword adjustment operation in the comment interface, display a second set of keywords in the comment interface, where at least some of the keywords in the second set of keywords are different from the keywords in the first set of keywords;

[0103] Optionally, in this embodiment, when the user is not satisfied with the first set of keywords given by the template, a keyword adjustment operation can be performed in the comment interface to adjust the first set of keywords to obtain a second set of keywords.

[0104] S22, when the keyword used to generate comment information in the comment interface for the automatic generation operation is the second set of keywords, in response to the automatic generation operation, display the second comment information of the target application in the comment interface, where the second comment information is the comment information generated by the AIGC model according to the second set of keywords.

[0105] Optionally, in this embodiment, the process of the AIGC model generating the second comment information according to the second set of keywords is similar in principle to the process of the AIGC model generating the first comment information according to the first set of keywords, and will not be elaborated here.

[0106] As an alternative solution, in response to obtaining a keyword adjustment operation in the comment interface, displaying a second set of keywords includes at least one of the following:

[0107] S31, in response to obtaining a keyword addition operation in the comment interface, display one or more added keywords in the comment interface, where the second set of keywords includes the one or more keywords, and the keyword adjustment operation includes the keyword addition operation;

[0108] Optionally, in this embodiment, when the user is not satisfied with the first set of keywords given by the template, a keyword addition operation can be performed in the comment interface, andFigure 4 After the keyword of

[0109] S32. In response to obtaining a keyword refresh operation in the comment interface, replace the first group of keywords with a new group of keywords in the comment interface, where the second group of keywords includes the new group of keywords, and the keyword adjustment operation includes the keyword refresh operation;

[0110] Optionally, in this embodiment, when the user is not satisfied with the first group of keywords given by the template, a keyword refresh operation can be performed in the comment interface, and the Figure 4 "Other group of words" button under the keyword box can be clicked to obtain a new group of keywords, and the new group of keywords is determined as the second group of keywords.

[0111] S33. In response to obtaining a keyword deletion operation in the comment interface, delete some of the keywords in the first group of keywords in the comment interface, where the second group of keywords includes the remaining keywords after deleting the part of the keywords in the first group of keywords, and the keyword adjustment operation includes the keyword refresh operation.

[0112] Optionally, in this embodiment, when the user is not satisfied with the first group of keywords given by the template, a keyword deletion operation can be performed in the comment interface to delete some of the keywords in the first group of keywords. For example, when the first group of keywords is: plot (smooth, interesting, rich), the "rich" in the plot can be deleted by performing a keyword deletion operation in the comment interface, and the second group of keywords obtained is: plot (smooth, interesting).

[0113] Optionally, in this embodiment, the above keyword addition operation, keyword refresh operation, and keyword deletion operation can be used in combination, and the order and number of times of use are not limited.

[0114] As an alternative solution, when the keyword for generating comment information obtained in the comment interface during the automatic generation operation is the second group of keywords, in response to the automatic generation operation, displaying the second comment information of the target application in the comment interface further includes:

[0115] S41. When the keyword for generating comment information during the automatic generation operation obtained in the comment interface is the second set of keywords, the score of the target application is the first score, and the second set of keywords matches the first score, in response to the automatic generation operation, display the second comment information of the target application in the comment interface, where the second comment information is the comment information generated by the AIGC model based on the second set of keywords and the first score;

[0116] Optionally, in this embodiment, the second set of keywords matching the first score may but is not limited to meaning that the emotion expressed by the second set of keywords is consistent with the first score given by the user. For example, when the first score is a high score indicating a good user experience with the target application, and at the same time the corresponding second set of keywords also express positive feelings about the target application, it can be considered that the second set of keywords matches the first score.

[0117] S42. When the keyword for generating comment information during the automatic generation operation obtained in the comment interface is the second set of keywords, the score of the target application is the first score, and at least some of the second set of keywords do not match the first score, in response to the automatic generation operation, display the target comment information of the target application in the comment interface, where the target comment information is the comment information generated by the AIGC model based on the first score, or is the comment information generated by the AIGC model based on the first score and the keywords in the second set of keywords other than the at least some keywords.

