An information display method, device, equipment, medium and product

Abstract

Embodiments of the present application provide an information display method, device, equipment, medium and product, relating to the technical field of artificial intelligence, which comprises: presenting a resource preview page, wherein the resource preview page contains resource links of multiple electronic resources respectively; in response to a triggering operation on a resource link of an electronic resource in the multiple electronic resources, displaying attribute summary information of the electronic resource under each preset dimension; the attribute summary information under each preset dimension is generated based on attribute detail content associated with the resource link. This process omits the operation of switching from a resource application to a search application, then searching for a large amount of related information in the search application and summarizing, which greatly simplifies the operation process, thereby improving the efficiency of information summarization. Secondly, the attribute summary information under each preset dimension is generated based on the attribute detail content associated with the resource link, which no longer relies on manual searching and summarizing of a large amount of information, thereby effectively improving the accuracy of information summarization.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to an information display method, apparatus, device, medium and product. Background Technology

[0002] With the popularization of the Internet and social media, the speed and scale of information production are growing exponentially.

[0003] Under relevant technologies, resource applications typically display basic information and the latest status of electronic resources (such as goods, news, and stocks) when showcasing them. For example, a shopping application might display information such as the brand, model, and latest pricing of a mobile phone. If the target audience wants a more comprehensive understanding of the electronic resource, they need to trigger a search application on their smart device, search for a large amount of relevant information, and then spend considerable time piecing together and summarizing this information to obtain a summary of the electronic resource's attributes.

[0004] In the above process, the target needs to operate the resource application and the search application in sequence; and, it needs to manually search for a large amount of information from electronic resources to summarize, which results in low information summarization efficiency. Summary of the Invention

[0005] This application provides an information display method, apparatus, device, medium, and product to improve the efficiency of information summarization and display.

[0006] On the one hand, embodiments of this application provide an information display method, which includes: A resource preview page is displayed, which contains resource links for each of the multiple electronic resources; In response to a triggered operation for a resource link of one of the plurality of electronic resources, the system switches from the resource preview page to the resource details page of the electronic resource, the resource details page including: resource status description information and attribute summary components of the electronic resource; In response to a triggered operation on the attribute summary component, an attribute summary page is displayed. The attribute summary page includes attribute summary information of the electronic resource under various preset dimensions. The attribute summary information under each preset dimension is generated based on the attribute details associated with the resource link.

[0007] On one hand, embodiments of this application provide an information display device, which includes: The display module is used to present a resource preview page, which contains resource links for each of the multiple electronic resources. The display module is further configured to, in response to a trigger operation for a resource link of one of the plurality of electronic resources, switch from the resource preview page to the resource details page of the electronic resource, wherein the resource details page includes: resource status description information and attribute summary component of the electronic resource; and, in response to a trigger operation for the attribute summary component, display the attribute summary page, wherein the attribute summary page includes: attribute summary information of the electronic resource under various preset dimensions, wherein the attribute summary information under various preset dimensions is generated based on the attribute details content associated with the resource link.

[0008] Optionally, the display module is specifically used for: In response to a triggered operation on the attribute summary component, the attribute summary page is displayed as a floating card on the resource details page.

[0009] Optionally, the display module is further used for: In response to an operation initiated for the conversion of the electronic resource, a conversion confirmation page for the electronic resource is displayed; the conversion confirmation page includes: the resource conversion amount of the electronic resource; In response to a conversion confirmation operation triggered on the conversion confirmation page, a conversion result page for the electronic resource is displayed; the conversion result page includes: the resource conversion certificate for the electronic resource.

[0010] Optionally, the display module is further used for: In response to a trigger operation on the attribute summary component, after displaying the attribute summary page, In response to a sharing operation triggered on the attribute summary page, the user is redirected from the attribute summary page to a target sharing page; the target sharing page includes attribute summary information under each preset dimension.

[0011] Optionally, the attribute summary page includes a question-and-answer component; The display module is also used for: In response to a trigger operation on the attribute summary component, after displaying the attribute summary page, in response to a trigger operation on the question-and-answer component, the page switches from the attribute summary page to the intelligent question-and-answer page; the intelligent question-and-answer page includes: an input operation area and a history dialogue area, the history dialogue area including: attribute summary information under each preset dimension; In response to a question action triggered in the input operation area, a corresponding reply text is displayed in the history dialogue area; the reply text is generated based on the question text associated with the question action and the attribute summary information under each preset dimension.

[0012] Optionally, the attribute summary page may further include: the recommendation level and the reason for recommendation of an electronic resource, wherein the recommendation level and the reason for recommendation are obtained based on the weights of each preset dimension and the attribute summary information under each preset dimension.

[0013] Optionally, the display module is specifically used for: In response to a trigger operation on the attribute summary component, an attribute summary request is sent to the server. The attribute summary request carries the resource identifier of the electronic resource, so that the server can obtain attribute summary information under each preset dimension that matches the resource identifier. Receive the attribute summary information under each preset dimension returned by the server; The attribute summary information under each preset dimension is rendered to obtain the attribute summary page, and the attribute summary page is displayed.

[0014] Optionally, it may also include a processing module; The processing module is specifically used for: For each preset dimension, obtain the dimension details associated with the preset dimension from the attribute details content; Based on the dimension details associated with the preset dimension, a prompt text is generated, indicating that a summary of the dimension details associated with the preset dimension should be performed. Using the prompt text as a prompt instruction, input it into the large language model for reasoning to obtain the attribute summary information of the preset dimension.

[0015] Optionally, the processing module is specifically used for: Using the large language model, perform the following steps: Based on the contextual information contained in the prompt text, text intent recognition is performed on the prompt text to obtain a recognition result; the recognition result indicates that a content summary of the dimension details associated with the preset dimension is performed. Based on the recognition results, core element information is extracted from the dimension details and reconstructed to obtain the attribute summary information of the preset dimension.

[0016] Optionally, the processing module is specifically used for: Feature extraction is performed on the details of the aforementioned dimensions to obtain semantic features of the details; Based on the recognition results, core element features are extracted from the semantic features of the details, where the core element features are the semantic features of the core element information in the dimension details content. An autoregressive approach is used to generate attribute summary information for the preset dimensions based on the core element features.

[0017] Optionally, the processing module is further configured to: For each preset dimension, obtain the dimension details associated with the preset dimension from the attribute details content; When the amount of data in the dimension details exceeds a preset threshold, the dimension details will be split into multiple data blocks. Summarize the information for each data block to obtain corresponding sub-summary content; The obtained sub-summaries are merged to obtain the attribute summary information of the preset dimension.

[0018] On one hand, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described information display method.

[0019] On one hand, embodiments of this application provide a computer-readable storage medium storing a computer program executable by a computer device, which, when run on the computer device, causes the computer device to perform the steps of the above-described information display method.

[0020] On one hand, embodiments of this application provide a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer device, cause the computer device to perform the steps of the above-described information display method.

[0021] In this embodiment of the application, when the resource link of the electronic resource is triggered, the attribute summary information of the electronic resource under each preset dimension is displayed. This process omits the operation of switching from the resource application to the search application, and then searching for and summarizing a large amount of relevant information in the search application. This greatly simplifies the operation process and improves the efficiency of information summarization.

[0022] Secondly, attribute summary information under each preset dimension is generated based on the attribute details associated with resource links, eliminating the need for manual searching of large amounts of information for summarization. This reduces the impact of subjective factors on the summary results, thereby effectively improving the accuracy and objectivity of the information summary.

[0023] In addition, integrating information summarization into resource applications eliminates the need to run resource and search applications simultaneously on smart devices, thereby reducing the workload on smart devices and improving their overall efficiency. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 A schematic diagram of a system architecture provided in an embodiment of this application; Figure 2 This application provides an illustration of an application scenario. Figure 1 ; Figure 3 This application provides an illustration of an application scenario. Figure 2 ; Figure 4 A flowchart illustrating an information display method provided in this application embodiment. Figure 1 ; Figure 5A An illustration of a product link provided in an embodiment of this application. Figure 1 ; Figure 5B An illustration of a product link provided in an embodiment of this application. Figure 2 ; Figure 6 A schematic diagram summarizing the attributes of the battery life dimension provided in the embodiments of this application; Figure 7A A flowchart illustrating an attribute summarization method provided in this application embodiment. Figure 1 ; Figure 7B A schematic diagram summarizing the attributes of the core positioning dimensions provided in the embodiments of this application; Figure 7C A schematic diagram summarizing the attributes of the company's quality dimension provided in the embodiments of this application; Figure 7D A schematic diagram summarizing the attributes of the company valuation dimension provided in the embodiments of this application; Figure 8 A flowchart illustrating a block aggregation reasoning method provided in an embodiment of this application; Figure 9A A flowchart illustrating a recommendation scoring method provided in this application embodiment. Figure 1 ; Figure 9B A flowchart illustrating a recommendation scoring method provided in this application embodiment. Figure 2 ; Figure 10A A flowchart illustrating an attribute summarization method provided in this application embodiment. Figure 2 ; Figure 10B A flowchart illustrating an attribute summarization method provided in this application embodiment. Figure 3 ; Figure 11A A flowchart illustrating an attribute summarization method provided in this application embodiment. Figure 4 ; Figure 11B A flowchart illustrating an attribute summarization method provided in this application is shown in Figure 5. Figure 12 A flowchart illustrating an information interaction method provided in this application embodiment. Figure 1 ; Figure 13 A flowchart illustrating an information interaction method provided in this application embodiment. Figure 2 ; Figure 14 A flowchart illustrating an attribute summarization method provided in this application embodiment. Figure 6 ; Figure 15A A flowchart illustrating a resource conversion method provided in this application embodiment. Figure 1 ; Figure 15B A flowchart illustrating a resource conversion method provided in this application embodiment. Figure 2 ; Figure 16A A flowchart illustrating a page sharing method provided in this application embodiment. Figure 1 ; Figure 16B A flowchart illustrating a page sharing method provided in this application embodiment. Figure 2 ; Figure 17A A flowchart illustrating an intelligent question-answering method provided in this application embodiment. Figure 1 ; Figure 17B A flowchart illustrating an intelligent question-answering method provided in this application embodiment. Figure 2 ; Figure 17C A flowchart illustrating an information display method provided in this application embodiment. Figure 2 ; Figure 18 This is a schematic diagram of the structure of an information display device provided in an embodiment of this application; Figure 19 A schematic diagram of the structure of a computer device provided in an embodiment of this application; Figure 20 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and beneficial effects of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0027] For ease of understanding, the terms used in the embodiments of this invention are explained below.

