Text display method and device, electronic equipment and readable storage medium

Abstract

The invention discloses a text display method and device, electronic equipment and a readable storage medium, and belongs to the technical field of computers. The text display method comprises the following steps: receiving a first input of a user on a first page; in response to the first input, generating a first text according to first page content in the first page; and displaying a second text in combination with the first text, wherein the second text is a comment text corresponding to the first page content.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and specifically relates to a text display method, device, electronic device and readable storage medium. Background Art

[0002] Typically, when a user wants to comment on a merchant's product or service, the user can first trigger the electronic device to display a page of the merchant's products or services to be reviewed, and then enter the comment text the user requires on the page, so that the electronic device can display the comment text on the page, and thus the user can trigger the electronic device to publish the comment text the user requires on the page.

[0003] However, since the user may need to make multiple entries in the merchant's page of products or services to be reviewed before the electronic device can display the review text the user requires on the page, the user's operation in triggering the electronic device to publish the review text the user requires on the page is cumbersome and time-consuming, resulting in low convenience in the electronic device publishing review texts. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a text display method, device, electronic device and readable storage medium, which can reduce the number of input times required to display the comment text required by the user on the page, thereby simplifying the user's operation in the process of triggering the electronic device to publish the comment text required by the user on the page and reducing the time consumption, thereby improving the convenience of the electronic device in publishing the comment text.

[0005] In a first aspect, an embodiment of the present application provides a text display method, the method comprising: receiving a first input from a user on a first page; generating a first text based on first page content in the first page in response to the first input; and displaying a second text in combination with the first text, the second text being a comment text corresponding to the first page content.

[0006] In a second aspect, an embodiment of the present application provides a text display device, which may include: a receiving module, a processing module, and a display module. The receiving module is used to receive a first input from a user in a first page. The processing module is used to generate a first text according to the first page content in the first page in response to the first input received by the receiving module. The display module is used to display a second text in combination with the first text.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, which includes 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 method described in the first aspect are implemented.

[0008] 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 method described in the first aspect are implemented.

[0009] 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 method described in the first aspect.

[0010] 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 method described in the first aspect.

[0011] In an embodiment of the present application, the electronic device can generate a first text according to the first page content in the first page according to the first input of the user in the first page, and display a second text in combination with the first text, where the second text is a comment text corresponding to the first page content. Since the user can trigger the electronic device to generate a first text according to the first page content of the object to be commented on in the first page through a single input (i.e., the first input), and directly display the comment text corresponding to the first page content in combination with the first text, that is, display the comment text for the object to be commented on required by the user, without the need for the user to input multiple times, the number of inputs required to display the comment text required by the user in the first page can be reduced, thereby simplifying the user's operation in the process of triggering the electronic device to publish the comment text required by the user in the first page and reducing time consumption, thus improving the convenience of the electronic device in publishing comment texts. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is one of the flowcharts of the text display method provided in the embodiment of the present application;

[0013] Figure 2A This is one of the interface diagrams of the mobile phone interface provided in the embodiment of the present application;

[0014] Figure 2B This is the second interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0015] Figure 2C This is the third interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0016] Figure 3A This is the fourth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0017] Figure 3B This is the fifth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0018] Figure 4 This is the sixth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0019] Figure 5 This is the second flowchart of the text display method provided in the embodiment of the present application;

[0020] Fig. 6A This is the seventh interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0021] Figure 6B This is the eighth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0022] Figure 6C This is the ninth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0023] Fig.6D This is the tenth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0024] Fig. 7A This is the eleventh interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0025] Figure 7B This is the twelfth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0026] Figure 7C This is the thirteenth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0027] Figure 8 This is the fourteenth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0028] Fig. 9 This is the third flowchart of the text display method provided in the embodiment of the present application;

[0029] Fig.10 This is the fourth flowchart of the text display method provided in the embodiment of the present application;

[0030] Fig.11 This is the fifth flowchart of the text display method provided in the embodiment of the present application;

[0031] Fig.12 This is the fifteenth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0032] Fig.13 This is the sixteenth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0033] Fig.14This is the seventeenth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0034] Fig.15 This is the eighteenth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0035] Fig.16A This is the nineteenth interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0036] Fig. 16B This is the 20th interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0037] Fig.17 This is the sixth flowchart of the text display method provided in the embodiment of the present application;

[0038] Fig.18A This is the twenty-first interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0039] Fig.18B This is the twenty-second schematic diagram of the mobile phone interface provided in the embodiment of the present application;

[0040] Fig.18C This is the twenty-third interface diagram of the mobile phone interface provided in the embodiment of the present application;

[0041] Fig.19 is a structural schematic diagram of a text display device provided in an embodiment of the present application;

[0042] Fig. 20 This is one of the hardware structure diagrams of the electronic device provided in the embodiment of the present application;

[0043] Fig.21 This is the second schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0044] 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.

[0045] The following is an explanation of the professional terms involved in the embodiments of the present application.

[0046] 1. Prompt

[0047] Usually, Prompt is the Prompt of the model, which refers to a piece of text or question provided to the model, used to instruct the model to generate a specific answer or continue to generate text, etc. The Prompt should clearly indicate the task to be performed by the model, as well as the text parameters that the output answer or text must meet. The text parameters may include at least one of the following: word count range, sentiment tendency, etc.

[0048] Here, the above-mentioned tasks may include at least one of the following: answering questions, generating text, translating, extracting summaries, classifying, etc.

[0049] 2. Optical Character Recognition (OCR)

[0050] OCR refers to a technology that converts text on an image into machine-readable text. Electronic devices using OCR can analyze the pixels on an image, determine the text on the image, and convert the text into machine-readable text.

[0051] 3. Soft Fine-Tuning (SFT)

[0052] SFT refers to a technique used in the field of natural language processing and machine learning. SFT usually refers to a relatively small-scale and gentle parameter adjustment based on a pre-trained large language model. Its main purpose is to make the model better suited to specific tasks or fields.

[0053] 4. Other terms

[0054] The terms "first", "second", etc. in the specification and claims of the present 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 under appropriate circumstances, 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 with each other are in an "or" relationship.

[0055] The terms "at least one (item)", "at least one of" and the like in the specification and claims of the present application refer to any one, any two or a combination of more than two of the objects included therein. For example, at least one (item) of a, b, and c can be represented by: "a", "b", "c", "a and b", "a and c", "b and c" and "a, b and c", where a, b, and c can be single or multiple. Similarly, "at least two (items)" refers to two or more, and its meaning is similar to that of "at least one (item)".

[0056] It should be noted that the text 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, a mobile phone is used as the execution subject to execute the text display method as an example to illustrate the text display method provided in the embodiments of the present application.

[0057] The text display method, device, electronic device and readable storage medium provided in the embodiments of the present application are described in detail below with reference to the accompanying drawings through specific embodiments and their application scenarios.

[0058] The text display method provided in the embodiment of the present application can be applied to a scenario where a user wants to comment on a service, and can also be applied to a scenario where a user wants to comment on a product.

[0059] For example, in the case of a page displaying the services of merchant 1, the user directly inputs once in the page, which can trigger the electronic device to automatically obtain the description text of merchant 1, which is used to describe the services of merchant 1, and automatically display the comment text required by the user according to the description text, such as "Merchant 1 is a restaurant worth recommending, with authentic dishes, warm and thoughtful service attitude, and comfortable and pleasant dining environment. Both the taste and service are good" comment text 4, and directly display the comment text 4, so that the user only needs to click and input the publishing control in the page to trigger the electronic device to publish the comment text 4 in the page. It can be understood that since the user only needs to input once to trigger the electronic device to display the comment text 4 in the page, and input once to trigger the electronic device to publish the comment text 4 in the page, that is, the user only needs to input twice in the process of triggering the electronic device to publish the comment text required by the user in the page. Therefore, compared with the three examples in the above-mentioned related technologies, the operation of the user in the process of triggering the electronic device to publish the comment text required by the user in the page can be simplified, which is more cumbersome and time-consuming.

[0060] In another specific application scenario, assume that a user wants to use an electronic device to comment on a product of merchant 2 in a shopping application.

[0061] In an example of the related art, a user can first trigger an electronic device to display the page of the product 1 of the merchant 2, and then make multiple inputs in the text input box on the page to enter the comment text required by the user, such as "The fabric of product 1 is very good, it feels very comfortable, it does not deform after washing, the style is good, the overall size is large, and the quality and texture are good" comment text 5, so that the comment text 5 is displayed on the page, so that the user can click and input the publishing control on the page to trigger the electronic device to publish the comment text 5 on the page. However, since the user needs to make multiple inputs for each word in the comment text 5 on the page of the product 1 of the merchant 2 before entering the comment text 5 in the text input box to display the comment text 5 on the page, the operation of the user in the process of triggering the electronic device to publish the comment text required by the user on the page is relatively cumbersome and time-consuming.