[0118] Optionally, in this embodiment, at least some of the second set of keywords not matching the first score may but is not limited to meaning that the emotion expressed by the second set of keywords is inconsistent with the first score given by the user. For example, when the first score is a high score indicating a good user experience with the target application, and some of the corresponding second set of keywords express a poor user experience with the target application, it can be considered that at least some of the second set of keywords do not match the first score. When some keywords conflict with the score, the first score shall prevail. At this time, the AIGC model can directly generate the target comment information based on the first score, or generate the comment information based on the first score and the keywords in the second set of keywords other than the at least some keywords.

[0119] As an optional solution, it further includes:

[0120] S51. In response to a second interaction operation performed on the scoring interaction object, adjust the score of the target application from the first score to a second score, and display a third set of keywords corresponding to the second score in the comment interface;

[0121] S52. When the keyword for generating comment information during the automatic generation operation obtained in the comment interface is the third set of keywords, in response to the automatic generation operation, display third comment information of the target application in the comment interface, where the third comment information is comment information generated by the AIGC model based on the third set of keywords.

[0122] Optionally, in this embodiment, in the above-mentioned solution, various ways of adjusting the first set of keywords corresponding to the first score are assumed under the condition that the score remains unchanged at the first score. This embodiment also proposes an operation for adjusting the score, and the first score can be adjusted to a second score by performing a second interaction operation on the scoring interaction object.

[0123] Optionally, in this embodiment, after the first score is adjusted to a second score, the corresponding keywords will also change synchronously, changing from the first set of keywords to the third set of keywords. Thereafter, the above-mentioned keyword adjustment operation can also be continued for the third set of keywords.

[0124] As an alternative solution, it further includes:

[0125] S61. When the keyword for generating comment information during the information refresh operation obtained in the comment interface is the first set of keywords, in response to the information refresh operation, display fourth comment information of the target application in the comment interface, where the fourth comment information is comment information generated by the AIGC model based on the first set of keywords, and the fourth comment information is different from the first comment information.

[0126] Optionally, in this embodiment, Figure 6 is a schematic diagram of an alternative information refresh operation according to an embodiment of the present invention, as Figure 6As shown, when the user completes the setting of the first group of keywords and clicks the "Start" button in the right display box, the AIGC model deployed on the cloud is called to generate the first comment information. If the user is not satisfied with the first comment information, they can perform an information refresh operation in the comment interface. The specific method can be to click the "Start" button again, and the AIGC model will generate the fourth comment information. Although both the first comment information and the fourth comment information are generated based on the first group of keywords, the fourth comment information is different from the first comment information. The information refresh operation can be executed multiple times until the comment information that satisfies the user is generated, and the comment information is displayed in real time in the right display box. For example, the comment information: "Game A is my first soul-like game. I encountered challenging enemies in the game, and they made the whole game experience fascinating. The storyline is also very attractive. I will give a high-quality review of its content".

[0127] Optionally, in this embodiment, when the user is not satisfied with the first comment information, they have three options. Option 1: Without changing the score and keywords, let the AIGC model generate a new paragraph. In this case, simply click the "Start" button to generate a new paragraph directly; Option 2: When changing the score or keywords, let the AIGC model generate a new paragraph. In this case, the user directly modifies the score or keywords and then clicks the "Start" button, and the AIGC model will generate a new paragraph; Option 3: When the user is not satisfied with the generated comment, they can directly exit the AI intelligent comment module and enter the comment by themselves.

[0128] As an optional solution, it further includes:

[0129] S71, when the keyword for generating comment information in the comment interface is empty and the score of the target application is the first score, in response to the automatic generation operation, display the fifth comment information of the target application in the comment interface, where the fifth comment information is the comment information generated by the AIGC model according to the first score.

[0130] Optionally, in this embodiment, when the keyword for generating comment information is empty, the AIGC model can directly generate the fifth comment information according to the first score.

[0131] As an optional solution, before displaying the score interaction object in the comment interface of the target application, it further includes:

[0132] S81, when the target account obtains the target application and the target account cannot cancel the acquisition of the target application, send a comment link to the target account, where the comment link is used to display the comment interface; or,

[0133] S82. When the target account acquires the target application and the target account cannot cancel the acquisition of the target application, a comment link is displayed in the target application logged in by the target account, where the comment link is used to display the comment interface.

