Content favoriting method and apparatus, computer device and storage medium

Abstract

A content favoriting method, executed by a computer device. The method comprises: displaying solution content in an application, the solution content comprising strategy information describing achieving a specified goal (202); in response to a favoriting operation for the solution content, displaying a favoriting result of adding the solution content to favorites of the application (204); and in response to a display trigger event for the solution content, displaying in the application an operation scheme extracted from the solution content, the operation scheme comprising an operation step extracted from the strategy information (206).

Description

Content collection method and device, computer device, and storage medium

[0001] Related Applications

[0002] The present application claims priority to the Chinese patent application No. 202411239713.3, filed on September 4, 2024, and entitled "Content collection method and device, computer device, and storage medium", the contents of which are hereby incorporated by reference in their entirety. TECHNICAL FIELD

[0003] The present application relates to the technical field of computer, in particular to a content collection method and device, computer device, and storage medium. BACKGROUND

[0004] With the development of computer technology, users can browse various contents through computer devices according to needs and collect the browsed contents, for example, when a user searches for a solution to a problem on an information flow app, the user often browses multiple contents in this process, and the user can evaluate the reliability of the contents by likes, comments, etc. under the contents, and collect the contents considered reliable.

[0005] In related technologies, the contents collected by users may be only contents produced by other users based on personal experience, and these contents often have the problem of poor readability. SUMMARY

[0006] Therefore, the present application provides a content collection method and device, computer device, computer readable storage medium, and computer program product.

[0007] In a first aspect, the present application provides a content collection method, executed by a computer device, the method comprising:

[0008] displaying a solution content in an application, the solution content comprising strategy information for achieving a specified target;

[0009] in response to a collection operation for the solution content, displaying a collection result of adding the solution content to a collection folder of the application; and

[0010] in response to a display triggering event for the solution content, displaying an operation scheme extracted from the solution content in the application, the operation scheme comprising an operation step extracted from the strategy information.

[0011] In a second aspect, the present application also provides a content collection device, the device comprising:

[0012] In the application program, a content display module is configured to display solution content, the solution content including strategy information for achieving a specified goal;

[0013] A content collection module is configured to, in response to a collection operation on the solution content, display a collection result of adding the solution content to a collection folder of the application program; and

[0014] An operation scheme display module is configured to, in response to a presentation trigger event on the solution content, display, in the application program, an operation scheme extracted from the solution content, the operation scheme including operation steps extracted from the strategy information.

[0015] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the content collection method in the above embodiments when executing the computer program.

[0016] In a fourth aspect, the present application further provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program implements the steps of the content collection method in the above embodiments when executed by a processor.

[0017] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and the computer program implements the steps of the content collection method in the above embodiments when executed by a processor.

[0018] The details of one or more embodiments of the present application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the present application will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the related art, the drawings needed to be used in the embodiments or the related art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0020] FIG. 1 is an application environment diagram of the content collection method in some embodiments;

[0021] FIG. 2 is a flowchart of the content collection method in some embodiments;

[0022] FIG. 3 is a display page diagram of the collection result in some embodiments;

[0023] FIG. 4 is a schematic diagram of a display page for adding content to a sub- collection in some embodiments;

[0024] FIG. 5 is a schematic diagram of an interactive process for displaying an operation scheme in some embodiments;

[0025] FIG. 6 is a schematic diagram of an interactive process for displaying an operation scheme in some other embodiments;

[0026] FIG. 7 is a schematic diagram of a page of an operation scheme in some embodiments;

[0027] FIG. 8 is a schematic diagram of a page of a data details page in yet some other embodiments;

[0028] FIG. 9 is a schematic diagram of a display process for collecting user comment content in some embodiments;

[0029] FIG. 10 is a schematic diagram of a display process for an operation scheme in yet some other embodiments;

[0030] FIG. 11 is a schematic diagram of a display page of statistical information and user feedback information in some embodiments;

[0031] FIG. 12 is a schematic diagram of a page of a collection page in some embodiments;

[0032] FIG. 13 is a schematic diagram of a page of a collection page in some other embodiments;

[0033] FIG. 14 is a schematic diagram of an interactive process for starting a companion mode for the operation scheme in some embodiments;

[0034] FIG. 15 is a schematic diagram of a page change in a companion mode in some embodiments;

[0035] FIG. 16 is a schematic diagram of a page change in a companion mode in some other embodiments;

[0036] FIG. 17 is a schematic diagram of a page for triggering an operation reminder in some embodiments;

[0037] FIG. 18 is a schematic diagram of a flow of a reminder time determination step in some embodiments;

[0038] FIG. 19 is a schematic diagram of a setting process for an event time of an event to which an operation step is directed in some embodiments;

[0039] FIG. 20 is a diagram for introducing technical principles involved in a content collection method in some embodiments;

[0040] FIG. 21 is a structural block diagram of a content collection device in some embodiments;

[0041] FIG. 22 is a diagram of an internal structure of a computer device in some embodiments;

[0042] FIG. 23 is a diagram of an internal structure of a computer device in some other embodiments; DETAILED DESCRIPTION

[0043] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0044] The content collection method provided by the embodiments of the present application can be applied in an application environment as shown in FIG. 1. The terminal 120 and the server 140 can be directly or indirectly connected through wired or wireless communication. For example, the terminal 120 can be indirectly connected with the server 140 through a wireless access point, or the terminal 120 can be directly connected with the server 140 through the Internet, which is not limited in the present application. The terminal 120 can load an application program, so that one or more solution contents can be displayed in the application program. The application program can be an information stream application, which can provide various contents for users to browse and provide a collection function, through which the users can collect the browsed contents. Of course, the application program can also be other application programs that can provide content browsing and collection functions, which are not limited in the present application. In addition, the form of the application program is not limited in the present application, which can be a parent application running in an operating system, or a sub-application running in the parent application, such as a small program, or a web page.

[0045] The terminal 120 can be, but is not limited to, various desktop computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 140 can be a standalone physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and basic cloud computing services such as big data and artificial intelligence platforms.

[0046] The execution subject of each step of the content collection method provided by the embodiments of the present application can be a computer device, which refers to an electronic device with data calculation, processing and storage capabilities. Taking the application environment shown in FIG. 1 as an example, the content collection method can be executed by the terminal 120 alone, or executed by the server 140 alone, or executed by the terminal 120 and the server 140 in cooperation, which is not limited in the present application.

[0047] With reference back to FIG. 1, taking the terminal 120 alone to perform the content collection method as an example, the terminal 120 can first display a solution content 121 in the application program, the solution content including strategy information for achieving a specified target, when the user performs a collection operation on the solution content, the terminal 120 can display a collection result 122 of adding the solution content to the collection folder of the application program, the terminal 120 can further display an operation solution 123 extracted from the solution content in the application program, the operation solution including operation steps extracted from the strategy information, in response to a display triggering event of the solution content.

[0048] In some embodiments, as shown in FIG. 2, a content collection method is provided, the method is performed by a computer device, the computer device can be the server 140 or the terminal 120 in FIG. 1, in the embodiments of the present application, taking the method applied to the terminal 120 in FIG. 1 as an example for description, including the following steps:

[0049] Step 202, display a solution content in an application program, the solution content including strategy information for achieving a specified target.

[0050] Wherein, the solution content is content including strategy information for achieving a specified target, the solution content can be specifically a guide for achieving a specified target. For example, achieving a specified target can specifically solve a specified problem, for example, assuming that the problem the user wants to solve is "how to perform train ticket grabbing", the solution content can be content including strategy information describing the process of solving the "train ticket grabbing" problem; for example, achieving a specified target can also be completing a specified matter, for example, the solution content can be a travel guide for traveling to a certain place.

[0051] Specifically, the terminal can load an application program, so that one or more solution contents can be displayed in the application program. For example, the solution content displayed by the terminal can be part of the solution content, the user can perform page jumping by clicking the solution content, so that the complete data of the solution content can be viewed on the page after jumping. For example, the terminal displays the solution content can be a complete data page of the solution content, the user can trigger the page to update and display the content not currently displayed by triggering operations such as screen sliding.

[0052] For example, when the terminal displays multiple solution contents in the application, the solution contents can be solution contents for solving the same problem, i.e., the solution contents can be contents containing similar strategy information, for example, the application can provide a search function through which the user can input a specific problem to be solved, and the terminal displays multiple solution contents that can solve the problem through the application. For example, when the terminal displays multiple solution contents through the application, the solution contents can be solution contents for solving different problems, for example, the terminal can display the latest updated solution contents on the home page of the application, and the solution contents are respectively for solving various different problems.

[0053] At step 204, in response to the collection operation for the solution content, a collection result of adding the solution content to the collection folder of the application is displayed.

[0054] The collection operation is an operation for adding the content to the collection folder. For example, the terminal can display a collection control on the display page of the solution content, and the collection operation can be a trigger operation for the collection control, for example, the trigger operation can be any one of a single-click operation, a double-click operation, or a press operation, and the like, which can be set as needed. It can be understood that the collection operation can also be other operations, such as a gesture operation, a voice operation, and the like.

[0055] Specifically, when the user wants to collect the displayed solution content, the terminal can trigger the collection operation for the solution content, at this time, if the collection is successful, the terminal displays a collection result of adding the solution content to the collection folder of the application, for example, the terminal can display a prompt information of "collection success" on the current display page of the solution content, if the collection fails, for example, the number of collected contents in the collection folder reaches the upper limit, the terminal displays a collection result indicating the collection failure, for example, the terminal can display a prompt information of "collection failure" on the current display page of the solution content. For example, referring to FIG. 3, it is a display page of the collection result in some embodiments, when the user clicks the collection control 302 in FIG. 3, a prompt information of "collection success" is displayed on the display page of the solution content.

[0056] For example, in the collection, the collected content can be classified, i.e., the collection includes multiple sub-collections, and different sub-collections are used to collect content of different themes or different types. When the terminal displays the collection result of adding the solution content to the collection of the application, the terminal can also display an operation portal for adding the solution content to a sub-collection. The terminal can further display multiple sub-collections in response to a triggering operation on the operation portal. When the user selects one of the sub-collections, the terminal adds the solution content to the sub-collection. For example, referring to FIG. 4, which is a display page for adding content to a sub-collection in some embodiments, the terminal can display an operation portal with a prompt information of “add to album” in addition to the prompt information of “collection success”. When the user clicks the operation portal, the terminal further displays multiple selectable sub-collections, such as ticket rush, house rental, and home appliance. When the user selects the sub-collection of “ticket rush”, the terminal can add the solution content to the sub-collection.

[0057] In step 206, in response to a display triggering event of the solution content, an operation scheme extracted from the solution content is displayed in the application. The operation scheme includes operation steps extracted from the strategy information.

[0058] Specifically, for the solution content added to the collection, an operation scheme can be extracted from the solution content. The operation scheme can include a scheme name and operation steps extracted from strategy information included in the solution content. For example, the terminal can extract the operation scheme from the solution content, e.g., the terminal detects a display triggering event of the solution content after successfully adding the solution content to the collection, and extracts the operation scheme from the solution content. In some other embodiments, the server can also extract the operation scheme from the solution content, e.g., the server extracts the operation scheme from the solution content when the solution content is generated, and stores the operation scheme in association with the content identifier of the solution content. The terminal can query the operation scheme corresponding to the solution content from the server after successfully adding the solution content to the collection, and detect a display triggering event of the solution content.

[0059] The terminal can display the operation scheme extracted from the solution content in the application in response to a display triggering event for the solution content, i.e., an event triggering the display of the solution content. For example, the terminal can display a floating page in the current page to display the operation scheme in the floating page. Alternatively, the terminal can jump from the current page to a browsing page of the solution content, and then display a floating page in the browsing page to display the operation scheme in the floating page. In this way, when the user triggers the floating page to close, the user can directly browse the original content of the solution content.

[0060] For example, the display triggering event can be an event triggered in the application. Alternatively, after the solution content is successfully collected, the user can browse the collection folder as needed and select the solution content, so that the terminal can detect the display triggering event for the solution content. In response to the display triggering event, the terminal displays the operation scheme extracted from the solution content. For example, referring to FIG. 6, when the user is browsing the collection folder, the user selects a solution content in the collection folder list to view, for example, the first solution content in the upper left corner. The terminal can enter the display page of the solution content, and display the operation scheme extracted from the solution content in the form of a floating window in the display page of the solution content. The operation scheme includes the scheme name and the operation steps extracted from the strategy information of the solution content.

[0061] Alternatively, when the user exits the application, the terminal can also display a floating window to display the operation scheme corresponding to the solution content in the floating window. When the user opens another application, the floating window can be displayed in the display page of the other application, so that the user can operate the operation steps in the operation scheme in the other application. The user can also directly reference the operation scheme in the other application. For example, the user can drag the floating window to an edit box in the other application. When the terminal detects that the position of the floating window is in the edit box, the terminal can copy the content in the floating window and then paste it into the edit box, so that the operation scheme can be directly displayed in the edit box. Further, when the edit box is an edit box in a conversation page, the user can further send the operation scheme in the edit box to other users in the conversation page. When the edit box is an edit box in a sharing page, the user can further share the operation scheme in the edit box in the social circle of the other application.

[0062] Optionally, the user can also perform position moving, enlarging or reducing, etc. operations on the floating window in the display interface of the other application. Further optionally, the user can also perform a preset triggering operation on the floating window to trigger entering the application program, so as to return to the application program, continue displaying the operation scheme in the application program, and further edit, collect or share the operation scheme to other applications, etc. operations in the application program. The preset triggering operation can be flexibly set according to requirements, for example, it can be clicking a preset control in the floating window, double-clicking the floating window, or triggering by voice, gesture, etc. control mode.

[0063] Optionally, after the collection is successful, the user can also perform a sharing operation on the solution content through the application program to share the solution content to other applications. When other users in the other applications view the shared solution content, a display triggering event for the solution content can be triggered, so that the operation scheme of the solution content is displayed on the terminal of the other user.

[0064] It can be understood that in some other embodiments, the timing of displaying the operation scheme by the terminal can be flexibly set according to requirements, and is not limited to detecting the display triggering event, which will be described below in combination with embodiments.

