Information display method and device and electronic equipment

Abstract

The invention discloses an information display method and device and electronic equipment, and belongs to the technical field of artificial intelligence. The method comprises the steps that area selection input of a program interface is received; and displaying at least one item of viewpoint information related to the effective information under the condition that the area selected by the area selection input contains the effective information.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and specifically relates to an information display method, device and electronic equipment. Background Art

[0002] With the continuous development of mobile Internet technology, electronic devices have gradually become one of the main ways for people to obtain information. For example, users can read information in online applications or locally saved information on electronic devices. However, in the related art, when users read information on electronic devices, if they want to know more relevant information about the current information, they need to search manually, read the search result pages one by one after the search, and manually summarize all relevant information. The reading volume is large, and there may be a large amount of repeated information in the search results, resulting in low reading efficiency. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide an information display method, device and electronic device, which can improve the efficiency of users reading information.

[0004] In a first aspect, an embodiment of the present application provides an information display method, comprising:

[0005] Receive area selection input for the program interface;

[0006] In the case where the area selected by the area selection input contains valid information, at least one item of viewpoint information related to the valid information is displayed.

[0007] In a second aspect, an embodiment of the present application provides an information display device, including:

[0008] A receiving module, used for receiving an area selection input on a program interface;

[0009] A display module is used to display at least one item of viewpoint information related to the valid information when the area selected by the area selection input contains valid information.

[0010] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the information display method described in the first aspect are implemented.

[0011] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the information display method described in the first aspect are implemented.

[0012] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the information display method described in the first aspect.

[0013] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the steps of the information display method as described in the first aspect.

[0014] In the embodiment of the present application, an area selection input is received on the program interface, and when the area selected by the area selection input contains valid information, at least one point of view information related to the valid information is displayed. It can be seen that in the embodiment of the present application, when the user is reading information on the electronic device, if he wants to know more relevant information of the current reading information, he only needs to perform a simple area selection input on the valid information of interest on the program interface where the current reading information is located, and at least one point of view information with a different point of view related to the valid information of interest can be obtained, thereby avoiding the tedious operation of manual search and manual summary by the user, and improving the efficiency of the user in reading information. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of an information display method provided by some embodiments of the present application;

[0016] Figure 2 is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0017] Figure 3A is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0018] Figure 3B is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0019] Figure 3C is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0020] Figure 3D is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0021] Figure 3E is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0022] Figure 3F is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0023] Figure 4 is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0024] Figure 5 is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0025] Figure 6 is a flow chart of an information display method provided by some embodiments of the present application;

[0026] Figure 7 is a flowchart of a process for generating a first database provided by some embodiments of the present application;

[0027] Figure 8 is a flow chart of an information display method provided by some embodiments of the present application;

[0028] Fig.9A is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0029] Fig. 9B is an example diagram of screen display information of an electronic device provided by some embodiments of the present application;

[0030] Fig.10 is a flow chart of an information display method provided by some embodiments of the present application;

[0031] Fig.11 is a structural block diagram of an information display device provided by some embodiments of the present application;

[0032] Fig.12 is a schematic diagram of the structure of an electronic device provided by some embodiments of the present application;

[0033] Fig.13 It is a schematic diagram of the hardware structure of an electronic device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0035] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable when appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated before and after are in an "or" relationship. The logo in this application is a text, symbol, image, etc. used to indicate information, and a control or other container can be used as a carrier for displaying information, including but not limited to a text logo, a symbol logo, and an image logo.

[0036] To facilitate understanding, the concepts involved in the embodiments of the present application are first explained.

[0037] Generative Pre-trained Transformer (GPT) is a natural language processing model that can learn the structure and rules of language through a large amount of text training data to generate high-quality text.

[0038] Prompt is a natural language text that describes the task that the artificial intelligence should perform.

[0039] Embedding, in computer science and machine learning, usually refers to the process of converting categories, vocabulary or other types of data into real number vectors. Specifically, a high-dimensional space with the dimension of all words is embedded into a continuous vector space with much lower dimension, and each word or phrase is mapped to a vector on the real number field.

[0040] Fine-tuning, which usually occurs on the basis of a pre-trained model, is a subsequent training step that aims to adapt this general pre-trained model to a specific task or dataset.

[0041] ES index refers to the search engine provided by Elasticsearch.

[0042] Recall refers to the process of finding as many correct results as possible from a large set of information and returning the results.

[0043] A card is an information carrier with a closed outline, which provides various information of various applications in a condensed form, intuitively and quickly, and is used for displaying and interacting with various program information. In the Android system, a card is a window interface that can be stacked and presented. The shape of a card is usually a rounded rectangle, similar to the shape of a credit card, but it can also be other shapes. Cards make it more convenient and intuitive for users of electronic devices to obtain information and perform operations, and are therefore widely used. In the embodiments of the present application, the size, position, shape, etc. of the card are not limited.

[0044] Controls are objects that users can interact with to input or manipulate data. The classification of controls includes but is not limited to: 1) User interface controls: controls used to develop and build user interfaces, helping to complete the development of interface elements such as windows, text boxes, buttons, and drop-down menus in software development; 2) Chart controls: controls used to develop charts, helping the software to achieve data visualization and realize complex charts that are difficult to complete independently during development; 3) Report controls: controls used to develop reports, realizing the functions of browsing, viewing, designing, editing, and printing reports in the software; 4) Table controls: controls specifically used to develop tables, mainly realizing the functions of data processing and operation in the grid; 5) Barcode controls: controls used for barcode generation, scanning, reading, and printing; 6) Image processing controls: controls that help the software to realize image browsing and simple editing functions; 7) Document processing controls: controls that realize the browsing and editing functions of document files.

[0045] The information display method provided by the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0046] It should be noted that the information display method provided in the embodiments of the present application can be executed by electronic devices such as mobile phones, tablet computers, laptop computers, PDAs, and vehicle-mounted electronic devices. In some embodiments of the present application, the information display method provided in the embodiments of the present application is described by taking the electronic device as the execution subject to execute the information display method.

[0047] The information display method provided by the embodiment of the present application can be applied to reading scenarios; one specific scenario is that a user reads a scientific article in a memo, and there is a paragraph in the article describing "Does autonomous driving technology have obvious advantages or obvious disadvantages?" After seeing this paragraph, the user is more interested in this paragraph and wants to learn more about the advantages and disadvantages of autonomous driving technology. Another specific application scenario is that a user reads a skin care article in an information application, and there is a paragraph in the article describing "Washing your face with cold water is good for your skin." After seeing this paragraph, the user is more interested in this paragraph and wants to learn more about why washing your face with cold water is good for your skin and whether washing your face with cold water is really good for your skin.

[0048] Figure 1 is a flowchart of an information display method provided by some embodiments of the present application, such as Figure 1 As shown, the method at least includes the following steps: step 101 and step 102;

[0049] In step 101, an area selection input of a program interface is received.

[0050] In some embodiments of the present application, the above program interface is the program interface currently displayed on the electronic device. In practical applications, the above program interface can be any program interface, including but not limited to: a program interface of an information application, a program interface of a memo, a program interface of a social application, and a program interface of a local system, etc. Since the above program interface can be any program interface, the information display method based on the program interface is applicable to a wide range of scenarios.

[0051] In some embodiments of the present application, the area selection input may include at least one of the following: fingertip touch input and knuckle touch input.

[0052] In some embodiments of the present application, considering that fingertips and knuckles are commonly used input tools by users, and the input process of fingertips and knuckles on the screen of electronic devices is relatively simple and easy to control, fingertip touch input or knuckle touch input is used as area selection input, which can reduce the complexity of area selection operation and improve the user's operation experience and convenience. In addition, users are supported to make area selection input through fingertips and knuckles, making the input method more diverse and improving the flexibility of users in selecting areas on the screen.

[0053] In some embodiments of the present application, when the area selection input includes a fingertip touch input, the fingertip touch input includes an input in which a fingertip contacts the screen and circles an area along a reference direction.

[0054] In some embodiments of the present application, the fingertips include but are not limited to: the tip of the thumb, the tip of the index finger, the tip of the middle finger, the tip of the ring finger, the tip of the little finger, etc.

[0055] In some embodiments of the present application, fingertip contacting the screen includes but is not limited to: pressing the screen with a fingertip, gently sliding a fingertip on the screen, etc.

[0056] In some embodiments of the present application, the reference direction includes but is not limited to: counterclockwise direction, clockwise direction, etc.

[0057] In some embodiments of the present application, the shape of the circled area includes but is not limited to: circle, ellipse, rectangle or other irregular shapes.

[0058] Exemplarily, the area selection input is an input in which the user touches the screen with a fingertip on the program interface and draws a circle in a counterclockwise direction.