[0134] Optionally, in this embodiment, the target account that sends the comment link needs to meet certain comment conditions. It can be determined whether the target account meets the comment conditions by confirming the order for the target account to acquire the target application. For example, it is necessary to confirm that the target account has purchased the target application and the return period has expired.

[0135] As an alternative solution, in response to the automatic generation operation, displaying the first comment information of the target application in the comment interface further includes:

[0136] S91. In response to the automatic generation operation, the first comment information of the target application is displayed in the comment interface, where the first comment information is the comment information generated by the AIGC model according to the first set of keywords and the preset description information of the target application, or the first comment information is the comment information generated by the AIGC model according to the first set of keywords, the first score, the description information of the target application, and the generated comment information.

[0137] Optionally, in this embodiment, the description information may include, but is not limited to: developer information, publisher information, release time information, category information, product type information, user score information, etc. Figure 5 What is shown is the process of the AIGC model generating the first comment information according to the first set of keywords, the first score, and the description information of the target application.

[0138] As an alternative solution, after the first comment information of the target application is displayed in the comment interface, it further includes:

[0139] S101. When the comment information to be published obtained during the information publishing operation in the comment interface is the first comment information, in response to the information publishing operation, the first comment information is published.

[0140] Optionally, in this embodiment, as Figure 6 shown, after obtaining satisfactory comment information, the user can choose to directly click the "Publish Comment" button to perform the information publishing operation; or when the user confirms that the comment content generated by the AI is correct, click the "Confirm" button next to the "Start" button, then the AI intelligent comment module automatically closes, and the generated comment is transferred to the formal comment information preview interface. Figure 7 is a schematic diagram of an alternative comment information preview interface according to an embodiment of the present invention, asFigure 7 As shown, the comment information preview interface displays the comment information to be published. Below the comment information to be published, the attributes of the comment can be set, including visibility, language, and whether comments are allowed. After the settings are completed, click the "Publish Comment" button to perform the information publishing operation.

[0141] As an optional solution, after publishing the first comment information, it further includes:

[0142] S111, display the first comment information in the comment information display interface of the target application, where the first comment information is marked as generated by the AIGC model or marked as generated by artificial intelligence.

[0143] Optionally, in this embodiment, after publishing the first comment information, the first comment information is displayed in the comment information display interface of the target application. Different from the product comments entered by the user himself, the first comment information is marked as generated by the AIGC model or marked as generated by artificial intelligence. Figure 8 is a schematic diagram of an optional comment information publishing interface according to an embodiment of the present invention. As Figure 8 shown, above the first comment information "Game A is my first Soulslike game. I encountered challenging enemies in the game, and they made the whole game experience fascinating. The storyline is also very attractive. I will give a high-quality review of its content." is marked "Publication Date: August 20, 2023, AI Generated" to indicate that the first comment information is generated by the AIGC model or artificial intelligence.

[0144] Figure 9 is a schematic diagram of an optional information generation process according to an embodiment of the present invention. As Figure 9 shown, the information generation method proposed in this application includes 4 modules: a front-end module, a back-end module, a database, and the cloud. Among them, the cloud is mainly used to host the AIGC model for generating comment information. The database is a data storage unit that the product should obtain to implement corresponding functions except for training the AI model. The back-end module is a logical unit for processing after user interaction, and the front-end module is an interface for user interaction. The information generation process includes 4 main verification logics:

[0145] Logic 1: Confirm whether the target account of the user meets the comment conditions. The specific method is to confirm whether the actual payment amount of the order purchased by the target account has been made and the return period has expired. If the actual payment amount of the order purchased by the target account has been made and the return period has expired, the target account meets the comment conditions.

[0146] Logic 2: Confirm whether the user needs to change a set of keywords. This is to prevent the user from being dissatisfied with the keywords provided by the platform. The user can choose to regenerate a set of keywords for comment generation.