[0065] For example, the terminal can display the operation scheme after successfully adding the solution content to the collection folder. In specific applications, if the user needs to further add the solution content to a sub-collection folder, the operation scheme can be displayed after successfully adding the solution content to the sub-collection folder. For example, referring to FIG. 5, it is a display page of the operation scheme in some embodiments. When the user selects the "ticket grabbing" sub-collection folder from the multiple sub-collection folders displayed on the terminal, the operation scheme extracted from the solution content is displayed, which includes the scheme name "PC ticket grabbing" and four operation steps.

[0066] In some embodiments, the order of "displaying the operation scheme extracted from the solution content" and "displaying the collection result of adding the solution content to the collection folder of the application" can not be limited, and according to specific application scenarios, the operation scheme extracted from the solution content can be displayed first, and then the collection result of adding the solution content to the collection folder of the application is displayed; or the collection result of adding the solution content to the collection folder of the application is displayed first, and then the operation scheme extracted from the solution content is displayed. In this case, optionally, when the terminal displays "displaying the operation scheme extracted from the solution content", the "confirm collection" and "cancel collection" options can be provided at the same time, and when the user selects "confirm collection", then "display the collection result of adding the solution content to the collection folder of the application", so that the user can better understand the solution by displaying the operation scheme with better readability, and then decide whether to continue to collect the solution content. Of course, in some other embodiments, the terminal can also simultaneously "display the operation scheme extracted from the solution content" and "display the collection result of adding the solution content to the collection folder of the application", and the specific implementation can be flexibly limited as needed, which will not be described herein.

[0067] Exemplarily, on the display page of the operation scheme, the terminal can also display a collection control for the operation scheme, and the user can trigger an operation on the collection control. The terminal can add the operation scheme to the collection folder in response to the triggering operation.

[0068] In a specific implementation, the text content in the collected solution content can be analyzed by a large language model to extract the scheme name and operation steps. If there are pictures, the picture text in the collection content can be extracted by OCR, and the picture objects can be recognized by a target detection algorithm (SSD) to associate the picture to the text steps. The SSD algorithm first extracts features from the picture, and uses a convolutional neural network to extract feature information in the picture. Then, target detection is performed on feature maps of different scales to predict the bounding box and class of objects in the picture. For example, for a picture containing a ticket grabbing interface, the SSD can identify objects such as input boxes and buttons in the interface. When associated with the text steps, the identified objects are matched with the descriptions in the text steps, such as "click the ticket grabbing button" in the text steps. If the SSD identifies the ticket grabbing button in the picture, the picture is associated with the step.

[0069] Among them, the large language model (LLM) is a language model composed of artificial neural networks with many parameters (usually tens of billions of weights or more), trained on a large amount of unlabeled text using self-supervised learning or semi-supervised learning. It usually refers to deep learning models with parameter quantities in the order of billions or more. Large language models are general-purpose models that perform well in a wide range of tasks, rather than being trained for a specific task (such as sentiment analysis, named entity recognition, or mathematical reasoning). SSD (Single Shot MultiBox Detector) is a fast and accurate object detection algorithm that can detect multiple objects in a single inference for an image. SSD uses multiple scale feature maps to predict bounding boxes and classes, suitable for objects of different sizes. The present scheme is mainly applied to chat scenes, and a lighter dataset can be used to train the model. The MobileNet-SSD model pre-trained with the COCO dataset (a commonly used object detection dataset) can recognize 80 different object categories, such as people, bicycles, cars, dogs, etc.

[0070] In the content collection method described above, by displaying the solution content in the application program, the solution content includes strategy information for achieving the specified target, in response to the collection operation for the solution content, the collection result of adding the solution content to the collection folder of the application program is displayed, in response to the display trigger event for the solution content, the operation scheme extracted from the solution content is displayed in the application program, and the operation scheme includes the operation steps extracted from the strategy information. Since the displayed operation scheme includes the operation steps extracted from the strategy information, that is, the operation scheme is the content refined from the solution content, displaying the operation scheme can enable the user to better understand the collected content according to the clear steps contained in the operation scheme when collecting the content, thereby improving the readability and operability of the collected content.

[0071] In some embodiments, the content collection method of the present application further includes: corresponding to the operation scheme, displaying statistical information obtained by statistically analyzing user feedback information related to the operation scheme.

[0072] The operation scheme related user feedback information refers to information of user feedback on the operation scheme related solution content. The user feedback information can be one or more of user comment content, user like / dislike behavior, content forwarding, or user collection behavior. The user feedback information can include user positive feedback information and user negative feedback information. The user positive feedback information is used to represent a positive attitude of the user expressing approval, agreement, etc. on the operation scheme related solution content, and the user negative feedback information is used to represent a negative attitude of the user expressing disapproval, disagreement, etc. on the operation scheme related solution content. Taking the user comment content as an example, the user positive feedback information is positive user comment content, and the user negative feedback information is negative user comment content. For example, if the user comment content includes keywords such as “super”, “thank you”, exclamation mark, [heart] [rose] [happy] emoticons, etc. expressing degree, tone, and positive emotion, it can be considered as positive user comment content. If the comment includes keywords such as “completely”, “not at all”, exclamation mark, [vomit] [petrification] [angry] emoticons, etc. expressing degree, tone, and negative emotion, it can be considered as negative user comment content.

[0073] The operation scheme related solution content refers to solution content that can be extracted from the same or similar content as the operation scheme. The statistical information is information obtained by statistics. Optionally, the statistical information can be specific numerical information, such as the number of user comments, the number of collections, etc. Alternatively, the statistical information can also be information expressed in the form of a chart, such as a plurality of bar charts reflecting the number of various types of user feedback information from multiple dimensions.

[0074] Specifically, the terminal can also display statistical information at a position corresponding to the operation scheme in the display page of the operation scheme. The statistical information is obtained by statistics on the operation scheme related user feedback information. By displaying the statistical information, the user can have a more intuitive understanding of the operation scheme. Here, the position corresponding to the operation scheme refers to a position where the statistical information is displayed, which is a position related to the operation scheme, so that the user can intuitively feel that the statistical information is related to the operation scheme. For example, the position can be above the display position of the operation scheme and close to the display position of the operation scheme, or the position can be below the display position of the operation scheme and close to the display position of the operation scheme. The specific position can be flexibly set as needed.

[0075] For example, the operation scheme related user feedback information can include user feedback information for the solution content and user feedback information for the associated strategy content of the solution content, and the operation scheme extracted from the associated strategy content is the same or similar to the operation scheme extracted from the solution content.

[0076] In this embodiment, the statistical information obtained by displaying the statistical information of the user feedback information related to the operation scheme can intuitively display the reliability of the operation scheme, and facilitate the user to select the operation scheme.

[0077] In some embodiments, the user feedback information related to the operation scheme includes user positive feedback information related to the operation scheme and user negative feedback information related to the operation scheme; and displaying the statistical information obtained by statistically processing the user feedback information related to the operation scheme includes displaying a statistical quantity comparison relationship between the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme.

[0078] The statistical quantity comparison relationship is a relationship for quantitatively comparing the statistical information. By displaying the positive feedback statistical information and the negative feedback statistical information in the same display manner, the difference between the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme can be more intuitively reflected, and the reliability of the operation scheme can be reflected.

[0079] Specifically, in this embodiment, when the terminal displays the statistical information obtained by statistically processing the user feedback information related to the operation scheme, the positive feedback statistical information obtained by statistically processing the user positive feedback information related to the operation scheme and the negative feedback statistical information obtained by statistically processing the user negative feedback information related to the operation scheme can be displayed respectively. The positive feedback statistical information and the negative feedback statistical information are displayed in the same display manner, so that the statistical quantity comparison relationship between the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme can be displayed.

[0080] For example, referring to FIG. 7, the statistical quantity comparison relationship between the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme is displayed in the dashed box 702 in FIG. 7. The column chart corresponding to "useful" is the positive feedback statistical information obtained by statistically processing the user positive feedback information related to the operation scheme, and the column chart corresponding to "not useful" is the negative feedback statistical information obtained by statistically processing the user negative feedback information related to the operation scheme. The statistical quantity comparison relationship in FIG. 7 can clearly show that the user positive feedback information is significantly more than the user negative feedback information, that is, most users have a positive and approving attitude towards the operation scheme.

[0081] In the above embodiments, the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme can be statistically processed respectively, and the statistical quantity comparison relationship between the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme can be displayed, so that the reliability of the operation scheme can be more intuitively reflected.

[0082] In some embodiments, the method further comprises: displaying, in the application, operation scheme related user feedback information; wherein the operation scheme related user feedback information comprises user feedback information for the solution content and user feedback information for the associated policy content of the solution content, and the operation scheme extracted from the associated policy content is the same as or similar to the operation scheme extracted from the solution content.

[0083] Wherein the operation scheme extracted from the associated policy content is the same as or similar to the operation scheme extracted from the solution content, it can be considered that the associated policy content and the solution content can extract the same operation scheme, and thus the user feedback information for the associated policy content and the solution content can be considered as the user feedback information for the operation scheme.

[0084] In the embodiment, in addition to displaying the operation scheme extracted from the solution content, the terminal can also display operation scheme related user feedback information, wherein the user feedback information mainly refers to user comment content. For example, the user feedback information can be displayed on the same display page as the operation scheme, and the user can see more user feedback information by updating the display content of the page through screen sliding.

[0085] In other embodiments, the user feedback information and the operation scheme can be displayed on different pages, and an operation entry can be displayed on the display page of the operation scheme, and when the user clicks the operation entry, a new page can be entered, and the operation scheme related user feedback information can be displayed on the new page.

[0086] In other embodiments, when the terminal displays the operation scheme, the terminal can also display statistical information obtained by counting the operation scheme related user feedback information, and an operation entry can be displayed corresponding to the statistical information, and thus when the user clicks the operation entry, a new page can be displayed, and the operation scheme related user feedback information can be displayed on the new page. In this way, by first displaying the statistical information and guiding the user to view the user feedback information through the display of the operation entry, the flexibility of page display can be improved. For example, referring to FIG. 7, the display page of the operation scheme displays the "view detailed data" operation entry 704, and when the user clicks the operation entry 704, a new page can be displayed, and thus the user feedback information can be displayed on the new page.

[0087] In the embodiment, the operation scheme related user feedback information can also be displayed, and since the operation scheme related user feedback information not only contains user feedback information for the solution content, but also contains user feedback information for the associated policy content of the solution content, the feedback of the user for the operation scheme can be more comprehensive.

[0088] In some embodiments, the user feedback information is displayed on a data details page of the operation scheme, and the user feedback information related to the operation scheme is displayed, including: displaying positive feedback statistical information and negative feedback statistical information on the data details page; displaying user positive feedback information related to the operation scheme for obtaining the positive feedback statistical information corresponding to the positive feedback statistical information; and displaying user negative feedback information related to the operation scheme for obtaining the negative feedback statistical information corresponding to the negative feedback statistical information.

[0089] The positive feedback statistical information is information obtained by counting the user positive feedback information related to the operation scheme, which can be in the form of a specific numerical value (such as the number of user positive feedback comments) or expressed by a chart (such as a column chart) for intuitively presenting the positive attitude of the user to the operation scheme.

[0090] The negative feedback statistical information is information obtained by counting the user negative feedback information related to the operation scheme, which can be in the form of a specific numerical value (such as the number of user negative feedback comments) or expressed by a chart (such as a column chart) for intuitively presenting the negative attitude of the user to the operation scheme.

[0091] In the embodiment, the user feedback information is displayed on a data details page of the operation scheme, and the data details page and the operation scheme are displayed on different pages. The terminal can also display the positive feedback statistical information and the negative feedback statistical information on the data details page. In the data details page, the user positive feedback information related to the operation scheme for obtaining the positive feedback statistical information can also be displayed at a position corresponding to the positive feedback statistical information, so that the positive attitude of the user to the operation scheme can be intuitively displayed from the macro and micro dimensions. In the data details page, the user negative feedback information related to the operation scheme for obtaining the negative feedback statistical information can also be displayed at a position corresponding to the negative feedback statistical information, so that the negative attitude of the user to the operation scheme can be intuitively displayed from the macro and micro dimensions.

[0092] For example, referring to FIG. 8, it is a page schematic diagram of the data details page in some embodiments. When the user clicks the operation entry 704 in FIG. 7, the terminal can display the data details page. As shown in FIG. 8, the positive feedback statistical information is displayed in the page, which includes a specific statistical quantity value and statistical information represented by a column chart. The user positive feedback information related to the operation scheme is displayed below the positive feedback statistical information. The negative feedback statistical information is also displayed in the page, which includes a specific statistical quantity value and statistical information represented by a column chart. The user negative feedback information related to the operation scheme is displayed below the negative feedback statistical information.

[0093] In some embodiments, the success rate of the operation scheme can also be displayed on the data details page of the operation scheme, and the success rate can be the proportion of the number of positive feedback information of the user in the total number of feedback information of the user. For example, taking the user feedback information as the user comment content, the success rate = the number of "useful" comments / (the number of "useful" comments + the number of "useless" comments). For example, continuing to refer to FIG. 8, the success rate of the operation scheme is 76% in FIG. 8. Among them, the number of "useful" and "useless" comments is determined by semantic recognition of the user comment content. If the keywords such as "super", "thank you", exclamation mark, [heart] [rose] [happy] emoji, and the like expressing the degree, tone, and positive emotion appear in the comment, it is considered as a "useful" comment. If the keywords such as "completely", "not at all", exclamation mark, [vomit] [petrification] [angry] emoji, and the like expressing the degree, tone, and negative emotion appear in the comment, it is considered as a "useless" comment.

[0094] In the above embodiments, corresponding to the positive feedback statistical information, the user positive feedback information related to the operation scheme used to obtain the positive feedback statistical information is displayed, and corresponding to the negative feedback statistical information, the user negative feedback information related to the operation scheme used to obtain the negative feedback statistical information is displayed, which can provide effective data basis based on real user feedback for the user to judge the reliability of the scheme.

[0095] In some embodiments, displaying the user feedback information related to the operation scheme includes: displaying a feedback information display area corresponding to the solution content and a feedback information display area corresponding to each associated strategy content of the solution content; displaying the user feedback information for the solution content in the feedback information display area corresponding to the solution content; and displaying the user feedback information for the associated strategy content in each feedback information display area corresponding to the associated strategy content.

[0096] The associated strategy content of the solution content refers to the solution content that can extract the same or similar operation scheme as the solution content. When two or more solution contents extract the same or similar operation scheme, it can be considered that these solution contents can extract the same operation scheme.