[0028] Large Language Models (LLMs), also known as large models, natural language models, or large-scale language models, refer to natural language processing models with a large number of parameters and training data. The training process of LLMs typically employs unsupervised learning, meaning the model is trained on a large-scale text corpus to learn the probability distribution and rules of language. During training, LLMs usually use a language model as the objective function, optimizing the model parameters by maximizing the prediction probability of the next word. Trained on a large-scale corpus, they can generate high-quality natural language text, such as articles and dialogues.

[0029] Prompt: A prompt text used to provide input text or instructions to the model, guiding it to generate a specific type of response. A prompt can be a question, a description, a task instruction, or even a portion of the conversation history. By designing and optimizing prompts, you can guide the model to generate expected responses or complete specific tasks.

[0030] With the research and advancement of artificial intelligence (AI) technology, AI is being studied and applied in various fields, such as smart homes, smart wearable devices, virtual assistants, smart speakers, smart marketing, autonomous driving, drones, digital twins, virtual humans, robots, AI-generated content (AIGC), conversational interaction, smart healthcare, smart customer service, and game AI. It is believed that with the development of technology, AI will be applied in more fields and play an increasingly important role.

[0031] The solutions provided in this application mainly involve the application of artificial intelligence technology in information summarization, that is, refining, condensing and reorganizing fragmented, multi-source or multimodal input information through a large language model, outputting structured and concise content, retaining core points, logical relationships and key information, while filtering out redundant details.

[0032] It is understood that in the specific implementation of this application, data related to electronic resources, resource links, etc. are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0033] The design concept of the embodiments of this application will be introduced below.

[0034] When resource applications showcase electronic resources (such as products, news, and stocks), they typically display basic information and the latest status of the electronic resources; for example, a shopping application might display information such as the brand, model, and latest pricing of a mobile phone. If the target audience wants a more comprehensive understanding of the electronic resource, they need to trigger a search application on their smart device, then search for a large amount of relevant information within the search application, and then spend a significant amount of time piecing together and summarizing the relevant information to obtain a summary of the electronic resource's attributes.

[0035] In the above process, the target needs to operate the resource application and the search application in sequence; and, it needs to manually search for a large amount of information from electronic resources to summarize, which results in low information summarization efficiency.

[0036] Based on this, embodiments of this application provide an information display method, the method comprising: The system presents a resource preview page containing links to multiple electronic resources. In response to a trigger action on a resource link of one of the electronic resources, the system switches from the preview page to the resource details page for that resource. The resource details page includes a description of the resource's status and an attribute summary component. In response to a trigger action on the attribute summary component, the system displays the attribute summary page, which includes attribute summary information for the electronic resource across various preset dimensions. This process eliminates the need to switch from the resource application to the search application, then search for and summarize a large amount of relevant information within the search application, greatly simplifying the workflow and improving the efficiency of information summarization.

[0037] Secondly, attribute summary information under each preset dimension is generated based on the attribute details associated with resource links, eliminating the need for manual searching of large amounts of information for summarization. This reduces the impact of subjective factors on the summary results, thereby effectively improving the accuracy and objectivity of the information summary.

[0038] In addition, integrating information summarization into resource applications eliminates the need to run resource and search applications simultaneously on smart devices, thereby reducing the workload on smart devices and improving their overall efficiency.

[0039] The following is a brief introduction to the system architecture diagram applicable to the technical solutions of the embodiments of this application. It should be noted that the system architecture diagram described below is only used to illustrate the embodiments of this application and is not intended to limit the scope of the application.

[0040] refer to Figure 1 This is a system architecture diagram applicable to the embodiments of this application. The system architecture includes at least terminal device 101 and server 102. The number of terminal devices 101 can be one or more, and the number of servers 102 can also be one or more. This application does not specifically limit the number of terminal devices 101 and servers 102.

[0041] Terminal device 101 may be a smart device such as a smartphone, tablet computer, laptop computer, desktop computer, smart home appliance, smart voice interaction device, smart in-vehicle device, etc., but is not limited to these.

[0042] Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms, but it is not limited to these.

[0043] It should be noted that the method in this embodiment can be executed by terminal device 101. When executed by terminal device 101 alone, terminal device 101 presents a resource preview page, which contains resource links for multiple electronic resources; in response to a trigger operation for a resource link of one of the multiple electronic resources, it switches from the resource preview page to the resource details page of that electronic resource, which includes: resource status description information and attribute summary component of the electronic resource; in response to a trigger operation for the attribute summary component, it displays the attribute summary page, which includes: attribute summary information of the electronic resource under each preset dimension; the attribute summary information under each preset dimension is generated based on the attribute details content associated with the resource link.

[0044] The method in this embodiment can also be executed jointly by server 102 and terminal device 101. Terminal device 101 presents a resource preview page containing resource links for multiple electronic resources. In response to a trigger operation targeting a resource link of one of the multiple electronic resources, it retrieves and displays the resource status description information and attribute summary component of that electronic resource from server 102. In response to a trigger operation targeting the attribute summary component, terminal device 101 retrieves attribute summary information of the electronic resource under various preset dimensions from server 102, and then displays the attribute summary information of the electronic resource under various preset dimensions on the attribute summary page. The attribute summary information of the electronic resource under various preset dimensions is generated by server 102 based on the attribute details associated with the resource links.

[0045] Both server 102 and terminal device 101 may include one or more processors, memory, and interactive I / O interfaces. The memory of server 102 and terminal device 101 may store program instructions required for execution in the information display method provided in this application embodiment. When these program instructions are executed by the processor, they can implement the information display process provided in this application embodiment.

[0046] It should be noted that when the information display method provided in this application embodiment is executed solely by terminal device 101, the system architecture of this application may also include only terminal device 101, or server 102 and terminal device 101 may be considered as the same device. Of course, in practical applications, when the information display method provided in this application embodiment is executed jointly by server 102 and terminal device 101, server 102 and terminal device 101 may also be the same device; that is, server 102 and terminal device 101 may be different functional modules of the same device, or virtual devices virtualized from the same physical device.

[0047] In this embodiment, the terminal device 101 and the server 102 can communicate directly or indirectly through one or more networks. The network can be a wired network or a wireless network; for example, the wireless network can be a mobile cellular network or a Wireless-Fidelity (WIFI) network, or other possible networks. This embodiment does not limit the types of networks used.

[0048] The following is a brief introduction to the application scenarios to which the technical solutions of the embodiments of this application are applicable. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.

[0049] The solution provided in this application is applicable to the information display of electronic resources in various application scenarios, such as shopping scenarios, news aggregation and summarization scenarios, travel guide integration scenarios, and financial and investment scenarios. This solution can also be used as a foundational technology in various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, assisted driving, and audio-visual scenarios.

[0050] The following provides an illustrative example of the application scenarios to which the solution provided in this application is applicable.

[0051] Application Scenario 1: Shopping Scenario.

[0052] See Figure 2 In a shopping scenario, electronic resources represent goods, and resource links represent product links. The terminal device has a shopping application pre-installed, and the homepage (page 201) of the shopping application displays product links for multiple items; for example, links for mobile phones, short-sleeved shirts, high heels, and sneakers.

[0053] When the target user clicks the mobile link, the shopping app redirects from the homepage 201 to the product details page 202, where the AI ​​quick review card 203 is displayed. The AI ​​quick review card 203 includes attribute summary information under the following preset dimensions: "XX mobile phone, 3299 yuan;" Battery life: One charge lasts for 1-2 days, but battery life decreases significantly in low temperatures; Screen experience: 2K resolution, videos are clear and pixel-free, but there is severe glare under strong light; Game performance: Fast loading speed, the device gets hot after playing continuously for more than 1 hour; Transaction speed rating: 75 / 100; Reason for rating: Strong battery life, clear video playback.

[0054] Application Scenario 2: Finance and Investment Scenario.

[0055] Stock market information is complex and constantly changing, and investors rely on understanding relevant information to aid their investment decisions. Related financial applications offer homogenized display or operational areas, such as price quotes, candlestick charts, and news sections. While this interwoven information provides comprehensiveness, it also tests investors' ability to summarize information. In understanding a stock, investors might look at candlestick charts, check the latest news, and then spend a significant amount of time piecing together and summarizing a vague conclusion—a method that is inefficient and inaccurate.

[0056] Based on this, in the embodiments of this application, see [reference] Figure 3The resource preview page 301 for financial applications is displayed. The resource preview page 301 contains multiple stock links, namely: stock links for Company A, stock links for Company B, and stock links for Company C.