[0147] Logic 3: Whether to re-enter keywords. This is a verification to check if the user wants to modify the prompt keywords that have been input into the AIGC model when the user is not satisfied with the generated comment and chooses to regenerate the comment. When the user re-modifies the score, the keyword template should change accordingly, but when the user does not modify the score, the template remains unchanged, and the user can click or enter other keywords.

[0148] Logic 4: Select whether to accept the automatically generated comment. This is the comment verification before final upload. If the user accepts, the comment will be transferred to the formal comment template.

[0149] The information generation method proposed in this application starts from the perspective of reducing the threshold for users to write comments and optimizes the entire comment process using the AIGC model. The user only needs to click to rate the game, and the application solution will retrieve the corresponding comment keyword template according to the rating. After the user selects or customizes and enters relevant words, the present invention automatically generates a comment text through the Transformer and GRU encoding-decoder algorithms. After the user confirms, the text automatically generated by the AI can be uploaded and made public to other users. This information generation method includes the product design and corresponding product processes for both the front end and the back end, and can be directly applied to the product development of online game stores. The information generation method can be applied to online game stores (PC games, Console games) and app stores (mobile games or apps). By integrating the information generation method proposed in this application into the product comment module of a website or app and deploying the corresponding machine learning model, users who purchase game products on this platform can be allowed to use the AI tool to automatically generate corresponding comments. Deploying the information generation method proposed in this application on an online game mall can significantly reduce the threshold for users to write comments, save more time for users, and thus enhance the user's desire to share after purchasing products. From the perspective of the platform, using the information generation method proposed in this application can encourage users to share more, help the platform accumulate more product comment data, and play an important role in product marketing, community operation, and even business model transformation. The information generation method proposed in this application can cooperate with the membership operation system of the game store to improve the user activity of the platform and promote platform operation; it can also provide this function as a paid function to designated game developers to improve the economic benefits of the platform.

[0150] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0151] According to another aspect of the embodiments of the present invention, there is also provided an information generation device for implementing the above information generation method. Figure 10 is a structural block diagram of an information generation device according to an embodiment of the present application, as Figure 10 shown, the device includes:

[0152] A first display unit 1002, configured to display a rating interaction object in a comment interface of a target application, where the rating interaction object is used to determine a rating of the target application;

[0153] A determination unit 1004, configured to, in response to a first interaction operation performed on the rating interaction object, determine a first rating of the target application and display a first set of keywords corresponding to the first rating in the comment interface;

[0154] A second display unit 1006, configured to, when the keyword for generating comment information obtained in the comment interface during an automatic generation operation is the first set of keywords, in response to the automatic generation operation, display a first comment information of the target application in the comment interface, where the first comment information is comment information generated by an artificial intelligence generation content AIGC model according to the first set of keywords.

[0155] As an optional solution, the device further includes:

[0156] An acquisition unit, configured to, in response to obtaining a keyword adjustment operation in the comment interface, display a second set of keywords in the comment interface, where at least some of the keywords in the second set of keywords are different from the keywords in the first set of keywords;

[0157] A generation unit, configured to, when the keyword for generating comment information obtained in the comment interface during the automatic generation operation is the second set of keywords, in response to the automatic generation operation, display a second comment information of the target application in the comment interface, where the second comment information is comment information generated by the AIGC model according to the second set of keywords.

[0158] As an optional solution, the acquisition unit includes at least one of the following:

[0159] An addition module, configured to display one or more added keywords in the comment interface in response to obtaining a keyword addition operation in the comment interface, where the second set of keywords includes the one or more keywords, and the keyword adjustment operation includes the keyword addition operation;

[0160] A replacement module, configured to replace the first set of keywords with a new set of keywords in the comment interface in response to obtaining a keyword refresh operation in the comment interface, where the second set of keywords includes the new set of keywords, and the keyword adjustment operation includes the keyword refresh operation;

[0161] A deletion module, configured to delete some keywords in the first set of keywords in the comment interface in response to obtaining a keyword deletion operation in the comment interface, where the second set of keywords includes the keywords remaining after deleting the some keywords from the first set of keywords, and the keyword adjustment operation includes the keyword refresh operation.