[0097] The feedback information display area is a region divided in the data details page of the operation scheme, used to display the user feedback information of the corresponding content, including a feedback information display area corresponding to the solution content and a feedback information display area corresponding to each associated strategy content of the solution content. Each area can be further divided into a positive feedback information display area and a negative feedback information display area.

[0098] Specifically, in the data details page of the operation scheme, a plurality of feedback information display areas can be divided, including a feedback information display area corresponding to the solution content and a feedback information display area corresponding to at least one associated strategy content of the solution content, and in each feedback information display area, user feedback information corresponding to the content can be displayed, so that the source of each user feedback information can be intuitively displayed.

[0099] The positive feedback information display area is part of the feedback information display area, and is used to display user positive feedback information corresponding to the content. For example, the positive feedback information display area corresponding to the solution content displays user positive feedback information corresponding to the solution content, and the positive feedback information display area corresponding to the associated strategy content displays user positive feedback information corresponding to the associated strategy content. The negative feedback information display area is part of the feedback information display area, and is used to display user negative feedback information corresponding to the content. For example, the negative feedback information display area corresponding to the solution content displays user negative feedback information corresponding to the solution content, and the negative feedback information display area corresponding to the associated strategy content displays user negative feedback information corresponding to the associated strategy content.

[0100] For example, the feedback information display area corresponding to the solution content can include a positive feedback information display area corresponding to the solution content and a negative feedback information display area corresponding to the solution content, the positive feedback information display area can display user positive feedback information corresponding to the solution content, and the negative feedback information display area can display user negative feedback information corresponding to the solution content. Similarly, the feedback information display area corresponding to the associated strategy content can include a positive feedback information display area corresponding to the associated strategy content and a negative feedback information display area corresponding to the associated strategy content, the positive feedback information display area can display user positive feedback information corresponding to the associated strategy content, and the negative feedback information display area can display user negative feedback information corresponding to the associated strategy content.

[0101] For example, the feedback information display area corresponding to the solution content can also display the representation information corresponding to the solution content, for example, the title corresponding to the solution content or part of the content contained in the solution content. The feedback information display area corresponding to the associated strategy content can also display the representation information corresponding to the associated strategy content, for example, the title corresponding to the associated strategy content, the reference of the associated strategy content or part of the content contained in the associated strategy content. For example, when the user performs a trigger operation on the representation information corresponding to the solution content, the content display page of the solution content can also be jumped to, and similarly, when the user performs a trigger operation on the representation information corresponding to the associated strategy content, the content display page of the associated strategy content can also be jumped to.

[0102] Exemplarily, the total number of user feedback information under the content corresponding to each feedback information display area can also be displayed in the feedback information display area.

[0103] For example, continuing to refer to FIG. 8, the feedback information display area corresponding to the solution content can include a positive feedback information display area A corresponding to the solution content and a negative feedback information display area B corresponding to the solution content, and the feedback information display area corresponding to the associated strategy content can include a positive feedback information display area C corresponding to the associated strategy content and a negative feedback information display area D corresponding to the associated strategy content. The positive feedback information display area C corresponding to the associated strategy content also displays the reference “Same Solution Note 2” corresponding to the associated strategy content and the total number of user feedback information under the associated strategy content, i.e., “17 people say it is useful”.

[0104] In the above embodiments, since the user feedback information of each solution content can be displayed in different zones, the source of the user feedback information can be intuitively displayed.

[0105] In some embodiments, the content collection method of the present application further includes: displaying at least one user comment content for the solution content in the application; in response to a collection operation on a target user comment content in the at least one user comment content, displaying a collection result of adding the target user comment content to a collection folder of the application; and displaying an operation scheme for the target user comment content, the operation scheme of the target user comment content including an operation step extracted from the associated strategy content corresponding to the target user comment content, the associated strategy content including key information in the target user comment content.

[0106] The key information is information related to the solution in the target comment content, and the associated strategy content of the target user comment content contains and describes the key information in detail, i.e., the strategy information included in the associated strategy content for achieving the specified target is for the solution of the problem involved in the target user comment content.

[0107] Specifically, in this embodiment, considering that the solution to the problem in the user comment content may also be different from the original solution content, the user can also perform a collection operation on the user comment content of the solution content, and the terminal can collect the target user comment content in response to the collection operation on the target user comment content in the at least one user comment content. If the collection is successful, the terminal displays a collection result of adding the target user comment content to the application program collection folder, for example, the terminal can display a prompt information of "collection success". If the collection fails, such as the number of collected contents in the collection folder reaches the upper limit, the terminal displays a collection result indicating that the collection fails, for example, the terminal can display a prompt information of "collection failure". For example, referring to FIG. 9, the terminal displays a plurality of user comment contents, and when the user clicks any target user comment content, a semi-pop-up page can be pulled up on the display page of the user comment content. The page can display a "collection" button, and when the user further clicks the "collection" button, if the terminal successfully collects the target user comment content, the terminal can display a prompt information of "collection success" on the page.

[0108] For example, in the collection folder, the collected contents can be classified and collected, that is, the collection folder includes a plurality of sub-collection folders, and different sub-collection folders are used to collect contents of different themes or different types. Therefore, when the terminal displays the collection result of adding the solution content to the application program collection folder, the terminal can also display an operation entrance of adding the solution content to the sub-collection folder. In response to the triggering operation on the operation entrance, the terminal displays a plurality of sub-collection folders, and when the user selects one of the sub-collection folders, the terminal adds the target user comment content to the sub-collection folder. For example, referring to FIG. 10, when the user further clicks the "collection" button, if the terminal successfully collects the target user comment content, the terminal displays a prompt information of "collection success" and also displays an operation entrance of "add album" prompt information. When the user clicks the operation entrance, the terminal further displays a plurality of selectable sub-collection folders, such as ticket purchase, house renovation, and home appliances. When the user selects the "ticket purchase" sub-collection folder, the terminal can add the solution content to the sub-collection folder.

[0109] Further, the terminal can also display an operation scheme for the target user comment content. Since the target user comment content may only simply mention the solution to the problem and does not involve specific operation steps, the terminal can extract the operation scheme from the associated strategy content corresponding to the target user comment content, and use the extracted operation scheme as the operation scheme for the target user comment content.

[0110] The association strategy content includes key information in the target user comment content, where the key information is information about a solution in the target comment content, and the association strategy content of the target user comment content contains and describes the key information in detail, that is, the strategy information included in the association strategy content of the target user comment content is for the solution to the problem involved in the target user comment content. For example, assuming that the question searched by the user is "how to perform train ticket rush", a comment under a certain solution content is "try XX method to split rush, good", it can be seen that the target user comment contains the key information "split rush", but does not involve specific operation steps, and therefore the operation scheme can be extracted from the association strategy content containing the key information as the operation scheme of the target user comment. The data such as the like amount and the praise rate under the association strategy content can be counted to determine the association strategy content with the most positive feedback information of the user. When there are multiple association strategy contents including the key information in the target user comment content, the association strategy content used to extract the operation scheme for the target user comment content can be the association strategy content with the highest like amount among the association strategy contents, and the like amount can be determined by counting the like number under the association strategy content.

[0111] For example, when there are multiple association strategy contents including the key information in the target user comment content, the association strategy content used to extract the operation scheme for the target user comment content can be the association strategy content with the most positive feedback information of the user among the association strategy contents, for example, the association strategy content with the highest like amount.

[0112] It can be understood that the terminal can display the operation scheme for the target user comment content at any time according to actual needs. For example, the terminal can display the operation scheme after successfully adding the target user comment content to the collection folder. In actual applications, if the user needs to further add the target user comment content to a sub-collection folder, the terminal can display the operation scheme after successfully adding the target user comment content to the sub-collection folder. For example, with reference to FIG. 10, when the user selects the sub-collection folder “ticket rush” from the plurality of sub-collection folders displayed by the terminal, the terminal displays the operation scheme for the target user comment content, which includes the scheme name “ticket rush” and three operation steps. For example, the terminal can also display the operation scheme for the target user comment content in response to a display trigger operation of the user on the target user comment content. For example, the terminal displays the operation scheme for the target user comment content when the user browses the collection folder and selects the target user comment content, so that the terminal can display the operation scheme for the target user comment content. For example, when the user browses the collection folder, the user selects a target user comment content in the collection folder list to view, the terminal displays the operation scheme for the target user comment content in the form of a floating window on the display page of the target user comment content.

[0113] It should be further noted that the order of displaying the collection result of adding the target user comment content to the collection folder of the application program and displaying the operation scheme for the target user comment content can not be limited. According to actual application scenarios, the terminal can first display the collection result of adding the target user comment content to the collection folder of the application program, and then display the operation scheme for the target user comment content, or the terminal can first display the operation scheme for the target user comment content, and then display the collection result of adding the target user comment content to the collection folder of the application program. In this case, when the terminal displays the operation scheme for the target user comment content, the terminal can provide the “confirm collection” and “cancel collection” options, and when the user selects the “confirm collection” option, the terminal displays the collection result of adding the target user comment content to the collection folder of the application program. Therefore, the terminal can display the operation scheme with better readability, so that the user can better understand the target user comment content and decide whether to further collect the target user comment content. Of course, in some other embodiments, the terminal can simultaneously display the operation scheme for the target user comment content and the collection result of adding the target user comment content to the collection folder of the application program. The specific implementation can be flexibly defined according to actual needs, and details are not described herein.

[0114] In the process of displaying the operation scheme for the target user comment content, the terminal can display other content related to the operation scheme in various alternative embodiments, specifically:

[0115] Alternatively, the terminal can also display statistical information obtained by counting the user feedback information related to the operation scheme corresponding to the operation scheme for the target user comment content.

[0116] Alternatively, the user feedback information related to the operation scheme includes user positive feedback information related to the operation scheme and user negative feedback information related to the operation scheme; thus, the terminal displaying the statistical information obtained by counting the user feedback information related to the operation scheme can specifically be implemented as displaying a statistical quantity comparison relationship between the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme. For example, referring to FIG. 11, FIG. 11 is a schematic diagram of an interface of an operation scheme for a target user comment in some alternative embodiments, and the statistical quantity comparison relationship between the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme is displayed in the dashed box 1102 in FIG. 11, where the column chart corresponding to "useful" is positive feedback statistical information obtained by counting the user positive feedback information related to the operation scheme, and the column chart corresponding to "not useful" is negative feedback statistical information obtained by counting the user negative feedback information related to the operation scheme.

[0117] Alternatively, the terminal can also display the user feedback information related to the operation scheme; wherein the user feedback information related to the operation scheme includes all user feedback information from which the solution content of the operation scheme can be extracted. In specific applications, the terminal can display statistical information obtained by counting the user feedback information related to the operation scheme when displaying the operation scheme, and can also display an operation entry corresponding to the statistical information, and thus when a user clicks the operation entry, a new page can be displayed to display the user feedback information related to the operation scheme. In this way, by first displaying the statistical information and guiding the user to view the user feedback information by displaying the operation entry, the flexibility of page display can be improved. For example, continuing to refer to FIG. 11, the operation entry 1104 "view detailed data" is displayed on the page displaying the operation scheme, and when a user clicks the operation entry 1104, a new page can be displayed to display the user feedback information.

[0118] Optionally, the operation scheme related user feedback information is displayed on the data detail page of the operation scheme, and the terminal displays the operation scheme related user feedback information. Specifically, the positive feedback statistical information and the negative feedback statistical information can be displayed on the data detail page. The operation scheme related user positive feedback information used to obtain the positive feedback statistical information can be displayed corresponding to the positive feedback statistical information. The operation scheme related user negative feedback information used to obtain the negative feedback statistical information can be displayed corresponding to the negative feedback statistical information. For example, when the user clicks the operation entry 1104 in FIG. 11, the terminal can display the data detail page. As shown in FIG. 11, the positive feedback statistical information is displayed on the data detail page. The positive feedback statistical information includes a specific statistical quantity value and statistical information represented by a column chart. The operation scheme related user positive feedback information is displayed below the positive feedback statistical information. The negative feedback statistical information is also displayed on the page. The negative feedback statistical information includes a specific statistical quantity value and statistical information represented by a column chart. The operation scheme related user negative feedback information is displayed below the negative feedback statistical information.

[0119] In some embodiments, the success rate of the operation scheme can also be displayed on the data detail page of the operation scheme. The success rate of the operation scheme can be the proportion of the number of user positive feedback information in the total number of user feedback information. For example, the success rate of the user feedback information is the number of comments indicating usefulness / (the number of comments indicating usefulness+the number of comments indicating uselessness). For example, as shown in FIG. 11, the success rate of the operation scheme is 63%.

[0120] Optionally, the display of the user feedback information related to the operation scheme can further include: displaying a feedback information display area corresponding to the target user comment content and a feedback information display area corresponding to at least one associated strategy content of the target user comment content; displaying the user feedback information for the target user comment content in the feedback information display area corresponding to the target user comment content; and displaying the user feedback information for the associated strategy content in the feedback information display area corresponding to each associated strategy content. For example, continuing to refer to FIG. 11, the feedback information display area corresponding to the target user comment content can include a positive feedback information display area A corresponding to the target user comment content and a negative feedback information display area B corresponding to the target user comment content, the positive feedback information display area A displays useful comments for the target user comment content, and the negative feedback information display area B displays useless comments for the target user comment content. The feedback information display area corresponding to one associated strategy content can include a positive feedback information display area C corresponding to the associated strategy content and a negative feedback information display area D corresponding to the associated strategy content. The positive feedback information display area C corresponding to the associated strategy content also displays the reference "Note 2 of the same scheme" corresponding to the associated strategy content and the total number of user feedback information under the associated strategy content, i.e., "12 people indicate that it is useful".

[0121] In the above embodiment, when the user performs the collection operation on the comment content, other non-comment content that can be refined into the same scheme can be captured, and a step-by-step scheme can be generated and displayed based on the non-comment content, so that the user can directly collect valuable comments without having to exit the current content and manually search for the scheme proposed by the comments, thereby improving the interaction efficiency.