[0062] However, in the embodiment of the present application, in the case of displaying the page of the product 1 of the merchant 2, the user directly inputs once in the page, which can trigger the electronic device to automatically obtain the description text of the product 1 of the merchant 2, the description text is used to describe the product 1 of the merchant 2, and automatically generate the comment text of the user's needs according to the description text, such as "the product 1 is very good overall, the style is casual, the quality is very good, the texture of the clothes is very good, and it is worth buying" comment text 8, and directly display the comment text 8, so that the user only needs to click and input the publishing control in the page to trigger the electronic device to publish the comment text 8 in the page. It can be understood that since the user only needs to input once to trigger the electronic device to display the comment text 8 in the page, and input once to trigger the electronic device to publish the comment text 8 in the page, that is, the user only needs to input twice in the process of triggering the electronic device to publish the comment text required by the user in the page, therefore, compared with the three examples in the above-mentioned related art, the operation of the user in the process of triggering the electronic device to publish the comment text required by the user in the page can be simplified, which is more cumbersome and time-consuming.

[0063] The present application embodiment provides a text display method. Figure 1 A flowchart of a text display method provided by an embodiment of the present application is shown. Figure 1 As shown, the text display method provided in the embodiment of the present application may include the following steps 101 to 103.

[0064] Step 101: An electronic device receives a first input from a user on a first page.

[0065] In some embodiments of the present application, the electronic device receives a first input from a user on the first page while displaying the first page.

[0066] In some embodiments of the present application, the first page may be a page in the first application, and the first page is used to comment on the goods or services of the merchant in the first application. The first page may include description information of the goods or services of one merchant, or may include description information of the goods or services of at least two merchants.

[0067] In some examples, when the first page includes a product or service of a merchant, the first page may be a review page for the product or service of the merchant. When the first page includes products or services of at least two merchants, the first page may be a review center page of the first application, and the review center page is used to display description information of the product or service of the merchant to be reviewed.

[0068] The first application may be any of the following: a service application, a shopping application, a social application, etc. Of course, the first application may also be other applications, which is not limited in the embodiments of the present application.

[0069] In some embodiments of the present application, when a user needs to comment on an object to be commented on, the user can trigger the electronic device to display a first page, so that the user can make a first input on the first page.

[0070] In the embodiment of the present application, the first input is used to display the comment text of the object to be commented on in the first page.

[0071] The object to be reviewed may be at least one of a merchant, a product, and a service in the first page.

[0072] Exemplarily, the above-mentioned first input includes but is not limited to: touch input of the user to the display screen of the electronic device 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 embodiment of the present invention. The specific gesture in the embodiment of the present application can be any one of a single-click gesture, a sliding gesture, a dragging gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double-press gesture, and a double-click gesture; the click input in the embodiment of the present application can be a single-click input, a double-click input, or any number of click inputs, etc., and can also be a long press input or a short press input.

[0073] For example, the first input mentioned above may be: a sliding input by the user on the first page, or a pressing input on the first page, etc.

[0074] Step 102: The electronic device generates a first text according to first page content in a first page in response to a first input.

[0075] Step 103: The electronic device displays the second text in combination with the first text.

[0076] In this embodiment of the present application, the second text is a comment text corresponding to the first page content.

[0077] In some embodiments of the present application, the electronic device may first obtain a picture of the first page (i.e., the first page content), which may be a picture of the entire page area or a partial page area of ​​the first page, and then use OCR technology to recognize the picture to obtain the above-mentioned first text.

[0078] In some embodiments of the present application, the first page content may be a page content corresponding to the object to be reviewed in the first page. The first page content may be a picture, text, etc.

[0079] In some embodiments of the present application, the first text is used to describe the object information of the object to be reviewed in the first page.

[0080] In some embodiments of the present application, the above-mentioned object information may include at least one of the following: the name of the object to be reviewed, the details of the object to be reviewed, the content to be evaluated of the object to be reviewed, etc.

[0081] Exemplarily, the content to be evaluated of the above-mentioned object to be reviewed may include at least one of the following: service quality, performance, customer service experience, cost performance, etc. Of course, the content to be evaluated may also include other content, which is not limited in the embodiment of the present application.

[0082] It can be understood that the second text is a review text for the object to be reviewed as required by the user.

[0083] In some embodiments of the present application, the electronic device may generate the second text based on the first text through an AI application, wherein the AI ​​application may be a default application in the electronic device or an application set by the user.

[0084] It should be noted that the above-mentioned AI applications can be understood as: applications associated with AI models, through which electronic devices input information (such as text, images, audio, video, etc.) to the AI ​​model associated with the application, so as to obtain information output by the AI ​​model through the application. Among them, the AI ​​model associated with the AI ​​application can be deployed on a cloud server or in an electronic device.

[0085] In some embodiments of the present application, the electronic device may display the second text in the first page, or the electronic device may display the second text in a floating manner on the first page.

[0086] In one example, when the electronic device displays the second text in the first page, the electronic device may display the second text in a blank area in the first page, or the electronic device may display the second text in a text input box in the first page.

[0087] In another example, when the electronic device displays the second text in a floating manner on the first page, the electronic device may display the second text in a floating manner on the object to be commented on, or the electronic device may directly display an interface in a floating manner on the first page and display the second text in the interface.

[0088] Two different examples are used below to illustrate a specific scheme for an electronic device to obtain the first text.

[0089] In a possible implementation of the present application, before "generating a first text according to the first page content in the first page" in the above step 102, the text display method provided in the embodiment of the present application may also include the following steps 201 to 203, and the above step 102 can be specifically implemented by the following step 102a.

[0090] Step 201: The electronic device displays a fourth control in response to a first input.

[0091] In the embodiment of the present application, the fourth control is used to determine the page content of the object to be reviewed in the first page.

[0092] In some embodiments of the present application, the electronic device may, in response to a first input, first display a second page on a first page, the second page including at least one application icon, so that a user clicks on an application icon of the above-mentioned AI-type application in the at least one application icon to enable the electronic device to display a first interface in a floating manner on the first page, the first interface being the interface of the AI-type application, and the first interface including a fourth control.

[0093] For example, a mobile phone is used as an example. Figure 2A As shown, the first page of the mobile phone (e.g., page 10) includes page content of the object to be reviewed (e.g., merchant 1), such as "merchant 1" page content 11, "overall review is great" page content 12, "taste is great" page content 13, "environment is OK" page content 14, and "service is great" page content 15, so that the user can make a first input in the page 10, for example, the user slides from the right edge of the page 10 to the center of the page 10; Figure 2BAs shown, after the user performs the sliding input, the mobile phone can display a second page on page 10, such as page 16, and the page 16 includes at least one application icon, such as application icon 17 of "Application 1", application icon 18 of "Application 2", application icon 19 of "Application 3", application icon 20 of "Application 4" and application icon 21 of "AI Assistant", so that the user can click on the application icon 21 of "AI Assistant" to input; Figure 2C As shown, after the user clicks and inputs the application icon 21 of the "AI assistant", the mobile phone can display a first interface, such as an "AI assistant" interface 22, and the "AI assistant" interface 22 includes a fourth control, such as a "screen recognition" control 23.

[0094] Step 202: The electronic device receives a third input from the user to a fourth control.

[0095] In the embodiment of the present application, the third input is used to trigger the fourth control.

[0096] Exemplarily, the third input includes but is not limited to: a user's touch input to the display screen of an electronic device 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 inputs, which can be determined according to actual usage requirements and are not limited in the embodiments of the present invention. The specific gesture in the embodiments of the present application can be any one of a single-click gesture, a sliding gesture, a dragging gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double-press gesture, and a double-click gesture; the click input in the embodiments of the present application can be a single-click input, a double-click input, or any number of click inputs, etc., and can also be a long press input or a short press input.

[0097] For example, the third input mentioned above may be: a click input of the fourth control by the user.

[0098] Step 203: In response to the third input, the electronic device determines all page contents in the first page as first page contents.

[0099] Step 102a: The electronic device generates a first text according to the first page content in the first page.

[0100] In some embodiments of the present application, the electronic device can take a screenshot of the first page to obtain the first page content (the first page content is a picture of the entire page area of ​​the first page), and then use OCR technology to recognize the first page content to obtain the above-mentioned first text.

[0101] In some embodiments of the present application, the electronic device may first cancel display of the above-mentioned first interface to display the first page, and obtain a picture of the entire page area of ​​the first page (i.e., the first page content), and then use OCR technology to recognize the first page content to obtain all the text in the first page, so that the electronic device can determine the entire text as the first text.

[0102] For example, combining Figure 2C ,like Figure 3A As shown, the user can make a third input to the "screen recognition" control 23, such as a click input; Figure 3B As shown, after the user clicks and inputs the "screen recognition" control 23, the mobile phone can first cancel the display of the "AI assistant" interface 22, that is, display page 10, and obtain the picture of the entire page area of ​​page 10 to obtain the first page content, and then use OCR technology to recognize the first page content to obtain all the texts in the entire page area of ​​the page 10, such as the "Merchant 1" text, the "Taste is great" text, the "Environment is OK" text and the "Service is great" text, so that the mobile phone can determine the "Merchant 1" text, the "Taste is great" text, the "Environment is OK" text and the "Service is great" text as the first text, that is, the first text includes the "Merchant 1" text 11, the "Overall review is great" text 12, the "Taste is great" text 13, the "Environment is OK" text 14 and the "Service is great" text 15.

