Information generation method, information display method, recommendation method, computing device, storage medium and program product

Abstract

The embodiment of the invention provides an information generation method, an information display method, a recommendation method, computing equipment, a storage medium and a program product. The method comprises the steps of obtaining selection mode prompt information corresponding to a target category; determining a target object belonging to the target category; extracting object attribute information matched with the selection mode prompt information from the object description information of the target object; according to the selection mode prompt information and the object attribute information, recommendation prompt information of the target object is generated, and the recommendation prompt information can be used for recommending the target object. According to the technical scheme provided by the embodiment of the invention, personalized recommendation prompt information can be generated for different target objects, so that a user can quickly and deeply understand the target objects, the selection efficiency of the user can be improved, the user interaction frequency can be reduced, and the system performance can be improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular to an information generation method, an information display method, a recommendation method, a computing device, a storage medium, and a program product. Background Art

[0002] With the development of Internet technology, people can now use resources online to exchange objects. Currently, in some online systems that provide object exchange, such as online trading systems for commodity purchases, in order to provide users with a better interactive experience and help them select objects for further exchange operations, selection prompts can be provided for categories that require professional knowledge guidance. This selection prompt information, as a type of recommendation information, can provide users with professional guidance, information interpretation, and selection strategies. For example, selection prompts for health care categories can include information interpretation and selection strategies for multiple selection dimensions such as source, ingredients, and efficacy. Users can then select appropriate products based on the selection prompts.

[0003] However, in actual applications, although the selection method prompt information, as recommendation information, can provide users with general selection knowledge, users need to enter the object page of different objects to view the object description information, and then repeatedly compare it with the selection method prompt information before deciding which object to select. The process is relatively cumbersome, the user experience is poor, and it will increase the number of interactions with the online system, which will also affect system performance. Summary of the Invention

[0004] The embodiments of the present application provide an information generation method, an information display method, a recommendation method, a computing device, a storage medium, and a program product to solve the problem in the prior art that inaccurate selection prompt information leads to cumbersome user interaction.

[0005] In a first aspect, an embodiment of the present application provides an information generation method, comprising:

[0006] Get the selection method prompt information corresponding to the target category;

[0007] determining target objects belonging to the target category;

[0008] extracting object attribute information matching the selection method prompt information from the object description information of the target object;

[0009] Recommendation prompt information of the target object is generated according to the selection method prompt information and the object attribute information; the recommendation prompt information is used to recommend the target object.

[0010] In a second aspect, an embodiment of the present application provides an information display method, comprising:

[0011] Detecting viewing operations on target objects;

[0012] In response to the viewing operation, recommended prompt information of the target object is displayed on the object details page of the target object; wherein, the recommended prompt information is generated based on the selection method prompt information corresponding to the target category to which the target object belongs and the object attribute information extracted from the object description information of the target object and matching the selection method prompt information.

[0013] In a third aspect, an embodiment of the present application provides a recommendation method, comprising:

[0014] Acquiring recommendation prompt information of the target object; the recommendation prompt information is generated based on selection method prompt information corresponding to the target category to which the target object belongs and object attribute information extracted from the object description information of the target object and matching the selection method prompt information;

[0015] The target object is recommended based on the recommendation prompt information.

[0016] In a fourth aspect, an embodiment of the present application provides an information generation method, comprising:

[0017] Get the selection method prompt information corresponding to the target category;

[0018] determining target products belonging to the target category;

[0019] Extracting product attribute information matching the selection method prompt information from the product description information of the target product;

[0020] Recommendation prompt information of the target product is generated according to the selection method prompt information and the product attribute information; the recommendation prompt information is used to recommend the target product.

[0021] In a fifth aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component;

[0022] The storage component stores a computer program; the computer program is called and executed by the processing component to implement the information generation method as described in the first aspect above, the information display method as described in the second aspect above, the recommendation method as described in the third aspect above, or the information generation method as described in the fourth aspect above.

[0023] In the sixth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processing component, it implements the information generation method described in the first aspect above, the information display method described in the second aspect above, the recommendation method described in the third aspect above, or the information generation method described in the fourth aspect above.

[0024] In the seventh aspect, a computer program product is provided in an embodiment of the present application, including a computer program or instructions, which, when executed by a processing component, implements the information generation method described in the first aspect above, the information display method described in the second aspect above, the recommendation method described in the third aspect above, or the information generation method described in the fourth aspect above.

[0025] The embodiment of the present application obtains selection method prompt information corresponding to the target category; determines the target object belonging to the target category; extracts object attribute information that matches the selection method prompt information from the object description information of the target object; generates recommendation prompt information of the target object based on the selection method prompt information and the object attribute information, and the recommendation prompt information can be used to recommend the target object. Personalized recommendation prompt information can be generated for different target objects. Compared with the selection method prompt information, the recommendation prompt information is more accurate, which helps the user to quickly gain an in-depth understanding of the target object and avoids the user repeatedly comparing the selection method prompt information and the object description information. It can improve the user's selection efficiency, reduce the number of user interactions, improve system performance, and enhance the user's selection experience.

[0026] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0028] Figure 1 A system architecture diagram is shown in which the technical solution of an embodiment of the present application can be applied;

[0029] Figure 2 A flowchart of an embodiment of an information generation method provided by the present application is shown;

[0030] Figure 3 A schematic diagram of a preset image template in a practical application of an embodiment of the present application is shown;

[0031] Figure 4 A flowchart of an embodiment of an information display method provided by the present application is shown;

[0032] Figure 5 A flowchart of an embodiment of a recommended method provided by the present application is shown;

[0033] Figure 6 A flowchart of an embodiment of an information generation method provided by the present application is shown;

[0034] Figure 7 A schematic diagram of scene interaction in a practical application of an embodiment of the present application is shown;

[0035] Figure 8 A schematic diagram showing the display of an object details page in an actual application of an embodiment of the present application is shown;

[0036] Figure 9 A schematic diagram showing the display of a customer service conversation page in an actual application of an embodiment of the present application is shown;

[0037] Figure 10 A schematic structural diagram of an embodiment of an information generating device provided by the present application is shown;

[0038] Figure 11 A schematic structural diagram of an embodiment of an information display device provided by the present application is shown;

[0039] Figure 12 A schematic structural diagram of an embodiment of a recommended device provided by the present application is shown;

[0040] Figure 13 A schematic structural diagram of another embodiment of an information generating device provided by the present application is shown;

[0041] Figure 14 A schematic structural diagram of an embodiment of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0042] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0043] It should be noted that, in the case of user information involved in the embodiments of this application, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse. In addition, the various models involved in this application are in compliance with relevant laws and standards.

[0044] In response to the technical problem that the existing selection method prompt information is inaccurate, resulting in cumbersome user interaction, an embodiment of the present application provides a solution. The basic idea is: obtain the selection method prompt information corresponding to the target category; determine the target object belonging to the target category; extract the object attribute information that matches the selection method prompt information from the object description information of the target object; generate recommendation prompt information of the target object based on the selection method prompt information and the object attribute information; the recommendation prompt information is used to recommend the target object.

[0045] The embodiment of the present application can generate recommendation prompt information of the target object based on the selection method prompt information of the target category and the object attribute information of the target object belonging to the target category that matches the selection method prompt information. Personalized recommendation prompt information can be generated for different target objects. Compared with the selection method prompt information, the recommendation prompt information is more accurate, which helps the user to quickly gain an in-depth understanding of the target object and avoids the user from repeatedly comparing the selection method prompt information and the object description information. It can improve the user's selection efficiency, reduce the number of user interactions, improve system performance, and improve the user's selection experience.

[0046] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0047] Figure 1 A system architecture diagram is shown in which the technical solution of an embodiment of the present application can be applied. The system architecture may include a user terminal 101 and a server terminal 102.