[0122] In some embodiments, when multiple solution contents are collected in the collection folder, the content collection method of the present application further includes: displaying a collection folder page of the collection folder in the application program, displaying a scheme graph center node of an operation scheme graph corresponding to at least one operation scheme in the collection folder page, and each operation scheme graph center node is used to represent the corresponding operation scheme; for each scheme graph center node, at least one of a first subsidiary node or a second subsidiary node connected to the scheme graph center node through a connection line is displayed, the first subsidiary node is used to represent the associated strategy content of the operation scheme represented by the scheme graph center node in the collection folder, and the second subsidiary node is used to represent the associated user comment content of the operation scheme represented by the scheme graph center node in the collection folder.

[0123] The scheme graph is a graph for displaying the collected solution content with an operation scheme as a center, which is composed of a scheme graph center node and a plurality of subsidiary nodes (first subsidiary node or second subsidiary node) connected with the scheme graph center node through connecting lines, and is used for intuitively presenting effective information of the solution content and improving the efficiency of the user in screening the scheme.

[0124] Specifically, a plurality of solution contents are collected in the collection folder, and the terminal can generate at least one operation scheme in the process of collecting the solution contents, so that the terminal displays the collected solution content with the generated operation scheme as a center when displaying the collection folder page of the collection folder. Each operation scheme is displayed with an operation scheme graph, and the operation scheme graph includes a scheme graph center node and a plurality of subsidiary nodes connected with the scheme graph center node through connecting lines. The scheme graph center node of each operation scheme graph is used to represent the corresponding operation scheme, and the subsidiary nodes of each operation scheme graph are used to represent the solution content or user comment content associated with the operation scheme in the collection folder. The subsidiary nodes include at least one of the first subsidiary node or the second subsidiary node. The first subsidiary node is used to represent the associated strategy content of the operation scheme represented by the scheme graph center node in the collection folder, and the associated strategy content of the operation scheme in the collection folder is the associated strategy content of the solution content to which the operation scheme belongs in the collection folder. The second subsidiary node is used to represent the associated user comment content of the operation scheme represented by the scheme graph center node in the collection folder, and the associated user comment content of the operation scheme in the collection folder is also extracted from the associated strategy content corresponding to the associated user comment content, that is, the associated user comment content involves the operation scheme.

[0125] In the above embodiment, the solution content is displayed with the operation scheme as a center, which can intuitively present the effective information of the solution content, so that the user does not need to enter the detail page to recall the reason for collecting the content and judge whether the content is reliable, thereby improving the efficiency of the user in reading the collected content and screening the favorite scheme.

[0126] In some embodiments, the content collection method of the present application further includes: for each scheme graph center node, displaying the scheme identifier of the operation scheme represented by the scheme graph center node at the display position of the scheme graph center node, and displaying at least one of the following information: the content identifier of the solution content to which the operation scheme represented by the scheme graph center node belongs, the scheme content of the operation scheme represented by the scheme graph center node, and statistical information obtained by statistically processing the user feedback information related to the operation scheme represented by the scheme graph center node.

[0127] The scheme identifier of the operation scheme is an identifier for identifying the operation scheme, and can be specifically a name of the operation scheme. A user can trigger an operation (such as clicking) on the scheme identifier, and then view the specific scheme content. The content identifier is an identifier for identifying the solution content, and can be specifically a title of the solution content. If the solution content has an explicit title field, the content of the field is used as the title. If there is no explicit title field, a key sentence can be extracted from the beginning of the content as the title. A user can trigger an operation (such as clicking) on the content identifier, and then view the specific content. The title of the solution content is usually the title used when the solution content is displayed in the application. If the solution content has an explicit title field, the content of the field is used as the title. If there is no explicit title field, a key sentence can be extracted from the beginning of the content as the title.

[0128] Specifically, for each operation scheme graph, the scheme identifier or the scheme content of the operation scheme corresponding to the operation scheme graph can be displayed at the display position of the scheme graph center node of the operation scheme graph. The content identifier or the specific content of the solution content to which the operation scheme corresponding to the operation scheme graph belongs can also be displayed. Statistical information obtained by counting user feedback information related to the operation scheme can also be displayed. For example, if the scheme identifier of the operation scheme is displayed, a user can trigger an operation (such as clicking) on the scheme identifier, and then view the specific scheme content. If the content identifier of the solution content is displayed, a user can trigger an operation (such as clicking) on the content identifier, and then view the specific content.

[0129] For example, referring to FIG. 12, a page schematic diagram of a collection page in some embodiments is shown. An operation scheme graph is displayed in the upper left corner. The scheme graph center node of the operation scheme graph represents the operation scheme of “Scheme Name A”. The success rate, the note content to which the operation scheme belongs, the scheme content, and the statistical information are also displayed at the display position of the scheme graph center node.

[0130] In the above embodiments, various information can be displayed at the display position of the scheme graph center node, which can more intuitively present effective information, and further improve the readability of the operation scheme graph.

[0131] In some embodiments, when multiple topic-type contents are also collected in the collection, the content collection method of the application further includes: displaying the topic graph center node of at least one topic graph corresponding to each topic on the collection page. The topic graph center node of each topic graph represents the corresponding topic. For each topic graph center node, at least one of the third subsidiary node or the fourth subsidiary node connected to the topic graph center node by a connection line is displayed.

[0132] The topic type content, which can also be referred to as non-solution content, refers to content from which operation steps cannot be extracted. For these content from which operation steps cannot be extracted, semantic recognition can be performed, and one or more topics can be abstracted. The topic graph is a graph for displaying the collected topic type content with the topics as the center, and is composed of a topic graph center node and a plurality of subsidiary nodes (third subsidiary nodes or fourth subsidiary nodes) connected to the topic graph center node through connection lines. The topic graph can intuitively present effective information of the topic type content, and facilitate user screening of the content.

[0133] Specifically, when a plurality of topic type contents are collected in the collection folder, the terminal can abstract topics from the topic type contents. Therefore, when the collection folder is displayed on the collection folder page, the terminal can display the collected topic type contents with the abstracted topics as the center. For each topic, a topic graph is displayed, which includes a topic graph center node and a plurality of subsidiary nodes connected to the topic graph center node through connection lines. The topic graph center node of each topic graph is used to represent the corresponding topic. The subsidiary nodes of each topic graph are used to represent the solution content or the user comment content in the collection folder associated with the topic. The subsidiary nodes include at least one of the third subsidiary nodes or the fourth subsidiary nodes. The third subsidiary nodes are used to represent the topic type content in the collection folder related to the topic represented by the topic graph center node. The fourth subsidiary nodes are used to represent the user comment content in the collection folder related to the topic represented by the topic graph center node. The topic type content related to a certain topic refers to the topic type content from which the topic can be abstracted. The user comment content related to a certain topic refers to the user comment content from which the topic can be abstracted.

[0134] In the above embodiments, the topic type content is displayed with the topic as the center, which can intuitively present the effective information of the topic type content, and let the user not need to enter the detail page to recall the reason for collecting the content and then judge whether the content is reliable, thereby improving the efficiency of the user reading the collected content and screening the desired solution.

[0135] In some embodiments, the content collection method of the present application further includes: for each topic graph center node, displaying the topic represented by the topic graph center node, the target topic type content in the collection folder related to the topic represented by the topic graph center node, and statistical information obtained by statistically processing the user feedback information related to the topic represented by the topic graph center node at the display position of the topic graph center node.

[0136] The target topic type content is the topic type content with the most user positive feedback information among all topic type contents related to the topic represented by the topic graph center node. The user feedback information related to the topic is user feedback information related to the topic type content related to the topic, which can include user positive feedback information such as positive comments of the user on the topic, and which can include user negative feedback information such as negative comments of the user on the topic.

[0137] The number of user positive feedback information and negative feedback information is counted by performing semantic recognition on the comments under the topic type content related to the topic. If the comments contain keywords such as “super”, “thank you”, exclamation marks, [heart] [rose] [happy] emoticons, and the like, which express degree, tone, and positive emotions, it is considered to be positive feedback information. If the comments contain keywords such as “completely”, “not at all”, exclamation marks, [vomit] [petrification] [angry] emoticons, and the like, which express degree, tone, and negative emotions, it is considered to be negative feedback information.

[0138] Specifically, at the display position of the topic graph center node of each topic graph, the terminal can display the content identifier of the target topic type content or the target topic content in the collection folder related to the topic represented by the topic graph center node, and can also display statistical information obtained by counting the user feedback information related to the topic represented by the topic graph center node. The statistical information can be a statistical quantity comparison relationship between the user positive feedback information and the user negative feedback information related to the topic represented by the topic graph center node.

[0139] For example, continuing to refer to FIG. 12, a topic graph is displayed in the lower right corner, and the topic graph center node of the topic graph is used to represent the topic of “topic name a”. The note content with the most likes related to the topic and the statistical information are also displayed at the display position of the topic graph center node.

[0140] In the above embodiments, since multiple information can be displayed at the display position of the topic graph center node, the effective information can be more intuitively presented, and the readability of the topic graph is further improved.

[0141] In some embodiments, the collection folder page also displays a first collection folder display mode option and a second collection folder display mode option. The collection folder page displays the scheme graph center node of the operation scheme graph corresponding to at least one operation scheme, including: in the case that the first collection folder display mode option is in the selected state, the collection folder page displays the scheme graph center node of the operation scheme graph corresponding to at least one operation scheme. The content collection method of the present application also includes: in the case that the second collection folder display mode option is in the selected state, the collected content in the collection folder is sequentially arranged and displayed.

[0142] The first collection display mode option is a display mode option provided by the collection page. When the option is in a selected state, the content in the collection is displayed in the form of a graph, such as an operation scheme graph and a topic graph. The second collection display mode option is another display mode option provided by the collection page. When the option is in a selected state, the content in the collection is displayed in a conventional display mode, that is, the content in the collection is sequentially arranged and displayed, for example, can be sequentially arranged and displayed in the form of a list.

[0143] Specifically, in this embodiment, the collection display page provides two collection display modes, that is, a first collection display mode and a second collection display mode. In the first collection display mode, the content in the collection is displayed in the form of a graph. In the second collection display mode, the content in the collection is displayed in a conventional display mode, that is, the content in the collection is sequentially arranged and displayed, for example, can be sequentially arranged and displayed in the form of a list.

[0144] For example, continuing to refer to FIG. 12, the first collection display mode option, that is, “graph mode”, and the second collection display mode option, that is, “conventional mode”, are displayed in FIG. 12. In FIG. 12, “graph mode” is in a selected state, and therefore the collection page displays the content in the form of a graph. Referring to FIG. 13, which is a page schematic diagram of a collection display page in some embodiments, in FIG. 13, “conventional mode” is in a selected state, and therefore the collection page sequentially arranges and displays the content collected in the collection.

[0145] The conventional mode is a display mode of the collection. In this mode, the system sequentially arranges and stores the content in the collection in the database according to the collection time of the collection content, the title alphabetical order, and other preset rules. When the user selects this mode, the collection displays the content in the form of a list. The graph mode is another display mode of the collection. In this mode, the system analyzes and processes the content from which an operation scheme can be extracted, generates an operation scheme graph and a topic graph, displays the collection content with the generated operation scheme as a center point, displays the related information of the operation scheme on the center node, displays the brief information of the associated content on the auxiliary node, and displays the association between them through a connecting line, so as to intuitively present the effective information of the collection content.

[0146] Exemplarily, the sharing control can also be displayed on the collection display page, and when the user clicks the sharing control, the collection display page can be shared with other users. Optionally, when the first collection display mode option is in the selected state, the collection page in the first collection display mode is displayed when the other user enters the collection page through the sharing link, and when the second collection display mode option is in the selected state, the collection page in the second collection display mode is displayed when the other user enters the collection page through the sharing link. For example, referring to FIGS. 12 and 13, the control corresponding to the prompt information “Invite friends to share” is the sharing control.

[0147] In the above embodiments, two different page display modes are provided to display the collected content, which can improve the flexibility of content display on the collection page.

[0148] In some embodiments, the content collection method of the present application further includes: in response to an operation of triggering the accompanying mode for the operation scheme, starting the accompanying mode for the operation scheme; in the accompanying mode, displaying step description information of a current operation step to be executed; and when a trigger condition of a next operation step to be executed is met, displaying step description information of the next operation step to be executed.

[0149] The accompanying mode is an auxiliary mode for the operation scheme, and after the mode is started, in the operation scheme execution process, step description information of a current operation step to be executed is displayed, and when a trigger condition of a next operation step to be executed is met, step description information of the next operation step to be executed is displayed, guiding the user to execute the operation steps in order and improving the operation execution efficiency. The step description information of the operation step is information describing the operation process of the operation step, and is used to guide the user's operation behavior. In the accompanying mode, the terminal displays the corresponding step description information according to the execution of the operation step. The trigger condition of the next operation step to be executed is a condition that can trigger the start of the next operation step to be executed, for example, it can be that the current operation interface enters the next operation step to be executed or the current time reaches the operation time of the next operation step to be executed.

[0150] The operation of triggering the accompanying mode for the operation scheme is an operation of triggering the accompanying mode for the operation scheme. Exemplarily, the terminal can display an accompanying mode triggering control for the operation scheme, and then the accompanying mode for the operation scheme can be started in response to the triggering operation of the accompanying mode triggering control. For example, referring to FIG. 14, when the user selects an operation scheme on the collection page, for example, the operation scheme in the upper left corner of the collection page in FIG. 14, the data detail page of the operation scheme can be displayed, and the accompanying mode triggering control 1402 can be displayed on the data detail page, and then the accompanying mode for the operation scheme can be started.

[0151] The operation scheme includes a plurality of operation steps, which need to be executed in sequence. In the accompanying mode, the terminal can display the step description information of the current operation step to be executed, so that the user can execute the current operation step to be executed according to the step description information of the current operation step to be executed. When the trigger condition of the next operation step to be executed is reached, the terminal displays the step description information of the next operation step to be executed, and the user can execute the next operation step to be executed according to the step description information of the next operation step to be executed, until all operation steps in the operation scheme are executed.

[0152] For example, the terminal can display the step description information of the next operation step to be executed while displaying the step description information of the current operation step to be executed, and display the step description information of the current operation step to be executed as completed, and display the step description information of the next operation step to be executed as to be executed. For example, the terminal can also update and display the step description information of the current operation step to be executed as the step description information of the next operation step to be executed.