[0103] In some embodiments of the present application, after obtaining the first text, the electronic device can directly generate the second text based on the above-mentioned AI application program and display the second text on the first page.

[0104] In some embodiments of the present application, the electronic device may directly display the second text in the first page, or suspend and display the first interface again on the first page, and display the second text in the first interface.

[0105] For example, combining Figure 3B ,like Figure 4 As shown, the mobile phone can display the second text in the "AI Assistant" interface 22, for example, "Merchant 1 is a restaurant worth recommending. The dishes are authentic, the service attitude is warm and thoughtful, and the dining environment is comfortable and pleasant. Both the taste and the service are good."

[0106] It can be seen that since the electronic device can display the fourth control, the user can input the fourth control once, which can trigger the electronic device to determine all the page content in the first page as the first page content, and directly generate the first text corresponding to the first page content, without the user having to enter all the text in the first page one by one to enter the first text. Therefore, the user's input in the process of the electronic device determining the second text can be simplified and the time consumption can be reduced.

[0107] In another possible implementation of the present application, in combination with Figure 1 ,like Figure 5 As shown, before "generating the first text according to the first page content in the first page" in the above step 102, the text display method provided in the embodiment of the present application may also include the following steps 204 to 206, and the above step 102 can be specifically implemented by the following step 102b.

[0108] Step 204: The electronic device displays a fifth control in response to the first input.

[0109] In the embodiment of the present application, the fifth control is used to determine the page content of the object to be reviewed.

[0110] In some embodiments of the present application, the electronic device may, in response to a first input, first display a second page on the first page, the second page including at least one application icon, so that the user can click on an application icon of the above-mentioned AI-type application in the at least one application icon to input, so that the electronic device can display a first interface in suspension on the first page, the first interface being the interface of the AI-type application, and the first interface including the above-mentioned fifth control, so that the user can make an input to the fifth control, such as a long press input, so that the electronic device can display the fifth control in the first interface.

[0111] Another example is given, such as Fig. 6A As shown, the mobile phone displays a first page, such as page 24, and the page 24 includes multiple objects, including objects to be commented on, for example, the multiple objects include merchant 2, merchant 3 and merchant 4, and the merchants 2, merchant 3 and merchant 4 include objects to be commented on (for example, merchant 3). The page 24 includes the page content of merchant 3, such as "Merchant 3" 25 and "Long Men's Down Jacket 2024 Autumn Warm and Comfortable Cotton Jacket Duck Down Outdoor Bread Jacket Ivory White XL" page content 26, so that the user can make a first input in the page 24, for example, the user can slide from the right edge of the page 24 to the center of the page 24; Figure 6BAs shown, after the user performs the sliding input, the mobile phone can display a second page on page 24, such as page 27, and the page 27 includes at least one application icon, such as application icon 28 of "Application 1", application icon 29 of "Application 2", application icon 30 of "Application 3", application icon 31 of "Application 4" and application icon 32 of "AI Assistant", so that the user can click on the application icon 32 of "AI Assistant" to input; Figure 6C As shown, after the user clicks the application icon 32 of the "AI Assistant" to input, the mobile phone can display the first interface, such as the "AI Assistant" interface 33, and the "AI Assistant" interface 33 includes a fifth control, such as the "Screen Recognition" control 34. Thus, the user can make an input to the "Screen Recognition" control 34, such as a long press input. Fig.6D As shown, after the user long presses the "screen recognition" control 34, the mobile phone can display a fifth control, such as a "circle selection" control 35, in the "AI assistant" interface 33. Of course, the mobile phone can also display a "full screen" control 36 in the "AI assistant" interface 33, and the "full screen" control 36 can have the same function as the "screen recognition" control 23 in the above embodiment, and the embodiment of the present application will not be repeated here.

[0112] Step 205: The electronic device receives a fourth input from the user on a fifth control and a first page area of ​​the first page.

[0113] In the embodiment of the present application, the fourth input is used to trigger the fifth control and select the page area where the object to be commented on is located.

[0114] Exemplarily, the fourth input includes but is not limited to: a user's touch input to the display screen of an electronic device 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 inputs, which can be determined according to actual usage requirements and are not limited in the embodiments of the present invention. The specific gesture in the embodiments of the present application can be any one of a single-click gesture, a sliding gesture, a dragging gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double-press gesture, and a double-click gesture; the click input in the embodiments of the present application can be a single-click input, a double-click input, or any number of click inputs, etc., and can also be a long press input or a short press input.

[0115] For example, the fourth input may include a first sub-input and a second sub-input, the first sub-input being: a click input of the user on the fifth control, and the second sub-input being a selection input of the user on the first page area in the first page.

[0116] Step 206: In response to the fourth input, the electronic device determines the page content in the first page area as the first page content.

[0117] Step 102b: The electronic device generates a first text according to the first page content.

[0118] In some embodiments of the present application, the electronic device may first take a screenshot of the first page, then extract a picture of a partial page area of ​​the first page (i.e., the first page content) from the screenshot, and then use OCR technology to recognize the first page content to obtain the above-mentioned first text.

[0119] In some embodiments of the present application, in response to the first sub-input, the electronic device may first cancel display of the first interface to display the first page, and then determine the first page area based on the user's second sub-input in the first page area, and obtain a picture of the first page area to obtain the first page content, so that the electronic device can use OCR technology to recognize the first page content to obtain the text in the first page area (for example, all text), so that the electronic device can determine the all text as the first text.

[0120] For example, combining Fig.6D ,like Fig. 7A As shown, the user can perform a first sub-input on the "circle selection" control 35, such as a click input; Figure 7B As shown, after the user clicks and inputs the "circle" control 35, the mobile phone can first cancel the display of the "AI assistant" interface 33, that is, display page 24, so that the user can perform a second sub-input, such as a sliding input in page 24; Figure 7C As shown, after the user performs a sliding input, the mobile phone can determine the first page area, such as page area 37, according to the input trajectory of the sliding input, and obtain a picture of the page area 37 to obtain the first page content, and then use OCR technology to identify the first page content to obtain the text in the page area 37, such as the "Merchant 3" text and the "Long Men's Down Jacket 2024 Autumn Warm and Comfortable Cotton Jacket Duck Down Outdoor Bread Jacket Ivory White XL" text, so that the mobile phone can determine the "Merchant 3" text and the "Long Men's Down Jacket 2024 Autumn Warm and Comfortable Cotton Jacket Duck Down Outdoor Bread Jacket Ivory White XL" text as the first text, that is, "Merchant 3" 25 and "Long Men's Down Jacket 2024 Autumn Warm and Comfortable Cotton Jacket Duck Down Outdoor Bread Jacket Ivory White XL" text 26.

[0121] It should be noted that Figure 7C The area enclosed by the dashed frame is used to indicate the page area 37, and the dashed frame may not be displayed in actual applications.

[0122] In some embodiments of the present application, after obtaining the first text, the electronic device may directly generate a second text based on the first text through the above-mentioned AI application program, and display the second text on the first page.

[0123] In some embodiments of the present application, the electronic device may directly display the second text in the first page, or suspend and display the first interface again on the first page, and display the second text in the first interface.

[0124] For example, combining Figure 7C ,like Figure 8 As shown, the mobile phone can display a second text in the "AI Assistant" interface 33, for example, a comment text "The clothes of Merchant 3 are very good overall, the style is casual, the quality is very good, the texture of the clothes is very good, and it is worth buying."

[0125] It can be seen that, since the electronic device can display the fifth control, on the one hand, the user makes the fourth input to the fifth control and the first page area, which can trigger the electronic device to determine the text in the first page area of ​​the first page as the first text, without the user having to input all the text in the first page area one by one. Therefore, the user's input in the process of the electronic device determining the first text can be simplified and the time consumption can be reduced; on the other hand, the electronic device will only determine the text in the first page area required by the user in the first page as the first text, and will not determine the text that the user does not require as the first text. Therefore, it can be ensured that the electronic device can accurately display the second text required by the user. In this way, the convenience of the electronic device to publish comment text can be improved while improving the accuracy of displaying the second text required by the user.

[0126] The specific scheme of the electronic device generating the second text is described below by way of example.

[0127] In some embodiments of the present application, Figure 1 ,like Fig. 9 As shown, before the above step 103, the text display method provided in the embodiment of the present application may further include the following steps 207 and 208.

[0128] Step 207: The electronic device determines the first type information and the first summary text of the first text.

[0129] In some embodiments of the present application, the first type of information may be any one of the following: “review” type information, “non-review” type information.

[0130] In some embodiments of the present application, the electronic device may determine the first type information and the first summary text of the first text through the above-mentioned AI application.

[0131] In some embodiments of the present application, the electronic device may first generate a prompt word text prompt (such as the first prompt word text in the following embodiments) based on the first text, and then input the prompt into the AI ​​model associated with the above-mentioned AI application, so that the AI ​​model can determine the first type of information and the first summary text of the first text based on the prompt word text prompt. Fig. 9 ,like Fig.10 As shown, the above step 207 can be specifically implemented through the following steps 207a and 207b.