[0048] The client 101 and the server 102 can be connected via a network. The network provides a medium for the communication link between the client 101 and the server 102. The network can include various connection types, such as wired, wireless, or fiber optic cables. The client 101 can interact with the server 102 via the network to receive or send messages.

[0049] The user terminal 101 may be a browser, an APP (Application), or a web application such as an H5 (HyperText Markup Language 5, version 5 of Hypertext Markup Language) application, or a light application (also known as a mini-program, a lightweight application) or a cloud application. The user terminal 101 may be deployed in an electronic device and may rely on the device to run or on certain apps in the device to run. For example, the electronic device may have a display screen and support information browsing, such as a personal mobile terminal such as a mobile phone, a tablet computer, a personal computer, a desktop computer, a smart speaker, a smart watch, etc. For ease of understanding, Figure 1 The user end is mainly represented by the image of a device. Various other types of applications can usually be configured in electronic devices, such as human-computer dialogue applications, model training applications, text processing applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc. Electronic devices can refer to devices used by users, which have the functions of computing, Internet access, communication, etc. required by users, such as mobile phones, tablet computers, personal computers, wearable devices, etc. Electronic devices can usually include at least one processing component and at least one storage component. Electronic devices may also include basic configurations such as network card chips, IO (input / output) buses, audio and video components, which are not limited in this application. Optionally, according to the implementation form of the electronic device, some peripheral devices may also be included, such as keyboards, mice, input pens, printers, etc., which are not limited in this application.

[0050] The server 102 may include servers that provide various services, such as a server for background training that provides support for the model used on the user terminal 101, or a server that processes interactive information sent by the user terminal.

[0051] It should be noted that the server 102 can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. The server can also be a server of a distributed system, or a server combined with a blockchain. The server can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology.

[0052] It should be noted that the information generation method provided in the embodiments of the present application is generally executed by the server 102, and the corresponding information generation device is generally provided in the server 102. However, in other embodiments of the present application, the user terminal 101 may also have similar functions to the server 102, thereby executing the information generation method provided in the embodiments of the present application. In other embodiments, the information generation method provided in the embodiments of the present application may also be jointly executed by the user terminal 101 and the server 102.

[0053] It should be understood that Figure 1 The number of user terminals and server terminals in the figure is only for illustration. Any number of user terminals and server terminals may be provided according to implementation requirements.

[0054] It should be noted that the technical solutions of the embodiments of this application are applicable to a virtual network environment. The users described are generally referred to as "virtual users." Real users can register user accounts on the server through registration to obtain user identities in the network environment. The same user account can be logged into the server through different types of client terminals, allowing the server to identify the same user.

[0055] Interactions between the server and the user can be implemented based on user accounts. Data sent or received by the server to the user is also based on user accounts. The user corresponding to the user account actually receives or sends data to the server. Furthermore, users can communicate with each other through user accounts. The term "user" can refer to an individual or an organization, such as a business, and this application does not impose specific restrictions on this.

[0056] The implementation details of the technical solution of the embodiment of the present application are described in detail below.

[0057] Figure 2 This is a flowchart of an embodiment of an information generation method provided by this application. The technical solution of this embodiment can be executed by the server. The method may include the following steps:

[0058] 201: Obtaining selection method prompt information corresponding to the target category.

[0059] Different categories have different characteristics and uses, and therefore require different selection methods. For example, electronics products are frequently updated and have complex technical specifications, so selection decisions should focus on performance parameters and after-sales service. Therefore, selection prompts for electronics products could include information interpretation and selection strategies for multiple selection dimensions, such as performance parameters and after-sales service. Healthcare products typically have different effects depending on their source and ingredients, so selection prompts for healthcare products could include information interpretation and selection strategies for their source, ingredients, and effects.

[0060] 202: Determine a target object belonging to a target category.

[0061] The target object can be any object belonging to the target category, or a specified target object.

[0062] 203: Extracting object attribute information matching the selection method prompt information from the object description information of the target object.

[0063] In an e-commerce scenario, an object may refer to a product, and the product description information of the target product may include the title name and / or attribute parameter information of the target product.

[0064] For example, assuming the target category is fish oil and the target object is AA brand fish oil, the selection prompt information corresponding to the target category is "Look at the source: Generally, fish from waters near the poles or deep-sea fish are purer and safer. For example, the waters of Peru and Norway have lower concentrations of heavy metals and other harmful substances. Look at the purity: Purity = DHA (Docosahexaenoic Acid) and EPA (Eicosapentaenoic Acid) content / Omega-3 content. The higher the purity, the better the effect. Products with a purity of 90% or more are preferred. Look at the ratio: Those who want to protect eye and brain health can choose products with a high DHA content; those who want to protect blood vessel health can choose products with a high EPA content." The object attribute information in the object description information of the target object that matches the selection prompt information is the object attribute information corresponding to the source, purity, and ratio, such as "Source: Norwegian deep-sea fish; purity 70%; ratio: EPA: 700mg (milligrams), DHA: 400mg."

[0065] 204: Generate recommendation prompt information of the target object according to the selection method prompt information and the object attribute information.

[0066] The recommendation prompt information may be used to recommend a target object.

[0067] This embodiment can generate recommendation prompt information of the target object based on the selection method prompt information of the target category and the object attribute information of the target object belonging to the target category that matches the selection method prompt information. Personalized recommendation prompt information can be generated for different target objects. Compared with the selection method prompt information, the recommendation prompt information is more accurate, which helps the user to quickly gain an in-depth understanding of the target object and avoids the user from repeatedly comparing the selection method prompt information and the object description information. It can improve the user's selection efficiency, reduce the number of user interactions, improve system performance, and improve the user's selection experience.

[0068] In some embodiments, obtaining selection method prompt information corresponding to the target category may include: obtaining selection method prompt information corresponding to multiple selection dimensions of the target category.

[0069] Extracting object attribute information matching the selection mode prompt information from the object description information of the target object may include: extracting object attribute information matching at least one target selection dimension from the object description information of the target object;

[0070] Generating recommendation prompt information of the target object according to the selection method prompt information and the object attribute information may include: generating recommendation prompt information of the target object according to the selection method prompt information and the object attribute information respectively corresponding to at least one target selection dimension.

[0071] Among them, the selection method prompt information may include multiple selection dimensions. Among them, the object description information extracted from the object description information can match one or more target selection dimensions in multiple dimensions. For example, assuming the target category is fish oil, the multiple selection dimensions may include source, certification, concentration, purity, ratio, compounding and packaging, etc. The target object is AA brand fish oil, and the object description information of the target object only contains information related to the source, purity and ratio. Then, the object attribute information matching the three target selection dimensions of source, purity and ratio can be extracted from the object description information of the target object. For example, among the three target selection dimensions, the object attribute information matching the source dimension is "Norwegian deep-sea fish", the object attribute information matching the purity dimension is "70%", and the object attribute information matching the ratio dimension is "EPA: 700mg, DHA: 400mg".

[0072] In some embodiments, as an optional method, extracting object attribute information that matches at least one target selection dimension from the object description information of the target object may include: using text matching to extract object attribute information that matches at least one target selection dimension from the object description information of the target object.

[0073] The text matching method can be, for example, based on a predetermined regular expression and / or by calculating the text similarity between the selection method prompt information and the object description information of the target object, extracting object attribute information that matches at least one target selection dimension from the object description information of the target object.

[0074] As another optional manner, extracting object attribute information matching at least one target selection dimension from the object description information of the target object may include: extracting object attribute information matching at least one target selection dimension from the object description information of the target object using a first extraction model.

[0075] Among them, a first prompt instruction can be generated based on the selection method prompt information corresponding to multiple selection dimensions of the target category and the object description information of the target object, and the first prompt instruction can be input into the first extraction model to instruct the first extraction model to extract object attribute information matching at least one target selection dimension from the object description information of the target object.

[0076] For example, the first prompt instruction may be generated based on the selection method prompt information corresponding to the target category and the multiple selection dimensions, the object description information of the target object, and the first prompt template.