[0057] In response to the triggered action of the stock link for Company A in the resource preview page 301, the stock details page 302 is displayed; and the AI ​​quick rating card 303 for Company A's stock is displayed on the stock details page 302. The AI ​​quick rating card 303 includes attribute summary information under the following preset dimensions: Company A (123456); Real-time stock price: 345 yuan; Updated on: XX year - XX month - XX day; Core positioning: Digital ecosystem giant, attractive valuation but requires liquidity support; Quality: Possesses a core social ecosystem with a deep moat; Valuation: Significantly lower than international internet giants and similar companies listed on the A-share market, indicating a high margin of safety; Timing: The stock price rebounded and is now fluctuating around the key level of the annual moving average. Transaction speed rating: 79 / 100; Reason for rating: "Deep ecological moat, attractive valuation."

[0058] It should be noted that the embodiments of this application are not limited to the application scenarios exemplified above, but may also be other application scenarios, which are not specifically limited in this application.

[0059] based on Figure 1 The system architecture diagram shown in this application illustrates the flow of an information display method. Figure 4 As shown, the process of this method is executed by a computer device, which can be... Figure 1 The terminal device 101 and / or server 102 shown include the following steps: Step 401: Present the resource preview page, which contains resource links for each of the multiple electronic resources.

[0060] Specifically, electronic resources can include commodity resources, media resources, and financial products; commodity resources can be goods and services used for transactions, such as a two-person meal or coffee; or electronic park tickets and home cleaning services. Media resources can include news and short videos; financial products refer to various carriers through which funds are exchanged, such as stocks and securities.

[0061] In this embodiment, a resource preview page is displayed in the resource application; the corresponding resource application varies depending on the electronic resource. For example, when the electronic resource is a product resource, the resource application may be a shopping application, a review application, etc.; when the electronic resource is a media resource, the resource application may be a browser application, a video application, etc.; when the electronic resource is a financial product, the resource application may be a financial application.

[0062] A resource preview page can be the homepage of a resource application or another page within the application. A resource link is a URL link that points to a specific electronic resource; the target audience can access the page associated with that resource by clicking the link, and can then perform actions such as viewing resource details, converting resources (e.g., purchasing), reserving resources, and sharing resources on that page.

[0063] Resource links can be plaintext links or resource cards; in addition to containing key information such as images and titles of electronic resources, resource cards also include interactive entry points for electronic resources, and the target object can trigger a jump by clicking any position on the resource card.

[0064] For example, see Figure 5A The shopping app's homepage displays multiple product links: mobile phone link, short-sleeved shirt link, high heels link, and sneakers link.

[0065] For example, see Figure 5B The stock selection page of the financial application displays multiple stock links, namely the stock links of Company A, Company B, and Company C.

[0066] Step 402: In response to a triggered operation for a resource link of one of the multiple electronic resources, switch from the resource preview page to the resource details page of that electronic resource.

[0067] Specifically, the resource details page includes: resource status description information and attribute summary components for the electronic resource. The resource status description information includes the latest status information of the electronic resource. For example, when the electronic resource is a commodity, the resource details page displays the latest price, promotional information, latest inventory, and other status description information. Similarly, when the electronic resource is a stock, the resource details page displays the stock's real-time quotes, real-time trading volume, real-time trading value, and other status description information.

[0068] Step 403: In response to the triggered operation on the attribute summary component, display the attribute summary page.

[0069] Specifically, the attribute summary component on the resource details page is an interactive component used to trigger the display of the attribute summary page. This component can be displayed on the resource details page as a button, icon, or other similar format. When the target user clicks on the attribute summary component displayed on the resource details page, the attribute summary page is displayed, which includes attribute summary information for the electronic resource across various preset dimensions.

[0070] There can be one or more preset dimensions; different preset dimensions can be set for different electronic resources; the attribute summary information under each preset dimension is generated based on the attribute details associated with the resource link (i.e., the attribute details associated with the electronic resource).

[0071] The attribute details include the dimension details associated with each preset dimension; attribute summary information for each preset dimension is generated based on the dimension details associated with each preset dimension.

[0072] For example, when the electronic resource is a product called "mobile phone", the attribute details of "mobile phone" include: function description data, review data, and news data.

[0073] The preset dimensions include: battery life, screen experience, and gaming performance. The battery life dimension details include: feature introduction data and user reviews; based on the feature introduction data and user reviews, a summary of battery life attribute information is generated.

[0074] The details of the screen experience dimension include: comment data and news data; based on the comment data and news data, attribute summary information for the screen experience dimension is generated.

[0075] The detailed information for the game performance dimension includes: feature description data. Based on the feature description data, a summary of the game performance dimension's attributes is generated.

[0076] In this embodiment of the application, when the resource link of the electronic resource is triggered, the attribute summary information of the electronic resource under each preset dimension is displayed. This process omits the operation of switching from the resource application to the search application, and then searching for and summarizing a large amount of relevant information in the search application. This greatly simplifies the operation process and improves the efficiency of information summarization.

[0077] Secondly, attribute summary information under each preset dimension is generated based on the attribute details associated with resource links, eliminating the need for manual searching of large amounts of information for summarization. This reduces the impact of subjective factors on the summary results, thereby effectively improving the accuracy and objectivity of the information summary.

[0078] In addition, integrating information summarization into resource applications eliminates the need to run resource and search applications simultaneously on smart devices, thereby reducing the workload on smart devices and improving their overall efficiency.

[0079] One possible implementation is that the attribute summary information for each preset dimension can be generated offline by the server. Specifically, the processing logic for generating attribute summary information is initiated via a scheduled task. In this way, after retrieving the required dimension details, the offline service on the server summarizes and categorizes the dimension details to obtain the corresponding attribute summary information, which is then stored in the database. Thus, when the attribute summary of electronic resources is triggered for display, the terminal device retrieves the attribute summary information for each preset dimension from the server and renders and displays it.

[0080] Of course, the attribute summary information under each preset dimension can also be generated online by the server; specifically, when the attribute summary of electronic resources is triggered, the terminal device sends a request to the server; the server summarizes and categorizes the dimension details of each preset dimension online, obtains the corresponding attribute summary information, and then returns the obtained attribute summary information to the terminal device; the terminal device renders and displays the attribute summary information under each preset dimension.

[0081] One possible implementation involves obtaining the dimension details associated with the preset dimension from the attribute details for each preset dimension; then generating a prompt text based on the dimension details associated with the preset dimension, indicating that a summary of the dimension details associated with the preset dimension should be performed; finally, using the prompt text as a prompt instruction, inputting it into a large language model for reasoning to obtain the attribute summary information of the preset dimension.

[0082] Specifically, based on a preset prompt content template and the dimension details associated with the preset dimensions, prompt text is generated. The prompt content template is a template type that the large language model can recognize, used to help the model understand the semantic information of each part of the content. The prompt content template presets the position and order of each item, so the corresponding prompt text can be generated simply by following the prompt content template. In practical applications, in addition to the dimension details described above, the prompt text can also include other auxiliary content.

[0083] The prompt text is input as a prompt instruction into the large language model for inference. The large language model is based on a prompt learning method, which predicts the content following the prompt instruction based on the input prompt instruction. That is, it summarizes the content of the dimension details associated with each preset dimension, retains the core points, logical relationships and key information, and filters out redundant details to obtain the dimension summary information for each preset dimension.

[0084] One possible implementation involves performing the following steps using a large language model: Based on the contextual information contained in the prompt text, text intent recognition is performed on the prompt text to obtain the recognition result; the recognition result indicates: to summarize the content of the dimension details associated with the preset dimension; then, according to the recognition result, core element information is extracted from the dimension details and reconstructed to obtain the attribute summary information of the preset dimension.

[0085] Specifically, the prompt text is segmented into a sequence of tokens that the model can recognize using the token segmenter, and then each token is converted into a corresponding vector representation. Next, multi-layer self-attention computation is performed on the obtained vector representations to obtain the association information between each token and other related tokens in the prompt text. Based on the obtained association information, the contextual information contained in the prompt text is obtained. During the pre-training phase, the large language model has already learned the task paradigm and language rules in massive amounts of text. Therefore, based on the contextual information contained in the prompt text, the textual intent indicated by the prompt text can be obtained, that is, a summary of the content of the dimensional details associated with the preset dimensions.

[0086] In addition to recognizing the textual intent indicated by the prompt text, constraint information can also be extracted and generated from the prompt text, such as "the summary should be kept within 50 words" or "summarize the paper from a technical perspective".

[0087] By combining textual intent and generation constraint information, core element information is extracted from the dimensional details, while secondary information is ignored. Then, according to the rules of natural language generation, the extracted core element information is reconstructed to obtain the attribute summary information of the preset dimensions.

[0088] In this embodiment, based on the semantic understanding, information compression, and text generation capabilities learned by the large language model during the pre-training stage, and combined with the input prompt text, the core element information in the dimension details is quickly extracted, and the core element information is reconstructed to obtain attribute summary information, thereby effectively improving the efficiency and accuracy of attribute summarization.

[0089] One possible implementation involves extracting features from the dimension details to obtain semantic features; extracting core element features from the semantic features based on the recognition results, where the core element features are the semantic features of the core element information in the dimension details; and then using an autoregressive approach to generate attribute summary information for a preset dimension based on the core element features.

[0090] Specifically, the dimensional details are first segmented into a sequence of terms that the model can recognize, and then each term is converted into a corresponding vector representation. Multi-layer self-attention computation is performed on the obtained vector representations to obtain the semantic features of the details. Core element features are extracted from the semantic features of the details, including: core themes, key arguments, and core data.