[0059] In some embodiments of the present application, when the area selection input includes a knuckle touch input, the knuckle touch input includes an input of tapping the screen with a knuckle and circling an area along a reference direction from the tapping position.

[0060] In some embodiments of the present application, finger joints include but are not limited to: thumb joints, index finger joints, middle finger joints, ring finger joints, little finger joints, etc.

[0061] In some embodiments of the present application, the reference direction includes but is not limited to: counterclockwise direction, clockwise direction, etc.

[0062] In some embodiments of the present application, the shape of the circled area includes but is not limited to: circle, ellipse, rectangle or other irregular shapes.

[0063] Exemplarily, the area selection input is an input in which the user taps the screen on the program interface using the knuckle of the index finger and draws a circle in a counterclockwise direction starting from the tapped position on the screen.

[0064] In some embodiments of the present application, tapping the screen with the knuckles is used to select the starting point of the circling action, and the knuckles are used to start circling the area along a reference direction from the starting point of the circling action until returning to the above-mentioned starting point to complete the area selection, so that the entire area selection process has a clear starting point and end point, thereby improving the stability, accuracy and convenience of the user's area selection operation.

[0065] For example, Figure 2 As shown, a memo program interface 21 is displayed on the screen of an electronic device 20, and the program interface 21 includes some text. The user uses the index finger of a hand 22 to draw an ellipse in a counterclockwise direction on the program interface 21 to circle an area, and obtains a circled area 23. The circled area 23 includes information: "Does the autonomous driving technology have obvious advantages or obvious defects?"

[0066] In step 102, when the area selected by the area selection input contains valid information, at least one item of viewpoint information related to the valid information is displayed.

[0067] In some embodiments of the present application, the effective information may include at least one of the following: information containing at least two viewpoints, information containing a single viewpoint, and declarative information without a viewpoint.

[0068] For example, a user reads a science and technology article in the memo, and there is a paragraph in the article describing "Does autonomous driving technology have obvious advantages or obvious disadvantages?" After seeing this paragraph, the user is quite interested in it and wants to learn more about the advantages and disadvantages of autonomous driving technology. At this time, the user can select the area where the above text is located through area selection input. The text in the area is valid information, which is information containing at least two viewpoints, namely, "Does autonomous driving technology have obvious advantages or obvious disadvantages?"

[0069] For example, a user reads a skin care article in an information application, and there is a paragraph in the article describing that "washing your face with cold water is good for your skin." After seeing this paragraph, the user is interested in it and wants to learn more about why washing your face with cold water is good for your skin and whether washing your face with cold water is really good for your skin. At this time, the user can select the area where the above text is located through area selection input. The text in the area is valid information, which is information that contains a single point of view, namely, "washing your face with cold water is good for your skin."

[0070] For example, a user reads a financial article in a social application, and there is a paragraph in the article describing "Federal Reserve cuts interest rates". After seeing this paragraph, the user is interested in it and wants to learn more about the specific content of the Federal Reserve's interest rate cut. At this time, the user can select the area where the above text is located through area selection input. The text in the area is valid information, which is declarative information without opinion, that is, "Federal Reserve cuts interest rates."

[0071] In some embodiments of the present application, the types of valid information include but are not limited to: text type, image type, video type, audio type, etc.

[0072] In some embodiments of the present application, after the area selection input selects an area on the screen, it can be detected whether the area is a blank area. If it is not a blank area, semantic detection is performed on the information in the area or a GPT model is used to determine whether the information in the area is valid information. If the information in the area is one of information containing at least two viewpoints, information containing a single viewpoint, and declarative information without viewpoints, then the information in the area is determined to be valid information.

[0073] Exemplarily, the information in the region and the fifth prompt word are input into the fifth GPT model, and the fifth GPT model outputs the type of information in the region, wherein the fifth prompt word is "You are an expert in text information processing, please read 'input text', determine the type of text, the optional types include one of information with at least two viewpoints, information containing a single viewpoint, and declarative information without viewpoints, and output the type of text". At this time, the input text is the information in the region.

[0074] In some embodiments of the present application, when at least two items of viewpoint information related to valid information are displayed, the at least two items of viewpoint information include at least two viewpoints.

[0075] In some embodiments of the present application, at least two viewpoint information related to the effective information can be displayed to help users understand the more detailed content of the information from multiple perspectives and in an all-round manner, thereby improving the effectiveness of information output.

[0076] In some embodiments of the present application, viewpoint refers to a view on an object or issue from a certain standpoint or angle.

[0077] In some embodiments of the present application, for information circled by a user on a program interface, if the information is one of information containing at least two viewpoints, information containing a single viewpoint, and declarative information without a viewpoint, then displaying at least one viewpoint information related to the information can help the user understand the information in more detail from multiple perspectives and in an all-round manner, thereby improving the effectiveness of information output.

[0078] In some embodiments of the present application, the opinion information may include: the content of the opinion, and the opinion information may also include at least one of the following: information about the author of the opinion, and information source of the opinion.

[0079] In some embodiments of the present application, the content of the opinion includes, but is not limited to: text-type opinion content, image-type opinion content, audio-type opinion content, and video-type opinion content.

[0080] In some embodiments of the present application, the author information of the viewpoint includes, but is not limited to: the author's name, the author's headshot, the author's educational background, the author's work experience, the author's written documents, etc.

[0081] In some embodiments of the present application, the information source of the opinion includes but is not limited to: a program icon of the source application of the opinion, a link to the source application of the opinion, etc.

[0082] In some embodiments of the present application, when the opinion information includes information about the author of the opinion, the provided information display method may further include at least one of the following: displaying the name of the author of the opinion, and displaying an avatar of the author of the opinion.

[0083] In some embodiments of the present application, at least one of the author's name and the author's avatar of the opinion is displayed. On the one hand, this allows users to more intuitively understand the author of the opinion information. On the other hand, since the content published by the same author is highly correlated, it is convenient for users to further expand their knowledge by reading other works of the author.

[0084] In some embodiments of the present application, in the case where the opinion information includes the information source of the opinion, the provided information display method may further include: displaying a program icon of the source application of the opinion.

[0085] In some embodiments of the present application, displaying the program icon of the application from which the opinion comes can, on the one hand, help users to more intuitively understand the source of the opinion information, and on the other hand, users can subsequently acquire further knowledge by accessing the application corresponding to the program icon.

[0086] In some embodiments of the present application, in addition to the most basic opinion content, the opinion information related to the effective information may also include some other information to assist users in reading, such as the author information of the opinion and the information source of the opinion, so that users can understand the relevant opinion information of the effective information more comprehensively and conveniently, thereby improving users' reading skills.

[0087] In some embodiments of the present application, when the area selected by the area selection input contains valid information, an item of viewpoint information related to the valid information may be displayed.

[0088] For example, Figure 3A As shown, the effective information displayed on the screen of the electronic device 30 is information containing two viewpoints, namely, "Is washing your face with cold water better for your skin or with warm water?" 31, and one viewpoint information related to the effective information is: "Cold water can help shrink pores, reduce oil secretion, relieve skin inflammation and redness, and can also reduce skin allergies and acne inflammation. In the hot summer, washing your face with cold water can make you feel refreshed and relaxed." 32.

[0089] For example, Figure 3B As shown, the effective information displayed on the screen of the electronic device 30 is information containing a point of view, namely, "the advantages of autonomous driving technology are obvious" 33, and a point of view information related to the effective information is: "The advantages of autonomous driving technology mainly include improving safety, improving efficiency, saving time, reducing energy consumption and environmental pollution, and improving travel convenience" 34.

[0090] For example, Figure 3C As shown, the effective information displayed on the screen of the electronic device 30 is declarative information without opinion, namely, "energy-saving lamp" 35, and an opinion information related to the effective information is: "Energy-saving lamp, also known as energy-saving light bulb, electronic light bulb, compact fluorescent lamp and integrated fluorescent lamp, refers to a lighting device that combines a fluorescent lamp and a ballast into a whole" 36.

[0091] In some embodiments of the present application, when the area selected by the area selection input contains valid information, at least two items of viewpoint information related to the valid information can be displayed, wherein the at least two items of viewpoint information include at least two viewpoints, and each viewpoint information has at least one item of viewpoint information.

[0092] For example, Figure 3D As shown, the valid information displayed on the screen of the electronic device 30 is information containing at least two viewpoints, namely, "Does the autonomous driving technology have obvious advantages or obvious disadvantages" 37, and at least two viewpoints related to the valid information are: "Viewpoint 1, the advantages of autonomous driving technology mainly include improving safety, improving efficiency, saving time, reducing energy consumption and environmental pollution, improving travel convenience, promoting the development of new transportation services, significant economic benefits, life safety protection, improving time efficiency, making congestion a thing of the past, significantly reducing accident rates, strengthening safety lines, better taxi services, improved delivery efficiency, more efficient space utilization, more efficient long-distance transportation, lowering driving thresholds, and cost optimization" 38; "Viewpoint 2, the disadvantages of autonomous driving technology mainly include technology maturity, safety hazards, adaptation to regulations and road rules, data privacy, road infrastructure, social acceptance, vehicle ownership and insurance, environmental impact, dependency issues, and cost issues" 39.