[0162] As an optional solution, the generation unit includes: a generation module, configured to display the second comment information of the target application in the comment interface in response to the automatic generation operation when the keyword for generating the comment information obtained in the comment interface is the second set of keywords, the score of the target application is the first score, and the second set of keywords matches the first score, where the second comment information is the comment information generated by the AIGC model according to the second set of keywords and the first score;

[0163] The generation unit further includes: a first display module, configured to display the target comment information of the target application in the comment interface in response to the automatic generation operation when the keyword for generating the comment information obtained in the comment interface is the second set of keywords, the score of the target application is the first score, and at least some of the keywords in the second set of keywords do not match the first score, where the target comment information is the comment information generated by the AIGC model according to the first score, or is the comment information generated by the AIGC model according to the first score and the keywords in the second set of keywords other than the at least some keywords.

[0164] As an optional solution, the device further includes:

[0165] An adjustment unit, configured to adjust the score of the target application from the first score to a second score in response to a second interaction operation performed on the score interaction object, and display a third set of keywords corresponding to the second score in the comment interface;

[0166] A third display unit, configured to, when the keyword for generating comment information in the comment interface during the automatic generation operation is the third set of keywords, in response to the automatic generation operation, display third comment information of the target application in the comment interface, where the third comment information is comment information generated by the AIGC model according to the third set of keywords.

[0167] As an optional solution, the device further includes:

[0168] A fourth display unit, configured to, when the keyword for generating comment information in the comment interface during the information refresh operation is the first set of keywords, in response to the information refresh operation, display fourth comment information of the target application in the comment interface, where the fourth comment information is comment information generated by the AIGC model according to the first set of keywords, and the fourth comment information is different from the first comment information.

[0169] As an optional solution, the device further includes:

[0170] A fifth display unit, configured to, when the keyword for generating comment information in the comment interface during the automatic generation operation is empty and the score of the target application is the first score, in response to the automatic generation operation, display fifth comment information of the target application in the comment interface, where the fifth comment information is comment information generated by the AIGC model according to the first score.

[0171] As an optional solution, the device further includes:

[0172] A sending unit, configured to, before the score interaction object is displayed in the comment interface of the target application, when the target account acquires the target application and the target account cannot cancel the acquisition of the target application, send a comment link to the target account, where the comment link is used to display the comment interface; or,

[0173] A sixth display unit, configured to, when the target account acquires the target application and the target account cannot cancel the acquisition of the target application, display a comment link in the target application logged in by the target account, where the comment link is used to display the comment interface.

[0174] As an optional solution, the second display unit includes:

[0175] A second display module, configured to respond to the automatic generation operation and display the first review information of the target application in the review interface, where the first review information is the review information generated by the AIGC model according to the first set of keywords and the preset description information of the target application, or the first review information is the review information generated by the AIGC model according to the first set of keywords, the first score, the description information of the target application, and the generated review information.

[0176] As an optional solution, the apparatus further includes:

[0177] A publishing unit, configured to, after displaying the first review information of the target application in the review interface, when the review information to be published obtained in the review interface is the first review information in response to the information publishing operation, publish the first review information.

[0178] As an optional solution, the apparatus further includes:

[0179] A third display unit, configured to, after publishing the first review information, display the first review information in the review information display interface of the target application, where the first review information is marked as being generated by the AIGC model or marked as being generated by artificial intelligence.

[0180] In the embodiments of the present application, the term "module" or "unit" refers to a computer program with a predetermined function or a part of a computer program, which works together with other related parts to achieve a predetermined goal, and can be fully or partially implemented by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of the overall module or unit that includes the function of the module or unit.

[0181] According to another aspect of the embodiments of the present invention, there is also provided an electronic device for implementing the above information generation method, and the electronic device can be Figure 1 the terminal device or server shown. In this embodiment, the server is taken as an example of the electronic device for illustration. Figure 11 is a schematic structural diagram of an optional electronic device according to the embodiments of the present invention, as Figure 11 shown, the electronic device includes a memory 1102 and a processor 1104, a computer program is stored in the memory 1102, and the processor 1304 is configured to execute the steps in any one of the above method embodiments through the computer program.