[0077] For example, the first prompt template may be: Please extract attribute information matching the selected dimensions from the description information {BBBB} based on the information {AAAA} of multiple selected dimensions.

[0078] The selection method prompt information corresponding to the target category and multiple selection dimensions may be filled into {AAAA}, and the object description information of the target object may be filled into {BBBB} to generate a first prompt instruction.

[0079] The first extraction model involved in the embodiment of the present application and the first text generation model, the second text generation model, the second extraction model, the third text generation model, etc. involved below can be a language model (Language Mode, LM) or a multimodal model (Multimodal Model, MM) based on artificial intelligence, etc. The embodiment of the present application does not limit the number of model parameters supported by the model, with the goal of meeting actual needs. If the model parameters are relatively more, the scale of the model will be relatively large, and the model performance will be relatively better. Of course, more time and resources will be consumed in the reasoning or training process; if the model parameters are relatively few, the scale of the model will be relatively small. When the performance meets the requirements, the model is more lightweight, and the time and resources consumed in the reasoning or training process are relatively less. The first extraction model model and the first text generation model, the second text generation model, the second extraction model, the third text generation model, etc. involved below can be a deep learning model for processing and generating natural language text or multimodal data, which can be implemented based on a neural network architecture and can be pre-trained on a large amount of data. In an optional implementation, the first extraction model and the first text generation model, second text generation model, second extraction model, and third text generation model mentioned below may include an encoder, a decoder, a self-attention layer, and a feed-forward neural network. The encoder is mainly used to convert input data (usually in sequence form) into a vector representation. This process can capture the semantic features of the input data. The decoder is responsible for converting the intermediate representation generated by the encoder into output data (usually in sequence form). The self-attention layer is a mechanism that allows the model to pay attention to other positions in the sequence to better encode the current position information. The feed-forward neural network can perform nonlinear transformations on the output of the self-attention layer to enhance the model's expressiveness. Each part works together so that the model built based on them can perform well in various complex processing tasks, such as natural language processing, computer vision, speech recognition, machine translation, text summarization, and intelligent question answering. Among them, the first extraction model and the first text generation model, second text generation model, second extraction model, and third text generation model mentioned below can be the same model or different models.

[0080] The selection method prompt information and the object attribute information of at least one target selection dimension can be used to form the recommended prompt information displayed on the user's page. Due to the limited display space on the page, it may not be possible to display the object attribute information that matches all selection dimensions. Therefore, in some embodiments, extracting the object attribute information that matches at least one target selection dimension from the object description information of the target object may include: extracting the object attribute information that matches multiple candidate selection dimensions from the object description information of the target object; screening a predetermined number of target selection dimensions from the multiple candidate selection dimensions according to the display priorities corresponding to the multiple candidate selection dimensions, and determining the object attribute information that matches the predetermined number of target selection dimensions.

[0081] Using the first extraction model to extract object attribute information that matches at least one target selection dimension from the object description information of the target object may include: using the first extraction model to extract object attribute information that matches multiple candidate selection dimensions from the object description information of the target object; screening a predetermined number of target selection dimensions from the multiple candidate selection dimensions according to the display priorities corresponding to the multiple candidate selection dimensions, and determining the object attribute information that matches the predetermined number of target selection dimensions.

[0082] The display priority of a candidate selection dimension can be determined based on its importance, with the higher the importance, the higher the display priority. Optionally, the display priorities corresponding to the multiple candidate selection dimensions can be determined by a model, and the specific implementation method can be described in detail below. Optionally, the display priorities corresponding to the multiple candidate selection dimensions can be manually determined.

[0083] In some embodiments, the method may further include generating attribute description information based on the object attribute information corresponding to at least one target selection dimension, and further generating target object recommendation information based on the selection method prompt information and the attribute description information corresponding to the at least one target selection dimension. Because the attribute description information is more accessible, users can easily understand the attributes of the target object through the attribute description information, thereby increasing their favorability towards the target object.

[0084] As an optional method, generating recommendation prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension may include: using a first text generation model to generate attribute description information based on the object attribute information corresponding to at least one target selection dimension; generating recommendation prompt information of the target object based on the selection method prompt information and attribute description information corresponding to at least one target selection dimension.

[0085] Among them, a second prompt instruction can be generated based on the object attribute information corresponding to at least one target selection dimension and the second prompt template, and the second prompt instruction can be input into the first text generation model to instruct the first text generation model to generate attribute description information according to the object attribute information corresponding to at least one target selection dimension.

[0086] For example, the second prompt template may be: generating corresponding attribute description information according to object attribute information {CCCC} of different selection dimensions.

[0087] Assume the target object is AA brand fish oil. The object description for the target object can be extracted to identify the three target selection dimensions: source, purity, and ratio. The source dimension matches "Norwegian deep-sea fish," the purity dimension matches "70%," and the ratio dimension matches "EPA: 700mg, DHA: 400mg." "The object attribute information matched by the source dimension is 'Norwegian deep-sea fish', the object attribute information matched by the purity dimension is '70%', and the object attribute information matched by the ratio dimension is 'EPA: 700mg, DHA: 400mg'" can be filled in {CCCC} to generate a second prompt instruction. For example, the attribute description information corresponding to the object attribute information "Norwegian deep-sea fish" generated by the first text generation model can be "This fish oil is selected from Norwegian deep-sea fish", the attribute description information corresponding to the object attribute information "purity 70%" can be "The purity of this fish oil: 70%", and the attribute description information corresponding to the object attribute information "EPA: 700mg, DHA: 400mg" can be "The ratio of this fish oil: EPA: 700mg, DHA: 400mg".

[0088] As another optional method, generating recommended prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension may include: generating attribute description information based on a preset attribute description template according to the object attribute information corresponding to at least one target selection dimension; generating recommended prompt information of the target object based on the selection method prompt information and attribute description information corresponding to at least one target selection dimension.

[0089] Among them, different selection dimensions can correspond to different preset attribute description templates.

[0090] Assume the target object is AB brand fish oil. The object description information for the target object can extract the object attribute information matching the source dimension as "Norwegian deep-sea fish," and the object attribute information matching the complex dimension as "eye-protecting ingredient lutein." The preset attribute description template for the source dimension might be: "This fish oil comes from {DDDD}," while the preset attribute description template for the complex dimension might be: "This fish oil contains {EEEE}." The object attribute information matching the source dimension, "Norwegian deep-sea fish," can be entered at {DDDD} to generate the corresponding attribute description information, "This fish oil comes from Norwegian deep-sea fish," and the object attribute information matching the complex dimension, "eye-protecting ingredient lutein," can be entered at {EEEE} to generate the corresponding attribute description information, "This fish oil contains the eye-protecting ingredient lutein."

[0091] In some embodiments, after object attribute information matching the selection method prompt information is extracted from the object description information of the target object, the selection method prompt information may be updated.

[0092] Generating recommendation prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension may include: using a second text generation model to update the selection method prompt information corresponding to at least one target selection dimension based on the object attribute information corresponding to at least one target selection dimension; generating recommendation prompt information of the target object based on the updated selection method prompt information and object attribute information corresponding to at least one target selection dimension.

[0093] Among them, a third prompt instruction can be generated based on the object attribute information corresponding to at least one target selection dimension and the third prompt template, and the third prompt instruction can be input into the second text generation model to instruct the second text generation model to generate selection method prompt information corresponding to at least one target selection dimension based on the object attribute information corresponding to at least one target selection dimension.

[0094] For example, the third prompt template may be: Please introduce the object attribute information {FFFF} and explain how to make a selection based on the object attribute information.

[0095] For example, the selection method prompt information corresponding to the inexperienced object attribute information in the object attribute information corresponding to at least one target selection dimension may be updated and / or the selection method prompt information corresponding to the more professional target selection dimension may be updated.