[0153] In specific applications, the terminal can display the step description information of the operation step in the form of a floating window. For example, referring to FIG. 15, which is a schematic diagram of page changes in the accompanying mode in some embodiments, the terminal first displays the step description information "open XXX APP" of the first step in a pop-up window. After the user executes the operation step according to the step description information, the current operation interface enters the second operation step, i.e., the trigger condition of the second operation step is reached, and the terminal updates the information displayed in the pop-up window to the step description information of the second operation step. After the user executes the operation step according to the step description information, the current operation interface enters the third operation step, i.e., the trigger condition of the third operation step is reached, and the terminal updates the information displayed in the pop-up window to the step description information of the third operation step.

[0154] For example, the terminal can perform semantic analysis on the operation step description information. If the analysis result indicates that the execution of a certain operation step in the operation scheme is not at the terminal, the terminal can provide an operation description input box and an operation picture upload control. The terminal can perform semantic analysis and image recognition on the operation description and operation image to determine whether the operation is completed correctly. If the determination is yes, the n th step is completed is displayed and the next step is entered. In terms of semantic analysis, the large language model understands the text of the operation description, analyzes the key information such as actions and results, and compares it with the standard description of the operation step. For example, the operation step requires “tightening the screw”. If the operation description mentions “the screw has been tightened”, it is preliminarily determined to meet the requirements. In terms of image recognition, the target detection algorithm (such as SSD) is used to analyze the operation image and identify the objects and states in the image. If the operation step requires tightening the screw, the image recognition will detect whether the screw is in the tightened state. Based on the results of semantic analysis and image recognition, if both meet the requirements of the operation step, it is determined that the operation is completed correctly; if one of them does not meet the requirements, it is determined that the operation is not completed.

[0155] For example, the third operation step in FIG. 15 is not at the terminal. The terminal can further display the page shown in the left page of FIG. 16. When the user fills in the operation description and uploads the operation screenshot in the page, the current operation page enters the fourth step, that is, the page shown in the right page of FIG. 16.

[0156] In the above embodiments, the companion mode can be enabled, and the step description information of each new operation step that meets the triggering condition can be displayed to guide the user to perform the operation, thereby improving the execution efficiency in the operation process of the user.

[0157] In some embodiments, when the current operation step to be executed indicates time constraint information; in the companion mode, displaying the step description information of the current operation step to be executed includes: in the companion mode, when the current time reaches the reminding time matched with the time constraint information, triggering an operation reminder for the current operation step to be executed; in response to the operation step triggering event of the operation reminder, displaying the step description information of the current operation step to be executed.

[0158] The time constraint information is information for constraining the execution of the operation step in time. Optionally, the time constraint information can be a specific time, which is the specific execution time of the operation step, for example, a certain operation step is to perform XX operation at 9 o’clock in the morning, and the 9 o’clock in the morning is the time constraint information. When the time constraint information is a specific time, the reminding time matched with the time constraint information is a certain time close to the specific time before the specific time, for example, for the operation step in the foregoing, the reminding time matched with the time constraint information can be 8:55 in the morning.

[0159] The operation reminder is triggered in the accompanying mode when the current time reaches the reminding time matched with the time constraint information, and the step description information of the current operation step to be executed is displayed in response to the operation step triggering event of the operation reminder.

[0160] In some other embodiments, the time constraint information can also be used to constrain the execution time of the current operation step to be executed relative to the event time of the event to which the current operation step to be executed is directed. In this case, the time constraint information is not a specific time, the current operation step to be executed is directed to an event, and the execution time of the current operation step to be executed needs to be determined according to the event time of the event and the time constraint information in the operation step description information, wherein the event time can be set by the user or determined according to some event conditions. For example, an operation step is "execute XX operation 2 minutes before XX event starts", and the 2 minutes is the time constraint information. When the time constraint information is used to constrain the execution time of the current operation step to be executed relative to the event time of the event to which the current operation step to be executed is directed, the reminding time matched with the time constraint information needs to be determined according to the execution time of the operation step, which can be a certain time close to the execution time before the execution time.

[0161] In this embodiment, when the current time reaches the reminding time matched with the time constraint information, the terminal can also trigger the operation reminder for the current operation step to be executed, and the terminal can further display the step description information of the current operation step to be executed in response to the operation step triggering event of the operation reminder. Optionally, the operation step triggering event of the operation reminder can be an operation step triggering operation of the operation reminder, for example, the user can trigger the operation step according to the operation reminder; and optionally, the operation step triggering event of the operation reminder can be that the current time reaches the operation step triggering time indicated by the operation reminder.

[0162] For example, referring to FIG. 17, it is assumed that the first operation step in FIG. 15 has time constraint information, i.e., the operation step is to open XXX app 2 minutes before invoicing, and after the execution time of opening XXX app is determined, the terminal can trigger the operation reminder for the operation step before the execution time, i.e., the left drawing in FIG. 17, when the user clicks the operation reminder in the left drawing, enters the right drawing in FIG. 17, and the user can operate according to the guidance in the right drawing in FIG. 17, so that the terminal can enter the page shown in the first drawing in FIG. 15 in response to the operation step triggering event of the operation reminder.

[0163] In the above embodiments, since in the companion mode, when the current time reaches the reminder time that matches the time constraint information, an operation reminder for the operation steps to be performed can be triggered, which can better guide the user's operation.

[0164] In some embodiments, when time constraint information is used to constrain the execution time of the currently to-be-executed operation step relative to the event time of the event targeted by the currently to-be-executed operation step, referring to Figure 18, the content collection method of this application further includes a reminder time determination step, specifically including:

[0165] Step 1802: Display the Companion Mode Settings page. This page displays an event time setting control for the currently pending operation step. The event time setting control is displayed on the Companion Mode Settings page, allowing the user to set the event time for the event corresponding to the currently pending operation step.

[0166] Step 1804: In response to the setting operation of the event time setting control, determine the event time of the event to which the operation step to be performed is targeted.

[0167] Specifically, the terminal can display a companion mode settings page. This page displays an event time setting control for the currently pending operation step. Users can use this control to set the event time for the event corresponding to the current operation step. For example, referring to Figure 19, when a user clicks the companion mode trigger control 1402 in Figure 14, they can enter the companion mode settings page shown on the left and right sides of Figure 19. On this page, the user can set the event time for the first operation step, "Issuing an Invoice." After setting the event time, clicking the "OK" control on this page will take the user to the page shown on the right side of Figure 19.

[0168] Step 1806: Determine the reminder time that matches the time constraint information based on the event time and time constraint information of the event targeted by the current operation step to be executed.

[0169] Specifically, the terminal can determine the execution time of the operation step to be executed based on the event time and time constraint information of the event targeted by the operation step to be executed, and then determine the reminder time matching the time constraint information based on the execution time.

[0170] Assume the event time is T. event If the time constraint is to execute the operation step t constraint minutes in advance, then the execution time T of the operation step is... execute =T event -tconstraint, reminder time T remind =Texecute -t advance wherein t advance is the time of the advance reminder, which can be set according to actual conditions, for example, 10 minutes in advance, then t advance = 10 minutes.

[0171] For example, continuing to refer to FIG. 19, the event time of the event to which the first operation step is directed is May 25, 2024, 15:00, and the time constraint information is 2 minutes in advance. Therefore, it can be determined that the execution time of the first operation step is May 25, 2024, 14:58, and the reminder time is a time before and close to the execution time, for example, May 25, 2024, 14:48, that is, 10 minutes in advance to trigger the operation reminder.

[0172] In the above embodiment, the user can set the event time through the event time setting control, and then set the reminder time from the interval, thereby improving the interaction flexibility in the accompanying mode, and ensuring the timeliness and effectiveness of the operation reminder triggering.

[0173] In some embodiments, when the current operation step to be executed ends and the trigger condition of the next operation step to be executed is not met, a failure reason for the execution failure of the current operation step to be executed is displayed.

[0174] Specifically, when the current operation step to be executed ends and the trigger condition of the next operation step to be executed is not met, the terminal does not display the step description information of the next operation step, but displays the failure reason for the execution failure of the current operation step to be executed, to help the user to re-execute the correct operation.

[0175] In some specific embodiments, the present application also provides an application scenario in which a user can find a solution to a problem on an information stream application. In this case, the user often browses multiple contents, and makes a perceptual assessment of the reliability of the content through likes, comments and the like under the content, and collects the content that the user considers reliable. However, when the user enters the collection folder after collecting multiple contents, the user still has difficulty in selecting the best solution from so many contents. The reasons can be as follows: (1) Without accurate data comparison, the user is easily misled by the description of a single or a few contents, and selects a solution that is not on the board or has poor authenticity; (2) When the collection amount is large, it is difficult to recall the reason why the user selected the content for collection when browsing the collection list without entering the details, which increases the difficulty of forming the final best solution from the fuzzy memory; (3) Moreover, many contents are only based on personal experience produced by other users, without processing, and clear steps; (4) The user may also collect multiple similar contents, resulting in a lot of invalid information in the collection folder. These reasons all increase the difficulty for the user to find the best solution.

[0176] However, the user clicks to collect a content because the content has a point that touches the user, so how to effectively use the collected content through collection, and as accurately as possible to clearly extract and intuitively present the fuzzy ideal scheme in the user's mind, and provide an effective basis for the user to compare and filter different schemes, is a pain point that the existing collection function cannot solve.

[0177] Based on this, the present application provides a content collection method, which can generate operation schemes through collection behavior, provide scheme success rate data, organize the content of the collection folder around the scheme, and provide a function of entering an accompanying mode after selecting the best scheme. The method allows the user to obtain multiple operation schemes with clear steps through collection, select an ideal scheme by intuitively comparing the success rate data and comment feedback of the operation schemes, and obtain timely operation guidance after entering the accompanying mode after selecting the ideal scheme. The content collection method of the present application efficiently utilizes the collected content, reduces the cost of reading the collected content, filtering the ideal scheme, and operating the scheme, and allows the user to more easily and calmly solve the problem. The content collection method of the present application at least includes the following improvements compared with the related art:

[0178] 1. Extracting saved content into clear, step-by-step operational plans. After a user browses content and clicks to save it, if the content can be extracted into a solution with detailed steps, a step-by-step operational plan is generated based on the content. The plan name is a summary of the content after AI semantic recognition, thus refining the user's original content and improving its readability and operability. Optionally, if a user saves other content that can be extracted into the same plan, a new plan will not be generated, and the content will be added to the favorites list as usual. When the user selects the solution content again in the favorites list to browse, a display trigger event is triggered for that solution content. The terminal can respond to this display trigger event and display the operational plan extracted from the solution content in the application.

[0179] 2. Calculate the success rate of the solution by crawling relevant content from the entire platform. After the solution is generated, the system will automatically crawl other content that can be extracted into the same solution within the platform, and crawl all text comments under these contents and the original content that has been saved. Semantic recognition will be performed on these text contents, and the comments will be divided into three categories: "indicates usefulness", "indicates inuselessness", and "neither indicates usefulness nor inuselessness", and the number of comments in these three categories will be counted.

[0180] The semantic recognition rules and methods are as follows: The large language model first performs word segmentation on the comments, analyzing the vocabulary, grammar, and sentiment. If the comments contain words and phrases expressing positive effects and affirmative attitudes, such as "super useful," "thanks for sharing, very helpful," or "solved my problem," they are judged as "useful." If the comments contain words and phrases expressing negative effects and negative attitudes, such as "completely useless," "not helpful at all," or "a waste of time," they are judged as "useless." If the comments do not contain obvious positive or negative expressions, such as simply describing related matters or asking questions, such as "How is this done?" or "I encountered the same situation," they are judged as "not useful / useless." Simultaneously, the model also combines the context and overall semantics of the comments for comprehensive judgment to improve classification accuracy.

[0181] After the statistics are completed, the number of "helpful" and "useless" comments is presented in a bar chart under the note. Users who click the "View Detailed Data" button can access the detailed data page for this solution, where they can see the solution's success rate: [Success Rate = Number of "Helpful" Comments / (Number of "Helpful" Comments + Number of "Useless" Comments)]. They will also see the original saved content, other content extracted by the system that can be refined into the same solution, and the specific "helpful" / "useless" comments below these contents. By calculating the solution's success rate, users can be provided with effective data based on real user feedback to judge the reliability of the solution.

[0182] 3. Collecting comments. Since the comments may also contain solutions different from the original content, the user can also click to collect a comment, and the system will automatically capture other non-comment content that can be refined into the same solution in the platform, and generate a step-by-step solution based on the highest number of likes in these non-comment content. The functions after the solution are the same as those in the first, second and third items. By collecting comments, users can directly collect valuable comments without having to exit the current content and manually search for solutions proposed by the comments.

[0183] 4. Favourites map mode. Set "regular mode" and "map mode" in the favourites.

[0184] At the system level, the implementation logic of the regular mode is that the system stores the contents in the favourites in the database in sequence according to the collection time, title letter order and other preset rules. When the user selects the regular mode, the system reads these contents arranged in sequence from the database and displays them in the form of a list in the favourites page, such as presenting each collected content in the form of a title, a thumbnail, etc. The implementation logic of the map mode is that the system analyzes and processes the contents that can be refined into operation solutions when the user collects the contents, generates operation solution maps and topic maps. The operation solution is taken as the center node of the map, the associated strategy content and the associated user comment content are taken as the subsidiary nodes, and the relationship between the nodes is stored through data structures such as linked lists, graphs, etc. When the user selects the map mode, the system displays the collected contents in the form of a map according to the stored node relationship, displays the relevant information of the operation solution in the center node, displays the brief information of the associated contents in the subsidiary nodes, and displays their association through connecting lines.

[0185] In the regular mode, the favourites are displayed in the form of sequentially arranged single contents. In the map mode, the favourites are displayed with the generated solutions as the center points. In the center point, the generated solution, the original content based on which the solution is generated and the comment column chart indicating whether it is useful or not are displayed. Each center point is connected to multiple subsidiary points, and in the subsidiary points, the other contents collected by the user that can be refined into the same solution are displayed. A center and its subsidiary points form a map, and multiple maps are displayed in the favourites. In addition, for the non-solution contents in the favourites that cannot be refined into detailed steps, the system will perform semantic recognition on these contents and refine several "topics", and these contents are displayed with the topics as the center points. By displaying the favourites in the form of a map, the effective information, i.e. the solution content and the success rate data, can be directly presented, so that the user does not have to enter the detail page to recall the reason for collecting the content and then judge whether the content is reliable, thereby improving the efficiency of the user in reading the collected content and screening the desired solution.