[0091] An autoregressive approach is used for multi-round text prediction based on core feature elements. In the initial text prediction, a first output word is generated based on the core feature elements. This first output word is then appended to the input sequence, and a second round of text prediction is performed based on the input sequence to obtain a second output word. Next, the second output word is appended to the input sequence, and a third round of text prediction is performed based on the input sequence to obtain a third output word, and so on, until a prediction termination condition is met, thus obtaining attribute summary information of a preset dimension. The prediction termination condition in this embodiment includes at least one of the following conditions: (1) When the length of the predicted output word sequence reaches its upper limit, the iterative prediction stops.

[0092] (2) Stop iterative prediction when the terminator is obtained by decoding or prediction.

[0093] In this embodiment, the autoregressive word-by-word prediction mechanism is based on the continuous derivation of the generated content and the semantic vector of the original text. In this way, the generated attribute summary information is not a simple sentence splicing, but a text with a complete grammatical structure and logical chain, thereby improving the accuracy of the attribute summary.

[0094] One possible implementation is that when the content of the dimension details associated with the preset dimension is too large, even exceeding the processing capacity of a large language model in a single run, the reasoning process of the preset dimension needs to be broken down into multiple reasoning steps. That is, the reasoning can be carried out step by step using the block aggregation (MapReduce) method to obtain the dimension summary information of the preset dimension.

[0095] Specifically, for each preset dimension, the dimension details associated with that preset dimension are obtained from the attribute details. When the data volume of the dimension details exceeds a preset threshold, the dimension details are split into multiple data blocks. Then, information is summarized for each data block to obtain corresponding sub-summary content. Finally, the obtained multiple sub-summary contents are merged to obtain the attribute summary information of the preset dimension.

[0096] Specifically, the preset threshold can be the upper limit of the amount of data that a large language model can process in a single run, or it can be other thresholds; this application does not impose any specific limitations on this. In practical applications, the dimension details can be split into multiple data blocks according to data type, or according to collection time.

[0097] For each data block, a prompt text is generated according to the prompt content template and the data block. This prompt text indicates that the information of the data block should be summarized. Then, the prompt text is used as a prompt instruction to be input into the large language model for reasoning to obtain the corresponding sub-summary content. Then, the large language model merges and reasons the obtained multiple sub-summary contents to obtain the dimension summary information of the preset dimension.

[0098] For example, when the electronic resource is a product called "mobile phone", a scheduled task will trigger a query to retrieve the attribute details of the electronic resource; the attribute details include: feature description data, comment data, and news data.

[0099] The preset dimensions include: battery life, screen experience, and gaming performance.

[0100] The details for the battery life dimension include: feature introduction data, review data, and news data; the details for the screen experience dimension include: review data and news data; and the details for the game performance dimension include: feature introduction data.

[0101] Regarding battery life, see [link / reference]. Figure 6 Based on the preset prompt content template, and using the function introduction data, comment data, and news data, the system generates prompt text; prompt text 601 includes the following content: "Now I'm providing you with information on the phone's features, reviews, and news. Based on this information, summarize the phone's battery life in one sentence, keeping the summary to 20 Chinese characters or less."

[0102] Using the prompt text as the instruction, the large language model is input for inference to obtain attribute summary information for the battery life dimension. The attribute summary information includes the following: Battery life: One charge lasts 1-2 days, but battery life decreases significantly in low temperatures. The same method can be used to obtain summary information on the attributes of both the screen experience dimension and the game performance dimension, which will not be elaborated here. For example, see Figure 7A When the electronic resource is a stock of Company A, a scheduled task will trigger to query the attribute details of the electronic resource. The attribute details include: company information, company risk items, company financial data, market data, institutional rating data, institutional research report data, recent news data, individual stock technical indicators, and matching popular industries.

[0103] Specifically, company information is stored in a database, which can be accessed and queried directly.

[0104] The risks include: fundamental risks and technical risks. Fundamental risks are obtained through the exchange, while technical risks are calculated daily.

[0105] Market data includes real-time and historical market data. Real-time market data is obtained directly from the exchange's market data service and stored in a cache. After the market closes, the cached real-time market data is persistently stored in the database to form historical data. When summarizing information, real-time market data is read from the cache, and historical market data is read from the database.

[0106] Recent news data includes: individual stock news from the last 14 days. After deduplication by title, the news is sorted in reverse chronological order by publication time, and the top 20 news items are selected.

[0107] Individual stock technical indicators include: KDJ, MACD, and K-line moving averages, all of which require historical market data for calculation.

[0108] The following method is used to obtain matching popular industries: sort all sectors by price change, and select the top ten sectors with the largest price increase as popular sectors; then match the target with the corresponding industry and concept sectors, and if a match can be found, it is considered a popular industry.

[0109] The preset dimensions include: core positioning dimension, company quality dimension, company valuation dimension, and transaction timing dimension.

[0110] During the model inference stage, to avoid errors in the generated content due to inaccurate or delayed company information, this application combines company information and company financial data to generate attribute summary information for the core positioning dimension. That is, the dimension details associated with the core positioning dimension include: company information and company financial data.

[0111] See Figure 7B Based on a preset prompt template and company information and financial data, a prompt text is generated. The prompt text includes the following: "As a fundamental stock analyst, I am now providing you with company information and financial data for Company A. Based on this information, summarize the core positioning of this company in one sentence, within 20 Chinese characters."

[0112] Using the prompt text as the instruction, the large language model is input for inference to obtain attribute summary information for the core localization dimensions. The attribute summary information includes the following: "Core positioning: digital ecosystem giant, attractive valuation but requires liquidity support."

[0113] Regarding the company's quality dimension, the related dimension details include: company information, company risk items, and company financial data.

[0114] See Figure 7C Based on a preset prompt template, and using company information, company risk items, and company financial data, a prompt text is generated. The prompt text includes the following: "As a stock and financial media analyst, you are now provided with company information, risk items, and financial data for Company A. Based on this information, summarize the company's fundamentals in one sentence, and explain the company's core business direction and revenue generation capabilities. The summary should be accurate, concise, and within 30 Chinese characters."

[0115] Using the prompt text as the prompt instruction, the large language model is input for inference to obtain attribute summary information for the company's quality dimension. The attribute summary information includes the following: "Quality: Possesses a core social ecosystem and has a deep moat."

[0116] Regarding company valuation, the relevant details include: market data and institutional rating data. See also... Figure 7D Based on market data and institutional rating data, a pre-defined prompt template is generated to display prompt text. The prompt text includes the following: "As a financial analyst, you are now provided with market data and institutional ratings for Company A. Based on this information, infer the company's current valuation level."

[0117] Using the prompt text as the prompt instruction, the large language model is input for reasoning to obtain attribute summary information for the company valuation dimension. The attribute summary information includes the following: Valuation: Significantly lower than international internet giants and similar companies in the A-share market, with a high margin of safety.

[0118] Regarding the timing of trades, the relevant details include: institutional research reports, recent news data, individual stock technical indicators, and matching popular industries.

[0119] Because the content of the dimension details is too large to be processed by the model in a single step, a block aggregation approach is adopted for step-by-step reasoning, as follows: Figure 8 As shown: The algorithm iterates through recent news data to extract company events, then aggregates the extracted events, and finally uses a large language model to summarize the extracted events to obtain the first result.

[0120] The algorithm iteratively extracts institutional viewpoints from institutional research reports, then summarizes the extracted viewpoints, and finally uses a large language model to summarize the extracted viewpoints to obtain a second result.

[0121] By combining and reasoning the first result, second result, individual stock technical indicators, and matching popular industries using a large language model, we can obtain attribute summary information for the trading timing dimension.

[0122] In this embodiment, by calling a large language model, the content of the dimension details of each preset dimension is summarized, effectively extracting key information from the dimension details, filtering redundant details, and obtaining dimension summary information, thereby improving the accuracy and efficiency of information summarization.

[0123] One possible implementation is to display, in addition to showing the attribute summary information of electronic resources under each preset dimension, the recommendation level and reasons for the recommendation of electronic resources, which are obtained based on the weight of each preset dimension and the attribute summary information under each preset dimension.

[0124] Specifically, the weight of each preset dimension is set by the target object according to actual needs, and the weights of each preset dimension can be modified. The weights of each preset dimension will affect the recommendation level and reasons for the final electronic resources.

[0125] For example, considering the three dimensions of company quality, company valuation, and trading timing, if trading timing is given the highest weight, then the quick score emphasizes the timeliness and importance of short-term catalysts. When comparing quick scores of multiple stocks, under the same conditions, quick scores with clearer recent event catalysts (i.e., recommendation levels) have higher scores.

[0126] If the company quality dimension is given the highest weight, then under the same conditions, companies with stronger fundamental information and higher profits will have a higher quick score (i.e., a higher recommendation level).

[0127] After obtaining the attribute summary information for each preset dimension, a prompt text is constructed based on the attribute summary information and corresponding weights for each preset dimension. This prompt text indicates that, in combination with the attribute summary information and weights for each preset dimension, the recommendation level and reasons for the electronic resource are given.

[0128] Next, the prompt text is used as a prompt instruction and input into the large language model for reasoning to obtain the recommendation level and reasons for the electronic resources.

[0129] It should be noted that after obtaining the attribute summary information for each preset dimension, a portion of the attribute summary information and corresponding weights for each preset dimension can be selected from the attribute summary information for each preset dimension to generate the recommendation level of the electronic resources. This application does not make specific limitations on this.