[0132] Step 207a: The electronic device generates a first prompt word text based on the first text and the prompt word text template.

[0133] In the embodiment of the present application, the first prompt word text is used to instruct classification and summary extraction of the first text.

[0134] In some embodiments of the present application, the prompt word text template may be a template pre-set in the electronic device, or a template obtained from other electronic devices, or a template determined according to user input.

[0135] In some embodiments of the present application, the above-mentioned prompt word text template may also indicate text parameters for classification and summary extraction, and the text parameters may include format, output content, etc.

[0136] In some embodiments of the present application, the prompt word text template includes at least one text and one blank text, and the at least one text is used to indicate classification and summary extraction, so that the electronic device can replace the blank text with the first text to obtain the first prompt word text.

[0137] Exemplarily, the above prompt word text template may specifically be:

[0138] “Now you are an expert in extracting and classifying unstructured texts. You can judge from the [screen content] whether these texts belong to the category of “comments”. Please output the final [answer] according to the following requirements.

[0139] <Output requirements>

[0140] 1. Output in a fixed JavaScript Object Notation (JSON) format, and do not output anything else.

[0141] 2. [Screen content] When it belongs to the "Review" type, output: {"Type":"Review","Content":"Brief summary"};

[0142] [Screen content] If it does not belong to the "Review" type, output: {"Type":"Other","Content":"Brief summary"}.

[0143] Now let's start the actual practice. Please strictly follow the above <output requirements> to refine and classify the [screen content] and output the final [answer].

[0144]

Screen content

[0145]

answer

[0146] Example 1: Combination Figure 3B The electronic device can replace the blank text in the above prompt word text template with the first text, that is, "Merchant 1, the overall review is great, the taste is great, the service attitude is great, and the environment is OK" text to generate the first prompt word text.

[0147] Example 2: Combination Figure 7C The electronic device can replace the blank text in the above prompt word text template with the first text, such as the text "Merchant 3's long men's down jacket 2024 autumn warm and comfortable cotton jacket duck down outdoor jacket ivory white XL" to generate the first prompt word text.

[0148] Step 207b: The electronic device inputs the first prompt word text into the text processing model, and classifies and extracts a summary of the first text according to the first prompt word text through the text processing model to obtain first type information and a first summary text.

[0149] In some embodiments of the present application, the above text processing model may specifically be a model in a large model. Of course, the above text processing module may also be other models, which is not limited in the embodiments of the present application.

[0150] In some embodiments of the present application, the text processing model is an AI model associated with the AI ​​application program. The text processing model can be deployed in a server or an electronic device.

[0151] In which, when the text processing model is deployed on a server, the electronic device can send the first prompt word text to the server through an AI-type application, so that the server can input the first prompt word text into the text processing model, and obtain the first type of information and the first summary text output by the text processing model, and send the first type of information and the first summary text to the electronic device, so that the electronic device can obtain the first type of information and the first summary text.

[0152] When the text processing model is deployed on an electronic device, the electronic device can directly input the first prompt word text into the text processing model through an AI application to obtain the first type of information and the first summary text output by the text processing model.

[0153] In combination with the above example 1, after the electronic device inputs the first prompt word text into the text processing model, the text processing model can output {"Type":"Review"; "Content": The overall evaluation of Merchant 1 is good, including the taste of the dishes, service attitude and environment}.

[0154] In combination with the above example 2, after the electronic device inputs the first prompt word text into the text processing model, the text processing model can output {"Type":"Review";"Content":A long men's down jacket in size XL from Merchant 3, 2024 autumn warm and comfortable cotton jacket, duck down outdoor ivory white down jacket}.

[0155] As can be seen, since the electronic device can generate the first prompt word text for indicating the classification and summary extraction of the first text through the first text and the prompt word text template without user input, the user's operation in the process of obtaining the first prompt word text can be reduced and the time consumption can be reduced; and, since the electronic device can input the first prompt word text into the text processing model to obtain the accurate first type information and the first summary text through the text processing model, the accuracy of determining the first type information and the first summary text can be improved. In this way, the efficiency of determining the first type information and the first summary text can be improved while the accuracy of determining the first type information and the first summary text can be improved.

[0156] Step 208: When the first type information matches the preset type information, the electronic device generates a second text based on the first summary text.

[0157] In some embodiments of the present application, the above-mentioned preset type information may specifically be “review” type information.

[0158] It should be noted that the above “matching” can be understood as: being the same, or the similarity between the two being greater than or equal to a preset threshold.

[0159] In the embodiment of the present application, if the first type information matches the preset type information, it can be considered that the first text acquired by the electronic device is a text that can be used for comment, and therefore, the electronic device can generate a second text based on the first summary text.

[0160] In some embodiments of the present application, the electronic device may input the first summary text into an associated AI model through the above-mentioned AI application program to generate the second text through the AI ​​model, wherein the AI ​​model and the text processing model may be the same or different.

[0161] Thus, it can be known that since the electronic device can first determine the first type information and the first summary text of the first text, and determine whether the first type information matches the preset type information, it determines whether the first text can be used for commenting. In this way, when it is determined that the first type information matches the preset type information, that is, when it is determined that the first text can be used for commenting, the electronic device generates the second text based on the first summary text. Therefore, it can avoid the situation where a comment text that the user does not need is generated based on a text that cannot be used for commenting, thereby saving computing resources. In addition, since the electronic device can generate the second text based on the first summary text with fewer words, rather than generating the comment text based on the first text with more words, it can reduce the amount of calculation in generating the second text, thereby saving computing resources.

[0162] Of course, in order to make the generated second text meet the needs of the user, the electronic device can also instruct the user to input text parameters to constrain the second text output by the AI ​​model through the text parameters, so that the AI ​​model can output the second text that better meets the user's needs. Fig. 9 ,like Fig.11 As shown, before "generating the second text based on the first summary text" in the above step 208, the text display method provided in the embodiment of the present application may also include the following steps 301 to 303, and the above step 208 can be specifically implemented by the following step 208a.

[0163] Step 301: When first type information matches preset type information, the electronic device displays N first controls.

[0164] In the embodiment of the present application, each of the above-mentioned N first controls is used to determine a text parameter, and N is a positive integer.

[0165] In some embodiments of the present application, the above text parameters are used to indicate requirements that the second text needs to meet.

[0166] In some embodiments of the present application, the above-mentioned text parameters may include at least one of the following: word range, sentiment tendency, format, etc.

[0167] In some embodiments of the present application, the electronic device may display N first controls in the above-mentioned first interface.

[0168] Step 302: The electronic device receives a second input from a user on N first controls.

[0169] In the embodiment of the present application, M is a positive integer less than or equal to N.

[0170] In the embodiment of the present application, the second input is used to input text parameters required by the user.

[0171] Exemplarily, the second input includes, but is not limited to: a user's touch input to the display screen of an electronic device 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 inputs, which can be determined according to actual usage requirements and are not limited in the embodiments of the present invention. The specific gesture in the embodiments of the present application can be any one of a single-click gesture, a sliding gesture, a dragging gesture, a pressure recognition gesture, a long-press gesture, an area change gesture, a double-press gesture, and a double-click gesture; the click input in the embodiments of the present application can be a single-click input, a double-click input, or any number of click inputs, etc., and can also be a long-press input or a short-press input.

[0172] For example, the second input mentioned above is: a click input of the user on N first controls.

[0173] Step 303: The electronic device determines N text parameters corresponding to the second input in response to the second input.

[0174] In some embodiments of the present application, the electronic device may determine a text parameter for each input parameter of each first control according to the second input, so as to determine N text parameters.

[0175] The specific schemes for the electronic device to determine N text parameters will be described below with examples.

[0176] In some embodiments of the present application, the N first controls include a second control, the second control is used to determine a first text parameter, the first text parameter is a word range, the second control includes T input nodes, each input node corresponds to a word number, and T is a positive integer. The above step 302 can be specifically implemented by the following step 302a, and the above step 303 can be specifically implemented by the following step 303a.

[0177] Step 302a: The electronic device receives a second input from a user to a first input node among the T input nodes.

[0178] In the embodiment of the present application, the first input node corresponds to a first word number.

[0179] Step 302b: The electronic device determines the first word range as the first text parameter in response to the second input.

[0180] In the embodiment of the present application, a critical value of the first word number range is the first word number.

[0181] In some embodiments of the present application, the electronic device may use the first word number as a critical value and 0 as another critical value, thereby obtaining a first word number range.

[0182] For example, combining Figure 3B ,like Fig.12 As shown, the mobile phone can display N first controls, such as a second control 38 and a third control 39, in the "AI assistant" interface 22 when the first type information of the first text matches the preset type information, for example, when the first type information of the first text is "comment" type information. The first control 38 is used to determine the first text parameter, which is a word range. The second control 38 includes T input nodes, for example: "50" input node 40, "100" input node 41, "150" input node 42, "300" input node 43, "400" input node 44 and "500" input node 45. The third control 39 is used to determine the second text parameter, which is an emotional tendency, so that the user can make a second input to the first input node (for example, "100" input node 41), such as click input, so that the mobile phone can determine the first word range (0,100] as the word range of the second text.