[0096] For example, assuming the target category is fish oil, the multiple selection dimensions of the selection prompt information may include the object's source, certification, concentration, purity, ratio, compounding, and packaging. The selection prompt information corresponding to the source dimension is "Look at the source: Generally, fish from waters near the poles or deep-sea are purer and safer." The selection prompt information corresponding to the purity dimension is "Purity = DHA and EPA content / Omega-3 content. The higher the purity, the better the effect." The selection prompt information corresponding to the certification dimension is "Look at the certification: Prefer globally recognized, high-quality third-party fish oil certification." The target object is AC brand fish oil. The object description information of the target object can extract object attribute information that matches the three target selection dimensions of source, purity, and certification. For example, the object attribute information matching the source dimension is "Norwegian deep-sea fish," the object attribute information matching the purity dimension is "70%," and the object attribute information matching the certification dimension is "PM certified."

[0097] Among them, since the PM certification in the object attribute information "PM certified" matched by the certification dimension is not widely known, for example, the object attribute information "PM certified" can be filled in to {FFFF} to generate a third prompt instruction. The second text generation model can generate detailed introduction information of PM certification such as "See certification: PM certification is an international product quality certification standard, which ensures that the product is high in purity and does not contain heavy metals and environmental toxins" to update the original selection method prompt information "See certification: preferably the globally recognized third-party fish oil quality certification with high gold content".

[0098] In some embodiments, generating recommended prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension may include: obtaining an attribute description image corresponding to the object attribute information corresponding to at least one target selection dimension; generating recommended prompt information of the target object based on the selection method prompt information, object attribute information and attribute description image corresponding to at least one target selection dimension.

[0099] Optionally, the attribute description image may be pre-generated based on the object attribute information of the target object using an image generation model. Optionally, the attribute description image may be generated in real time based on the object attribute information of the target object using an image generation model.

[0100] The image generation model can be a multimodal model based on artificial intelligence, which can convert natural language descriptions into images. In this embodiment, object attribute information in text form can be input into the image generation model to generate an attribute description image. When the first extraction model, the first text generation model, the second text generation model, the second extraction model, and the third text generation model are multimodal models, the image generation model can be the same model as the first extraction model, the first text generation model, the second text generation model, the second extraction model, and the third text generation model.

[0101] The attribute description image can reflect the attributes of the object. The attribute description image can be a static image or a dynamic video. For example, if the object attribute information matched in the source dimension is "Norwegian deep-sea fish," the attribute description image generated based on this object attribute can be an image of deep-sea fish. For example, if the object attribute matched in the composite dimension is "eye-protecting ingredient lutein," the attribute description image generated based on this object attribute information can be a video of a person massaging their eye area due to eye fatigue.

[0102] In this embodiment, an attribute description image is generated based on the object attribute information of the target object to form recommended information for display to the user. This can intuitively display the attribute characteristics of the target object, enhance visual appeal, help users quickly capture key information, and improve the conversion rate of the target object.

[0103] In some embodiments, the recommendation prompt information may be in the form of an image to facilitate user downloading and sharing. Generating the recommendation prompt information for the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension may include: combining the selection method prompt information and object attribute information corresponding to the at least one target selection dimension into a recommendation image, and using the recommended image as the recommendation prompt information for the target object.

[0104] In addition, the recommended prompt information can also be a recommended video, which can present a dynamic data display effect, etc. Therefore, in some embodiments, generating the recommended prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension can include: synthesizing the selection method prompt information and object attribute information corresponding to at least one target selection dimension into a recommended video, and using the recommended video as the recommended prompt information of the target object.

[0105] Of course, the recommended image can also be a dynamic image to present a dynamic data display effect, etc.

[0106] In some embodiments, synthesizing the selection method prompt information and object attribute information corresponding to at least one target selection dimension into a recommended image may include: filling the selection method prompt information and object attribute information corresponding to at least one target selection dimension into the preset image template according to the display position defined by the preset image template to generate a recommended image.

[0107] When the recommendation prompt information is a recommended video or dynamic image, it can be based on the display position defined by the preset image template, fill the selection method prompt information and object attribute information corresponding to at least one target selection dimension into the preset image template, and add different dynamic effect elements to form multiple image frames, and then form a recommended video or dynamic image from the multiple image frames. This application does not limit this.

[0108] For ease of understanding, Figure 3 The schematic diagram of the preset image template in an actual application of the embodiment of the present application is shown. Among them, the top can display the target category selection guide sentence, such as if the target category is fish oil, it is "How to choose fish oil", and then, according to the display priority corresponding to the multiple target selection dimensions, the selection method prompt information corresponding to the multiple target selection dimensions and the attribute description information generated based on the object attribute information can be displayed from top to bottom. In addition, the preset image template can also determine the display position of the attribute description image, such as Figure 3 As shown, a property description image can be displayed in the upper right corner.

[0109] In some embodiments, obtaining selection method prompt information corresponding to multiple selection dimensions of the target category may include: using a second extraction model to extract information from at least one selection method description content corresponding to the target category to obtain selection method prompt information corresponding to the multiple selection dimensions.

[0110] At least one selection method description corresponding to multiple categories may be input into the second extraction model. A fourth prompt instruction is generated based on the target category and the fourth prompt template, and the fourth prompt instruction is input into the second extraction model to instruct the second extraction model to extract information from the at least one selection method description corresponding to the target category to obtain selection method prompt information corresponding to the multiple selection dimensions.

[0111] For example, the fourth prompt template may be: You are now a nutrition expert. Please tell me how to select {FFFF}. If there are seven selection dimensions, what are the seven selection dimensions?

[0112] Among them, the target category can be filled to {FFFF} to generate a fourth prompt instruction.

[0113] At least one selection method description content includes one or more of the following: selection method description content related to the target category captured from the Internet; selection method description content preset for the target category; professional knowledge content related to the target category; selection method description content corresponding to the target category generated using a third text generation model.

[0114] Optionally, the display priorities corresponding to the plurality of candidate selection dimensions may be determined by a second extraction model. Using the second extraction model to extract information from at least one selection method description corresponding to the target category to obtain selection method prompt information corresponding to the plurality of selection dimensions may include: using the second extraction model to extract information from at least one selection method description corresponding to the target category to obtain selection method prompt information corresponding to the plurality of selection dimensions, and determining the display priorities corresponding to the plurality of selection dimensions.

[0115] The fourth prompt template may include information prompting the display priority of multiple selection dimensions. For example, the fourth prompt template may be: "You are a nutrition expert. Please tell me how to select {FFFF}. If there are seven selection dimensions, what are they? Please prioritize the display of the more important selection dimensions."

[0116] The content crawled from the internet describing the selection method related to the target category can include UGC (User-Generated Content), which is a variety of content in the form of text, images, videos, audio, etc. independently created, published, and shared by internet users. Professional knowledge content related to the target category can come from, for example, professional publications.

[0117] A fifth prompt instruction may be generated according to the target category and the fifth prompt template, and the fifth prompt instruction may be input into the third text generation model to instruct the third text generation model to generate selection mode description content corresponding to the target category.

[0118] For example, the fifth prompt template may be: You are now an expert in nutrition. Could you please tell me based on what information I can choose {GGGG}?

[0119] Among them, the target category can be filled in {GGGG} to generate the fifth prompt instruction.

[0120] In some embodiments, obtaining the selection method prompt information corresponding to the target category may include: obtaining the selection method prompt information corresponding to the target category in response to a search request for the target category.

[0121] The method may further include: generating a search result page based on the selection method prompt information and the object prompt information of the plurality of objects matching the target category, so as to display the selection method prompt information on the search result page.

[0122] Determining the target object belonging to the target category includes determining the target object in response to a selection request for a plurality of objects in a search result page.

[0123] This embodiment can generate a search result page based on the selection method prompt information corresponding to the target category to display the selection method prompt information of the target category on the search result page, which helps users understand the characteristics of the target category through the selection method prompt information and make wise selection decisions.