[0130] For example, see Figure 9AThe weighting of battery life (50%), screen experience (30%), and gaming performance (20%) is set. Based on the attribute summary information and weights of each of the three dimensions (battery life, screen experience, and gaming performance), a prompt text is generated. The prompt text includes the following: "Based on the following information, rate this phone in terms of battery life, screen experience, and gaming performance, and explain your reasoning. Specific requirements are as follows:" 1. Out of 100 points, battery life is 50%, screen experience is 30%, and gaming performance is 20%; 2. The evaluation criteria must include assessments of the phone's battery life and screen experience; 3. The conclusion should not exceed 100 words. Using the prompt text as the prompt instruction, the large language model is input for reasoning to obtain the mobile phone's transaction quick score (i.e., recommendation level) and the corresponding score reasons, as follows: "Transaction speed rating: 75 / 100; Reason for rating: Strong battery life, clear video playback.

[0131] For example, see Figure 9B The weighting of the company quality dimension is set at 30%, the weighting of the company valuation dimension is 30%, and the weighting of the transaction timing dimension is 40%.

[0132] Based on the attribute summary information and weights of the company quality dimension, company valuation dimension, and transaction timing dimension, a prompt text is generated; the prompt text includes the following: "Based on the information provided below, rate Company A based on its quality, valuation, and timing, and explain your reasoning. Specific requirements are as follows:" 1. The maximum score is 100 points, with quality accounting for 30%, valuation for 30%, and timing for 30%. 2. The evaluation criteria must include a fundamental assessment of the company; 3. The scoring criteria must include the company's valuation level; 4. The conclusion should not exceed 100 words. Using the prompt text as the prompt instruction, the large language model is input for reasoning to obtain a quick stock trading score and the corresponding scoring reason, as detailed below: "Transaction speed rating: 79 / 100; Reason for rating: "Deep ecological moat, attractive valuation."

[0133] In this embodiment, the weights of each preset dimension and the attribute summary information under each preset dimension are merged and summarized to obtain the recommendation level of the electronic resources and display them, so that the target audience can understand the electronic resources more intuitively, thereby improving the user experience.

[0134] It should be noted that, in addition to displaying the attribute summary information of electronic resources under each preset dimension and the recommendation level of electronic resources on the attribute summary page, other information such as the latest status information of electronic resources can also be displayed. This application does not make specific limitations on this.

[0135] One possible implementation involves displaying the attribute summary page as a floating card in the resource details page in response to a triggered operation on the attribute summary component.

[0136] Specifically, after the target object clicks on the attribute summary component displayed on the resource details page, the resource details page continues to be displayed; at the same time, an attribute summary page in the form of a card is displayed floating above the resource details page. The page size of the attribute summary page is smaller than that of the resource details page. In addition, the attribute summary page is a non-transparent page, so the attribute summary page will obscure part of the content of the resource details page.

[0137] In the embodiments of this application, when displaying the attribute summary page on the resource details page, the attribute summary page may be fixed or may move on the resource details page according to a preset trajectory. This application does not make specific limitations on this.

[0138] For example, see Figure 10A The shopping app's homepage displays multiple product links: mobile phone link, short-sleeved shirt link, high heel link, and sneaker link.

[0139] After the target user clicks the mobile phone link, the shopping application switches from the homepage 1001 to the product details page 1002. The product details page 1002 includes: an AI quick review button 1003 and mobile phone status description information, including: image, name, price, sales volume, etc.

[0140] After the target user clicks the AI ​​Quick Review button 1003, the AI ​​Quick Review Card 1004 (i.e., an attribute summary page displayed in a floating card format) is displayed on the product details page 1002. The AI ​​Quick Review Card 1004 includes the following content: "XX mobile phone, 3299 yuan;" Battery life: One charge lasts for 1-2 days, but battery life decreases significantly in low temperatures; Screen experience: 2K resolution, videos are clear and pixel-free, but there is severe glare under strong light; Game performance: Fast loading speed, the device gets hot after playing continuously for more than 1 hour; Transaction speed rating: 75 / 100; Reason for rating: Strong battery life, clear video playback.

[0141] For example, see Figure 10B On the stock selection page of the financial application, 1005 displays multiple stock links, namely: stock links for Company A, Company B, and Company C.

[0142] After the target user clicks on the stock link of Company A, the financial application switches from the stock selection page 1005 to the stock details page 1006. The stock details page 1006 includes: the AI ​​quick review button 1007 and the stock status description information, which includes: real-time market data, real-time trading volume, real-time trading amount, etc.

[0143] After the target clicks the AI ​​Quick Review button 1007, the AI ​​Quick Review card 1008 is displayed on the stock details page 1006. The AI ​​Quick Review card 1008 includes the following content: Company A (123456) Real-time stock price: 345 yuan; Updated on: XX year - XX month - XX day; Core positioning: Digital ecosystem giant, attractive valuation but requires liquidity support; Quality: Possesses a core social ecosystem with a deep moat; Valuation: Significantly lower than international internet giants and similar companies listed on the A-share market, indicating a high margin of safety; Timing: The stock price rebounded and is now fluctuating around the key level of the annual moving average. Transaction speed rating: 79 / 100; Reason for rating: "Deep ecological moat, attractive valuation."

[0144] In this embodiment, in response to a trigger operation on the attribute summary component, the attribute summary page is displayed in a floating card format on the resource details page. This process omits the operation of searching and summarizing a large amount of relevant information in the search application, which greatly simplifies the operation process and improves the efficiency of information summarization.

[0145] One possible implementation involves switching from the resource details page to the attribute summary page in response to a trigger operation on the attribute summary component, displaying attribute summary information for each preset dimension on the attribute summary page; in some cases, the recommendation level and reasons for the electronic resource can also be displayed on the attribute summary page.

[0146] For example, see Figure 11AThe shopping app displays a product details page 1002, which includes an AI quick review button 1003 and a status description of the phone, including its image, name, price, and sales volume. When the target user clicks the AI ​​quick review button 1003, the app switches from the product details page 1002 to the phone's attribute summary page 1101. The attribute summary page 1101 includes the following content: "XX mobile phone, 3299 yuan;" Battery life: One charge lasts for 1-2 days, but battery life decreases significantly in low temperatures; Screen experience: 2K resolution, videos are clear and pixel-free, but there is severe glare under strong light; Game performance: Fast loading speed, the device gets hot after playing continuously for more than 1 hour; Transaction speed rating: 75 / 100; Reason for rating: Strong battery life, clear video playback.

[0147] For example, see Figure 11B The financial application showcases Company A's stock details page 1006. Page 1006 includes an AI Quick Comment button 1007 and stock status description information, including real-time market data, real-time trading volume, and real-time trading value. After the target audience clicks the AI ​​Quick Comment button 1007, they are redirected from stock details page 1006 to the stock's attribute summary page 1102. Attribute summary page 1102 includes the following: Company A (123456) Real-time stock price: 345 yuan; Updated on: XX year - XX month - XX day; Core positioning: Digital ecosystem giant, attractive valuation but requires liquidity support; Quality: Possesses a core social ecosystem with a deep moat; Valuation: Significantly lower than international internet giants and similar companies listed on the A-share market, indicating a high margin of safety; Timing: The stock price rebounded and is now fluctuating around the key level of the annual moving average. Transaction speed rating: 79 / 100; Reason for rating: "Deep ecological moat, attractive valuation."

[0148] In one possible implementation, the terminal device displays the attribute summary page by interacting with the server as follows (see [link]). Figure 12 This includes the following steps: Step 1201: In response to the trigger operation for the attribute summary component, the terminal device sends an attribute summary request to the server.

[0149] Specifically, the terminal device sends an attribute summary request to the server via an HTTP interface, and the attribute summary request carries the resource identifier of the electronic resource.

[0150] Step 1202: The server obtains attribute summary information for each preset dimension that matches the resource identifier.

[0151] Specifically, the server generates attribute summary information of electronic resources under each preset dimension offline and saves the obtained attribute summary information under each preset dimension in the database; the specific process of obtaining attribute summary information has been introduced above and will not be repeated here.

[0152] In this way, after receiving the attribute summary request, the server directly queries the database based on the resource identifier carried in the attribute request to obtain the attribute summary information of the electronic resource under each preset dimension.

[0153] If the server generates the recommendation level and reasons for the electronic resources offline and also stores the recommendation level and reasons for the electronic resources in the database, then when the server receives an attribute summary request, it will not only retrieve the attribute summary information of the electronic resources under each preset dimension from the database, but also retrieve the recommendation level and reasons for the electronic resources.

[0154] Step 1203: The terminal device receives the attribute summary information for each preset dimension returned by the server.

[0155] Step 1204: The terminal device renders the attribute summary information under each preset dimension, obtains the attribute summary page, and displays the attribute summary page.

[0156] In practice, if the terminal device receives not only the attribute summary information under each preset dimension returned by the server, but also the recommendation level and reasons for the electronic resources, then the attribute summary information under each preset dimension, the recommendation level and reasons for the electronic resources are rendered to obtain and display the attribute summary page.

[0157] For example, see Figure 13 The terminal device displays Company A's stock details page, which includes an AI Quick Comment button and a stock status description. After the target user clicks the AI ​​Quick Comment button, the terminal device sends an attribute summary request to the server.

[0158] The server queries real-time stock quotes and AI quick rating cards, which include: core positioning, company quality, company valuation, trading timing, and recommendation score. The server then returns the real-time quotes and AI quick rating cards to the terminal device.