[0183] It can be seen that since the electronic device can accurately determine the word range of the comment text (i.e., the second text) required by the user based on the user's second input to the first input node without the user inputting the word range, the user's operation can be simplified and the time spent in the process of the electronic device determining the word range of the comment text required by the user can be reduced.

[0184] In some embodiments of the present application, the N first controls include a third control, the third control is used to determine a second text parameter, the second text parameter is an emotional tendency, the third control includes Q input options, each input option corresponds to an emotional tendency, and Q is a positive integer. The above step 302 can be specifically implemented by the following step 302b, and the above step 303 can be specifically implemented by the following step 303b.

[0185] Step 302b: The electronic device receives a second input from the user for a first input option among the Q input options.

[0186] In the embodiment of the present application, the above-mentioned first input option corresponds to the first emotional tendency.

[0187] In some embodiments of the present application, the Q emotional tendencies may include at least one of the following: positive emotional tendency and negative emotional tendency. The positive emotional tendency may include at least one of the following: happiness, praise, good reviews, etc. The negative emotional tendency may include at least one of the following: anger, derogation, bad reviews, etc.

[0188] In some embodiments of the present application, the first emotional tendency may be any one of the following: a positive emotional tendency, a negative emotional tendency.

[0189] Step 303b: The electronic device determines the first emotional tendency as the second text parameter in response to the second input.

[0190] For example, combining Figure 3B and Fig.12 ,like Fig.13 As shown, the mobile phone can display N first controls, such as a second control 38 and a third control 39, when the first type information of the first text matches the preset type information, for example, when the first type information of the first text is "comment" type information. The second control 38 is used to determine the first text parameter, which is the word range. The third control 39 is used to determine the second text parameter, which is the emotional tendency. The third control 39 includes Q input options, such as a "generate bad review" input option 46 and a "generate good review" input option 47. The "generate bad review" input option 46 corresponds to a negative emotional tendency, and the "generate good review" input option 47 corresponds to a positive emotional tendency, so that the user can make a second input to the first input option (such as the "generate good review" input option 47), such as a click input, so that the mobile phone can determine the positive emotional tendency as the second text parameter.

[0191] It can be seen that since the electronic device can accurately determine the emotional tendency of the comment text (i.e., the second text) required by the user based on the user's second input to the first input option without the user inputting the emotional tendency, the user's operation can be simplified and the time spent in the process of the electronic device determining the emotional tendency of the comment text required by the user can be reduced.

[0192] Step 208a: The electronic device inputs the first summary text and N text parameters into a comment generation model, and generates a second text according to the first summary text and the N text parameters through the comment generation model.

[0193] In some embodiments of the present application, the comment generation model may be a model in a large model. Of course, the text processing module may also be other models, which is not limited in the embodiments of the present application.

[0194] In some embodiments of the present application, the comment generation model is an AI model associated with the AI ​​application. The comment generation model can be deployed in a server or an electronic device.

[0195] In which, when the comment generation model is deployed on a server, the electronic device can send the first summary text and N text parameters to the server through an AI-type application, so that the server can input the first summary text and N text parameters into the comment generation model, and obtain the second text output by the comment generation model, and send the second text to the electronic device, so that the electronic device can obtain the second text.

[0196] When the comment generation model is deployed on an electronic device, the electronic device can directly input the first summary text and N text parameters into the comment generation model through an AI application to obtain a second text output by the comment generation model.

[0197] In some embodiments of the present application, the electronic device may display the second text in the above-mentioned first interface.

[0198] For example, combining Fig.12 and Fig.13 ,like Fig.14 As shown, the mobile phone can input the first summary text and N text parameters (such as the first word range (0,100] and the first emotional tendency (i.e., positive emotional tendency)) into the comment generation model, and generate the object comment text according to the first summary text, the first word range (0,100] and the positive emotional tendency through the comment generation model, and display the second text in the "AI Assistant" interface 22, such as "Merchant 1 is a restaurant worth recommending. The dishes are authentic, the service attitude is warm and thoughtful, and the dining environment is comfortable and pleasant. Both the taste and the service are impressive." The second text 48.

[0199] It can be seen that since the electronic device can also display N first controls for determining N text parameters, the electronic device can determine the N text parameters required by the user based on the user's second input to the N first controls, and input the first summary text and the N text parameters into the comment generation model, thereby obtaining a second text that better meets the user's needs.

[0200] In some embodiments of the present application, before the above step 208a, the text display method provided by the embodiment of the present application may further include the following steps 401 to 403.

[0201] Step 401: The electronic device obtains a training summary text and at least one training text parameter while displaying the third page.

[0202] In some embodiments of the present application, the third page may be a page in any application in the electronic device, and the third page is used to comment on the goods or services of the merchants in the any application. The third page may include the goods or services of one merchant, or may include the goods or services of at least two merchants.

[0203] Among them, the arbitrary application program may be any of the following: a service application program, a shopping application program, a social application program, etc.

[0204] It can be understood that the number of the third page can be one or more.

[0205] In some embodiments of the present application, when a user uses an electronic device, the electronic device can monitor in real time whether the currently displayed page is the third page, so that when it is detected that the third page is displayed, the electronic device can obtain the training summary text and at least one training text parameter.

[0206] In the embodiment of the present application, the training summary text is generated from the page content of the comment object in the third page.

[0207] It should be noted that, for the description of the electronic device acquiring the training summary text, reference may be made to the specific description of the electronic device acquiring the first summary text in the above embodiment, which will not be repeated herein in the embodiment of the present application.

[0208] In some embodiments of the present application, the number of the above training summary texts may be one or more.

[0209] In some embodiments of the present application, the above-mentioned training text parameters are used to indicate the requirements that the training review text needs to meet.

[0210] The at least one training text parameter may include at least one of the following: word range, sentiment tendency, format, etc.

[0211] In some embodiments of the present application, a training prompt word text template may be pre-set in the electronic device, and the training prompt word text template includes at least one training text parameter, so that the electronic device can obtain the training prompt word text template to obtain at least one training text parameter.

[0212] Among them, at least one training text parameter in the training prompt word text template can be preset or determined according to the user's historical usage data. For example, if the user usually requires the word range of the comment text to be output to be (0,100], the electronic device can set the word range of the comment text required to be output in the training prompt word text template to be (0,100].

[0213] Exemplarily, the above training prompt word text template may specifically be:

[0214] "Now you are a senior review expert. Please output the final [answer] according to the following requirements.

[0215] <Output requirements>

[0216] 1. Carefully read the [Content Summary Text] on the product or merchant details page.

[0217] 2. Write a short review based on the [word range] selected by the user.

[0218] 3. Ensure that the review matches the user's specified [emotional tendency]: positive or negative.

[0219] 4. The review should include an evaluation of the product or service quality, performance, customer service experience, and cost-effectiveness (if applicable).

[0220] 5. Make sure your review is fair and objective, and reflects your insights and professional assessment as an expert.

[0221] Now let’s start the actual practice. Please strictly follow the above <output requirements> to output the final [answer].

[0222]

Content summary text

[0223] [Word range for evaluation]: [word range selected by the user];

[0224] [Sentimental tendency]: [positive / negative];

[0225]

answer

[0226] Step 402: The electronic device inputs the training summary text and at least one training text parameter into a preset model, and generates a training comment text according to the training summary text and the at least one training text parameter through the preset model.

[0227] In some embodiments of the present application, the electronic device can replace the blank text in the above-mentioned training prompt word text template with the training summary text to obtain the training prompt word text, and then input the training prompt word text into the preset model to obtain the training comment text output by the preset model.

[0228] Step 403: The electronic device trains a preset model according to the training comment text and the predetermined comment text to obtain a comment generation model.

[0229] In some embodiments of the present application, the above-mentioned predetermined comment text may be training comment text generated by other models based on the above-mentioned training summary text and at least one training text parameter, or may be comment text entered by a user, or may be a popular comment text in the above-mentioned third page.

[0230] In some embodiments of the present application, the electronic device may first calculate the target loss function of the training comment text and the predetermined comment text, and then train the preset model through the target loss function to obtain a comment generation model.

[0231] It can be seen that since the electronic device can also obtain the training summary text and at least one training text parameter during the user's daily browsing of the third page, and train the preset model based on the training summary text and at least one training text parameter, it is possible to obtain a comment generation model that meets the user's habitual needs, thereby increasing the probability of the comment generation model outputting a comment text that meets the user's needs during subsequent use.

[0232] In some embodiments of the present application, before the above step 403, the text display method provided by the embodiment of the present application may further include the following steps 501 and 502.

[0233] Step 501: The electronic device determines the popular comment text with the most likes from the L comment texts on the third page.

[0234] In the embodiment of the present application, each of the above L comment texts corresponds to a number of likes, and L is a positive integer.

[0235] In some embodiments of the present application, the electronic device can read the number of likes corresponding to each comment text in the third page to determine the number of likes corresponding to each comment text, so that the electronic device can accurately determine the popular comment text with the most corresponding likes.

[0236] Step 502: The electronic device determines the popular comment text as a predetermined comment text.