[0124] In some embodiments, after generating the target object's recommendation prompt information, the method may further include: updating the target object's object details page based on the recommendation prompt information, so as to display the recommendation prompt information on the object details page. This allows the user to quickly gain an in-depth understanding of the target object based on the purchase method prompt information and object attribute information in the recommendation prompt information on the object details page.

[0125] Figure 4 This is a flowchart of an embodiment of an information display method provided by the present application. The technical solution of this embodiment can be executed by a user terminal. The method may include the following steps:

[0126] 401: Detects a view operation on the target object.

[0127] 402: In response to the viewing operation, display the recommended prompt information of the target object on the object details page of the target object.

[0128] The recommendation prompt information is generated based on the selection method prompt information corresponding to the target category to which the target object belongs and the object attribute information extracted from the object description information of the target object and matching the selection method prompt information.

[0129] The specific method of generating recommended prompt information can be found in Figure 2 The embodiments described above are not described in detail here.

[0130] In this embodiment, the recommended prompt information of the target object can be displayed on the object details page of the target object, wherein the recommended prompt information is generated based on the selection method prompt information of the target category and the object attribute information of the target object belonging to the target category that matches the selection method prompt information. Personalized recommended prompt information can be generated for different target objects. Compared with the selection method prompt information, the recommended prompt information is more accurate, which helps the user to quickly gain an in-depth understanding of the target object and avoids the user from repeatedly comparing the selection method prompt information and the object description information. It can improve the user's selection efficiency, reduce the number of user interactions, improve the system processing efficiency, and improve the user's selection experience.

[0131] In some embodiments, the method may further include: displaying selection prompt information on the search results page in response to a search operation for the target category, thereby helping the user understand the characteristics of the target category through the selection prompt information and make an informed selection decision.

[0132] Detecting a viewing operation on the target object may include: detecting a viewing operation on the target object on a search result page.

[0133] Figure 5 The following is a flowchart showing an embodiment of a recommended method provided by the present application, which may include the following steps:

[0134] 501: Get the recommended prompt information of the target object.

[0135] The recommendation prompt information may be generated based on the selection method prompt information corresponding to the target category to which the target object belongs and the object attribute information extracted from the object description information of the target object and matching the selection method prompt information.

[0136] The specific method of generating recommended prompt information can be found in Figure 2 The embodiments described above are not described in detail here.

[0137] 502: Recommend a target object based on the recommendation prompt information.

[0138] In this embodiment, recommendation prompt information can be generated based on the selection method prompt information of the target category and the object attribute information of the target object belonging to the target category that matches the selection method prompt information. Personalized recommendation prompt information can be generated for different target objects. Compared with the selection method prompt information, the recommendation prompt information is more accurate, which helps the user to quickly gain an in-depth understanding of the target object and avoids the user from repeatedly comparing the selection method prompt information and the object description information. It can improve the user's selection efficiency, reduce the number of user interactions, improve system performance, and improve the user's selection experience.

[0139] In some embodiments, based on the recommendation prompt information, recommending the target object may include one or more of the following implementation methods: in response to a request to view the details of the target object, sending the recommendation prompt information to the user end to display the recommendation prompt information in the object details page; in response to a customer service request for the target object, sending the recommendation prompt information to the user end to display the recommendation prompt information in the customer service session page; when the target object is the current explanation object in the live broadcast room, displaying the recommendation prompt information in the live broadcast interface; determining the target user who matches the target object, and sending the recommendation prompt information to the target user; in response to a sharing request for the target object, generating a sharing picture including the recommendation prompt information and the object link.

[0140] Displaying recommendation prompts on the object details page can help users avoid repeatedly searching and comparing object descriptions based on the selection prompts. Displaying recommendation prompts on the customer service conversation page can automate recommendations, reducing customer service staff's manual product search time, improving service response speed, and promptly resolving user inquiries. Displaying recommendation prompts on the live broadcast interface can further deepen users' understanding of the target object. Generating a shareable image with recommendation prompts and object links can help the target object reach more potential users and achieve low-cost promotion.

[0141] In a practical application, the technical solution of the embodiment of the present application can be applied to an e-commerce scenario to generate recommendation prompt information for a target product. In an e-commerce scenario, an object refers to a product, such as Figure 6 As shown, the embodiment of the present application also provides an information generation method. The technical solution of this embodiment can be executed by the server. The method may include the following steps:

[0142] 601: Obtaining selection method prompt information corresponding to the target category.

[0143] 602: Determine target products belonging to the target category.

[0144] 603: Extracting the product attribute information that matches the selection method prompt information from the product description information of the target product. The product description information of the target product may include the title name and / or attribute parameter information of the target product.

[0145] 604: Generate recommendation prompt information of the target product based on the selection method prompt information and the product attribute information.

[0146] Among them, the recommendation prompt information can be used to recommend target products.

[0147] It should be noted that Figure 6 The embodiment shown and Figure 2The difference between the embodiment shown and the above-mentioned related embodiments is that the object is specifically implemented as a commodity. Other identical or corresponding operations can be found in detail in Figure 2 The illustrated embodiment and the above-mentioned related embodiments are described and will not be repeated here.

[0148] This embodiment can generate recommendation prompt information for the target product based on the selection method prompt information of the target category and the product attribute information of the target product belonging to the target category that matches the selection method prompt information. Personalized recommendation prompt information can be generated for different target objects. Compared with the selection method prompt information, the recommendation prompt information is more accurate, which helps the user to quickly gain an in-depth understanding of the target product and avoids the user from repeatedly comparing the selection method prompt information and the product description information. It can improve the user's selection efficiency, reduce the number of user interactions, improve system performance, and improve the user's selection experience.

[0149] For ease of understanding, Figure 7 A schematic diagram of scene interaction in a practical application of an embodiment of the present application is shown.

[0150] The user terminal 701 can send a search request to the server terminal 702 in response to the search operation for the target category. The server terminal 702 can obtain the selection method prompt information corresponding to multiple selection dimensions of the target category in response to the search request for the target category, generate a search result page based on the selection method prompt information and the object prompt information of multiple objects matching the target category, and send the search result page to the user terminal 701 so that the user terminal can display the selection method prompt information on the search result page.

[0151] The user terminal 701 can detect the viewing operation for the target object on the search results page and send a detail viewing request to the server terminal 702. The server terminal 702 can respond to the detail viewing request and send the object details page updated based on the recommended prompt information to the user terminal 701, so that the user terminal 701 can display the recommended prompt information of the target object on the object details page.

[0152] The server 702 may utilize a second extraction model to extract information from at least one selection method description corresponding to a target category, obtain selection method prompt information corresponding to multiple selection dimensions, and determine display priorities for each of the multiple selection dimensions. The server 702 may utilize a first extraction model to extract object attribute information corresponding to each of the multiple candidate selection dimensions from the target object's object description information. Furthermore, a predetermined number of target selection dimensions may be selected from the multiple candidate selection dimensions based on their display priorities, and object attribute information corresponding to each of the predetermined number of target selection dimensions may be determined. The server 702 may utilize a second text generation model to update the selection method prompt information corresponding to the at least one target selection dimension based on the object attribute information corresponding to the at least one target selection dimension. The server 702 may utilize a first text generation model to generate attribute description information based on the object attribute information corresponding to the at least one target selection dimension. An attribute description image corresponding to the object attribute information corresponding to the at least one target selection dimension may also be obtained. The attribute description image may be generated based on the target object attribute information using an image generation model. The server 702 may utilize a first extraction model to extract object attribute information corresponding to the at least one target selection dimension, and the server 702 may utilize a first extraction model to extract object attribute information corresponding to the at least one target selection dimension. The server 702 may utilize a second extraction model to extract information corresponding to the at least one target selection dimension. The server 702 may utilize a first extraction model to extract ...