[0159] The terminal device renders the AI ​​quick-review card based on real-time market data and AI quick-review card content, and then displays the AI ​​quick-review card. By building a technical application process of data query - model content reasoning - front-end and back-end interactive display, it solves the challenges of rapid cognition and dynamic comparison faced by information overload when understanding a stock.

[0160] In this embodiment, the server pre-generates and stores attribute summary information of electronic resources in each preset dimension offline. In this way, when the target object triggers the attribute summary, the attribute summary information of electronic resources in each preset dimension can be quickly obtained and rendered, thereby improving the display efficiency of attribute summary information.

[0161] One possible implementation involves switching from a resource preview page to a resource details page of an electronic resource in response to a triggered operation for a resource link to that electronic resource.

[0162] Specifically, the resource details page includes: attribute summary information of electronic resources under various preset dimensions; the attribute summary information under various preset dimensions can be displayed as cards floating on the resource details page, or it can be displayed directly within the resource details page.

[0163] In addition to displaying a summary of the attributes of electronic resources across various preset dimensions, the resource details page can also display the recommendation level, reasons for recommendation, and description of the resource status.

[0164] For example, see Figure 14 On the stock selection page of the financial application, 1005 displays multiple stock links, namely: stock links for Company A, Company B, and Company C.

[0165] After the target user clicks on the stock link of Company B, the financial application switches from the stock selection page 1005 to the stock details page 1401 of Company B. The stock details page 1401 includes: AI Quick Assessment Card 1402 and stock status description information, including: real-time market data, real-time trading volume, and real-time trading value. AI Quick Assessment Card 1402 includes the following: Company B (2345678); Real-time stock price: 376 yuan; Updated on: XX year - XX month - XX day; Core positioning: A global leader in power battery technology; Material quality: The long-term focus lies in next-generation technology; Valuation: Lower than that of major global battery companies, reflecting concerns about market competition; Timing: Recent trend: The trend has been relatively flat; Transaction speed rating: 70 / 100; Reason for rating: Strong technological moat and reasonable valuation.

[0166] In this embodiment of the application, when the resource link of the electronic resource is triggered, the attribute summary information under each preset dimension is directly displayed on the resource details page of the electronic resource. This allows the target object to understand the characteristics of the electronic resource more directly, thereby improving the user experience.

[0167] In some embodiments, in response to a conversion initiation operation triggered for an electronic resource, a conversion confirmation page for the electronic resource is displayed; the conversion confirmation page includes: the resource conversion amount of the electronic resource; in response to a conversion confirmation operation triggered on the conversion confirmation page, a conversion result page for the electronic resource is displayed; the conversion result page includes: the resource conversion certificate of the electronic resource.

[0168] Specifically, in response to a conversion initiation action triggered on the resource details page or attribute summary page, a conversion confirmation page for the electronic resource is displayed; the conversion initiation action can be clicking an initiation button or a predefined gesture.

[0169] For resource details pages or attribute summary pages, after the target audience triggers the conversion initiation operation, the page switches from the resource request page to the conversion confirmation page. The target audience can enter the resource conversion amount on the conversion confirmation page. In addition, the conversion confirmation page can also display at least one payment method. Accordingly, the target audience can select a payment method on the conversion confirmation page and then trigger the conversion confirmation operation. After the payment is completed, the conversion result page of the electronic resource is displayed. The conversion result page includes: the resource conversion voucher of the electronic resource.

[0170] For example, see Figure 15A AI Quick Review Card 1501 includes the following: Company A (123456) Real-time stock price: 345 yuan; Updated on: XX year - XX month - XX day; Core positioning: Digital ecosystem giant, attractive valuation but requires liquidity support; Quality: Possesses a core social ecosystem with a deep moat; Valuation: Significantly lower than international internet giants and similar companies listed on the A-share market, indicating a high margin of safety; Timing: The stock price rebounded and is now fluctuating around the key level of the annual moving average. Transaction speed rating: 79 / 100; Reason for rating: "Deep ecological moat, attractive valuation."

[0171] In addition, the AI ​​Quick Review Card 1501 also includes a buy button and a sell button; in response to the click operation of the buy button, the buy confirmation page 1502 is displayed, which includes: a buy quantity input box, a confirm button, payment method one and payment method two; after the target enters the buy quantity "123" and selects payment method two, the target clicks the confirm button.

[0172] In response to the confirmation button, the transaction results page 1503 is displayed. The transaction results page 1503 includes: a purchase success notification message, order number, date, and other information.

[0173] For example, see Figure 15B AI Quick Review Card 1504 includes the following: "XX mobile phone, 3299 yuan;" Battery life: One charge lasts for 1-2 days, but battery life decreases significantly in low temperatures; Screen experience: 2K resolution, videos are clear and pixel-free, but there is severe glare under strong light; Game performance: Fast loading speed, the device gets hot after playing continuously for more than 1 hour; Transaction speed rating: 75 / 100; Reason for rating: Strong battery life, clear video playback.

[0174] In addition, the AI ​​Quick Review Card 1504 also includes a purchase button; in response to the click operation of the purchase button, the purchase confirmation page 1505 is displayed, which includes: purchase quantity (default is 1), price, confirmation button, payment method one and payment method two; after the target object selects payment method two, click the confirmation button.

[0175] In response to a confirmation button press, the purchase results page 1506 is displayed. The purchase results page 1506 includes a payment success message and the estimated arrival time of the goods.

[0176] In this embodiment, the attribute summary page not only displays the attribute summary information of electronic resources under various preset dimensions, but also supports resource conversion. In this way, after the target object understands the relevant characteristics of electronic resources from the attribute summary page, it can quickly trigger resource conversion, thereby improving the efficiency of resource conversion.

[0177] One possible implementation involves redirecting from the attribute summary page to a target sharing page in response to a sharing operation triggered on the attribute summary page; the target sharing page includes attribute summary information for each preset dimension.

[0178] Specifically, the sharing action can be clicking a share button or using a predefined gesture. The target sharing page can be a page from another application; for example, the chat page of an instant messaging application, or the playback page of a video application. In addition to attribute summary information under each preset dimension, the shared content can also display the recommendation level of the electronic resource, its latest status information, etc. The shared content can be displayed on the target sharing page in the form of plain text links or cards.

[0179] For example, see Figure 16A The AI ​​quick review card 1501 includes a share button 1601. In response to a trigger action on the share button 1601, the user is redirected to the chat page 1602 of the instant messaging application, where the content of the AI ​​quick review card is displayed.

[0180] For example, see Figure 16B The AI ​​Quick Review Card 1504 includes a share button 1603. In response to a trigger action on the share button 1603, the user is redirected to the Moments page 1604 of the instant messaging application, where the content of the AI ​​Quick Review Card is displayed.

[0181] In this embodiment, attribute summary information is shared with other objects through a sharing operation, so that the attribute summary information not only has reading attributes, but also specifically transforms and shares social attributes, making it widely applicable.

[0182] One possible implementation involves switching from the attribute summary page to the intelligent question-and-answer page in response to a trigger operation on the question-and-answer component. The intelligent question-and-answer page includes an input operation area and a history dialogue area, where the history dialogue area includes attribute summary information for each preset dimension.

[0183] In response to a question triggered in the input area, the corresponding reply text is displayed in the history dialogue area; the reply text is generated based on the question text associated with the question and attribute summary information under each preset dimension.

[0184] Specifically, in response to a query triggered in the input area, the terminal device sends a query request to the server. The server, using a large language model, generates a response text based on the query text and attribute summary information under various preset dimensions. The response text is then sent to the terminal device. The terminal device displays the response text in the history dialog box area.

[0185] When the attribute summary page also includes the recommendation level of electronic resources, this recommendation level is also displayed in the history dialogue area of ​​the intelligent Q&A page. Correspondingly, in response to a question triggered in the input area, a question request is sent to the server. The server, using a large language model, generates a response text based on the question text, attribute summary information under each preset dimension, and the recommendation level of the electronic resources. The response text is then sent to the terminal device. The terminal device displays the response text in the history dialog area.

[0186] Of course, in this embodiment, the history dialogue area of ​​the intelligent Q&A page can also be blank after the intelligent Q&A page is invoked. In response to a question action triggered in the input area, the corresponding reply text is displayed in the history dialogue area; the reply text is generated based on the question text associated with the question action.

[0187] For example, see Figure 17A The AI ​​Quick Review Card 1501 includes: an "Ask AI" button 1701. In response to a trigger on the "Ask AI" button 1701, the user is redirected to the intelligent Q&A page 1702; the intelligent Q&A page 1702 includes: an input area 1703 and a history dialogue area 1704; the history dialogue area 1704 includes the following: Company A (123456) Real-time stock price: 345 yuan; Updated on: XX year - XX month - XX day; Quality: Possesses a core social ecosystem with a deep moat; Valuation: Significantly lower than international internet giants and similar companies listed on the A-share market, indicating a high margin of safety; Timing: The stock price rebounded and is now fluctuating around the key level of the annual moving average.

[0188] The target user enters the query text "Analyze the historical percentile of Company A" in input operation area 1703, and then submits the query text.

[0189] Accordingly, the reply text “at the 40th percentile in the past three years” is displayed in the history dialogue area 1704 of the intelligent Q&A page 1702.

[0190] See Figure 17B The AI ​​Quick Review Card 1504 includes: an AI Ask button 1705. In response to a trigger on the AI ​​Ask button 1705, the user is redirected to the intelligent Q&A page 1706; the intelligent Q&A page 1706 includes: an input area 1707 and a history dialogue area 1708; the history dialogue area 1708 is blank.