[0186] 5、Scheme Accompany Mode. After the user judges the best scheme in the collection folder by comparing the success rate of different schemes, the number of comments and the number of attachments, etc., he can choose to enter the scheme accompany mode. The highest success rate, the most useful comments, or the most attachments (indicating that the user is most interested in the scheme and has collected the most content pointing to the scheme) can be determined as the best scheme. The specific standard is subject to the user's idea. This scheme only provides a reference basis for judgment. After entering the accompany mode, the system will identify the time nodes (such as n hours in advance, the nth day, every nth day, etc.) appearing in the scheme steps. The user can customize the specific time of the operation start, and after setting, the system will send a reminder message at each time node. The user clicks the reminder message to enter the accompany mode page, which will present detailed operation steps. For mobile phone operations, when exiting the app to other pages, the operation step floating window will be displayed. The system will automatically display the next step operation in the floating window after detecting that the user has completed the current step. For offline non-mobile phone operations, the user can upload their own operation description and operation pictures. The system will identify the user's uploaded content to determine whether the user has completed the current step and give a prompt whether it is completed. For example, the user selects the "PC ticketing" scheme to enter the accompany mode. The system identifies the time node of "2 minutes before ticketing" in the first step and provides the user with a ticketing time setting entry. The user sets the ticketing time to May 25, 2024, 15:00. The process will start 2 minutes before ticketing, that is, May 25, 2024, 14:58. Ten minutes before the process starts, that is, 14:48 that day, the system will send a reminder message to the user. The user clicks the reminder message to enter the accompany mode page and waits until the process starts to operate according to the operation steps. When the user performs mobile phone operations such as "open XXX app", the system will display the operation description in the form of a floating window; after the user opens the XXX app, the system will present the next step "pre-fill ticketing information" in the floating window. When the user performs non-mobile phone operations such as "open computer XXX official website login account", he can return to the accompany mode page and upload the operation picture such as the PC screenshot. The system will judge the operation completion according to the picture and display "Step 3 completed". The content of Step 4 can be seen. Through the scheme accompany mode, the user does not have to manually set the time reminder of each operation step and does not have to judge whether his operation is correct. When performing mobile phone operations, the user does not have to switch between the app and other apps to view the operation steps, so the user can complete the operation more easily.

[0187] Referring to FIG. 20, a user operation involved in the present embodiment and its corresponding technical principle introduction diagram are shown. The technical principle involved in the present application is introduced as follows in combination with FIG. 20:

[0188] 1. Extract the collected content into a scheme with clear steps;

[0189] By using a large language model to analyze the semantic content of the collected text, the scheme name and steps are extracted. The large language model first performs word segmentation on the text of the collected content, identifying key theme words and action words. Then, according to the theme words, the scheme name is summarized, for example, the content related to "train ticket rush" is summarized as "train ticket rush scheme". For the extraction of steps, the model analyzes the logical order and action description in the text, and arranges the related actions in the order of operation steps, such as "open the rush ticket software", "input the departure place and destination", etc.

[0190] If there are pictures, the picture text in the collected content is extracted by OCR, and the picture objects are recognized by the target detection algorithm (SSD), and the picture is associated with the text steps. OCR first preprocesses the picture, including grayscale, noise reduction, and binarization operations, to improve the clarity and recognizability of the image. Then, using the optical character recognition algorithm, the characters in the preprocessed picture are recognized, and the text in the picture is converted into an editable text format. For example, for a picture containing operation steps, OCR will identify the text content in it, such as "Step 1: Prepare materials".

[0191] 2. Calculate the success rate of the scheme by grabbing all platform-related content;

[0192] Search for the scheme keyword (scheme name) on all platforms, and use a large language model to perform semantic recognition on all search results to filter out content that can be extracted as the same scheme.

[0193] The search method can be to call the search interface of the platform and input the scheme name as the search keyword into the search box. The search range includes all related content within the platform, such as articles, videos, pictures, etc. For example, if the scheme name is "travel guide", all content containing "travel guide" in the title, body, tags, etc. within the platform will be searched. At the same time, in order to improve the accuracy of the search, some search rules can also be combined, such as sorting the search results, and preferentially displaying the content with high relevance and high heat to the scheme name.

[0194] The large language model will first encode the text of the search results, converting the text into a vector representation. Then, analyze the key information in the text, such as the theme, core steps, and target. For each search result, compare its key information with the key information of the original scheme. For example, if the original scheme is about "bicycle repair", the large language model will determine whether the search results are related to bicycle repair and whether the steps are similar to the original scheme. By calculating the similarity (such as cosine similarity) between the text vectors, if the similarity reaches a certain threshold (such as 0.8), it is considered that the search result can be extracted as the same scheme.

[0195] The screening method is: after refining each search result into a step-by-step scheme, comparing each step with the original scheme step by step, and judging the similarity between each step through the sentence embedding method. Sentence embedding is to encode sentences into dense vector representations, and then calculate the similarity between two vectors. Specifically, for each step, a deep learning model is used to encode it into a fixed-length vector. Suppose the vector of the original scheme step is The vector of the search result step is Calculate their cosine similarity The value of S is closer to 1, the more similar the two steps are. If the distance between two vectors is very close, it means that the semantics of the two sentences are very similar. There are several different ways to quantify the similarity of the sentence embedding method. For example, the cosine similarity (Cosine Similarity) of two sentence vectors is calculated, and the range is between [-1, 1]. The value is closer to 1, the more similar the two sentences are. If the similarity of each step of the search result extracted from the scheme and the original scheme is greater than or equal to 0.8, the search result is judged to be the same scheme.

[0196] Among them, sentence embedding is a technology that encodes sentences into dense vector representations. Its core idea is as follows: 1) Encode sentence semantics: for a given sentence, use a deep learning model to encode it into a fixed-length vector. This vector can capture the semantic information of the sentence, such as the theme, sentiment, syntax structure, etc. of the sentence. 2) Vector space representation: The encoded sentence vector is mapped to a high-dimensional semantic vector space. In this space, semantically similar sentences will be encoded as close to each other. 3) Similarity calculation: In order to judge whether two sentences express the same meaning, we can calculate the similarity between their corresponding vectors, such as cosine similarity or Euclidean distance. If the distance between two vectors is very close, it means that the semantics of the two sentences are very similar.

[0197] The comments under the screened content are subjected to semantic recognition, and the comments are divided into "expressing useful", "expressing useless", and "not expressing useful / useless". The number of comments in the three categories is counted. The success rate of the scheme is "success rate = "expressing useful" comment number / ("expressing useful" comment number + "expressing useless" comment number)". Among them, the comments expressing useful can be subdivided into "expressing very useful" and "expressing generally useful". If the keywords such as "really", "super", "thank you", exclamation mark, [heart] [rose] [happy] emoji, and other expression degree, tone, and positive emotion appear in the comment, the comment can be determined as "expressing very useful"; if the above keywords do not appear, the comment is determined as "expressing generally useful". Similarly, the comments expressing useless can be subdivided into "expressing very useless" and "expressing generally useless". If the keywords such as "really", "completely", "not at all", exclamation mark, [vomit] [petrification] [angry] emoji, and other expression degree, tone, and negative emotion appear in the comment, the comment can be determined as "expressing very useless"; if the above keywords do not appear, the comment is determined as "expressing generally useless". The user can expand the above data by clicking the useful and useless comment bar chart.

[0198] 3. Favourites map mode

[0199] 1) Rendering of the scheme map: traverse the data in the scheme database, where each scheme is rendered as a center point, and the original content based on the scheme, the success rate of the scheme, and the "expressing useful / useless" comment bar chart are displayed at the center point. Traverse the other contents in the scheme database that can be refined into the same scheme, and select the part that is collected into the favourites by the user. Each such content is rendered as an affiliated point of the center point.

[0200] 2) Rendering of the topic map: through the semantic recognition of the large language model to the contents in the favourites that cannot be refined into a scheme, the topics are refined, and each topic is rendered as a center point. The comments under the topic content are subjected to semantic recognition and the number of "positive" and "negative" comments is counted, and the positive and negative comment bar charts are rendered and displayed at the topic center point.

[0201] The large language model performs semantic recognition on the comments under the topic content and counts the number of "positive" and "negative" comments. The large language model performs word segmentation processing on each comment, analyzes the words, sentence structure and emotional tendency in the comment. For example, if positive words such as "very good" and "very satisfied" appear in the comment, it is judged as a positive comment; if negative words such as "very bad" and "unsatisfied" appear, it is judged as a negative comment. For some comments with ambiguous semantics, the model will make a comprehensive judgment in combination with the context. In terms of the number of counts, two counters are set to record the number of positive and negative comments. Each time a positive comment is identified, the positive comment counter is incremented by 1; each time a negative comment is identified, the negative comment counter is incremented by 1. Finally, the specific number of "positive" and "negative" comments is obtained.

[0202] The collection plan and the topic are displayed in the form of a map, which is more intuitive, one glance, and more efficient than the form of sequential arrangement. Users no longer need to scroll down to view the content one by one, but can see the extracted key information (plan and topic) and the original content collected within one or two screens.

[0203] 4. Plan companion mode

[0204] 1) Set the operation time and send a message reminder: Identify the time nodes in the plan steps, and perform semantic analysis on the plan step text using the large language model to divide the text into time category text (such as n hours in advance, n days, every n days, etc.) and non-time category text. Time category text is a text type divided by the large language model after semantic analysis of the plan step text, containing time-related words (such as "in advance", "day", "every", etc.) and specific time units (such as "hours", "days", etc.), used to determine the execution time of the operation steps. Non-time category text is a text type divided by the large language model after semantic analysis of the plan step text, i.e. text that does not contain specific time-related words and specific time units, and is unrelated to the time constraints of the operation steps.

[0205] Specifically, the large language model will analyze the part of speech and semantics of each word in the plan step text. If the word is related to time, such as "in advance", "day", "every", etc., and is followed by a specific time unit, such as "hours", "days", etc., the text containing these words is divided into time category text, and the rest of the text is divided into non-time category text.

[0206] For operation steps with time category text, a time setting button is provided. Read the user-set time and use the natural language reasoning ability of the large language model to infer the real time of each operation start, and send a message reminder at that time point. Suppose the user sets the operation start time as T startIf the time class text in the plan step is to perform an operation tconstraint hours in advance, then the real time T real = T start The large language model will reason according to such a logical relationship.

[0207] 2) Mobile phone operation floating window companion: semantic analysis is performed on the operation steps, and it is judged that the operation is a mobile phone operation. After the user exits the app, the operation steps are rendered into a mobile phone floating window. The user's mobile phone screen is read frame by frame, and each frame is recognized by the SSD algorithm. The mobile phone screen and the operation steps are matched, and the floating window content is updated when the mobile phone screen enters the next operation step.

[0208] Specifically, first, the SSD algorithm performs target detection on each frame of the read mobile phone screen, identifying various objects in the screen and their positions, categories, and other information. Then, the identified object information is compared with the key elements in the operation steps. For example, the operation step is "click the payment button on the screen", and after the SSD identifies the button object in the screen, it will further judge whether the button is a payment button. This can be determined by the color, text identification, and other characteristics of the button. If the identified object matches the key elements in the operation step, it is considered that the mobile phone screen matches the operation step successfully; if it does not match, the next frame of the screen is identified and matched.

[0209] 3) Non-mobile phone operation supports uploading operation description and picture: semantic analysis is performed on the operation steps, and it is judged that the operation is a non-mobile phone operation. An operation description input box and an operation picture upload button are provided. Semantic analysis and image recognition are performed on the operation description and operation image to determine whether the operation is completed correctly. If it is determined that it is, the nth step is completed and the next step is entered; if it is determined that it is not, the nth step is not completed, and the large language model generates a reason for the incomplete operation, and the next step cannot be entered.

[0210] Among them, semantic analysis is performed on the operation steps to determine whether the operation is a mobile phone operation or a non-mobile phone operation. The large language model will deeply analyze the text of the operation steps to identify key information and features. If the operation steps contain specific words related to the mobile phone, such as "open the mobile phone APP", "click the mobile phone screen", "use the mobile phone camera", etc., or involve mobile phone-specific functions and operation methods, such as "slide the mobile phone screen", "receive mobile phone notifications", etc., it is determined to be a mobile phone operation. If the operation steps contain descriptions related to computers, offline devices, etc., such as "open computer software", "operate in a physical store", "connect external devices", etc., or the operation scene is obviously not suitable for mobile phones, such as "operate large mechanical devices", etc., it is determined to be a non-mobile phone operation.

[0211] When generating the unfinished reason by the large language model, the large language model first analyzes the standard requirements of the operation steps, the operation description, and the actual situation reflected by the operation image. It compares the differences between the two and finds out the factors that may cause the operation to be unfinished. For example, the operation step requires "pour the liquid into the container to the calibration line", while the operation description and image show that the liquid does not reach the calibration line. The large language model will generate the unfinished reason according to this information, such as "the amount of liquid poured is insufficient, and does not meet the calibration line requirement". At the same time, the model will combine the experience and knowledge of similar operations in the past to give more accurate and detailed unfinished reasons.

[0212] In this embodiment, by using the large language model to rework the collected content and related feedback, the operation scheme with clear steps is extracted from the original content produced by the user, and the success rate data of the scheme is extracted from the original feedback produced by the user. Secondly, by using OCR (Optical Character Recognition) and SSD (target detection algorithm) to identify the scheme picture and user operation image, by using the large language model to perform semantic analysis on the scheme steps and user operation description, the user operation and the scheme steps are matched. Finally, the above technologies are combined to reconstruct the collection, and the collection content is displayed around the scheme. This makes the user's collection content have more refined and accurate information and data, so that the user can more efficiently select the best solution to the problem and implement the operation.

[0213] In some specific embodiments, the present application also provides another application scenario. In this application scenario, the information stream application can push content to the user, so that the terminal can display the pushed content. If the user is interested in the content during browsing, the user can perform a collection operation. When the user selects the content in the collection folder to browse again, if the content is a solution content including strategy information describing the achievement of a specified target, the terminal can further display the operation scheme extracted from the solution content, so that the user can better understand the solution content by reading the operation scheme, improve the readability and operability of the content, and in addition, the user can also perform a collection operation directly on the operation scheme; if the content is a topic type content, the terminal can further display at least one topic extracted from the topic type content, and display other pushed contents under the topic that can extract the topic, so that the user can further understand the extracted topic by clicking these pushed contents.