[0093] For example, Figure 3E As shown, the effective information displayed on the screen of the electronic device 30 is information containing a single opinion, namely, "Washing your face with cold water is good for your skin" 310, and at least two opinion information related to the effective information, namely: "Opinion 1, cold water can help shrink pores, reduce oil secretion, relieve skin inflammation and redness, and can also reduce the inflammation of skin allergies and acne. In the hot summer, washing your face with cold water can make you feel refreshed and relaxed" 311; "Opinion 2, long-term use of cold water to wash your face may cause the capillaries of the skin to contract, causing the skin to become dry and lack elasticity. For people with sensitive skin, using cold water may irritate the skin, causing discomfort and tingling" 312.

[0094] For example, Figure 3F As shown, the effective information displayed on the screen of the electronic device 30 is declarative information without opinion, namely, "Federal Reserve cuts interest rates" 313, and at least two opinion information related to the effective information, namely: "Opinion 1, stimulate economic growth" 314; "Opinion 2, promote investment and consumption" 315; "Opinion 3, affect the global financial market" 316.

[0095] In some embodiments of the present application, an area selection input is received on a program interface, and when the area selected by the area selection input contains valid information, at least one point of view information related to the valid information is displayed. It can be seen that in the embodiments of the present application, when a user is reading information on an electronic device, if he wants to know more relevant information about the currently read information, he only needs to perform a simple area selection input on the valid information of interest on the program interface where the currently read information is located, and at least one point of view information different from the point of view related to the valid information of interest can be obtained, thereby avoiding the tedious operation of manual search and manual summary by the user, and improving the efficiency of the user in reading information.

[0096] In some embodiments of the present application, it is applicable to the scenario of displaying viewpoint information under at least one viewpoint in a classified manner. In order to facilitate intuitively displaying the correspondence between the viewpoint information and the viewpoint to which it belongs, the above step 102 may include the following steps: step 1021;

[0097] In step 1021, at least one information card is displayed; wherein each information card includes at least one item of viewpoint information of a viewpoint.

[0098] In some embodiments of the present application, when the number of information cards is 1, one information card is displayed on the screen.

[0099] In some embodiments of the present application, when the number of information cards is at least two, the at least two information cards may be displayed side by side horizontally on the screen, or the at least two information cards may be displayed side by side vertically on the screen.

[0100] In some embodiments of the present application, the shape of the information card includes but is not limited to: rectangle, oval, etc.

[0101] In some embodiments of the present application, the name of the viewpoint may be displayed above each information card.

[0102] For example, Figure 2 As shown, a memo program interface 21 is displayed on the screen of an electronic device 20, and the program interface 21 includes some text. The user uses the index finger of a hand 22 to draw an ellipse in a counterclockwise direction on the program interface 21 to circle an area, and obtains a circled area 23. The circled area 23 includes information: whether the autonomous driving technology has obvious advantages or obvious defects.

[0103] At this time, effective information is information that contains at least two viewpoints, namely, "Does autonomous driving technology have obvious advantages or obvious defects?", such as Figure 4 As shown, two information cards are displayed on the screen of the electronic device 20, namely, information card 24 and information card 25.

[0104] Among them, information card 24 includes: "Viewpoint 1, the advantages of autonomous driving technology mainly include improving safety, improving efficiency, saving time, reducing energy consumption and environmental pollution, improving travel convenience, promoting the development of new transportation services, significant economic benefits, life safety protection, improving time efficiency, congestion becomes a thing of the past, accident rate drops significantly, safety line is strengthened, better taxi service, delivery efficiency is improved, space utilization is more efficient, long-distance transportation is more efficient, driving threshold is lowered, and cost optimization", "The author's name of the viewpoint is Xiao Ming" and "Application 1 where the viewpoint comes from".

[0105] Information card 25 includes: "Viewpoint 2, the shortcomings of autonomous driving technology mainly include technology maturity, safety hazards, regulations and road rule adaptation, data privacy, road infrastructure, social acceptance, vehicle ownership and insurance, environmental impact, dependency issues, and cost issues", "The author name of the viewpoint author is Xiaoliang" and "Application 2 where the viewpoint comes from".

[0106] In some embodiments of the present application, opinion information is classified and displayed through the display of information cards, which can help users intuitively understand the correspondence between opinion information and the opinions to which it belongs, improve users' reading efficiency, and optimize users' reading experience of reading information.

[0107] In some embodiments of the present application, it is applicable to the scenario where the user independently chooses whether to display the viewpoint information. The information display method provided is Figure 1 Before step 102 in the illustrated embodiment, the following steps may also be included: step 103 and step 104.

[0108] In step 103, the viewpoint viewing angle control is displayed.

[0109] In some embodiments of the present application, the viewpoint perspective control is a visual object displayed on the screen for triggering the display of at least one viewpoint information related to the valid information, and the user can interact with it.

[0110] In some embodiments of the present application, the viewpoint viewing angle control can be displayed at any position on the screen.

[0111] In step 104, a control input to a viewpoint viewing angle control is received.

[0112] In some embodiments of the present application, the control input is used to interact with the viewpoint control, and the control input may be a first operation. Exemplarily, the control input includes but is not limited to: a user's touch input to the viewpoint control through a touch device such as a finger or a stylus, or a voice command input by the user, or a specific gesture input by the user, or other feasible input, which may be determined according to actual use requirements and is not limited in the embodiments of the present application.

[0113] In some embodiments of the present application, the above-mentioned specific gesture can be any one of a single-click gesture, a sliding gesture, a drag gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double-press gesture, and a double-click gesture.

[0114] In some embodiments of the present application, the click input may be a single click input, a double click input, or any number of click inputs, etc., and may also be a long press input or a short press input. For example, the control input may be a user's click input on a viewpoint control.

[0115] Accordingly, the above step 102 may include the following steps: step 1022;

[0116] In step 1022, in response to a control input, at least one item of viewpoint information related to the valid information is displayed.

[0117] For example, Figure 2 As shown, a memo program interface 21 is displayed on the screen of an electronic device 20, and the program interface 21 includes some text. The user uses the index finger of a hand 22 to draw an ellipse in a counterclockwise direction on the program interface 21 to circle an area, and obtains a circled area 23. The circled area 23 includes information: "Does the autonomous driving technology have obvious advantages or obvious defects?"

[0118] At this time, effective information is information that contains at least two viewpoints, namely, "Does autonomous driving technology have obvious advantages or obvious defects?", such as Figure 5 As shown, the screen of the electronic device 20 displays a "viewpoint" control 26. After the user clicks the "viewpoint" control 26, as shown in FIG. Figure 4 As shown, two information cards are displayed on the screen of the electronic device 20, namely, information card 24 and information card 25.

[0119] In some embodiments of the present application, when the area selected by the area selection input contains valid information, a viewpoint perspective control can be displayed. The viewpoint perspective control is a visualization object used to trigger the display of at least one viewpoint information related to the valid information. A user can interact with it, so that the user can independently choose whether to display at least one viewpoint information related to the valid information, thereby meeting the user's personalized viewpoint information viewing needs.

[0120] In some embodiments of the present application, it is applicable to the scenario where the user wants to further understand the detailed information of the viewpoint information, and the information display method provided is Figure 1 After step 102 in the illustrated embodiment, the following steps may also be included: step 105 and step 106.

[0121] In step 105 , an information selection input for one item of at least one item of opinion information is received.

[0122] In some embodiments of the present application, information selection input is used to trigger the display of detailed information of the viewpoint information, and the information selection input can be a second operation. Exemplarily, the above-mentioned information selection input includes but is not limited to: a user's touch input of a viewpoint information through a touch device such as a finger or a stylus, or a voice command input by the user, or a specific gesture input by the user, or other feasible input, which can be determined according to actual use requirements and is not limited in the embodiments of the present application.

[0123] In some embodiments of the present application, the above-mentioned specific gesture can be any one of a single-click gesture, a sliding gesture, a drag gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double-press gesture, and a double-click gesture.

[0124] In some embodiments of the present application, the click input may be a single click input, a double click input, or any number of click inputs, etc., and may also be a long press input or a short press input. For example, the information selection input may be: a user clicks on an item of viewpoint information.

[0125] In step 106, in response to the information selection input, detailed information of the viewpoint information selected by the information selection input is displayed.

[0126] In some embodiments of the present application, when a user wants to further understand the details of opinion information, the user can trigger the display of the details of the opinion information by making an information selection input on the opinion information, thereby satisfying the user's need to obtain the details.