[0182] Optionally, in this embodiment, the above-mentioned electronic device may be at least one of multiple network devices in a computer network.

[0183] Optionally, in this embodiment, the above-mentioned processor may be configured to execute the following steps through a computer program:

[0184] S1. Display a rating interaction object in the comment interface of the target application, where the rating interaction object is used to determine the rating of the target application;

[0185] S2. In response to a first interaction operation performed on the rating interaction object, determine that the rating of the target application is a first rating, and display a first set of keywords corresponding to the first rating in the comment interface;

[0186] S3. When the keyword for generating comment information during the automatic generation operation obtained in the comment interface is the first set of keywords, in response to the automatic generation operation, display the first comment information of the target application in the comment interface, where the first comment information is comment information generated by an artificial intelligence generation content AIGC model according to the first set of keywords.

[0187] Optionally, those of ordinary skill in the art can understand that Figure 11 The structure shown is only schematic. The electronic device may also be a terminal device such as a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a handheld computer, and a Mobile Internet Device (MID), a PAD, etc. Figure 11 It does not limit the structure of the above-mentioned electronic device. For example, the electronic device may further include more or fewer components (such as a network interface, etc.) than those shown Figure 11 in the figure, or have a different configuration from that shown Figure 11 in the figure.

[0188] Among them, the memory 1102 can be used to store software programs and modules, such as the program instructions / modules corresponding to the information generation method and device in the embodiments of the present invention. The processor 1104 executes various functional applications and data processing by running the software programs and modules stored in the memory 1102, that is, implements the above-mentioned information generation method. The memory 1102 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some instances, the memory 1102 may further include a memory remotely disposed relative to the processor 1104, and these remote memories can be connected to the terminal through a network. Examples of the above network include but are not limited to the Internet, enterprise intranet, local area network, mobile communication network, and combinations thereof. Among them, the memory 1102 can specifically but not limitedly be used to store information such as sample characteristics of items and target virtual resource accounts. As an example, as Figure 11 shown, the above memory 1102 may include but is not limited to the first display unit 1002, the determination unit 1004, and the second display unit 1006 in the above information generation device. In addition, it may also include but is not limited to other module units in the above information generation device, which will not be elaborated in this example.

[0189] Optionally, the above transmission device 1106 is used to receive or send data via a network. Specific examples of the above network may include a wired network and a wireless network. In one instance, the transmission device 1106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through a network cable, thereby enabling communication with the Internet or a local area network. In one instance, the transmission device 1106 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0190] In addition, the above electronic device further includes: a display 1108 for displaying the above order information to be processed; and a connection bus 1110 for connecting each module component in the above electronic device.

[0191] In other embodiments, the above terminal device or server may be a node in a distributed system. Among them, the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes can form a peer-to-peer network, and any form of computing device, such as a server, a terminal, and other electronic devices, can become a node in the blockchain system by joining the peer-to-peer network.

[0192] According to one aspect of the present application, there is provided a computer program product, which includes a computer program / instructions that contain program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 1209, and / or installed from the removable medium 1211. When the computer program is executed by the central processing unit 1201, various functions provided by the embodiments of the present application are executed.

[0193] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0194] Figure 12 It is a block diagram of the computer system structure of an optional electronic device according to an embodiment of the present invention. It should be noted that, Figure 12 The computer system 1200 of the electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application. As Figure 12 shown, the computer system 1200 includes a central processing unit 1201 (Central Processing Unit, CPU), which can execute various appropriate actions and processes according to the program stored in the read-only memory 1202 (Read-Only Memory, ROM) or the program loaded from the storage part 1208 into the random access memory 1203 (Random Access Memory, RAM). In the random access memory 1203, various programs and data required for system operation are also stored. The central processing unit 1201, the read-only memory 1202, and the random access memory 1203 are connected to each other through the bus 1204. The input / output interface 1205 (Input / Output interface, i.e., I / O interface) is also connected to the bus 1204.