[0214] In this application scenario, if the operation scheme corresponding to the solution content collected by the user is displayed, the statistical information obtained by counting the user feedback information related to the operation scheme is also displayed, so as to help the user intuitively understand the reliability of the operation scheme. When the user views the data detail page of the operation scheme, the positive feedback statistical information and the negative feedback statistical information, and the corresponding user positive feedback information and user negative feedback information are displayed. If the user comments on the solution content are collected, the process described in the claims is also performed, and the collection result and the corresponding operation scheme are displayed.

[0215] It should be understood that, although each step in the flowchart involved in each of the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each of the above embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.

[0216] Based on the same inventive concept, the embodiments of the present application also provide a content collection device for implementing the above-mentioned content collection method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more content collection device embodiments provided below can refer to the limitations of the content collection method in the above text, which will not be repeated here.

[0217] In some embodiments, as shown in FIG. 21, a content collection device 2100 is provided, which includes:

[0218] The content display module 2102 is configured to display solution content in the application program, the solution content including strategy information for achieving a specified target;

[0219] The content collection module 2104 is configured to, in response to a collection operation for the solution content, display a collection result of adding the solution content to a collection folder of the application program;

[0220] The operation scheme display module 2106 is configured to, in response to a display trigger event for the solution content, display an operation scheme extracted from the solution content in the application program, the operation scheme including operation steps extracted from the strategy information.

[0221] The above content collection device displays solution content including strategy information for achieving a specified goal in an application, displays a collection result adding the solution content to a collection folder of the application in response to a collection operation for the solution content, and displays an operation scheme extracted from the solution content in the application in response to a display trigger event for the solution content. The operation scheme includes operation steps extracted from the strategy information. Since the displayed operation scheme includes operation steps extracted from the strategy information, the operation scheme is content refined from the solution content. Displaying the operation scheme can enable a user to better understand the collected content according to clear steps included in the operation scheme when collecting content, and improve readability and operability of the collected content.

[0222] In some embodiments, the operation scheme display module is further configured to display statistical information obtained by counting user feedback information related to the operation scheme.

[0223] In some embodiments, the user feedback information related to the operation scheme includes user positive feedback information related to the operation scheme and user negative feedback information related to the operation scheme, and the operation scheme display module is further configured to display a statistical quantity comparison relationship between the user positive feedback information related to the operation scheme and the user negative feedback information related to the operation scheme.

[0224] In some embodiments, the operation scheme display module is further configured to display, in the application, user feedback information related to the operation scheme, wherein the user feedback information related to the operation scheme includes user feedback information for the solution content and user feedback information for associated strategy content of the solution content, and the operation scheme extracted from the associated strategy content is the same as or similar to the operation scheme extracted from the solution content.

[0225] In some embodiments, the user feedback information is displayed on a data detail page of the operation scheme, and the operation scheme display module is further configured to display, on the data detail page, positive feedback statistical information and negative feedback statistical information, display, corresponding to the positive feedback statistical information, user positive feedback information related to the operation scheme used to obtain the positive feedback statistical information, and display, corresponding to the negative feedback statistical information, user negative feedback information related to the operation scheme used to obtain the negative feedback statistical information.

[0226] In some embodiments, the operation scheme display module is further configured to display a feedback information display area corresponding to the solution content and feedback information display areas corresponding to at least one associated strategy content of the solution content respectively; display user feedback information for the solution content in the feedback information display area corresponding to the solution content; and display user feedback information for the associated strategy content in each feedback information display area corresponding to the associated strategy content.

[0227] In some embodiments, the content collection apparatus further comprises a comment content display module configured to display at least one user comment content for the solution content in the application program; in response to a collection operation on a target user comment content in the at least one user comment content, display a collection result of adding the target user comment content to a collection folder of the application program; and display an operation scheme for the target user comment content, the operation scheme for the target user comment content comprising operation steps extracted from associated strategy content corresponding to the target user comment content, the associated strategy content comprising key information in the target user comment content.

[0228] In some embodiments, when a plurality of solution contents are collected in the collection folder, the content collection apparatus further comprises a collection folder page display module configured to display a collection folder page of the collection folder in the application program, display a scheme graph center node of at least one operation scheme in the collection folder page respectively, the scheme graph center node of each operation scheme being used to represent the corresponding operation scheme; for each scheme graph center node, display at least one of a first subsidiary node or a second subsidiary node connected to the scheme graph center node by a connection line, the first subsidiary node being used to represent associated strategy content of the operation scheme represented by the scheme graph center node in the collection folder, and the second subsidiary node being used to represent associated user comment content of the operation scheme represented by the scheme graph center node in the collection folder.

[0229] In some embodiments, the collection folder page display module is further configured to, for each scheme graph center node, display a scheme identifier of the operation scheme represented by the scheme graph center node and at least one of the following information at a display position of the scheme graph center node: a content identifier of a solution content to which the operation scheme represented by the scheme graph center node belongs, scheme content of the operation scheme represented by the scheme graph center node, and statistical information obtained by counting user feedback information related to the operation scheme represented by the scheme graph center node.

[0230] In some embodiments, when the collection folder also collects multiple topic type contents, the collection folder page display module is further configured to: display, in the collection folder page, at least one topic graph center node corresponding to a topic graph of each topic, wherein each topic graph center node is used to represent a corresponding topic; and display, for each topic graph center node, at least one of a third subsidiary node or a fourth subsidiary node connected to the topic graph center node by a connection line, wherein the third subsidiary node is used to represent a topic type content in the collection folder that is related to the topic represented by the topic graph center node, and the fourth subsidiary node is used to represent a user comment content in the collection folder that is related to the topic represented by the topic graph center node.

[0231] In some embodiments, the collection folder page display module is further configured to: for each topic graph center node, display, at a display position of the topic graph center node, a topic represented by the topic graph center node, a target topic type content in the collection folder that is related to the topic represented by the topic graph center node, and statistical information obtained by counting user feedback information related to the topic represented by the topic graph center node; and the target topic type content is a topic type content with the largest number of positive feedback information among all topic type contents related to the topic represented by the topic graph center node.

[0232] In some embodiments, the collection folder page further displays a first collection folder display mode option and a second collection folder display mode option, and the collection folder page display module is further configured to: display, in the collection folder page, a scheme graph center node of an operation scheme graph corresponding to each operation scheme when the first collection folder display mode option is in a selected state; and display, in the collection folder page, the contents collected in the collection folder in sequence when the second collection folder display mode option is in the selected state.

[0233] In some embodiments, the content collection device further comprises an accompanying mode starting module configured to start an accompanying mode for an operation scheme in response to an accompanying mode triggering operation for the operation scheme; and display step description information of a current operation step to be performed in the accompanying mode, and display step description information of a next operation step to be performed when a triggering condition of the next operation step to be performed is met.

[0234] In some embodiments, when the current operation step to be performed is indicated with time constraint information, the accompanying mode starting module is further configured to: trigger an operation reminder for the current operation step to be performed when a current time reaches a reminding time matched with the time constraint information in the accompanying mode; and display step description information of the current operation step to be performed in response to an operation step triggering event for the operation reminder.

[0235] In some embodiments, when the time constraint information is used to constrain the execution time of the current operation step to be executed relative to the event time of the event to which the current operation step to be executed is directed, the companion mode starting module is further configured to: display a companion mode setting page, and display an event time setting control for the current operation step to be executed on the companion mode setting page; determine the event time of the event to which the current operation step to be executed is directed in response to a setting operation on the event time setting control; and determine the reminding time matched with the time constraint information according to the event time of the event to which the current operation step to be executed is directed and the time constraint information.

[0236] In some embodiments, the companion mode starting module is further configured to: when the current operation step to be executed ends and the trigger condition of the next operation step to be executed is not met, display a failure reason for the execution failure of the current operation step to be executed.

[0237] The above-mentioned various modules in the content collection apparatus can be implemented wholly or partially by software, hardware, and combinations thereof. The above-mentioned various modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to the above-mentioned various modules.

[0238] In some embodiments, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in FIG. 22. The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store solution content, topic type content, and the like. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement the content collection method provided in the embodiments of the present application.

[0239] In some embodiments, a computer device is provided, which can be a terminal, and its internal structure diagram can be as shown in FIG. 23. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement the content collection method provided in the embodiments of the present application. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device. It can also be an external keyboard, touchpad or mouse, etc.

[0240] Those skilled in the art can understand that the structure shown in FIG. 22 and FIG. 23 is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0241] In some embodiments, a computer device is provided, which includes a memory and a processor, and the memory stores a computer program. The processor executes the computer program to implement the steps of the above-mentioned content collection method.

[0242] In some embodiments, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by the processor to implement the steps of the above-mentioned content collection method.

[0243] In some embodiments, a computer program product is provided, which includes a computer program. The computer program is executed by the processor to implement the steps of the above-mentioned content collection method.

[0244] To sum up, the application provides a content collection method, device, computer equipment, computer readable storage medium and computer program product. By displaying the solution content containing the specified target strategy information in the application program, the user can directly obtain the strategy direction for solving specific problems in the application program. When receiving the collection operation for the solution content, the collection result of adding it to the application program collection is displayed. This process clearly shows the result of the user's collection behavior, so that the user knows whether the collection is successful. Then, if the display trigger event for the solution content is detected, the operation scheme containing the operation steps extracted from the solution content is displayed in the application program. Since the operation scheme is obtained by refining the solution content, the originally complex and disordered strategy information is converted into clear steps, which greatly improves the structural degree of information at the technical level, so that the user can more efficiently understand and absorb the collected content, significantly improves the readability and operability of the collected content, and reduces the cost of obtaining effective information.

[0245] Further, corresponding to the operation scheme, statistical information obtained by statistically analyzing the user feedback information related to the operation scheme is also displayed. In terms of technical implementation, by collecting, sorting and statistically analyzing a large amount of user feedback information, the scattered user opinions are converted into intuitive statistical data. This process uses data processing and analysis technology, so that the user can quickly understand the overall situation of the operation scheme from a macro perspective. By displaying the statistical information, the user can have a more intuitive understanding of the operation scheme, which provides an objective basis based on data for the user to judge the reliability of the operation scheme, avoids the user evaluating the scheme based on subjective feelings or a small amount of information, and improves the efficiency and accuracy of the user filtering scheme.

[0246] When the user feedback information related to the operation scheme includes positive feedback information and negative feedback information, the statistical quantity comparison relationship between the two is displayed. In terms of technology, by statistically analyzing the positive and negative feedback information respectively, and presenting the comparison relationship in the same display manner, such as a column chart or other visual means, the complex user attitude can be displayed in an intuitive graphical form. The presentation of this comparison relationship enhances the visualization effect of the information at the technical level, so that the user can more clearly understand the reliability of the operation scheme. The user can quickly judge the advantages and disadvantages of the operation scheme through simple visual comparison, improve the accuracy of the user's judgment of the reliability of the scheme, and reduce the decision-making time and cost of the user.

[0247] Further, the user feedback information related to the operation scheme is displayed in the application, which includes feedback for the solution content and its associated policy content, and the operation scheme extracted from the associated policy content is the same or similar to that extracted from the solution content. In terms of technical implementation, the system needs to associate and match a large amount of solution content and associated policy content, filter out the content with the same or similar operation scheme through semantic analysis, text matching and other technical means, and integrate and display the corresponding user feedback information. Since the feedback information not only includes the feedback for the original solution content, but also covers the associated policy content, it can more comprehensively reflect the user's feedback on the operation scheme, provide more rich reference information for the user, enable the user to understand the actual effect of the operation scheme from multiple angles, and improve the comprehensiveness and accuracy of the user's evaluation of the scheme.

[0248] When the user feedback information is displayed on the data detail page of the operation scheme, the positive feedback statistical information and the negative feedback statistical information are displayed on the page, and the user positive feedback information and the user negative feedback information used to obtain these information are correspondingly displayed. In terms of technology, this involves hierarchical display and associated display of data. The system needs to associate the statistical information and the specific user feedback information, and reasonably layout on the page to facilitate user viewing. This can intuitively show the positive and negative attitudes of users to the operation scheme from the macro and micro dimensions, and provide effective data basis based on real user feedback for the user to judge the reliability of the scheme. The user can quickly understand the overall situation through the statistical information, and can deeply understand the actual experience of other users through the specific user feedback information, which improves the scientificity and accuracy of the user's judgment of the reliability of the scheme.

[0249] Further, the feedback information display area corresponding to the solution content and its at least one associated policy content is displayed, and the corresponding user feedback information is displayed in each area. In terms of technical implementation, the page needs to be reasonably divided and laid out, and the feedback information of different contents is displayed in different areas. By partitioning the user feedback information of each solution content, the source of the user feedback information can be intuitively displayed, which facilitates user viewing and comparison of feedback of different contents. In terms of technology, this partitioned display improves the organization and readability of information, enabling users to more clearly distinguish the feedback differences of different contents, which helps users more accurately evaluate each scheme.

[0250] At least one user comment content for the solution content is displayed in the application, when a collection operation for a target user comment content is received, a collection result of adding it to the application collection is displayed, and an operation scheme for the target user comment content is displayed, the operation scheme including operation steps extracted from the associated strategy content. In technology, the system needs to identify and process the user comment content, find out the key information contained therein, and extract the corresponding operation scheme from the associated strategy content. Considering that there may be different problem-solving schemes in the user comment content than the original solution content, allowing users to collect comment content and generate corresponding operation schemes, technically expands the scope and depth of collection, allowing users to directly collect valuable comments without having to exit the current content and manually search for the scheme proposed by the comments, improving interaction efficiency and reducing user operation steps and time cost.

[0251] When multiple solution contents are collected in the collection, a collection page of the collection is displayed in the application, the scheme graph center node of at least one operation scheme is displayed in the page, each center node represents an operation scheme, and at least one of the first subsidiary node or the second subsidiary node connected by the connecting line is also displayed, the first subsidiary node represents the associated strategy content, and the second subsidiary node represents the associated user comment content. In technical implementation, a graph data structure needs to be constructed to associate and organize the operation scheme, the associated strategy content and the associated user comment content, and displayed in the form of a graph. Displaying solution content around the operation scheme can intuitively present the effective information of the solution content. In technology, the complex content relationship is presented in the form of a graph, so that users do not need to enter the detail page to recall the reason for collecting the content and judge whether the content is reliable, improving the efficiency of users reading the collected content and selecting the desired scheme, and reducing the difficulty of users obtaining effective information.