[0127] In some embodiments of the present application, an information interface corresponding to the information source of the selected opinion information may be displayed.

[0128] Exemplarily, if the opinion information selected by the information selection input comes from application 1, then the interface jumps to the information interface of application 1 where the opinion information is located.

[0129] In some embodiments of the present application, when displaying the detailed information of opinion information, it is possible to jump to the information interface of the application program from which the opinion information comes. This can satisfy the user's need to read the detailed information on the one hand, and can also help the user understand the original source of the opinion information on the other hand.

[0130] In some embodiments of the present application, the viewpoint information selected by the information selection input may be updated to detailed information of the viewpoint information.

[0131] Exemplarily, if the opinion information selected by the information selection input comes from application 1, the interface where the opinion information of application 1 is located is not jumped to, but the detailed information of the opinion information is displayed on the current program interface.

[0132] In some embodiments of the present application, when displaying the detailed information of the viewpoint information, the detailed information can be directly displayed on the current program interface. On the one hand, it can meet the user's reading needs for the detailed information, and on the other hand, it can avoid the time-consuming problem caused by interface jumping.

[0133] In some embodiments of the present application, it is applicable to scenarios where opinion information matching valid information is collected through a large model, such as Figure 6 As shown, the information display method provided is Figure 1 Before step 102 in the illustrated embodiment, the following steps may also be included: step 601 , step 602 , step 603 , step 604 and step 605 .

[0134] In step 601, valid information is input into a first GPT model, and at least one keyword of the valid information is output.

[0135] In some embodiments of the present application, considering the advantages of the GPT model such as powerful pre-training capability, high adaptability, ability to solve sentence coherence problems, extremely high language generation capability, self-training and improvement capability, and a wide range of application scenarios, the first GPT model can be a fine-tuned GPT model suitable for reading scenarios.

[0136] In some embodiments of the present application, the first GPT model is used to generate keywords for effective information. For example, the first GPT model is used to expand and rewrite words to generate a series of keywords.

[0137] In some embodiments of the present application, the valid information and the first prompt word can be input into the first GPT model together, and the first GPT model will generate keywords for the valid information according to the guidance of the first prompt word.

[0138] In some embodiments of the present application, the first prompt word is a prompt word automatically added by the electronic device for valid information, and the first prompt word is used to prompt the first GPT model to output keywords for valid information.

[0139] For example, the first prompt is “You are a text information processing expert, please read the 'input text', extract the key words in the text, and summarize and output them in a fluent and organized language.” At this point, the input text is valid information.

[0140] For example, if the valid information is "Does autonomous driving technology have obvious advantages or obvious defects", the keywords of the valid information output by the first GPT model are: autonomous driving, intelligent driving, advantages, strengths, defects, and deficiencies. For another example, if the valid information is "Washing your face with cold water is good for your skin", the keywords of the valid information output by the first GPT model are: cold water, cool water, wash your face, cleanse your face, and good skin.

[0141] In step 602, at least one keyword is input into the embedded model, and a keyword embedding vector of each keyword is output.

[0142] In some embodiments of the present application, considering that the embedded model can represent the semantics of words or sentences, perform vector operations, share and migrate among different natural language processing tasks, and capture the semantics and contextual information of words, each keyword can be input into the embedded model and processed by the embedded model to obtain a keyword embedding vector for each keyword.

[0143] For example, the valid information is "Does the autonomous driving technology have obvious advantages or obvious defects?" The keywords of the valid information output by the first GPT model are: autonomous driving, intelligent driving, advantages, strengths, defects, and deficiencies. After that, the six keywords of autonomous driving, intelligent driving, advantages, strengths, defects, and deficiencies are input into the embedded model, and the corresponding six keyword embedding vectors are obtained respectively: vector 1, vector 2, vector 3, vector 4, vector 5, and vector 6.

[0144] In step 603, at least one reference information matching the valid information is obtained from the first database according to each keyword and each keyword embedding vector; wherein the first database includes: at least one reference information and a reference embedding vector for each reference information.

[0145] Exemplarily, the valid information is "Does the autonomous driving technology have obvious advantages or obvious defects?" The keywords of the valid information output by the first GPT model are: autonomous driving, intelligent driving, advantages, strengths, defects, and deficiencies. Based on the six keywords of autonomous driving, intelligent driving, advantages, strengths, defects, and deficiencies and the corresponding six keyword embedding vectors: vector 1, vector 2, vector 3, vector 4, vector 5, and vector 6, at least one reference information matching "Does the autonomous driving technology have obvious advantages or obvious defects?" is obtained from the first database.

[0146] For example, a reference information obtained by matching is: the advantages of autonomous driving technology mainly include improving safety, improving efficiency, saving time, reducing energy consumption and environmental pollution, improving travel convenience, promoting the development of new transportation services, significant economic benefits, protecting life safety, improving time efficiency, making congestion a thing of the past, significantly reducing accident rates, strengthening safety lines, better taxi services, improved delivery efficiency, more efficient space utilization, more efficient long-distance transportation, lowering driving thresholds, and cost optimization.

[0147] For another example, two pieces of reference information are matched and are: Reference information 1, the advantages of autonomous driving technology mainly include improving safety, improving efficiency, saving time, reducing energy consumption and environmental pollution, improving travel convenience, promoting the development of new transportation services, significant economic benefits, life safety protection, improving time efficiency, making congestion a thing of the past, significantly reducing accident rates, strengthening safety lines, better taxi services, improved delivery efficiency, more efficient space utilization, more efficient long-distance transportation, lowering driving thresholds, and cost optimization; Reference information 2, the disadvantages of autonomous driving technology mainly include technology maturity, safety hazards, adaptation to regulations and road rules, data privacy, road infrastructure, social acceptance, vehicle ownership and insurance, environmental impacts, dependency issues, and cost issues.

[0148] In step 604, at least one item of reference information matching the valid information is determined as opinion information related to the valid information.

[0149] Exemplarily, the reference information matching the valid information includes: reference information 5, and the reference information 5 is the opinion information related to the valid information.

[0150] Exemplarily, the reference information matching the valid information includes: reference information 1, reference information 2, reference information 3, and reference information 4, and reference information 1, reference information 2, reference information 3, and reference information 4 are opinion information related to the valid information.

[0151] In step 605, opinion information related to valid information is input into the second GPT model, and the opinion type of each opinion information is output.

[0152] In some embodiments of the present application, after determining the opinion information related to the valid information, it is also necessary to determine the opinion type of the opinion information.

[0153] In some embodiments of the present application, considering the advantages of the GPT model such as powerful pre-training capability, high adaptability, ability to solve sentence coherence problems, extremely high language generation capability, self-training and improvement capability, and a wide range of application scenarios, the second GPT model can be a fine-tuned GPT model suitable for reading scenarios.

[0154] In some embodiments of the present application, the second GPT model is used to generate the opinion type of opinion information.

[0155] In some embodiments of the present application, for each opinion information, the opinion information and the second prompt word can be input into the second GPT model together, and the second GPT model will generate the opinion type of the opinion information according to the guidance of the second prompt word.

[0156] In some embodiments of the present application, the second prompt word is a prompt word automatically added by the electronic device to the opinion information, and the second prompt word is used to prompt the opinion type to which the opinion information output by the second GPT model belongs.

[0157] For example, the second prompt is “You are an information integration expert, please read the ‘input text’, extract relevant viewpoints related to the viewpoint information in the text, and summarize and output them in fluent and organized language.” At this time, the input text is the viewpoint information.

[0158] For example, the opinion information is "Does autonomous driving technology have obvious advantages or obvious defects?" and matches at least two reference information. For example, the two reference information are: Reference information 1, the advantages of autonomous driving technology mainly include improving safety, improving efficiency, saving time, reducing energy consumption and environmental pollution, improving travel convenience, promoting the development of new transportation services, significant economic benefits, life safety protection, improving time efficiency, making congestion a thing of the past, significantly reducing accident rates, strengthening safety lines, better taxi services, improved delivery efficiency, more efficient space utilization, more efficient long-distance transportation, lowering driving barriers, and cost optimization." The opinion type to which this opinion information belongs is the advantages of autonomous driving.

[0159] For another example, the opinion information is "The shortcomings of autonomous driving technology mainly include technology maturity, safety hazards, adaptation to regulations and road rules, data privacy, road infrastructure, social acceptance, vehicle ownership and insurance, environmental impacts, dependency issues, and cost issues." The opinion type to which this opinion information belongs is the defects of autonomous driving.

[0160] In some embodiments of the present application, a method for integrating multi-viewpoint information based on a large model can be implemented, allowing users to efficiently and quickly obtain full-view information of content of interest. During the reading process, users do not need to interrupt reading to open other search tools. They only need to circle the information they want to know to initiate a search. After searching for the topic that the user is interested in, the user does not need to read the search result pages one by one, which enables the user to aggregate multi-page information and improves the user's reading efficiency.