[0237] In the embodiment of the present application, since popular comment text can be understood as comment text with the largest number of likes, that is, comment text recognized by more users, that is, comment text required by more users, therefore, after the electronic device determines the popular comment text as a predetermined comment text and uses the predetermined comment text to train a preset model, the obtained comment generation model can meet the needs of more users, that is, the comment text output by the comment generation model meets the needs of more users.

[0238] It can be seen that since the electronic device can determine the popular comment text in the third page as the predetermined comment text used in the process of training the preset model, the comment generation model trained in this way can meet the needs of more users, and therefore, the probability of the comment generation model outputting comment text that meets user needs can be increased.

[0239] Of course, since the first type information may not match the preset type information, the electronic device may not generate text based on the first summary text, which will be explained below with examples.

[0240] In some embodiments of the present application, the above step 208 may also be replaced by the following step 209.

[0241] Step 209: When the first type information does not match the preset type information, the electronic device displays the first summary text.

[0242] In an embodiment of the present application, if the first type information does not match the preset type information, it can be considered that the first description information obtained by the electronic device may not be correct. Therefore, the electronic device can prompt the user that the first text obtained by the electronic device is incorrect by displaying the first summary text.

[0243] For example, combining Figure 3B ,like Fig.15 As shown, the mobile phone can display the first summary text in the "AI Assistant" interface 22, such as "Page content description: Merchant 1, the overall review is great, the taste is great, the environment is OK, and the service is great" first summary text 49.

[0244] It can be seen that, when the first type information does not match the preset type information, that is, when the first text obtained by the electronic device is incorrect, the electronic device can prompt the user that the first text obtained by the electronic device is incorrect by displaying the first summary text. Therefore, the user can quickly know that the first text obtained by the electronic device is incorrect, and trigger the electronic device again to obtain the correct text, that is, the text related to the object to be commented on, without waiting for a long time, thereby reducing the waiting time required before the trigger electronic device obtains the correct text.

[0245] In some embodiments of the present application, after the electronic device displays the second text, the user can input the second text so that the electronic device can display a copy control and a forward control, so that the user can input the copy control so that the electronic device can copy the second text; or, the user can input the forwarding control so that the electronic device can forward the second text to the contact required by the user.

[0246] For example, Fig.16AAs shown, the mobile phone displays a second text, such as "Merchant 1 is a restaurant worth recommending, with authentic dishes, warm and thoughtful service, and a comfortable and pleasant dining environment. Both the taste and the service are impressive." Text 50, so that the user can input the "Merchant 1 is a restaurant worth recommending, with authentic dishes, warm and thoughtful service, and a comfortable and pleasant dining environment. Both the taste and the service are impressive." Text 50, such as long pressing to input; Fig. 16B As shown, after the user performs a long press input, the mobile phone can display a copy control 51 and a forward control 52, so that the user can input the copy control 51 so that the mobile phone can copy the "Merchant 1 is a restaurant worth recommending, the dishes are authentic, the service attitude is warm and thoughtful, and the dining environment is comfortable and pleasant. Both the taste and the service are impressive." text 50; or, the user can input the forward control 52 so that the mobile phone can forward the "Merchant 1 is a restaurant worth recommending, the dishes are authentic, the service attitude is warm and thoughtful, and the dining environment is comfortable and pleasant. Both the taste and the service are impressive." text 50 to the contact required by the user.

[0247] An embodiment of the present application provides a text display method, in which an electronic device can generate a first text according to the first page content in the first page according to the first input of the user in the first page, and display a second text in combination with the first text, wherein the second text is a comment text corresponding to the first page content. Since the user can trigger the electronic device to generate a first text according to the first page content of the object to be commented on in the first page through a single input (i.e., the first input), and directly display the comment text corresponding to the first page content in combination with the first text, that is, display the comment text for the object to be commented on required by the user, without the user having to input multiple times, the number of inputs required to display the comment text required by the user in the first page can be reduced, thereby simplifying the user's operation in the process of triggering the electronic device to publish the comment text required by the user in the first page and reducing time consumption, thus improving the convenience of the electronic device in publishing comment texts.

[0248] In some embodiments of the present application, Figure 1 ,like Fig.17 As shown, after the above step 103, the text display method provided in the embodiment of the present application may further include the following steps 104 to 106.

[0249] Step 104: The electronic device receives a fifth input of a first picture and a fourth text parameter input by the user.

[0250] In the embodiment of the present application, the fifth input is used to input the picture and text parameters required by the user.

[0251] Exemplarily, the fifth input includes but is not limited to: a user's touch input to the display screen of an electronic device 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 inputs, which can be determined according to actual usage requirements and are not limited in the embodiments of the present invention. The specific gesture in the embodiments of the present application can be any one of a single-click gesture, a sliding gesture, a dragging gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double-press gesture, and a double-click gesture; the click input in the embodiments of the present application can be a single-click input, a double-click input, or any number of click inputs, etc., and can also be a long press input or a short press input.

[0252] For example, the fifth input may include a third sub-input and a fourth sub-input, the third sub-input being the user's selection input for the first picture, the third sub-input may include multiple sub-inputs, and the fourth sub-input being the user's input of a fourth text parameter.

[0253] Step 105: The electronic device generates a sixth text based on the first picture, the fourth text parameter, and the second text in response to the fifth input.

[0254] For example, combining Fig.14 ,like Fig.18A As shown, the mobile phone displays the text 48 "Merchant 1 is a restaurant worth recommending. The dishes are authentic, the service attitude is warm and thoughtful, and the dining environment is comfortable and pleasant. Both the taste and the service are impressive." in the "AI Assistant" interface 22, so that the user can make a third sub-input. For example, the user can first make an input to the more controls 53 in the "AI Assistant" interface 22, such as clicking to input; Fig.18B As shown, after the user clicks and inputs, the mobile phone can display a "Comment Photo" control 54 in the "AI Assistant" interface 22, so that the user can make another input to the "Comment Photo" control 54, such as clicking and inputting, so that the mobile phone can display multiple pictures, and then the user can select a first picture from the multiple pictures; Fig.18C As shown, the user can make a fourth sub-input, for example, input "requires you to comment and simplify based on the picture you just uploaded" text parameter 55 in the "AI Assistant" interface 22. In this way, the mobile phone can generate a third text based on the first picture, "requires you to comment and simplify based on the picture you just uploaded" text parameter 55 and "Merchant 1 is a restaurant worth recommending. The dishes are authentic, the service attitude is warm and thoughtful, and the dining environment is comfortable and pleasant. Both the taste and the service are impressive." text 48.

[0255] In some embodiments of the present application, the above step 105 can be specifically implemented through the following steps 105a and 105b.

[0256] Step 105a: The electronic device inputs the first picture, the fourth text parameter and the second text into the comment generation model in response to the fifth input, and generates a third text according to the first picture, the fourth text parameter and the second text through the comment generation model.

[0257] It should be noted that, for the instructions on how the electronic device generates a third text based on the first picture, the fourth text parameter and the second text through a comment generation model, reference can be made to the specific description of how the electronic device generates a second text based on the first summary text and N text parameters through a comment generation model in the above embodiment, and the embodiments of the present application will not be repeated here.

[0258] As can be seen, since the electronic device can generate the third text according to the first picture, the fourth text parameter and the second text through the comment generation model, the third text that meets the user's needs can be accurately generated.

[0259] Step 106: The electronic device displays the third text in the first page.

[0260] In some embodiments of the present application, the electronic device may display the third text in a blank area in the first page, or the electronic device may display the third text in the above-mentioned first interface.

[0261] It can be seen that since the electronic device can regenerate the third text based on the first picture, the fourth text parameter and the second text according to the user's fifth input without regenerating the comment text, the amount of calculation required to generate the third text can be reduced, thereby saving computing power resources.

[0262] The text display method provided in the embodiment of the present application can be executed by a text display device. In the embodiment of the present application, a text display device executing the text display method is taken as an example to illustrate the text display device provided in the embodiment of the present application.

[0263] Fig.19 FIG. 1 shows a schematic diagram of the structure of a text display device provided in an embodiment of the present application. Fig.19 As shown, the text display device 60 provided in the embodiment of the present application may include: a receiving module 61 , a processing module 62 and a display module 63 .

[0264] The receiving module 61 is used to receive a first input from a user in the first page. The processing module 62 is used to generate a first text according to the first page content in the first page in response to the first input received by the receiving module 61. The display module 63 is used to display a second text in combination with the first text generated by the processing module 62, where the second text is a comment text corresponding to the first page content.

[0265] An embodiment of the present application provides a text display device. Since the user can trigger the text display device to generate a first text according to the first page content of the object to be commented on in the first page through a single input (i.e., the first input), and directly display the comment text corresponding to the first page content in combination with the first text, that is, display the comment text for the object to be commented on required by the user, without the need for the user to make multiple inputs. Therefore, the number of inputs required to display the comment text required by the user in the first page can be reduced, thereby simplifying the user's operation in the process of triggering the text display device to publish the comment text required by the user in the first page and reducing the time consumption. In this way, the convenience of the text display device in publishing the comment text can be improved.