[0191] The target user enters the question text "Is the mobile phone suitable for daily commuting" in the input operation area 1707, and then submits the question text.

[0192] Correspondingly, the reply text “Strong battery life, no need for frequent charging, very worry-free, suitable for daily commutes” is displayed in the history dialogue area 1708 of the intelligent Q&A page 1706.

[0193] In this embodiment of the application, the attribute summary page supports launching the intelligent Q&A page. In this way, the target object can ask further questions about the electronic resources on the intelligent Q&A page to learn more about the electronic resources, thereby improving the user experience.

[0194] To better explain the embodiments of this application, the following describes an information display method provided by the embodiments of this application in conjunction with a specific implementation scenario. The process of this method can be as follows: Figure 1 The terminal device 101 shown can execute the command, or it can be executed by the server 102, or it can be executed interactively by the terminal device 101 and the server 102. The command includes the following steps: Figure 17C As shown: Server 102 initiates the processing logic for generating attribute summary information through a scheduled task. Specifically, it generates attribute summary information for each company offline using a large language model, covering dimensions such as core positioning, company quality, company valuation, transaction timing, transaction speed score, and score reasons. The attribute summary information for each dimension is then stored in the database. The specific process of obtaining attribute summary information has been described earlier and will not be repeated here.

[0195] In response to a triggered operation in a financial application, terminal device 101 displays the stock details page of Company A, which includes an AI quick review button and a status description of the stock. After the target user clicks the AI ​​quick review button, the terminal device sends an attribute summary request to server 102.

[0196] Server 102 queries real-time stock quotes and AI quick rating card content. The AI ​​quick rating card content includes: core positioning, company quality, company valuation, trading timing, quick rating score, and rating reason. Server 102 returns the real-time quotes and AI quick rating card content to terminal device 101.

[0197] Terminal device 101 renders the AI ​​Quick Comment Card based on real-time market data and its content, then displays the AI ​​Quick Comment Card on the stock details page. The AI ​​Quick Comment Card includes: an "Ask AI" button, a "Share" button, a "Buy" button, and a "Sell" button. Clicking the "Ask AI" button redirects to the intelligent Q&A page to ask further questions. Clicking the "Share" button allows users to share the AI ​​Quick Comment Card with other users; clicking the "Buy" and "Sell" buttons enables stock trading.

[0198] By establishing a technical application process of data query - model content reasoning - front-end and back-end interactive display, the challenges of rapid cognition and dynamic comparison faced by information overload when understanding a stock are solved.

[0199] Based on the same technical concept, this application provides a structural schematic diagram of an information display device, such as... Figure 18 As shown, the information display device 1800 includes: Display module 1801 is used to present a resource preview page, which contains resource links for each of the multiple electronic resources; The display module 1801 is further configured to, in response to a trigger operation for a resource link of one of the plurality of electronic resources, switch from the resource preview page to the resource details page of the electronic resource, wherein the resource details page includes: resource status description information and attribute summary component of the electronic resource; and, in response to a trigger operation for the attribute summary component, display the attribute summary page, wherein the attribute summary page includes: attribute summary information of the electronic resource under various preset dimensions, wherein the attribute summary information under various preset dimensions is generated based on the attribute details content associated with the resource link.

[0200] Optionally, the display module 1801 is specifically used for: In response to a triggered operation on the attribute summary component, the attribute summary page is displayed as a floating card on the resource details page.

[0201] Optionally, the display module 1801 is further configured to: In response to a conversion initiation operation triggered on the resource details page or the attribute summary page, a conversion confirmation page for the electronic resource is displayed; the conversion confirmation page includes: the resource conversion amount of the electronic resource; In response to a conversion confirmation operation triggered on the conversion confirmation page, a conversion result page for the electronic resource is displayed; the conversion result page includes: the resource conversion certificate for the electronic resource.

[0202] Optionally, the display module 1801 is further configured to: In response to a trigger operation on the attribute summary component, after displaying the attribute summary page, In response to a sharing operation triggered on the attribute summary page, the user is redirected from the attribute summary page to a target sharing page; the target sharing page includes attribute summary information under each preset dimension.

[0203] Optionally, the attribute summary page includes a question-and-answer component; The display module 1801 is also used for: In response to a trigger operation on the attribute summary component, after displaying the attribute summary page, in response to a trigger operation on the question-and-answer component, the page switches from the attribute summary page to the intelligent question-and-answer page; the intelligent question-and-answer page includes: an input operation area and a history dialogue area, the history dialogue area including: attribute summary information under each preset dimension; In response to a question action triggered in the input operation area, a corresponding reply text is displayed in the history dialogue area; the reply text is generated based on the question text associated with the question action and the attribute summary information under each preset dimension.

[0204] Optionally, the attribute summary page may further include: the recommendation level and the reason for recommendation of an electronic resource, wherein the recommendation level and the reason for recommendation are obtained based on the weights of each preset dimension and the attribute summary information under each preset dimension.

[0205] Optionally, the display module 1801 is specifically used for: In response to a trigger operation on the attribute summary component, an attribute summary request is sent to the server. The attribute summary request carries the resource identifier of the electronic resource, so that the server can obtain attribute summary information under each preset dimension that matches the resource identifier. Receive the attribute summary information under each preset dimension returned by the server; The attribute summary information under each preset dimension is rendered to obtain the attribute summary page, and the attribute summary page is displayed.

[0206] Optionally, it also includes a processing module 1802; The processing module 1802 is specifically used for: For each preset dimension, obtain the dimension details associated with the preset dimension from the attribute details content; Based on the dimension details associated with the preset dimension, a prompt text is generated, indicating that a summary of the dimension details associated with the preset dimension should be performed. Using the prompt text as a prompt instruction, input it into the large language model for reasoning to obtain the attribute summary information of the preset dimension.

[0207] Optionally, the processing module 1802 is specifically used for: Using the large language model, perform the following steps: Based on the contextual information contained in the prompt text, text intent recognition is performed on the prompt text to obtain a recognition result; the recognition result indicates that a content summary of the dimension details associated with the preset dimension is performed. Based on the recognition results, core element information is extracted from the dimension details and reconstructed to obtain the attribute summary information of the preset dimension.

[0208] Optionally, the processing module 1802 is specifically used for: Feature extraction is performed on the details of the aforementioned dimensions to obtain semantic features of the details; Based on the recognition results, core element features are extracted from the semantic features of the details, where the core element features are the semantic features of the core element information in the dimension details content. An autoregressive approach is used to generate attribute summary information for the preset dimensions based on the core element features.

[0209] Optionally, the processing module 1802 is further configured to: For each preset dimension, obtain the dimension details associated with the preset dimension from the attribute details content; When the amount of data in the dimension details exceeds a preset threshold, the dimension details will be split into multiple data blocks. Summarize the information for each data block to obtain corresponding sub-summary content; The obtained sub-summaries are merged to obtain the attribute summary information of the preset dimension.

[0210] In this embodiment of the application, when the resource link of the electronic resource is triggered, the attribute summary information of the electronic resource under each preset dimension is displayed. This process omits the operation of switching from the resource application to the search application, and then searching for and summarizing a large amount of relevant information in the search application. This greatly simplifies the operation process and improves the efficiency of information summarization.

[0211] Secondly, attribute summary information under each preset dimension is generated based on the attribute details associated with resource links, eliminating the need for manual searching of large amounts of information for summarization, thereby effectively improving the accuracy of information summarization.

[0212] In addition, integrating information summarization into resource applications eliminates the need to run resource and search applications simultaneously on smart devices, thereby reducing the workload on smart devices and improving their overall efficiency.

[0213] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0214] Based on the same technical concept, embodiments of this application provide a computer device, which can be... Figure 1 The terminal devices and / or servers shown, such as Figure 19 As shown, it includes at least one processor 1901 and a memory 1902 connected to at least one processor. In this embodiment, the specific connection medium between the processor 1901 and the memory 1902 is not limited. Figure 19 Taking the connection between processor 1901 and memory 1902 via a bus as an example, the bus can be divided into address bus, data bus, control bus, etc.

[0215] In this embodiment of the application, the memory 1902 stores instructions that can be executed by at least one processor 1901. By executing the instructions stored in the memory 1902, at least one processor 1901 can perform the steps of the above-described information display method.

[0216] The processor 1901 is the control center of the computer device. It can connect to various parts of the computer device through various interfaces and lines, and summarizes information by running or executing instructions stored in the memory 1902 and calling data stored in the memory 1902. Optionally, the processor 1901 may include one or more processing units. The processor 1901 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 1901. In one possible implementation, the processor 1901 and the memory 1902 can be implemented on the same chip; in another possible implementation, they can be implemented on separate chips.

[0217] Processor 1901 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0218] Memory 1902, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 1902 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. Memory 1902 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer device, but is not limited thereto. In the embodiments of this application, memory 1902 can also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0219] In another embodiment, the computer device may also be a terminal device. In this embodiment, the structure of the computer device may be as follows: Figure 20 As shown, it includes components such as: communication component 2010, memory 2020, display unit 2030, camera 2040, sensor 2050, audio circuit 2060, Bluetooth module 2070, and processor 2080.

[0220] The communication component 2010 is used to communicate with the server. In some embodiments, it may include a Circuit-Wireless Fidelity (WiFi) module, which is a short-range wireless transmission technology. Computer devices can use the WiFi module to help users send and receive information.