[0161] In some embodiments of the present application, it is applicable to the scenario of matching viewpoint information with effective information from multiple dimensions. Accordingly, the above step 603 may include the following steps: step 6031, step 6032, step 6033 and step 6034.

[0162] In step 6031, the content similarity between each keyword and each reference information in the first database is calculated.

[0163] In some embodiments of the present application, the content similarity between two pieces of information is used to indicate the similarity between the two pieces of information in the content dimension. In practical applications, the content similarity between the two pieces of information can be calculated by comparing the word overlaps in the texts of the two pieces of information.

[0164] Exemplarily, the keyword is autonomous driving, and the first database contains 100 items of reference information, then the content similarity between "autonomous driving" and the 100 items of reference information in the first database is calculated respectively.

[0165] In step 6032, the vector similarity between each keyword embedding vector and each reference embedding vector in the first database is calculated.

[0166] In some embodiments of the present application, the vector similarity between two vectors is used to represent the content similarity between two items of information corresponding to the two vectors. In practical applications, the vector similarity between the two vectors can be calculated by calculating the cosine distance between the two vectors.

[0167] Exemplarily, the keyword is autonomous driving, the keyword embedding vector is vector 1, the first database contains 100 reference information and 100 reference embedding vectors, then the vector similarity between vector 1 and the 100 reference embedding vectors in the first database is calculated respectively.

[0168] In step 6033, for each keyword, all reference information with content similarity greater than a first threshold is used to generate a first set, and all reference information with vector similarity greater than a second threshold is used to generate a second set.

[0169] In some embodiments of the present application, the first threshold and the second threshold may be numerical values ​​preset according to empirical values. For example, the first threshold is 85% and the second threshold is 90%.

[0170] In some embodiments of the present application, the first set includes all reference information in the first database whose content similarity is greater than a first threshold, and the second set includes all reference information in the first database whose vector similarity is greater than a second threshold.

[0171] In step 6034, a union of the first set and the second set is taken to obtain a third set; wherein the reference information in the third set is the reference information that matches the valid information.

[0172] Exemplarily, the first set includes reference information 1, reference information 2, and reference information 3, the second set includes reference information 1, reference information 2, reference information 3, and reference information 4, and the third set includes reference information 1, reference information 2, reference information 3, and reference information 4. Reference information 1, reference information 2, reference information 3, and reference information 4 are the reference information that matches the valid information.

[0173] In some embodiments of the present application, reference information matching the valid information is obtained from the first database through the original information dimension and the vector dimension. Since the above two dimensions can more comprehensively and accurately calculate the content similarity between the valid information and the reference information in the first database, the reference information matching the valid information can be obtained from the first database more comprehensively and accurately.

[0174] In some embodiments of the present application, it is applicable to the scenario where the first database is generated in advance. Accordingly, Figure 7 As shown, the following steps may be included: step 701, step 702, step 703, step 704 and step 705;

[0175] In step 701, at least one item of information is obtained from at least one information application.

[0176] In some embodiments of the present application, information applications include but are not limited to: news media applications, search engine applications, social applications, etc.

[0177] In some embodiments of the present application, massive amounts of information can be obtained from different information applications to enrich the content of the first database.

[0178] In step 702, text segmentation is performed on each item of information to obtain at least one text block for each item of information.

[0179] In some embodiments of the present application, considering that information is usually long and contains redundant information, in order to improve storage efficiency, each information item is segmented into text to obtain at least one text block for each information item.

[0180] In step 703, at least one text block is determined as at least one item of reference information.

[0181] In some embodiments of the present application, since the text blocks are obtained after text segmentation and there is no information redundancy, the text blocks are determined as reference information, which can improve the storage efficiency of the information.

[0182] In step 704, at least one item of reference information is input into the embedded model, and a reference embedding vector of each item of reference information is output.

[0183] In some embodiments of the present application, when recalling information, recall based on the embedding vector of the information is more comprehensive, so a reference embedding vector for each reference information is generated through an embedded model.

[0184] In step 705, each item of reference information and a reference embedding vector of each item of reference information are stored in a first database.

[0185] In some embodiments of the present application, the first database may be an ES index library.

[0186] In some embodiments of the present application, each item of reference information and a reference embedding vector of each item of reference information are stored in a first database for subsequent use.

[0187] In some embodiments of the present application, as much information as possible can be obtained from currently existing information applications, and a first database can be constructed based on the obtained information, so that the information in the first database is richer and more diverse, thereby being able to provide users with more, more comprehensive, and more detailed information of interest.

[0188] In some embodiments of the present application, it is suitable for efficiently reading detailed information of viewpoint information, such as Figure 8 As shown, the provided information display method may at least include the following steps: step 801, step 802, step 803, step 804, step 805 and step 806.

[0189] In step 801, an area selection input of a program interface is received.

[0190] In step 802, when the area selected by the area selection input contains valid information, at least one item of viewpoint information related to the valid information is displayed.

[0191] In step 803, an information selection input for one item of at least one item of opinion information is received.

[0192] In step 804, in response to the information selection input, detailed information of the viewpoint information selected by the information selection input is displayed.

[0193] The contents of steps 801 to 804 in the embodiment of the present application are similar to the contents of steps 101 to 106 described above, and are not repeated here.

[0194] In step 805, a control input for an unread information control is received.

[0195] In some embodiments of the present application, the unread information control is a visual object on the screen for triggering the display of viewpoint information of unread information in the detail information, and the user can interact with it.

[0196] In some embodiments of the present application, the unread information control may be displayed at any position on the screen.

[0197] In some embodiments of the present application, when the user wants to know which information in the detailed information is information that the user has not read, a control input can be made to the unread information control.

[0198] For example, Fig.9A As shown, the screen of the electronic device 90 displays the detail information 91 of the opinion information and the “unread information” control 92. Before reading the detail information 91, the user “Xiao Li” wants to know which information points in the detail information 91 he has not read. At this time, Xiao Li can click the “unread information” control 92 to trigger the electronic device 90 to display the opinion information of the unread information in the detail information 91.

[0199] In step 806, in response to the control input, the viewpoint information of the unread information in the detail information is displayed.

[0200] In some embodiments of the present application, the control input is used to interact with the unread information control, and the control input can be a third operation. Exemplarily, the control input includes but is not limited to: a user's touch input to the unread information control through a touch device such as a finger or a stylus, or a voice command input by the user, or a specific gesture input by the user, or other feasible input, which can be determined according to actual use requirements and is not limited in the embodiments of the present application.

[0201] In some embodiments of the present application, the above-mentioned specific gesture can be any one of a single-click gesture, a sliding gesture, a drag gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double-press gesture, and a double-click gesture.

[0202] In some embodiments of the present application, the click input may be a single click input, a double click input, or any number of click inputs, etc., and may also be a long press input or a short press input. For example, the control input may be: a user click input on an unread information control.

[0203] For example, a small click Fig.9A After the unread message control 92 in Fig. 9B As shown, the electronic device 90 displays the viewpoint information 93 of the unread information in the detailed information.

[0204] In some embodiments of the present application, it is possible to achieve an effect of extracting opinion information of user's unread information in detail information, so that the user can know which opinion information in the detail information the user has not seen without reading it, which can facilitate the user to view the unread opinion information, save the user's reading time, and improve the user's reading efficiency.

[0205] In some embodiments of the present application, it is applicable to the scenario of identifying the view information of unread information through a large model, such as Fig.10 As shown, the information display method provided is Figure 8 Before step 806 in the illustrated embodiment, the following steps may also be included: step 1001 , step 1002 , step 1003 , step 1004 and step 1005 .

[0206] In step 1001, detailed information is input into a third GPT model, and at least one key point information of the detailed information is output.

[0207] In some embodiments of the present application, key information refers to the core content in detailed information. An item of detailed information may include one item of key information or two or more items of key information.

[0208] In some embodiments of the present application, considering the advantages of the GPT model such as powerful pre-training capability, high adaptability, ability to solve sentence coherence problems, extremely high language generation capability, self-training and improvement capability, and a wide range of application scenarios, the third GPT model can be a fine-tuned GPT model suitable for reading scenarios.

[0209] In some embodiments of the present application, the third GPT model is used to summarize the key information of the detailed information.

[0210] In some embodiments of the present application, the detailed information and the third prompt word can be input into the third GPT model together, and the third GPT model will summarize the key points of the detailed information according to the guidance of the third prompt word.

[0211] In some embodiments of the present application, the third prompt word is a prompt word automatically added by the electronic device to the detailed information, and the third prompt word is used to prompt the third GPT model to output key information of the detailed information.