[0195] The following components are connected to the input / output interface 1205: an input part 1206 including a keyboard, a mouse, etc.; an output part 1207 including such as a cathode ray tube (Cathode Ray Tube, CRT), a liquid crystal display (Liquid Crystal Display, LCD), etc. and a speaker, etc.; a storage part 1208 including a hard disk, etc.; and a communication part 1209 including a network interface card such as a local area network card, a modem, etc. The communication part 1209 performs communication processing via a network such as the Internet. The drive 1210 is also connected to the input / output interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1210 as needed so that the computer program read from it can be installed into the storage part 1208 as needed.

[0196] In particular, according to an embodiment of the present application, the processes described in each method flowchart can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 1209, and / or installed from the removable medium 1211. When the computer program is executed by the central processing unit 1201, various functions defined in the system of the present application are executed.

[0197] According to one aspect of the present application, there is provided a computer-readable storage medium, and a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in various alternative implementations of the above aspects.

[0198] Optionally, in this embodiment, the above computer-readable storage medium may be set to store a computer program for executing the following steps:

[0199] S1, display a rating interaction object in the comment interface of the target application, where the rating interaction object is used to determine the rating of the target application;

[0200] S2, in response to a first interaction operation performed on the rating interaction object, determine that the rating of the target application is a first rating, and display a first set of keywords corresponding to the first rating in the comment interface;

[0201] S3, when the keyword for generating comment information during the automatic generation operation obtained in the comment interface is the first set of keywords, in response to the automatic generation operation, display the first comment information of the target application in the comment interface, where the first comment information is comment information generated by an artificial intelligence generation content AIGC model according to the first set of keywords.

[0202] Optionally, in this embodiment, those of ordinary skill in the art can understand that all or part of the steps in the above various methods can be completed by a program instructing the relevant hardware of the terminal device, and the program can be stored in a computer-readable storage medium. The storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0203] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage media. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing one or more computer devices (which can be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention.

[0204] In the above embodiments of the present invention, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0205] In the several embodiments provided by the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the units or modules can be in electrical or other forms.

[0206] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0207] In addition, the functional units in the various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0208] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An information generation method, characterized in that, Including: Display a rating interaction object in the comment interface of the target application, where the rating interaction object is used to determine the rating of the target application; In response to a first interaction operation performed on the rating interaction object, determine that the rating of the target application is the first rating, and display a first set of keywords corresponding to the first rating in the comment interface; When the keyword for generating the comment information obtained during the automatic generation operation in the comment interface is the first set of keywords, in response to the automatic generation operation, display the first comment information of the target application in the comment interface, where the first comment information is the comment information generated by the artificial intelligence generated content AIGC model according to the first set of keywords.

2. The method according to claim 1, wherein The method further includes: In response to obtaining a keyword adjustment operation in the comment interface, display a second set of keywords in the comment interface, where at least some of the keywords in the second set of keywords are different from the keywords in the first set of keywords; When the keyword for generating the comment information obtained during the automatic generation operation in the comment interface is the second set of keywords, in response to the automatic generation operation, display the second comment information of the target application in the comment interface, where the second comment information is the comment information generated by the AIGC model according to the second set of keywords.

3. The method according to claim 2, wherein Responding to obtaining a keyword adjustment operation in the comment interface and displaying a second set of keywords includes at least one of the following: In response to obtaining a keyword addition operation in the comment interface, display one or more added keywords in the comment interface, where the second set of keywords includes the one or more keywords, and the keyword adjustment operation includes the keyword addition operation; In response to obtaining a keyword refresh operation in the comment interface, replace the first set of keywords with a new set of keywords in the comment interface, where the second set of keywords includes the new set of keywords, and the keyword adjustment operation includes the keyword refresh operation; In response to obtaining a keyword deletion operation in the comment interface, delete some of the keywords in the first set of keywords in the comment interface, where the second set of keywords includes the remaining keywords in the first set of keywords after deleting the some keywords, and the keyword adjustment operation includes the keyword refresh operation.