[0153] The detailed implementation and beneficial effects of each step in the method of this embodiment have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0154] For ease of understanding, Figure 8A schematic diagram illustrates the display of an object details page updated based on recommended prompt information in an actual application. Recommended prompt information can be displayed on the object details page 800 for a target object. Assuming the target category is fish oil and the target object is AD brand fish oil, the server 702 uses a second extraction model to extract information from at least one selection method description corresponding to the fish oil, obtains selection method prompt information corresponding to multiple selection dimensions, and determines the display priority for each of the multiple selection dimensions. For example, the display priority is, in order, the selection method prompt information corresponding to the source, certification, purity, and ratio dimensions. The selection method prompt information corresponding to the source dimension is, "Look at the source: Generally, fish from waters near the poles or deep sea are purer and safer." The selection method prompt information corresponding to the certification dimension is, "Look at the certification: Prefer globally recognized, third-party certified fish oils with high quality." The selection method prompt information corresponding to the purity dimension is, "Look at the purity: Purity = DHA and EPA content / Omega-3 content. The higher the purity, the better the effect." The selection method prompt information corresponding to the ratio dimension is, "Those who want to protect eye and brain health can choose products with a high DHA content; those who want to protect vascular health can choose products with a high EPA content." Assume that the first extraction model extracts object attribute information corresponding to the source, certification, purity, and ratio dimensions from the object description information of AD brand fish oil using the first extraction model. For example, the object attribute information matching the source dimension is "Norwegian deep-sea fish," the object attribute information matching the certification dimension is "PM certified," the object attribute information matching the purity dimension is "80%," and the object attribute information matching the ratio dimension is "EPA: 700mg, DHA: 400mg." Assuming that the page display space is limited and only three selection dimensions can be displayed, only the selection method prompts and object attribute information corresponding to the source, certification, and purity dimensions can be displayed. Among the object attribute information matching the certification dimension, "PM certified" indicates that PM certification is not widely known. Therefore, the selection method prompt corresponding to the certification dimension can be updated to "See certification: Prefer globally recognized, third-party fish oil quality certification with high gold content" to, for example, a detailed description of PM certification, such as "See certification: PM certification is an international product quality certification standard that ensures high purity and the absence of heavy metals and environmental toxins." In addition, the first text generation model can also be used to generate corresponding attribute description information from the object attribute information. For example, the attribute description information corresponding to "Norwegian deep-sea fish" can be "This fish oil is selected from Norwegian deep-sea fish", the attribute description information corresponding to "PM certified" can be "This fish oil is PM certified", and the attribute description information corresponding to "80%" can be "The purity of this fish oil is: 80%". For example, the attribute description image corresponding to the object attribute information can be obtained, and then the selection method prompt information and attribute description information corresponding to the source, certification and purity dimensions, as well as the attribute description image, can be filled into the image. Figure 3The preset image templates shown are synthesized into a recommended image 801 , and the recommended image 801 is used as the recommended prompt information of the target object. For example, the recommended image 801 can be displayed in the image display area of ​​the object details page 800 .

[0155] For ease of understanding, Figure 9 A schematic diagram of the display of a customer service conversation page in an actual application of an embodiment of the present application is shown, wherein, for example, a link to a target object sent by a user to customer service can be displayed in the customer service conversation page 900, and the customer service staff can send a recommended image 801 of the target product to the user.

[0156] This embodiment can display recommended prompt information of the target object on the object details page, wherein the recommended prompt information is generated based on the selection method prompt information of the target category and the object attribute information of the target object belonging to the target category that matches the selection method prompt information. Personalized recommended prompt information can be generated for different target objects. Compared with the selection method prompt information, the recommended prompt information is more accurate, which helps the user to quickly gain an in-depth understanding of the target object and avoids the user from repeatedly comparing the selection method prompt information and the object description information. It can improve the user's selection efficiency, reduce the number of user interactions, improve the system processing efficiency, and improve the user's selection experience.

[0157] It should be noted that in some of the processes described in the above embodiments and the accompanying drawings, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or may be executed in parallel. The sequence numbers of the operations, such as 201, 202, etc., are only used to distinguish between different operations, and the sequence numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0158] Figure 10 This is a schematic diagram of the structure of an embodiment of an information generation device provided in an embodiment of the present application, the device comprising:

[0159] The first acquisition module 1001 is used to obtain selection method prompt information corresponding to the target category;

[0160] A determination module 1002 is used to determine a target object belonging to a target category;

[0161] Extraction module 1003, used to extract object attribute information matching the selection method prompt information from the object description information of the target object;

[0162] The first generating module 1004 is configured to generate recommendation prompt information of the target object according to the selection method prompt information and the object attribute information.

[0163] The recommendation prompt information may be used to recommend a target object.

[0164] In some embodiments, the first acquisition module acquiring the selection method prompt information corresponding to the target category may include: acquiring the selection method prompt information corresponding to multiple selection dimensions of the target category.

[0165] The determination module extracting object attribute information matching the selection mode prompt information from the object description information of the target object may include: extracting object attribute information matching at least one target selection dimension from the object description information of the target object.

[0166] The extraction module generates the recommended prompt information of the target object according to the selection method prompt information and the object attribute information, which may include: generating the recommended prompt information of the target object according to the selection method prompt information and the object attribute information corresponding to at least one target selection dimension.

[0167] In some embodiments, as an optional method, the extraction module extracts object attribute information that matches at least one target selection dimension from the object description information of the target object, which may include: using text matching to extract object attribute information that matches at least one target selection dimension from the object description information of the target object.

[0168] As another optional manner, the extraction module extracting object attribute information matching at least one target selection dimension from the object description information of the target object may include: extracting object attribute information matching at least one target selection dimension from the object description information of the target object using a first extraction model.

[0169] In some embodiments, the extraction module extracts object attribute information that matches at least one target selection dimension from the object description information of the target object, which may include: extracting object attribute information that matches multiple candidate selection dimensions respectively from the object description information of the target object; screening a predetermined number of target selection dimensions from the multiple candidate selection dimensions according to the display priorities corresponding to the multiple candidate selection dimensions respectively, and determining the object attribute information that matches the predetermined number of target selection dimensions respectively.

[0170] The above-mentioned use of the first extraction model to extract object attribute information matching at least one target selection dimension from the object description information of the target object may include: using the first extraction model to extract object attribute information matching multiple candidate selection dimensions from the object description information of the target object; screening a predetermined number of target selection dimensions from the multiple candidate selection dimensions according to the display priorities corresponding to the multiple candidate selection dimensions, and determining the object attribute information matching the predetermined number of target selection dimensions.

[0171] In some embodiments, the first acquisition module can also be used to: generate attribute description information based on the object attribute information corresponding to at least one target selection dimension, and then generate recommendation prompt information of the target object based on the selection method prompt information and attribute description information corresponding to at least one target selection dimension.

[0172] As an optional method, the first generation module generates recommendation prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension, which may include: using the first text generation model to generate attribute description information based on the object attribute information corresponding to at least one target selection dimension; generating recommendation prompt information of the target object based on the selection method prompt information and attribute description information corresponding to at least one target selection dimension.

[0173] As another optional method, the first generation module generates recommended prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension, which may include: generating attribute description information based on a preset attribute description template according to the object attribute information corresponding to at least one target selection dimension; generating recommended prompt information of the target object according to the selection method prompt information and attribute description information corresponding to at least one target selection dimension.

[0174] In some embodiments, the first generation module generates recommendation prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension, which may include: using the second text generation model to update the selection method prompt information corresponding to at least one target selection dimension based on the object attribute information corresponding to at least one target selection dimension; generating recommendation prompt information of the target object based on the updated selection method prompt information and object attribute information corresponding to at least one target selection dimension.