[0212] For example, the third prompt is “You are a text information processing expert, please read the ‘input text’, summarize the key information in the text, and output it in a fluent and organized language.” At this time, the input text is detailed information.

[0213] For example, the detailed information is: "The biggest advantage of live streaming with goods is that it can establish connections with consumers through real-time interaction, allowing consumers to better understand products and services. This not only helps to increase product awareness and purchasing intention, but also stimulates consumers' purchasing desire by directly displaying the characteristics and advantages of the goods. At the same time, the live streaming with goods industry faces many challenges and problems, including lack of integrity, product quality issues, false propaganda, inadequate after-sales service, etc. These problems not only damage the rights and interests of consumers, but also affect the healthy development of the industry." The key information is as follows: Key Information 1, the advantages of live streaming with goods help to increase consumers' purchasing desire; Key Information 2, live streaming with goods involves problems such as lack of integrity, product quality issues, false propaganda, and inadequate after-sales service.

[0214] In step 1002, at least one item of key point information is input into an embedded model, and a key point embedding vector of each item of key point information is output.

[0215] In some embodiments of the present application, considering that the embedded model can represent the semantics of words or sentences, perform vector operations, share and migrate among different natural language processing tasks, and capture the semantics and contextual information of words, each key point information can be input into the embedded model and processed by the embedded model to obtain the key point embedding vector of each key point information.

[0216] In step 1003, historical read information in the detail information is obtained from the second database according to each key point embedding vector; wherein the second database includes: at least one item of historical read information and a historical embedding vector for each item of historical read information.

[0217] In some embodiments of the present application, the historical read information refers to the information that the user has read. The information that the user has read can be a message that appears on the screen for more than 3 seconds.

[0218] In some embodiments of the present application, the vector similarity between each key point embedding vector and each historical embedding vector in the second database may be calculated, and all historically read information having a vector similarity greater than a third threshold may be determined as the historically read information in the detailed information.

[0219] In some embodiments of the present application, the third threshold may be a value preset based on experience, for example, the third threshold is 90%.

[0220] In some embodiments of the present application, a second database can be generated in advance, and the generation steps can be as follows: whenever a user completes reading a piece of information, the information is segmented into text to obtain at least one text block, and the at least one text block is determined as at least one item of historically read information. In addition, in order to improve the accuracy of information recall, a historical embedding vector for each item of historically read information is generated through an embedded model, and each item of historically read information and the historical embedding vector of each item of historically read information are stored in the second database for subsequent use.

[0221] In some embodiments of the present application, the second database may be an ES index library.

[0222] In some embodiments of the present application, information that has been read by a user can be obtained, and a second database can be constructed based on the information that has been read, so that the information in the second database is richer and more diverse, thereby providing the user with more and more comprehensive reading history information.

[0223] For example, the key information is as follows: Key information 1: the advantages of live streaming are helpful in increasing consumers' desire to buy; Key information 2: the disadvantages of live streaming involve lack of integrity, product quality issues, false advertising, and insufficient after-sales service. After recalling the second database, it is determined that key information 1 is read historical information.

[0224] In step 1004, information in the detailed information except the historically read information is determined as unread information.

[0225] In some embodiments of the present application, unread information refers to information that has not been read by the user.

[0226] For example, the key information is as follows: Key information 1, the advantages of live streaming are helpful in increasing consumers' desire to buy; Key information 2, the disadvantages of live streaming involve lack of integrity, product quality issues, false advertising, and insufficient after-sales service. After recalling the second database, it is determined that key information 1 is read historical information. At this time, it is determined that key information 2 is unread information in the detailed information.

[0227] In step 1005, the unread information is input into the fourth GPT model, and the opinion information of the unread information is output.

[0228] In some embodiments of the present application, considering the advantages of the GPT model such as powerful pre-training capability, high adaptability, ability to solve sentence coherence problems, extremely high language generation capability, self-training and improvement capability, and a wide range of application scenarios, the fourth GPT model can be a fine-tuned GPT model suitable for reading scenarios.

[0229] In some embodiments of the present application, the fourth GPT model is used to generate opinion information of unread information.

[0230] In some embodiments of the present application, the unread information and the fourth prompt word can be input into the fourth GPT model together, and the fourth GPT model will generate opinion information of the unread information according to the guidance of the fourth prompt word.

[0231] In some embodiments of the present application, the fourth prompt word is a prompt word automatically added by the electronic device for unread information, and the fourth prompt word is used to prompt the fourth GPT model to output opinion information of the unread information.

[0232] For example, the fourth prompt is “You are a text information processing expert, please read the 'input text', extract the viewpoint information in the text, and summarize and output it in a fluent and organized language.” At this time, the input text is unread information.

[0233] Exemplarily, the unread information is: live streaming with goods involves problems such as lack of integrity, product quality issues, false advertising, and insufficient after-sales service. The fourth GPT model summarizes the opinion information of the unread information as follows: live streaming with goods has defects in quality and service.

[0234] In some embodiments of the present application, a method for extracting opinion information of user's unread information in detail information based on a large model can be implemented, so that users can know which opinion information in the detail information they have not seen without reading it, which can facilitate users to view unread opinion information, save users' reading time, and improve users' reading efficiency.

[0235] Fig.11 is a structural block diagram of an information display device provided in an embodiment of the present application, such as Fig.11 As shown, the information display device 1100 may include: a receiving module 1101 and a display module 1102;

[0236] Receiving module 1101, used for receiving area selection input of the program interface;

[0237] The display module 1102 is used to display at least one item of viewpoint information related to the valid information when the area selected by the area selection input contains valid information.

[0238] In some embodiments of the present application, an area selection input is received on a program interface, and when the area selected by the area selection input contains valid information, at least one point of view information related to the valid information is displayed. It can be seen that in the embodiments of the present application, when a user is reading information on an electronic device, if he wants to know more relevant information about the currently read information, he only needs to perform a simple area selection input on the valid information of interest on the program interface where the currently read information is located, and at least one point of view information different from the point of view related to the valid information of interest can be obtained, thereby avoiding the tedious operation of manual search and manual summary by the user, and improving the efficiency of the user in reading information.

[0239] Optionally, in some embodiments of the present application, the valid information may include at least one of the following: information containing at least two viewpoints, information containing a single viewpoint, and declarative information without a viewpoint;

[0240] In a case where at least two items of viewpoint information related to the valid information are displayed, the at least two items of viewpoint information include at least two viewpoints.

[0241] Optionally, in some embodiments of the present application, the viewpoint information may include: the content of the viewpoint, and the viewpoint information may also include at least one of the following: information about the author of the viewpoint, information source of the viewpoint;

[0242] In the case where the viewpoint information includes information about the author of the viewpoint, the display module 1102 may also be used for at least one of the following: displaying the name of the author of the viewpoint, displaying the head portrait of the author of the viewpoint;

[0243] In the case that the opinion information includes the information source of the opinion, the display module 1102 may also be used to display the program icon of the source application of the opinion.

[0244] Optionally, in some embodiments of the present application, the display module 1102 may be specifically used to display at least one information card; wherein each information card includes at least one item of viewpoint information of a viewpoint.

[0245] Optionally, in some embodiments of the present application, the receiving module 1101 may also be used to receive an information selection input of one of the at least one item of opinion information;

[0246] The display module 1102 may also be configured to display detailed information of the viewpoint information selected by the information selection input in response to the information selection input.

[0247] Optionally, in some embodiments of the present application, the display module 1102 may be specifically used to display an information interface corresponding to an information source of the opinion information selected by the information selection input; or, to update the opinion information selected by the information selection input to detailed information of the opinion information.

[0248] Optionally, in some embodiments of the present application, the information display device 1100 may further include:

[0249] A processing module is used to input the effective information into a first generative pre-trained transformer (GPT) model and output at least one keyword of the effective information; input the at least one keyword into an embedded model and output a keyword embedding vector of each keyword; obtain at least one reference information matching the effective information from a first database according to each keyword and each keyword embedding vector; wherein the first database includes: at least one reference information and a reference embedding vector for each reference information; determine at least one reference information matching the effective information as opinion information related to the effective information; input the opinion information related to the effective information into a second GPT model and output the opinion type of each opinion information.

[0250] Optionally, in some embodiments of the present application, the processing module can be specifically used to calculate the content similarity between each keyword and each reference information in the first database; calculate the vector similarity between each keyword embedding vector and each reference embedding vector in the first database; for each keyword, generate a first set for all reference information with content similarity greater than a first threshold, and generate a second set for all reference information with vector similarity greater than a second threshold; take the union of the first set and the second set to obtain a third set; wherein the reference information in the third set is reference information that matches the valid information.