[0221] The memory 2020 can be used to store software programs and data. The processor 2080 executes various functions of the terminal device and data processing by running the software programs or data stored in the memory 2020. The memory 2020 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. The memory 2020 stores an operating system that enables the terminal device to run. In this application, the memory 2020 may store the operating system and various applications, and may also store code that executes the information display method of the embodiments of this application.

[0222] The display unit 2030 can also be used to display information input by the user or information provided to the user, as well as various menus of the terminal device, forming a graphical user interface (GUI). Specifically, the display unit 2030 may include a display screen 2032 disposed on the front of the terminal device. The display screen 2032 may be configured as a liquid crystal display, a light-emitting diode, or the like. The display unit 2030 can be used to display various search result pages or sub-result pages in the embodiments of this application.

[0223] The display unit 2030 can also be used to receive input digital or character information and generate signal inputs related to user settings and function control of the terminal device. Specifically, the display unit 2030 may include a touch screen 2031 disposed on the front of the terminal device, which can collect touch operations of the user on or near it, such as clicking buttons, dragging scroll boxes, etc.

[0224] The touchscreen 2031 can be placed on top of the display screen 2032, or the touchscreen 2031 and the display screen 2032 can be integrated to realize the input and output functions of the terminal device. After integration, it can be referred to as a touch display screen. In this application, the display unit 2030 can display the application and the corresponding operation steps.

[0225] Camera 2040 can be used to capture still images, which users can then post comments on via the application. There can be one or multiple cameras 2040. An object is projected onto a photosensitive element through a lens, generating an optical image. This photosensitive element can be a charge-coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the light signal into an electrical signal, which is then transmitted to the processor 2080 to be converted into a digital image signal.

[0226] The terminal device may also include at least one sensor 2050, such as an accelerometer 2051, a proximity sensor 2052, a fingerprint sensor 2053, and a temperature sensor 2054. The terminal device may also be equipped with other sensors such as a gyroscope, barometer, hygrometer, thermometer, infrared sensor, light sensor, and motion sensor.

[0227] Audio circuitry 2060, speaker 2061, and microphone 2062 provide an audio interface between the user and the terminal device. Audio circuitry 2060 converts received audio data into electrical signals and transmits them to speaker 2061, where speaker 2061 converts them into sound signals for output. The terminal device can also be equipped with volume buttons for adjusting the volume of the sound signal. Conversely, microphone 2062 converts collected sound signals into electrical signals, which are then received by audio circuitry 2060, converted back into audio data, and output to communication component 2010 for transmission to, for example, another terminal device, or to memory 2020 for further processing.

[0228] The Bluetooth module 2070 is used to interact with other Bluetooth devices that also have a Bluetooth module via the Bluetooth protocol. For example, a terminal device can establish a Bluetooth connection with a wearable computer device (such as a smartwatch) that also has a Bluetooth module through the Bluetooth module 2070, thereby exchanging data.

[0229] The processor 2080 is the control center of the terminal device, connecting various parts of the terminal through various interfaces and lines. It executes various functions and processes data by running or executing software programs stored in the memory 2020 and calling data stored in the memory 2020. In some embodiments, the processor 2080 may include one or more processing units; the processor 2080 may also integrate an application processor and a baseband processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the baseband processor mainly handles wireless communication. It is understood that the baseband processor may not be integrated into the processor 2080. In this application, the processor 2080 can run the operating system, applications, user interface display and touch response, and the information display method of the embodiments of this application. Furthermore, the processor 2080 is coupled to the display unit 2030.

[0230] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing a computer program executable by a computer device. When the program is run on the computer device, it causes the computer device to perform the steps of the above-described information display method.

[0231] Based on the same inventive concept, this application provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer device, cause the computer device to perform the steps of the above-described information display method.

[0232] Those skilled in the art will understand that embodiments of the present invention can be provided as methods or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0233] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer apparatus or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0234] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer device or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0235] These computer program instructions may also be loaded onto a computer device or other programmable data processing equipment to cause a series of operational steps to be performed on the computer device or other programmable equipment to produce a process implemented by the computer device, thereby providing instructions that execute on the computer device or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0236] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0237] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An information display method, characterized in that, include: A resource preview page is displayed, which contains resource links for each of the multiple electronic resources; In response to a triggered operation for a resource link of one of the plurality of electronic resources, the system switches from the resource preview page to the resource details page of the electronic resource, the resource details page including: resource status description information and attribute summary components of the electronic resource; In response to a triggered operation on the attribute summary component, an attribute summary page is displayed. The attribute summary page includes attribute summary information of the electronic resource under various preset dimensions. The attribute summary information under each preset dimension is generated based on the attribute details associated with the resource link.

2. The method as described in claim 1, characterized in that, The response to a trigger operation on the attribute summary component, displaying the attribute summary page, includes: In response to a triggered operation on the attribute summary component, the attribute summary page is displayed as a floating card on the resource details page.

3. The method as described in claim 1, characterized in that, After displaying the attribute summary page in response to a trigger operation on the attribute summary component, the method further includes: In response to a sharing operation triggered on the attribute summary page, the user is redirected from the attribute summary page to a target sharing page; the target sharing page includes attribute summary information under each preset dimension.

4. The method as described in claim 1, characterized in that, The attribute summary page includes a question-and-answer component; after displaying the attribute summary page in response to a trigger operation on the attribute summary component, it also includes: In response to a trigger operation on the question-and-answer component, the system switches from the attribute summary page to the intelligent question-and-answer page; the intelligent question-and-answer page includes an input operation area and a history dialogue area, the history dialogue area including attribute summary information under each preset dimension; In response to a question action triggered in the input operation area, a corresponding reply text is displayed in the history dialogue area; the reply text is generated based on the question text associated with the question action and the attribute summary information under each preset dimension.

5. The method as described in claim 1, characterized in that, The attribute summary page also includes: the recommendation level and the reason for recommendation of the electronic resource, which are obtained based on the weights of each preset dimension and the attribute summary information under each preset dimension.

6. The method as described in claim 1, characterized in that, The response to a trigger operation on the attribute summary component, displaying the attribute summary page, includes: In response to a trigger operation on the attribute summary component, an attribute summary request is sent to the server. The attribute summary request carries the resource identifier of the electronic resource, so that the server can obtain attribute summary information under each preset dimension that matches the resource identifier. Receive the attribute summary information under each preset dimension returned by the server; The attribute summary information under each preset dimension is rendered to obtain the attribute summary page, and the attribute summary page is displayed.

7. The method as described in claim 1, characterized in that, Also includes: In response to a conversion initiation operation triggered for the aforementioned electronic resource, a conversion confirmation page for the aforementioned electronic resource is displayed; The conversion confirmation page includes: the resource conversion amount of the electronic resource; In response to a conversion confirmation operation triggered on the conversion confirmation page, a conversion result page for the electronic resource is displayed; the conversion result page includes: the resource conversion certificate for the electronic resource.

8. The method according to any one of claims 1 to 7, characterized in that, The attribute summary information under each preset dimension is obtained in the following way: For each preset dimension, obtain the dimension details associated with the preset dimension from the attribute details content; Based on the dimension details associated with the preset dimension, a prompt text is generated, indicating that a summary of the dimension details associated with the preset dimension should be performed. Using the prompt text as a prompt instruction, input it into the large language model for reasoning to obtain the attribute summary information of the preset dimension.

9. The method as described in claim 8, characterized in that, The step of using the prompt text as a prompt instruction, inputting it into a large language model for reasoning, and obtaining the attribute summary information of the preset dimensions includes: Using the large language model, perform the following steps: Based on the contextual information contained in the prompt text, text intent recognition is performed on the prompt text to obtain a recognition result; the recognition result indicates that a content summary of the dimension details associated with the preset dimension is performed. Based on the recognition results, core element information is extracted from the dimension details and reconstructed to obtain the attribute summary information of the preset dimension.

10. The method as described in claim 9, characterized in that, The step of extracting core element information from the dimension details based on the recognition results, and reconstructing the core element information to obtain the attribute summary information of the preset dimension includes: Feature extraction is performed on the details of the aforementioned dimensions to obtain semantic features of the details; Based on the recognition results, core element features are extracted from the semantic features of the details, where the core element features are the semantic features of the core element information in the dimension details content. An autoregressive approach is used to generate attribute summary information for the preset dimensions based on the core element features.

11. The method according to any one of claims 1 to 7, characterized in that, The attribute summary information under each preset dimension is obtained in the following way: For each preset dimension, obtain the dimension details associated with the preset dimension from the attribute details content; When the amount of data in the dimension details exceeds a preset threshold, the dimension details will be split into multiple data blocks. Summarize the information for each data block to obtain corresponding sub-summary content; The obtained sub-summaries are merged to obtain the attribute summary information of the preset dimension.

12. An information display device, characterized in that, include: The display module is used to present a resource preview page, which contains resource links for each of the multiple electronic resources. The display module is also configured to switch from the resource preview page to the resource details page of the electronic resource in response to a trigger operation for a resource link of one of the plurality of electronic resources. The resource details page includes: resource status description information and attribute summary components of the electronic resource. In response to a triggered operation on the attribute summary component, an attribute summary page is displayed. The attribute summary page includes attribute summary information of the electronic resource under various preset dimensions. The attribute summary information under each preset dimension is generated based on the attribute details associated with the resource link.

13. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, It stores a computer program executable by a computer device, which, when run on the computer device, causes the computer device to perform the steps of the method according to any one of claims 1 to 11.

15. A computer program product, characterized in that, The computer program product includes a computer program stored on a computer-readable storage medium, the computer program including program instructions that, when executed by a computer device, cause the computer device to perform the steps of the method according to any one of claims 1-11.

Images