[0175] In some embodiments, the first generation module generates recommended prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension, which may include: obtaining an attribute description image corresponding to the object attribute information corresponding to at least one target selection dimension; generating recommended prompt information of the target object based on the selection method prompt information, object attribute information and attribute description image corresponding to at least one target selection dimension.

[0176] In some embodiments, the first generation module generates recommendation prompt information of the target object based on the selection method prompt information and object attribute information corresponding to at least one target selection dimension, which may include: synthesizing the selection method prompt information and object attribute information corresponding to at least one target selection dimension into a recommendation image, and using the recommended image as the recommendation prompt information of the target object.

[0177] In some embodiments, synthesizing the selection method prompt information and object attribute information corresponding to at least one target selection dimension into a recommended image may include: filling the selection method prompt information and object attribute information corresponding to at least one target selection dimension into the preset image template according to the display position defined by the preset image template to generate a recommended image.

[0178] In some embodiments, the first acquisition module acquiring the selection method prompt information corresponding to multiple selection dimensions of the target category may include: using the second extraction model to extract information from at least one selection method description content corresponding to the target category, and generating selection method prompt information corresponding to multiple selection dimensions respectively.

[0179] At least one selection method description content includes one or more of the following: selection method description content related to the target category captured from the Internet; selection method description content preset for the target category; professional knowledge content related to the target category; selection method description content corresponding to the target category generated using a third text generation model.

[0180] Optionally, the display priorities corresponding to the plurality of candidate selection dimensions may be determined by a second extraction model. Using the second extraction model to extract information from at least one selection method description corresponding to the target category to obtain selection method prompt information corresponding to the plurality of selection dimensions may include: using the second extraction model to extract information from at least one selection method description corresponding to the target category to obtain selection method prompt information corresponding to the plurality of selection dimensions, and determining the display priorities corresponding to the plurality of selection dimensions.

[0181] In some embodiments, the first acquisition module acquiring the selection method prompt information corresponding to the target category may include: acquiring the selection method prompt information corresponding to the target category in response to a search request for the target category.

[0182] The device may also include:

[0183] The second generating module is configured to generate a search result page based on the selection method prompt information and the object prompt information of the plurality of objects matching the target category, so as to display the selection method prompt information on the search result page.

[0184] The determining module determining the target object belonging to the target category may include determining the target object in response to a selection request for a plurality of objects in a search result page.

[0185] In some embodiments, after the first generating module generates the recommendation prompt information of the target object, the apparatus may further include: an updating module configured to update the object details page of the target object based on the recommendation prompt information, so as to display the recommendation prompt information in the object details page.

[0186] Figure 10 The information generating device may execute Figure 2 The implementation principle and technical effects of the information generation method described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the information generation device in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0187] Figure 11 This is a schematic structural diagram of an embodiment of an information display device provided in an embodiment of the present application, the device comprising:

[0188] The detection module 1101 is configured to detect a viewing operation on a target object.

[0189] The display module 1102 is configured to display the recommended prompt information of the target object on the object details page of the target object in response to the viewing operation.

[0190] The recommendation prompt information is generated based on the selection method prompt information corresponding to the target category to which the target object belongs and the object attribute information extracted from the object description information of the target object and matching the selection method prompt information.

[0191] In some embodiments, the display module may also be configured to: in response to a search operation for a target category, display selection method prompt information on a search result page.

[0192] The detecting module detecting the viewing operation on the target object may include: detecting the viewing operation on the target object on the search result page.

[0193] Figure 11 The information display device can perform Figure 4The implementation principle and technical effects of the information display method described in the embodiment are not described in detail. The specific manner in which each module and unit performs operations in the information display device in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0194] Figure 12 A schematic structural diagram of an embodiment of a recommended device provided in an embodiment of the present application, the device comprising:

[0195] The second acquisition module 1201 is configured to acquire recommendation prompt information of the target object; wherein the recommendation prompt information may be generated based on selection prompt information corresponding to the target category to which the target object belongs and object attribute information extracted from the object description information of the target object and matching the selection prompt information;

[0196] The recommendation module 1202 is configured to recommend a target object based on the recommendation prompt information.

[0197] In some embodiments, the recommendation module recommends the target object based on the recommendation prompt information, which may include one or more of the following implementation methods: in response to a request to view the details of the target object, sending the recommendation prompt information to the user end to display the recommendation prompt information in the object details page; in response to a customer service request for the target object, sending the recommendation prompt information to the user end to display the recommendation prompt information in the customer service session page; when the target object is the current explanation object in the live broadcast room, displaying the recommendation prompt information in the live broadcast interface; determining the target user who matches the target object, and sending the recommendation prompt information to the target user; in response to a sharing request for the target object, generating a sharing picture including the recommendation prompt information and the object link.

[0198] Figure 12 The recommended device can be implemented Figure 5 The implementation principle and technical effects of the recommendation method described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the recommendation device in the above embodiment has been described in detail in the embodiment of the method and will not be elaborated on here.

[0199] Figure 13 This is a schematic diagram of the structure of an embodiment of an information generation device provided in an embodiment of the present application, the device comprising:

[0200] The third acquisition module 1301 is used to obtain the selection method prompt information corresponding to the target category;

[0201] The second determining module 1302 is used to determine target products belonging to the target category;

[0202] The second extraction module 1303 is configured to extract the product attribute information that matches the selection method prompt information from the product description information of the target product;

[0203] The third generating module 1304 generates recommendation prompt information of the target product according to the selection method prompt information and the product attribute information.

[0204] Among them, the recommendation prompt information can be used to recommend target products.

[0205] Figure 13 The information generating device may execute Figure 6 The implementation principle and technical effects of the information generation method described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the information generation device in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0206] Figure 14 This is a schematic diagram of a computing device according to an embodiment of the present application. Figure 14 As shown, in practice, the computing device may include: a storage component 1401 and a processing component 1402 .

[0207] The storage component 1401 is used to store computer programs and can be configured to store various other data to support operations on the computing device. Examples of such data include instructions for any application or method operating on the computing device, data structures, contact data, phone book data, messages, images, videos, etc.

[0208] The processing component 1402 is coupled to the storage component 1401 and is used to execute the computer program in the storage component 1401 to implement the following Figure 2 The information generation method described in the embodiment shown or Figure 4 The information display method described in the embodiment shown or Figure 5 The recommended method described in the embodiment shown or Figure 6 The information generation method described in the illustrated embodiment.

[0209] Further, if Figure 14 As shown, the computing device may further include: a communication component 1403, a display component 1404, a power component 1405, an audio component 1406 and other components. Figure 14 Only some components are shown schematically, and it does not mean that the computing device only includes Figure 14 In addition, Figure 14The components in the dotted box are optional components, not mandatory components, and depend on the specific product form of the computing device. The computing device of this embodiment can be implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone or an IOT (Internet of Things) device, or a server device such as a conventional server, a cloud server or a server array. If the computing device of this embodiment is implemented as a terminal device such as a desktop computer, a laptop computer, a smart phone, etc., it can include Figure 14 If the computing device of this embodiment is implemented as a server device such as a conventional server, a cloud server or a server array, it may not include the components in the dotted box; Figure 14 Components within the dotted box.

[0210] The processing component includes one or more processors to execute computer instructions to perform all or part of the steps in the above method. Of course, the processing component can also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0211] The above-mentioned storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0212] The communication component is configured to facilitate wired or wireless communication between the device in which the communication component resides and other devices. The device in which the communication component resides may access a wireless network based on a communication standard, such as a mobile communication network, or a combination thereof. In an exemplary embodiment, the communication component receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel.

[0213] The display assembly may include a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0214] The power supply assembly provides power to various components of the device in which the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply assembly is located.

[0215] The above-mentioned audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as call mode, recording mode, and voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0216] Accordingly, an embodiment of the present application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to implement the steps in the above method embodiment. The computer-readable storage medium includes volatile or non-volatile or a combination thereof, and may be removable or non-removable. Examples of computer-readable storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic cassette, tape disk storage or other magnetic storage device or any other non-transmission medium.