[0251] Optionally, in some embodiments of the present application, the processing module can also be used to obtain at least one item of information from at least one information application; perform text segmentation on each item of information to obtain at least one text block for each item of information; determine the at least one text block as at least one item of reference information; input the at least one item of reference information into an embedded model, and output a reference embedding vector for each item of reference information; and store each item of reference information and the reference embedding vector of each item of reference information in a first database.

[0252] Optionally, in some embodiments of the present application, the display module 1102 may also be used to display a viewpoint viewing angle control;

[0253] The receiving module 1101 may also be used to receive a control input of the viewpoint viewing angle control;

[0254] The display module 1102 may be specifically configured to display at least one item of viewpoint information related to the valid information in response to the control input of the control.

[0255] Optionally, in some embodiments of the present application, the receiving module 1101 may also be used to receive a control input for an unread information control;

[0256] The display module 1102 may also be configured to display view information of unread information in the detail information in response to the control input of the control.

[0257] Optionally, in some embodiments of the present application, the information display device 1100 may further include:

[0258] A processing module is used to input the detailed information into a third GPT model and output at least one key point information of the detailed information; input the at least one key point information into an embedded model and output a key point embedding vector for each key point information; obtain the historical read information in the detailed information from a second database according to each key point embedding vector; wherein the second database includes: at least one historical read information and a historical embedding vector for each historical read information; determine the information in the detailed information other than the historical read information as unread information; input the unread information into a fourth GPT model and output the opinion information of the unread information.

[0259] Optionally, in some embodiments of the present application, the area selection input may include at least one of the following: fingertip touch input and knuckle touch input.

[0260] Optionally, in some embodiments of the present application, when the area selection input includes the knuckle touch input, the knuckle touch input may include an input of tapping the screen with the knuckles and circling an area along a reference direction from the tapping position.

[0261] The electronic device in the embodiments of the present application may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a mobile Internet device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. It may also be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., and the embodiments of the present application are not specifically limited.

[0262] The electronic device in the embodiment of the present application may be a terminal with an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0263] The electronic device provided in the embodiment of the present application can achieve Figures 1 to 10 To avoid repetition, the various processes implemented by the method embodiment will not be described again here.

[0264] Alternatively, if Fig.12 As shown, an embodiment of the present application further provides an electronic device 1200, including a processor 1201 and a memory 1202, wherein the memory 1202 stores programs or instructions that can be executed on the processor 1201, and when the program or instructions are executed by the processor 1201, the various steps of the above-mentioned information display method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not described here.

[0265] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0266] Fig.13 It is a schematic diagram of the hardware structure of an electronic device provided in various embodiments of the present application.

[0267] The electronic device 1300 includes but is not limited to: a radio frequency unit 1301, a network module 1302, an audio output unit 1303, an input unit 1304, a sensor 1305, a display unit 1306, a user input unit 1307, an interface unit 1308, a memory 1309, a processor 1310 and other components.

[0268] Those skilled in the art will appreciate that the electronic device 1300 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 1310 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Fig.13 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0269] The user input unit 1307 is used to receive an area selection input on the program interface;

[0270] The display unit 1306 is configured to display at least one item of viewpoint information related to the valid information when the area selected by the area selection input contains valid information.

[0271] In some embodiments of the present application, when a user is reading information on an electronic device and wants to know more relevant information about the currently read information, the user only needs to make a simple area selection input for the valid information of interest on the program interface where the currently read information is located, and at least one opinion information that is different from the opinion related to the valid information of interest can be obtained, thereby avoiding the tedious operations of manual search and manual summary by the user and improving the efficiency of the user in reading information.

[0272] Optionally, in some embodiments of the present application, the valid information includes at least one of the following: information containing at least two viewpoints, information containing a single viewpoint, and declarative information without a viewpoint;

[0273] In a case where at least two items of viewpoint information related to the valid information are displayed, the at least two items of viewpoint information include at least two viewpoints.

[0274] Optionally, in some embodiments of the present application, the viewpoint information includes: the content of the viewpoint, and the viewpoint information also includes at least one of the following: information about the author of the viewpoint, information source of the viewpoint;

[0275] In the case where the viewpoint information includes information about the author of the viewpoint, the display unit 1306 is further configured to display the name of the author of the viewpoint and the head portrait of the author of the viewpoint;

[0276] In the case that the opinion information includes the information source of the opinion, the display unit 1306 is further configured to display the program icon of the source application of the opinion.

[0277] Optionally, in some embodiments of the present application, the display unit 1306 is specifically configured to display at least one information card; wherein each information card includes at least one item of viewpoint information of a viewpoint.

[0278] Optionally, in some embodiments of the present application, the user input unit 1307 is further configured to receive an information selection input for one of the at least one item of opinion information;

[0279] The display unit 1306 is further configured to display detailed information of the viewpoint information selected by the information selection input in response to the information selection input.

[0280] Optionally, in some embodiments of the present application, the display unit 1306 is specifically used to display an information interface corresponding to the information source of the opinion information selected by the information selection input; or, to update the opinion information selected by the information selection input to detailed information of the opinion information.

[0281] Optionally, in some embodiments of the present application, the processor 1310 is used to input the effective information into a first generative pre-trained transformer GPT model, and output at least one keyword of the effective information; input the at least one keyword into an embedded model, and output a keyword embedding vector of each keyword; according to each keyword and each keyword embedding vector, obtain at least one reference information matching the effective information from a first database; wherein the first database includes: at least one reference information and a reference embedding vector for each reference information; determine at least one reference information matching the effective information as opinion information related to the effective information; input the opinion information related to the effective information into a second GPT model, and output the opinion type of each opinion information.

[0282] Optionally, in some embodiments of the present application, the processor 1310 is specifically used to calculate the content similarity between each keyword and each reference information in the first database; calculate the vector similarity between each keyword embedding vector and each reference embedding vector in the first database; for each keyword, generate a first set for all reference information whose content similarity is greater than a first threshold, and generate a second set for all reference information whose vector similarity is greater than a second threshold; take the union of the first set and the second set to obtain a third set; wherein the reference information in the third set is reference information that matches the valid information.

[0283] Optionally, in some embodiments of the present application, the processor 1310 is further used to obtain at least one item of information from at least one information application; perform text segmentation on each item of information to obtain at least one text block for each item of information; determine the at least one text block as at least one item of reference information; input the at least one item of reference information into an embedded model, and output a reference embedding vector for each item of reference information; and store each item of reference information and the reference embedding vector of each item of reference information in a first database.

[0284] Optionally, in some embodiments of the present application, the display unit 1306 is further configured to display a viewpoint viewing angle control;

[0285] The user input unit 1307 is further used to receive a control input of the viewpoint viewing angle control;

[0286] The display unit 1306 is specifically configured to display at least one item of viewpoint information related to the valid information in response to the control input of the control.

[0287] Optionally, in some embodiments of the present application, the user input unit 1307 is further used to receive a control input for an unread information control;

[0288] The display unit 1306 is further configured to display the view information of the unread information in the detailed information in response to the control input of the control.

[0289] Optionally, in some embodiments of the present application, the processor 1310 is further used to input the detailed information into a third GPT model, and output at least one key point information of the detailed information; input the at least one key point information into an embedded model, and output a key point embedding vector for each key point information; obtain historical read information in the detailed information from a second database based on each key point embedding vector; wherein the second database includes: at least one historical read information and a historical embedding vector for each historical read information; determine the information in the detailed information other than the historical read information as unread information; input the unread information into a fourth GPT model, and output opinion information of the unread information.

[0290] Optionally, in some embodiments of the present application, the area selection input includes at least one of the following: fingertip touch input and knuckle touch input.

[0291] Optionally, in some embodiments of the present application, when the area selection input includes the knuckle touch input, the knuckle touch input includes an input of tapping the screen with the knuckles and circling an area along a reference direction from the tapping position.

[0292] It should be understood that in the embodiment of the present application, the input unit 1304 may include a graphics processor (Graphics Processing Unit, GPU) 13041 and a microphone 13042, and the graphics processor 13041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 1306 may include a display panel 13061, and the display panel 13061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 1307 includes a touch panel 13071 and at least one of other input devices 13072. The touch panel 13071 is also called a touch screen. The touch panel 13071 may include two parts: a touch detection device and a touch controller. Other input devices 13072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0293] The memory 1309 can be used to store software programs and various data. The memory 1309 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1309 may include a volatile memory or a non-volatile memory, or the memory 1309 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 1309 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0294] The processor 1310 may include one or more processing units; optionally, the processor 1310 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1310.

[0295] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned information display method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0296] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0297] An embodiment of the present application also provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned information display method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0298] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0299] An embodiment of the present application also provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned information display method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0300] It should be noted that, in this article, the term "comprises", "includes" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0301] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for enabling a terminal (such as a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0302] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An information display method, characterized in that: include: Receive area selection input for the program interface; In the case where the area selected by the area selection input contains valid information, at least one item of viewpoint information related to the valid information is displayed.