[0266] In a possible implementation, the processing module 62 is also used to determine the first type information and the first summary text of the first text before the display module 63 displays the second text in combination with the first text; and to generate the second text based on the first summary text when the first type information matches the preset type information.

[0267] In a possible implementation, the processing module 62 is specifically used to generate a first prompt word text based on the first text and the prompt word text template, and the first prompt word text is used to indicate classification and summary extraction of the first text; the first prompt word text is input into the text processing model, and the first text is classified and summarized according to the first prompt word text through the text processing model to obtain the first type of information and the first summary text.

[0268] In a possible implementation, the display module 63 is further used to display N first controls before the processing module 62 generates the second text based on the first summary text, each first control is used to determine a text parameter, and N is a positive integer. The receiving module 61 is further used to receive a second input from a user to the N first controls displayed by the display module 63. The processing module 62 is further used to determine N text parameters corresponding to the second input in response to the second input received by the receiving module 61. The processing module 62 is specifically used to input the first summary text and the N text parameters into the comment generation model, and generate the second text according to the first summary text and the N text parameters through the comment generation model.

[0269] In a possible implementation, the N first controls include a second control, the second control is used to determine a first text parameter, the first text parameter is a word range, the second control includes T input nodes, each input node corresponds to a word number, and T is a positive integer. The receiving module 61 is specifically used to receive a second input of a user to a first input node among the T input nodes, the first input node corresponds to a first word number. The processing module 62 is specifically used to determine the first word range as the first text parameter, and a critical value of the first word range is the first word number.

[0270] In a possible implementation, the N first controls include a third control, which is used to determine a second text parameter, which is an emotional tendency, and the third control includes Q input options, each of which corresponds to an emotional tendency, and Q is a positive integer. The receiving module 61 is specifically used to receive a second input from a user for a first input option among the Q input options, and the first input option corresponds to a first emotional tendency. The processing module 62 is specifically used to determine the first emotional tendency as the second text parameter.

[0271] In one possible implementation, the processing module 62 is further used to obtain a training summary text and at least one training text parameter before inputting the first summary text and N text parameters into the comment generation model, when the third page is displayed, and the training summary text is generated by the page content in the third page; and input the training summary text and at least one training text parameter into a preset model, and generate a training comment text according to the training summary text and the at least one training text parameter through the preset model; and, train the preset model according to the training comment text and the predetermined comment text to obtain a comment generation model.

[0272] In a possible implementation, the above-mentioned processing module 62 is also used to train the preset model according to the training comment text and the predetermined comment text to obtain the comment generation model, and then determine the popular comment text with the largest number of likes from the L comment texts in the comment page, each comment text corresponds to a number of likes, and L is a positive integer; and determine the popular comment text as the predetermined comment text.

[0273] In a possible implementation, the display module 63 is further configured to display the first summary text when the first type information does not match the preset type information.

[0274] In a possible implementation, the display module 63 is further configured to display a fourth control before the processing module 62 generates the first text according to the first page content in the first page. The receiving module 61 is further configured to receive a third input from a user to the fourth control displayed by the display module 63. The processing module 62 is further configured to determine, in response to the third input received by the receiving module 61, all page contents in the first page as the first page content.

[0275] In a possible implementation, the display module 63 is further configured to display a fifth control before the processing module 62 generates the first text according to the first page content in the first page. The receiving module 61 is further configured to receive a fourth input from a user regarding the fifth control displayed by the display module 63 and the first page area of ​​the first page. The processing module 62 is further configured to determine the page content in the first page area as the first page content in response to the fourth input received by the receiving module 61.

[0276] In a possible implementation, the receiving module 61 is further configured to receive a fifth input of a first picture and a fourth text parameter input by a user after the display module 63 displays the second text in combination with the first text. The processing module 62 is further configured to generate a third text based on the first picture, the fourth text parameter and the second text in response to the fifth input received by the receiving module 61. The display module 63 is further configured to display the third text generated by the processing module 62 in the first page.

[0277] In a possible implementation, the processing module 62 is specifically used to input the first picture, the fourth text parameter and the second text into a comment generation model, and generate a third text according to the first picture, the fourth text parameter and the second text through the comment generation model.

[0278] The text display device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices other than a terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile internet device (mobile internet device, MID), an augmented reality (augmentedreality, AR) / virtual reality (virtualreality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook or a personal digital assistant (personal digital assistant, PDA), etc., and can also be a server, a network attached storage (network attached storage, NAS), a personal computer (personal computer, PC), a television (television, TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0279] The text display device in the embodiment of the present application may be a device having 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.

[0280] The text display device provided in the embodiment of the present application can achieve Figure 1 to Figure 1 To avoid repetition, the various processes implemented in the method embodiment of 8 are not described here.

[0281] In some embodiments of the present application, Fig. 20 As shown, an embodiment of the present application further provides an electronic device 70, including a processor 71 and a memory 72, wherein the memory 72 stores programs or instructions that can be executed on the processor 71, and when the program or instructions are executed by the processor 71, the various process steps of the above-mentioned text display method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not described here.

[0282] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0283] Fig.21 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0284] The electronic device 100 includes but is not limited to components such as a radio frequency unit 101, a network module 102, an audio output unit 103, an input unit 104, a sensor 105, a display unit 106, a user input unit 107, an interface unit 108, a memory 109, and a processor 110.

[0285] Those skilled in the art will appreciate that the electronic device 100 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 110 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Fig.21 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.

[0286] The user input unit 107 is used to receive a first input from a user on a first page.

[0287] The processor 110 is configured to generate a first text according to first page content in a first page in response to a first input.

[0288] The display unit 106 displays the second text in combination with the first text.

[0289] An embodiment of the present application provides an electronic device. Since the user can trigger the electronic device to generate a first text according to the first page content of the object to be commented on in the first page through a single input (i.e., the first input), and directly display the comment text corresponding to the first page content in combination with the first text, that is, display the comment text for the object to be commented on required by the user, without the need for the user to input multiple times, the number of inputs required to display the comment text required by the user in the first page can be reduced, thereby simplifying the user's operations in the process of triggering the electronic device to publish the comment text required by the user in the first page and reducing the time consumption. In this way, the convenience of the electronic device in publishing the comment text can be improved.

[0290] In some embodiments of the present application, the processor 110 is used to determine the first type information and the first summary text of the first text before displaying the second text in combination with the first text; and generate the second text based on the first summary text when the first type information matches the preset type information.

[0291] In some embodiments of the present application, the processor 110 is specifically used to generate a first prompt word text based on the first text and the prompt word text template, and the first prompt word text is used to indicate the classification and summary extraction of the first text; and the first prompt word text is input into the text processing model, and the first text is classified and the summary is extracted according to the first prompt word text through the text processing model to obtain the first type of information and the first summary text.

[0292] In some embodiments of the present application, the display unit 106 is further used to display N first controls before the processor 110 generates the second text based on the first summary text, each requiring the control to be used to determine a text parameter, and N is a positive integer.

[0293] The user input unit 107 is further used to receive the second input of the user to the N first controls.

[0294] The processor 110 is further configured to determine, in response to the second input, N text parameters corresponding to the second input.

[0295] The processor 110 is specifically configured to input the first summary text and N text parameters into the comment generation model, and generate a second text according to the first summary text and the N text parameters through the comment generation model.

[0296] In some embodiments of the present application, the above-mentioned N first controls include a second control, which is used to determine a first text parameter, the first text parameter is a word range, and the second control includes T input nodes, each input node corresponds to a word number, and T is a positive integer.

[0297] The user input unit 107 is specifically configured to receive a second input from a user to a first input node among the T input nodes, where the first input node corresponds to a first word number.

[0298] The processor 110 is specifically configured to determine a first word number range as a first text parameter, wherein a critical value of the first word number range is a first word number.

[0299] In some embodiments of the present application, the above-mentioned N first controls include a third control, which is used to determine a second text parameter, and the second text parameter is an emotional tendency. The third control includes Q input options, each input option corresponds to an emotional tendency, and Q is a positive integer.

[0300] The user input unit 107 is specifically configured to receive a second input from a user for a first input option among the Q input options, where the first input option corresponds to a first emotional tendency.

[0301] The processor 110 is specifically configured to determine the first emotional tendency as the second text parameter.

[0302] In some embodiments of the present application, the processor 110 is further used to obtain a training summary text and at least one training text parameter before inputting the first summary text and N text parameters into the comment generation model, while displaying the third page, and the training summary text is generated by the page content in the third page; and input the training summary text and at least one training text parameter into a preset model, and generate a training comment text according to the training summary text and the at least one training text parameter through the preset model; and train the preset model according to the training comment text and the predetermined comment text to obtain a comment generation model.

[0303] In some embodiments of the present application, the processor 110 is also used to train a preset model based on training comment texts and predetermined comment texts to obtain a comment generation model, and to determine, from L comment texts in the comment page, a popular comment text with the largest number of likes, each comment text corresponding to a number of likes, and L is a positive integer; and determine the popular comment text as the predetermined comment text.

[0304] In some embodiments of the present application, the display unit 106 is further configured to display the first summary text when the first type information does not match the preset type information.