4. According to the method of claim 2, wherein When the keyword for generating comment information when the automatic generation operation is obtained in the comment interface is the second set of keywords, in response to the automatic generation operation, display the second comment information of the target application in the comment interface, including: when the keyword for generating comment information when the automatic generation operation is obtained in the comment interface is the second set of keywords, the score of the target application is the first score, and the second set of keywords matches the first score, in response to the automatic generation operation, display the second comment information of the target application in the comment interface, where the second comment information is the comment information generated by the AIGC model according to the second set of keywords and the first score; The method further includes: when the keyword for generating comment information when the automatic generation operation is obtained in the comment interface is the second set of keywords, the score of the target application is the first score, and at least some of the keywords in the second set of keywords do not match the first score, in response to the automatic generation operation, display the target comment information of the target application in the comment interface, where the target comment information is the comment information generated by the AIGC model according to the first score, or is the comment information generated by the AIGC model according to the first score and the keywords in the second set of keywords other than the at least some keywords.

5. The method according to claim 1, wherein The method further includes: In response to a second interaction operation performed on the score interaction object, adjust the score of the target application from the first score to a second score, and display a third set of keywords corresponding to the second score in the comment interface; When the keyword for generating comment information when the automatic generation operation is obtained in the comment interface is the third set of keywords, in response to the automatic generation operation, display the third comment information of the target application in the comment interface, where the third comment information is the comment information generated by the AIGC model according to the third set of keywords.

6. The method according to claim 1, characterized in that The method further includes: When the keyword for generating comment information when the information refresh operation is obtained in the comment interface is the first set of keywords, in response to the information refresh operation, display the fourth comment information of the target application in the comment interface, where the fourth comment information is the comment information generated by the AIGC model according to the first set of keywords, and the fourth comment information is different from the first comment information.

7. The method according to claim 1, wherein The method further includes: When the keyword for generating comment information when the automatic generation operation is obtained in the comment interface is empty and the score of the target application is the first score, in response to the automatic generation operation, display the fifth comment information of the target application in the comment interface, where the fifth comment information is the comment information generated by the AIGC model according to the first score.

8. The method according to claim 1, characterized in that, Before displaying the score interaction object in the comment interface of the target application, the method further includes: When the target account acquires the target application and the target account cannot cancel the acquisition of the target application, send a comment link to the target account, where the comment link is used to display the comment interface; or, When the target account acquires the target application and the target account cannot cancel the acquisition of the target application, display a comment link in the target application logged in by the target account, where the comment link is used to display the comment interface.

9. The method according to any one of claims 1 to 8, characterized in that, In response to the automatic generation operation, display first comment information of the target application in the comment interface, including: In response to the automatic generation operation, display the first comment information of the target application in the comment interface, where the first comment information is comment information generated by the AIGC model according to the first set of keywords and the preset description information of the target application, or, the first comment information is comment information generated by the AIGC model according to the first set of keywords, the first score, the description information of the target application, and the generated comment information.

10. The method according to any one of claims 1 to 8, characterized in that After displaying the first comment information of the target application in the comment interface, the method further includes: When the comment information to be published at the time of the information publishing operation obtained in the comment interface is the first comment information, in response to the information publishing operation, publish the first comment information.

11. The method according to claim 10, wherein After publishing the first comment information, the method further includes: Display the first comment information in the comment information display interface of the target application, where the first comment information is marked as generated by the AIGC model or marked as generated by artificial intelligence.

12. An information generating device, characterized in that, Includes: A first display unit, configured to display a score interaction object in a comment interface of a target application, where the score interaction object is used to determine a score of the target application; A determination unit, configured to, in response to a first interaction operation performed on the score interaction object, determine that the score of the target application is a first score, and display a first set of keywords corresponding to the first score in the comment interface; A second display unit, configured to, when the keyword for generating comment information at the time of the automatic generation operation obtained in the comment interface is the first set of keywords, in response to the automatic generation operation, display the first comment information of the target application in the comment interface, where the first comment information is comment information generated by the artificial intelligence generation content AIGC model according to the first set of keywords.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, where the program, when running, executes the method described in any one of claims 1 to 11.

14. A computer program product comprising a computer program / instructions, characterized in that, The computer program / instructions, when executed by a processor, implement the steps of the method described in any one of claims 1 to 11.

15. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to execute the method described in any one of claims 1 to 11 through the computer program.

Images