2. The method according to claim 1, characterized in that The valid information includes at least one of the following: information containing at least two viewpoints, information containing a single viewpoint, and declarative information without a viewpoint; In a case where at least two items of viewpoint information related to the valid information are displayed, the at least two items of viewpoint information include at least two viewpoints.

3. The method according to claim 1, characterized in that The opinion information includes: the content of the opinion, and the opinion information also includes at least one of the following: the author information of the opinion, the information source of the opinion; In the case where the opinion information includes information about the author of the opinion, the method further includes at least one of the following: displaying the name of the author of the opinion, displaying the head portrait of the author of the opinion; In the case that the opinion information includes the information source of the opinion, the method further comprises: displaying a program icon of an application program that is the source of the opinion.

4. The method according to claim 1, characterized in that: The displaying of at least one item of viewpoint information related to the valid information includes: Display at least one information card; Each information card includes at least one item of viewpoint information of a viewpoint.

5. The method according to claim 1, characterized in that After displaying at least one item of viewpoint information related to the valid information, the method further includes: receiving an information selection input of one of the at least one item of opinion information; In response to the information selection input, detailed information of the viewpoint information selected by the information selection input is displayed.

6. The method according to claim 5, characterized in that The display information selects the detailed information of the selected viewpoint information, including: Displaying an information interface corresponding to the information source of the opinion information selected by the information selection input; Alternatively, the viewpoint information selected by the information selection input is updated to the detailed information of the viewpoint information.

7. The method according to claim 1, characterized in that Before displaying at least one item of viewpoint information related to the valid information, the method further includes: Inputting the valid information into a first generative pre-trained transformer GPT model, and outputting at least one keyword of the valid information; Inputting the at least one keyword into the embedded model, and outputting a keyword embedding vector for each keyword; According to each keyword and each keyword embedding vector, obtaining at least one reference information matching the valid information from a first database; wherein the first database includes: at least one reference information and a reference embedding vector for each reference information; determining at least one reference information matching the valid information as opinion information related to the valid information; The opinion information related to the valid information is input into the second GPT model, and the opinion type of each opinion information is output.

8. The method according to claim 7, characterized in that The acquiring, from the first database according to each keyword and each keyword embedding vector, at least one reference information matching the valid information comprises: Calculating the content similarity between each keyword and each reference information in the first database; Calculating vector similarity between each keyword embedding vector and each reference embedding vector in the first database; For each keyword, all reference information with content similarity greater than a first threshold is generated into a first set, and all reference information with vector similarity greater than a second threshold is generated into a second set; Taking the union of the first set and the second set to obtain a third set; The reference information in the third set is reference information that matches the valid information.

9. The method according to claim 7, characterized in that: Before acquiring at least one reference information matching the valid information from the first database according to each keyword and each keyword embedding vector, the method further includes: Obtaining at least one piece of information from at least one information application; Performing text segmentation on each piece of information to obtain at least one text block for each piece of information; determining the at least one text block as at least one item of reference information; Inputting the at least one item of reference information into an embedded model, and outputting a reference embedding vector for each item of reference information; Each item of reference information and a reference embedding vector for each item of reference information are stored in a first database.

10. The method according to claim 1, characterized in that Before displaying at least one item of viewpoint information related to the valid information, the method further includes: Display the viewpoint perspective controls; Receiving a control input for the viewpoint perspective control; The displaying of at least one item of viewpoint information related to the valid information includes: In response to the control input, at least one item of viewpoint information related to the valid information is displayed.

11. The method according to claim 5, characterized in that After displaying the detailed information of the viewpoint information selected by the information selection input, the method further includes: Receiving control input for an unread information control; In response to the control input, the view information of the unread information in the detail information is displayed.

12. The method according to claim 11, characterized in that Before displaying the view information of the unread information in the detailed information, the method further includes: Input the detailed information into a third GPT model, and output at least one key point information of the detailed information; Inputting the at least one key point information into an embedded model, and outputting a key point embedding vector for each key point information; According to each key point embedding vector, the historical read information in the detailed information is obtained from a second database; wherein the second database includes: at least one item of historical read information and a historical embedding vector for each item of historical read information; Determine the information in the detailed information other than the historically read information as unread information; The unread information is input into a fourth GPT model, and opinion information of the unread information is output.

13. The method according to claim 1, characterized in that The area selection input includes at least one of the following: fingertip touch input and knuckle touch input.

14. The method according to claim 13, characterized in that In the case where the area selection input includes the knuckle touch input, the knuckle touch input includes an input of tapping the screen with a knuckle and circling an area along a reference direction from the tapping position.

15. An information display device, characterized in that: include: A receiving module, used for receiving an area selection input on a program interface; A display module is used to display at least one item of viewpoint information related to the valid information when the area selected by the area selection input contains valid information.

16. The device according to claim 15, characterized in that The valid information includes at least one of the following: information containing at least two viewpoints, information containing a single viewpoint, and declarative information without a viewpoint; In a case where at least two items of viewpoint information related to the valid information are displayed, the at least two items of viewpoint information include at least two viewpoints.

17. The device according to claim 15, characterized in that The opinion information includes: the content of the opinion, and the opinion information also includes at least one of the following: the author information of the opinion, the information source of the opinion; In the case where the viewpoint information includes information about the author of the viewpoint, the display module is further used for at least one of the following: displaying the name of the author of the viewpoint, displaying the head portrait of the author of the viewpoint; In the case that the opinion information includes the information source of the opinion, the display module is further used to display the program icon of the source application of the opinion.

18. The device according to claim 15, characterized in that The display module is specifically used to display at least one information card; wherein each information card includes at least one item of viewpoint information of a viewpoint.

19. The device according to claim 15, characterized in that The receiving module is further used to receive information selection input of one of the at least one item of opinion information; The display module is further configured to display detailed information of the viewpoint information selected by the information selection input in response to the information selection input.

20. The device according to claim 19, characterized in that The display module is specifically used to display the information interface corresponding to the information source of the viewpoint information selected by the information selection input; or to update the viewpoint information selected by the information selection input to the detailed information of the viewpoint information.

21. The device according to claim 15, characterized in that The device also includes: A processing module is used to input the effective information into a first generative pre-trained transformer (GPT) model and output at least one keyword of the effective information; input the at least one keyword into an embedded model and output a keyword embedding vector of each keyword; obtain at least one reference information matching the effective information from a first database according to each keyword and each keyword embedding vector; wherein the first database includes: at least one reference information and a reference embedding vector for each reference information; determine at least one reference information matching the effective information as opinion information related to the effective information; input the opinion information related to the effective information into a second GPT model and output the opinion type of each opinion information.

22. The device according to claim 21, characterized in that The processing module is specifically used to calculate the content similarity between each keyword and each reference information in the first database; calculate the vector similarity between each keyword embedding vector and each reference embedding vector in the first database; For each keyword, a first set is generated for all reference information whose content similarity is greater than a first threshold, and a second set is generated for all reference information whose vector similarity is greater than a second threshold; a third set is obtained by taking the union of the first set and the second set; wherein the reference information in the third set is the reference information that matches the valid information.

23. The device according to claim 21, characterized in that The processing module is also used to obtain at least one information item from at least one information application; perform text segmentation on each information item to obtain at least one text block for each information item; determine the at least one text block as at least one reference information; input the at least one reference information into the embedded model and output a reference embedding vector for each reference information; store each reference information and the reference embedding vector for each reference information in the first database.

24. The device according to claim 15, characterized in that The display module is also used to display the viewpoint viewing angle control; The receiving module is further used to receive a control input of the viewpoint viewing angle control; The display module is specifically used to display at least one item of viewpoint information related to the valid information in response to the control input of the control.

25. The device according to claim 19, characterized in that The receiving module is further used to receive a control input for the unread information control; The display module is further configured to display the view information of the unread information in the detailed information in response to the control input of the control.

26. The device according to claim 25, characterized in that The device also includes: A processing module is used to input the detailed information into a third GPT model and output at least one key point information of the detailed information; input the at least one key point information into an embedded model and output a key point embedding vector for each key point information; obtain the historical read information in the detailed information from a second database according to each key point embedding vector; wherein the second database includes: at least one historical read information and a historical embedding vector for each historical read information; determine the information in the detailed information other than the historical read information as unread information; input the unread information into a fourth GPT model and output the opinion information of the unread information.

27. The device according to claim 15, characterized in that The area selection input includes at least one of the following: fingertip touch input and knuckle touch input.

28. The device according to claim 15, characterized in that In the case where the area selection input includes the knuckle touch input, the knuckle touch input includes an input of tapping the screen with a knuckle and circling an area along a reference direction from the tapping position.

29. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the information display method according to any one of claims 1 to 14 are implemented.

Images