[0217] Accordingly, an embodiment of the present application further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the processor is enabled to implement the steps in the above-mentioned method embodiment. It should be understood that each process or a combination of multiple processes in the above-mentioned method flow can be implemented by a computer program or instruction. In addition, these computer programs or instructions can be applied to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device, so that the processor of the general-purpose computer, the special-purpose computer, the embedded processor or other programmable data processing device can be implemented as a device for implementing the corresponding functions in the above-mentioned method embodiment.

[0218] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0219] It should also be noted that the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, object, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, object, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, object, or apparatus that includes the element.

[0220] Finally, it should be noted that the above are merely examples of the present application and are not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. An information generation method, characterized in that: include: Get the selection method prompt information corresponding to the target category; determining target objects belonging to the target category; extracting object attribute information matching the selection method prompt information from the object description information of the target object; generating recommendation prompt information of the target object according to the selection method prompt information and the object attribute information; The recommendation prompt information is used to recommend the target object.

2. The method according to claim 1, characterized in that The method of obtaining the selection method prompt information corresponding to the target category includes: Get the selection method prompt information for multiple selection dimensions corresponding to the target category; The extracting, from the object description information of the target object, object attribute information that matches the selection method prompt information includes: Extracting object attribute information matching at least one target selection dimension from the object description information of the target object; Generating the recommendation prompt information of the target object according to the selection method prompt information and the object attribute information includes: Recommendation prompt information of the target object is generated according to the selection method prompt information corresponding to the at least one target selection dimension and the object attribute information.

3. The method according to claim 2, characterized in that The extracting, from the object description information of the target object, object attribute information matching at least one target selection dimension includes: The first extraction model is used to extract object attribute information matching at least one target selection dimension from the object description information of the target object.

4. The method according to claim 3, characterized in that The extracting, from the object description information of the target object using the first extraction model, object attribute information matching at least one target selection dimension includes: Extracting object attribute information that matches multiple candidate selection dimensions from the object description information of the target object using a first extraction model; According to the display priorities respectively corresponding to the multiple candidate selection dimensions, a predetermined number of target selection dimensions are screened from the multiple candidate selection dimensions, and object attribute information respectively matched by the predetermined number of target selection dimensions is determined.

5. The method according to claim 2, characterized in that The generating of the recommendation prompt information of the target object according to the selection method prompt information corresponding to the at least one target selection dimension and the object attribute information includes: Generate attribute description information using a first text generation model based on object attribute information corresponding to the at least one target selection dimension; Recommendation prompt information of the target object is generated according to the selection method prompt information corresponding to the at least one target selection dimension and the attribute description information.

6. The method according to claim 2, characterized in that The generating of the recommendation prompt information of the target object according to the selection method prompt information corresponding to the at least one target selection dimension and the object attribute information includes: Using the second text generation model, based on the object attribute information corresponding to the at least one target selection dimension, the selection method prompt information corresponding to the at least one target selection dimension is updated; Recommendation prompt information of the target object is generated according to the updated selection method prompt information and object attribute information corresponding to the at least one target selection dimension.

7. The method according to claim 2, characterized in that The generating of the recommendation prompt information of the target object according to the selection method prompt information corresponding to the at least one target selection dimension and the object attribute information includes: Acquire an attribute description image corresponding to the object attribute information corresponding to the at least one target selection dimension; the attribute description image is generated according to the target object attribute information using an image generation model; Recommendation prompt information of the target object is generated according to the selection method prompt information corresponding to the at least one target selection dimension, the object attribute information, and the attribute description image.

8. The method according to claim 2, characterized in that The generating of the recommendation prompt information of the target object according to the selection method prompt information corresponding to the at least one target selection dimension and the object attribute information includes: The selection method prompt information corresponding to the at least one target selection dimension and the object attribute information are synthesized into a recommendation image, and the recommendation image is used as the recommendation prompt information of the target object.

9. The method according to claim 8, characterized in that The step of synthesizing the selection method prompt information corresponding to the at least one target selection dimension and the object attribute information into a recommended image includes: According to the display position defined by the preset image template, the selection method prompt information corresponding to the at least one target selection dimension and the object attribute information are filled into the preset image template to generate a recommended image.

10. The method according to claim 2, characterized in that The acquisition of selection method prompt information corresponding to multiple selection dimensions of the target category includes: Using a second extraction model, extracting information from at least one selection method description corresponding to the target category to obtain selection method prompt information corresponding to the plurality of selection dimensions; The at least one selection method description includes one or more of the following: Content describing the selected method related to the target category is crawled from the Internet; Description of the preset selection method for the target category; Professional knowledge content related to the target category; The selection method description content corresponding to the target category is generated using the third text generation model.

11. The method according to claim 1, wherein The method of obtaining the selection method prompt information corresponding to the target category includes: In response to a search request for a target category, obtaining selection method prompt information corresponding to the target category; The method further comprises: generating a search result page based on the selection method prompt information and object prompt information of a plurality of objects matching the target category, and displaying the selection method prompt information on the search result page; Determining the target object belonging to the target category includes: In response to a selection request for a plurality of objects in the search result page, a target object is determined.

12. The method according to claim 1, characterized in that After generating the recommendation prompt information of the target object, the method further includes: Based on the recommendation prompt information, the object details page of the target object is updated to display the recommendation prompt information on the object details page.

13. An information display method, characterized in that: include: Detecting viewing operations on target objects; In response to the viewing operation, recommended prompt information of the target object is displayed on the object details page of the target object; wherein, the recommended prompt information is generated based on the selection method prompt information corresponding to the target category to which the target object belongs and the object attribute information extracted from the object description information of the target object and matching the selection method prompt information.

14. The method according to claim 13, characterized in that Also includes: In response to a search operation for the target category, displaying the selection method prompt information on a search result page; The responding to the viewing operation on the target object includes: In response to a viewing operation on the target object on the search result page.

15. A recommendation method, characterized in that: include: Get the recommended prompt information of the target object; The recommendation prompt information is generated based on the selection method prompt information corresponding to the target category to which the target object belongs and the object attribute information extracted from the object description information of the target object and matching the selection method prompt information; The target object is recommended based on the recommendation prompt information.

16. The method according to claim 15, characterized in that The recommending the target object based on the recommendation prompt information includes one or more of the following implementations: In response to a request for viewing details of the target object, sending the recommendation prompt information to a user terminal so as to display the recommendation prompt information on an object details page; In response to a customer service request for the target object, sending the recommendation prompt information to the user terminal so as to display the recommendation prompt information on a customer service session page; When the target object is the current subject of the live broadcast, the recommendation prompt information is displayed in the live broadcast interface; Determine a target user that matches the target object, and send the recommendation prompt information to the target user; In response to a sharing request for the target object, a sharing picture including the recommendation prompt information and the object link is generated.

17. An information generation method, characterized in that: include: Get the selection method prompt information corresponding to the target category; determining target products belonging to the target category; Extracting product attribute information matching the selection method prompt information from the product description information of the target product; generating recommendation prompt information of the target product according to the selection method prompt information and the product attribute information; The recommendation prompt information is used to recommend the target product.

18. A computing device, characterized in that including processing components and storage components; The storage component stores a computer program; the computer program is called and executed by the processing component to implement the information generation method as described in any one of claims 1 to 12, the information display method as described in any one of claims 13 to 14, the recommendation method as described in any one of claims 15 to 16, or the information generation method as described in claim 17.

19. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by the processing component, it implements the information generation method according to any one of claims 1 to 12, the information display method according to any one of claims 13 to 14, the recommendation method according to any one of claims 15 to 16, or the information generation method according to claim 17.

20. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processing component, implements the information generation method according to any one of claims 1 to 12, the information display method according to any one of claims 13 to 14, the recommendation method according to any one of claims 15 to 16, or the information generation method according to claim 17.

Images