[0305] In some embodiments of the present application, the display unit 106 is further configured to display a fourth control before displaying the second text in combination with the first text.

[0306] The user input unit 107 is further configured to receive a third input from the user to the fourth control.

[0307] The processor 110 is further configured to, in response to the third input, determine all page contents in the first page as first page contents.

[0308] In some embodiments of the present application, the display unit 106 is further configured to display a fifth control before displaying the second text in combination with the first text.

[0309] The user input unit 107 is further used to receive a fourth input from the user on the fifth control and the first page area of ​​the first page.

[0310] The processor 110 is further configured to, in response to a fourth input, determine the page content in the first page area as the first page content.

[0311] In some embodiments of the present application, the user input unit 107 is further configured to receive a fifth input of a first picture and a fourth text parameter from a user after the display unit 106 displays the second text in combination with the first text.

[0312] The processor 110 is further configured to generate, in response to a fifth input, a third text based on the first image, the fourth text parameter, and the second text.

[0313] The display unit 106 is further configured to display a third text in the first page.

[0314] In some embodiments of the present application, the processor 110 is specifically used to input the first image, the fourth text parameter and the second text into a comment generation model, and generate a third text according to the first image, the fourth text parameter and the second text through the comment generation model.

[0315] It should be understood that in the embodiment of the present application, the input unit 104 may include a graphics processing unit (GPU) 1041 and a microphone 1042, and the graphics processor 1041 processes the image data of the static image 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 106 may include a display panel 1061, and the display panel 1061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 107 includes a touch panel 1071 and at least one of other input devices 1072. The touch panel 1071 is also called a touch screen. The touch panel 1071 may include two parts: a touch detection device and a touch controller. Other input devices 1072 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.

[0316] The memory 109 can be used to store software programs and various data. The memory 109 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 instruction required for at least one function (such as a sound playback function, a picture playback function, etc.), etc. In addition, the memory 109 may include a volatile memory or a non-volatile memory, or the memory 109 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 RAM (SRAM), a dynamic RAM (DRAM), a synchronous DRAM (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 rambus RAM (DRRAM). The memory 109 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0317] The processor 110 may include one or more processing units; optionally, the processor 110 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 110.

[0318] 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 text display method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0319] 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.

[0320] An embodiment of the present application further 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 text display method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0321] 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.

[0322] An embodiment of the present application 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 text display method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0323] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are 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 "comprise 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 methods and devices in the embodiments 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 reverse 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.

[0324] 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 a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0325] 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. A text display method, characterized in that: include: Receiving a first input from a user on a first page; In response to the first input, generating a first text according to the first page content in the first page; A second text is displayed in combination with the first text, where the second text is a comment text corresponding to the first page content.

2. The method according to claim 1, characterized in that Before displaying the second text in combination with the first text, the method further includes: Determining first type information and first summary text of the first text; In a case where the first type information matches preset type information, the second text is generated based on the first summary text.

3. The method according to claim 2, characterized in that The determining of the first type information and the first summary text of the first text includes: Based on the first text and the prompt word text template, generating a first prompt word text, wherein the first prompt word text is used to indicate classification and summary extraction of the first text; The first prompt word text is input into a text processing model, and the first text is classified and abstracted according to the first prompt word text by the text processing model to obtain the first type information and the first abstract text.

4. The method according to claim 2, characterized in that: Before generating the second text based on the first summary text, the method further includes: Display N first controls, each of which is used to determine a text parameter, and N is a positive integer; Receiving a second input from a user on the N first controls; In response to the second input, determining N text parameters corresponding to the second input; The step of generating the second text based on the first summary text comprises: The first summary text and the N text parameters are input into a comment generation model, and the second text is generated according to the first summary text and the N text parameters through the comment generation model.

5. The method according to claim 4, characterized in that The N first controls include a second control, the second control is used to determine a first text parameter, the first text parameter is a word range, the second control includes T input nodes, each input node corresponds to a word number, and T is a positive integer; The receiving a second input of the user to the N first controls includes: receiving the second input from the user to a first input node among the T input nodes, the first input node corresponding to a first word number; The determining N text parameters corresponding to the second input includes: A first word count range is determined as the first text parameter, and a critical value of the first word count range is the first word count.

6. The method according to claim 4, characterized in that The N first controls include a third control, the third control is used to determine a second text parameter, the second text parameter is a sentiment tendency, the third control includes Q input options, each input option corresponds to a sentiment tendency, and Q is a positive integer; The receiving a second input of the user to the N first controls includes: receiving the second input of the user for a first input option among the Q input options, wherein the first input option corresponds to a first emotional tendency; The determining N text parameters corresponding to the input parameters of the second input includes: The first emotional tendency is determined as the second text parameter.

7. The method according to claim 2, characterized in that The method further comprises: In a case where the first type information does not match the preset type information, the first summary text is displayed.

8. The method according to claim 1, characterized in that Before generating the first text according to the first page content in the first page, the method further includes: Displaying a fourth control; receiving a third input from a user to the fourth control; In response to the third input, all page contents in the first page are determined as the first page contents.

9. The method according to claim 1, characterized in that: Before generating the first text according to the first page content in the first page, the method further includes: Display the fifth control; receiving a fourth input from a user on the fifth control and the first page area of ​​the first page; In response to the fourth input, the page content in the first page area is determined as the first page content.

10. The method according to claim 1, characterized in that After displaying the second text in combination with the first text, the method further includes: receiving a fifth input of a first picture and a fourth text parameter input by a user; In response to the fifth input, generating a third text based on the first picture, the fourth text parameter and the second text; The third text is displayed in the first page.

11. A text display device, characterized in that: The text display device comprises: a receiving module, a processing module and a display module; The receiving module is used to receive a first input from a user on a first page; The processing module is configured to generate a first text according to the first page content in the first page in response to the first input received by the receiving module; The display module is used to display a second text in combination with the first text generated by the processing module, where the second text is a comment text corresponding to the first page content.

12. The device according to claim 11, characterized in that The processing module is further used to determine the first type information and the first summary text of the first text before the display module displays the second text in combination with the first text; and generate the second text based on the first summary text when the first type information matches the preset type information.

13. The device according to claim 12, characterized in that The processing module is specifically used to generate a first prompt word text based on the first text and the prompt word text template, wherein the first prompt word text is used to indicate classification and summary extraction of the first text; input the first prompt word text into a text processing model, and through the text processing model, classify and extract the first text according to the first prompt word text to obtain the first type information and the first summary text.

14. The device according to claim 12, characterized in that The display module is further used to display N first controls before the processing module generates the second text based on the first summary text, each first control is used to determine a text parameter, and N is a positive integer; The receiving module is further used to receive a second input from a user on the N first controls displayed by the display module; The processing module is further configured to determine N text parameters corresponding to the second input in response to the second input received by the receiving module; The processing module is specifically configured to input the first summary text and the N text parameters into a comment generation model, and generate the second text according to the first summary text and the N text parameters through the comment generation model.

15. The device according to claim 14, characterized in that The N first controls include a second control, the second control is used to determine a first text parameter, the first text parameter is a word range, the second control includes T input nodes, each input node corresponds to a word number, and T is a positive integer; The receiving module is specifically configured to receive the second input from the user to a first input node among the T input nodes, wherein the first input node corresponds to a first word number; The processing module is specifically configured to determine a first word range as the first text parameter, and a critical value of the first word range is the first word number.

16. The device according to claim 14, characterized in that The N first controls include a third control, the third control is used to determine a second text parameter, the second text parameter is a sentiment tendency, the third control includes Q input options, each input option corresponds to a sentiment tendency, and Q is a positive integer; The receiving module is specifically configured to receive the second input of the user for a first input option among the Q input options, wherein the first input option corresponds to a first emotional tendency; The processing module is specifically configured to determine the first emotional tendency as the second text parameter.

17. The device according to claim 12, characterized in that The display module is further configured to display the first summary text when the first type information does not match the preset type information.

18. The device according to claim 11, characterized in that The display module is further configured to display a fourth control before the processing module generates a first text according to the first page content in the first page; The receiving module is further used to receive a third input from a user to the fourth control displayed by the display module; The processing module is further configured to determine all page contents in the first page as the first page contents in response to the third input received by the receiving module.

19. The device according to claim 11, characterized in that The display module is further configured to display a fifth control before the processing module generates the first text according to the first page content in the first page; The receiving module is further used to receive a fourth input from a user on the fifth control displayed by the display module and the first page area of ​​the first page; The processing module is further configured to determine the page content in the first page area as the first page content in response to the fourth input received by the receiving module.

20. The device according to claim 11, characterized in that The receiving module is further configured to receive a fifth input of a first picture and a fourth text parameter input by a user after the display module displays the second text in combination with the first text; The processing module is further configured to generate a third text based on the first picture, the fourth text parameter and the second text in response to the fifth input received by the receiving module; The display module is further used to display the third text generated by the processing module in the first page.

21. An electronic device, characterized in that: The method 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 text display method according to any one of claims 1 to 10 are implemented.

22. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by a processor, the steps of the text display method according to any one of claims 1 to 10 are implemented.

Images