[0252] Further, for each scheme graph center node, the scheme identifier of the operation scheme is displayed at the display position, and at least one of the content identifier of the operation scheme, the content of the solution content to which the operation scheme belongs, and the statistical information obtained by counting the user feedback information related to the operation scheme is displayed. In technology, the display content of the graph center node needs to be reasonably laid out and displayed, and multiple information is integrated on one node. Displaying multiple information on the scheme graph center node can more intuitively present effective information, further improve the readability of the operation scheme graph, and facilitate users to quickly understand the key information of the operation scheme. By concentrating multiple information on one node, the information search cost of the user is reduced, and the information acquisition efficiency is improved.

[0253] When the collection still collects multiple topic type contents, at least one topic graph center node corresponding to the topic graph of each topic is displayed on the collection page, each center node represents a topic, and at least one of the third subsidiary node or the fourth subsidiary node connected to the center node by a connection line is also displayed, the third subsidiary node represents a topic type content, and the fourth subsidiary node represents a user comment content. In terms of technical implementation, semantic analysis needs to be performed on the topic type content, the topic is extracted, and a topic graph data structure is constructed to associate and display the topic, the topic type content and the user comment content. Displaying the topic type content around the topic can intuitively present the effective information of the topic type content. At the technical level, by visualizing the topic graph, the topic related content and comments are integrated, so that the user does not need to enter the detail page to recall the reason for collecting the content and judge whether the content is reliable, thereby improving the efficiency of the user reading the collected content and screening the favorite scheme, and improving the organization and accessibility of information.

[0254] Further, for each topic graph center node, the topic, the target topic type content related to the topic in the collection, and the statistical information obtained by counting the user feedback information related to the topic are displayed at the display position thereof. In terms of technology, the display content of the topic graph center node needs to be optimized and integrated, and the topic, the related content and the statistical information are reasonably arranged. Displaying multiple information on the topic graph center node can more intuitively present the effective information, further improve the readability of the topic graph, and help the user quickly understand the key information and feedback of the topic. By centrally displaying multiple information, the user can obtain comprehensive information about the topic on one page, improving the user's cognitive efficiency of the topic.

[0255] The collection page also displays a first collection display mode option and a second collection display mode option. When the first collection display mode option is in a selected state, the scheme graph center node of the operation scheme graph is displayed on the collection page. When the second collection display mode option is in a selected state, the contents collected in the collection are sequentially arranged and displayed. In terms of technical implementation, two different page layouts and display logics need to be implemented, and switching is performed according to the user's selection. Providing two different page display modes improves the flexibility of the collection page content display, and can meet the browsing needs of different users. Different users may have different information acquisition habits. By providing diversified display modes, the adaptability and user experience of the system are enhanced at the technical level.

[0256] Further, in response to the operation step triggering event of the operation reminder, the step description information of the current operation step to be executed is displayed. In terms of technology, time monitoring and reminding functions need to be implemented, and the reminding time is accurately calculated according to the time constraint information, and the reminding is triggered at the appropriate time. By triggering the operation reminder at the appropriate time, the user's operation can be better guided. In terms of technology, the time management and reminding technology is used to avoid the user missing the operation time, improve the accuracy and timeliness of the operation, and ensure the smooth execution of the operation scheme.

[0257] When the current operation step to be executed has time constraint information, in the accompanying mode, when the current time reaches the reminding time matched with the time constraint information, the operation reminder for the current operation step to be executed is triggered, and in response to the operation step triggering event of the operation reminder, the step description information of the current operation step to be executed is displayed. In terms of technology, time monitoring and reminding functions need to be implemented, and the reminding time is accurately calculated according to the time constraint information, and the reminding is triggered at the appropriate time. By triggering the operation reminder at the appropriate time, the user's operation can be better guided. In terms of technology, the time management and reminding technology is used to avoid the user missing the operation time, improve the accuracy and timeliness of the operation, and ensure the smooth execution of the operation scheme.

[0258] When the time constraint information is used to constrain the execution time of the current operation step to be executed relative to the event time of the event, the accompanying mode setting page is displayed, and the event time setting control for the current operation step to be executed is displayed on the page. After the user sets the event time through the control, the matching reminding time is determined according to the event time and the time constraint information. In terms of technology, the functions of event time setting and reminding time calculation need to be implemented, and accurate calculation is performed according to the event time set by the user and the time constraint information. The user can set the event time and determine the reminding time independently, which improves the interaction flexibility in the accompanying mode, and ensures the timeliness and effectiveness of the operation reminder triggering. By giving the user the right to set independently, the individualization and adaptability of the system are enhanced in terms of technology, and the time arrangement needs of different users are met.

[0259] When the current operation step to be executed ends and the trigger condition of the next operation step to be executed is not reached, the failure reason for the execution failure of the current operation step to be executed is displayed. In terms of technical implementation, the execution result of the operation step needs to be judged and analyzed to find out the operation failure reason and display it. Displaying the failure reason can help users understand the problem of operation failure. In terms of technology, through the analysis and feedback of the operation result, the user is provided with the direction of improving the operation, so as to re-execute the correct operation, improve the success rate of user operation, and reduce the trial and error cost of the user.

[0260] In addition, by using a large language model to perform semantic analysis on the text content in the collection content, the scheme name and steps are extracted. If there are pictures, the picture text is extracted by OCR, and the picture objects are recognized by a target detection algorithm (SSD) and associated with the text steps. In terms of technology, the semantic analysis technology of the large language model can deeply understand the meaning of the text, accurately summarize the scheme name and organize the operation steps, and improve the abstraction and structuring degree of information. The application of OCR technology and SSD algorithm makes the information in the pictures also be effectively utilized, enriching the information source of the operation scheme. This scheme improves the readability and operability of the content, and converts the originally complex and disordered collection content into clear and orderly operation scheme, reducing the difficulty of user understanding and execution, and improving the efficiency of user obtaining effective information.

[0261] Further, the success rate of the scheme is calculated by grabbing the relevant content on all platforms, the scheme keywords are searched on all platforms, the semantic recognition of the search results is performed by a large language model, the content that can be extracted into the same scheme is selected, and the comments under these contents are semantically recognized and classified. In terms of technology, by calling the search interface of the platform and the semantic recognition technology of the large language model, relevant scheme content can be accurately found in a large amount of platform content, and comments can be accurately classified. This scheme provides effective data basis for users to judge the reliability of the scheme based on real user feedback, so that users can understand the actual effect of the scheme from a wider range, and improve the accuracy and reliability of the user's selection of the scheme.

[0262] In the bookmark map mode, the system analyzes and processes the content that can be extracted into an operation scheme to generate an operation scheme map and a topic map, and displays the collection content in the form of a map. In terms of technology, it involves data association, organization and visualization display technology. By displaying the bookmark in the form of a map, the effective information can be intuitively presented, so that users can see the extracted key information and the original content of the collection within one or two screens, improve the screen efficiency, reduce the user's information search time, and improve the user's efficiency of reading the collection content and selecting the desired scheme.

[0263] In the scheme companion mode, the operation time is set and a message reminder is sent. The semantic analysis of the scheme step text is performed by the large language model, the time node is identified, the time setting button is provided, the real time of the operation start is inferred, and the reminder is sent. In terms of technology, the semantic analysis and natural language reasoning capabilities of the large language model are used to realize the accurate calculation and reminder of the operation time. This makes the user not have to manually set the time reminder of each operation step, improves the convenience and accuracy of the operation, and ensures that the operation scheme can be executed on time. The phone operation floating window companion renders the operation steps as a mobile floating window after determining that the operation steps are for mobile phone operation through semantic analysis. The image recognition of the mobile phone screen is performed using the SSD algorithm, the operation steps are matched, and the floating window content is updated. In terms of technology, the semantic analysis, image recognition, and floating window rendering technologies are combined to realize real-time monitoring and guidance of the user's mobile phone operation, so that the user does not need to frequently switch applications to view the steps during the operation, and the operation efficiency is improved. The non-mobile phone operation supports uploading operation description and pictures. The semantic analysis and image recognition of the operation description and operation images are performed to determine whether the operation is completed. In terms of technology, the semantic analysis and image recognition technologies are used to evaluate and feedback the user's non-mobile phone operation, ensure the correctness of the user's operation, and improve the success rate of the operation.

[0264] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use, and processing of related data need to comply with relevant national and regional laws, regulations, and standards.

[0265] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0266] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0267] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for collecting contents, executed by a computer device, the method comprising: displaying a solution content in an application, the solution content comprising strategy information describing a strategy for achieving a specified goal; in response to a collection operation for the solution content, displaying a collection result of adding the solution content to a collection folder of the application; and in response to a display trigger event for the solution content, displaying an operation scheme extracted from the solution content in the application, the operation scheme comprising operation steps extracted from the strategy information. 2.The method of claim 1, further comprising: in response to the operation scheme, displaying statistical information obtained by counting user feedback information related to the operation scheme. 3.The method of claim 2, wherein the user feedback information related to the operation scheme comprises positive user feedback information related to the operation scheme and negative user feedback information related to the operation scheme; and the displaying the statistical information obtained by counting the user feedback information related to the operation scheme comprises: displaying a statistical quantity comparison relationship between the positive user feedback information related to the operation scheme and the negative user feedback information related to the operation scheme. 4.The method of any one of claims 1 to 3, further comprising: in the application, displaying user feedback information related to the operation scheme; wherein the user feedback information related to the operation scheme comprises user feedback information for the solution content and user feedback information for associated strategy content of the solution content, and an operation scheme extracted from the associated strategy content is the same as or similar to the operation scheme extracted from the solution content. 5.The method of claim 4, wherein the user feedback information is displayed on a data detail page of the operation scheme, and the displaying the user feedback information related to the operation scheme comprises: in the data detail page, displaying positive feedback statistical information and negative feedback statistical information; in response to the positive feedback statistical information, displaying the positive user feedback information related to the operation scheme used to obtain the positive feedback statistical information; and in response to the negative feedback statistical information, displaying the negative user feedback information related to the operation scheme used to obtain the negative feedback statistical information. 6.The method of claim 4, wherein the displaying the user feedback information related to the operation scheme comprises: displaying a feedback information display area corresponding to the solution content and feedback information display areas corresponding to at least one associated strategy content of the solution content respectively; in the feedback information display area corresponding to the solution content, displaying user feedback information for the solution content; and in each of the feedback information display areas corresponding to the associated strategy content, displaying user feedback information for the associated strategy content. 7.The method of any one of claims 1 to 6, further comprising: in the application, displaying at least one user comment content for the solution content. ​ displaying a collection result of adding the target user comment content to the collection folder of the application in response to a collection operation on the target user comment content in the at least one user comment content; displaying an operation scheme for the target user comment content, the operation scheme for the target user comment content comprising operation steps extracted from associated strategy content corresponding to the target user comment content, the associated strategy content comprising key information in the target user comment content.

8. The method of any one of claims 1 to 7, when a plurality of solution contents are collected in the collection folder, the method further comprising: displaying a collection folder page of the collection folder in the application, and displaying a scheme graph center node of an operation scheme graph corresponding to each operation scheme in the collection folder page, each scheme graph center node of an operation scheme graph being used to represent the corresponding operation scheme; for each scheme graph center node, displaying at least one of a first subsidiary node or a second subsidiary node connected to the scheme graph center node by a connection line, the first subsidiary node being used to represent associated strategy content of the operation scheme represented by the scheme graph center node in the collection folder, and the second subsidiary node being used to represent associated user comment content of the operation scheme represented by the scheme graph center node in the collection folder.

9. The method of claim 8, the method further comprising: for each scheme graph center node, displaying a scheme identifier of the operation scheme represented by the scheme graph center node and displaying at least one of the following information at a display position of the scheme graph center node: a content identifier of a solution content to which the operation scheme represented by the scheme graph center node belongs, a scheme content of the operation scheme represented by the scheme graph center node, and statistical information obtained by counting user feedback information related to the operation scheme represented by the scheme graph center node.

10. The method of claim 8 or 9, when a plurality of topic contents are also collected in the collection folder, the method further comprising: displaying a topic graph center node of a topic graph corresponding to each topic in the collection folder page, each topic graph center node of a topic graph being used to represent the corresponding topic; for each topic graph center node, displaying at least one of a third subsidiary node or a fourth subsidiary node connected to the topic graph center node by a connection line, the third subsidiary node being used to represent topic contents related to the topic represented by the topic graph center node in the collection folder, and the fourth subsidiary node being used to represent user comment contents related to the topic represented by the topic graph center node in the collection folder.

11. The method of claim 10, the method further comprising: For each topic graph center node, display the topic graph center node at a display position of the topic graph center node, and display the topic graph center node represents a topic, the target topic type content in the collection related to the topic graph center node represents a topic, and the statistical information obtained by counting the user feedback information related to the topic graph center node represents a topic; The target topic type content is the topic type content with the most positive feedback information among all topic type contents related to the topic graph center node represents a topic.

12. The method of any one of claims 8-11, wherein the collection page further displays a first collection display mode option and a second collection display mode option, and the displaying the scheme graph center node of the operation scheme graph corresponding to each operation scheme on the collection page comprises: In a case where the first collection display mode option is in a selected state, displaying the scheme graph center node of the operation scheme graph corresponding to each operation scheme on the collection page. The method further comprises: In a case where the second collection display mode option is in a selected state, sequentially arranging and displaying the content collected in the collection.

13. The method of any one of claims 1-12, further comprising: In response to a companion mode triggering operation for the operation scheme, starting the companion mode for the operation scheme; In the companion mode, displaying step description information of a current operation step to be executed; When a triggering condition of a next operation step to be executed is met, displaying step description information of the next operation step to be executed.

14. The method of claim 13, when the current operation step to be executed indicates time constraint information, the displaying the step description information of the current operation step to be executed in the companion mode comprises: In the companion mode, when a current time reaches a reminder time matched with the time constraint information, triggering an operation reminder for the current operation step to be executed; In response to an operation step triggering event for the operation reminder, displaying the step description information of the current operation step to be executed.

15. The method of claim 14, when the time constraint information is used to constrain an execution time of the current operation step to be executed relative to an event time of an event to which the current operation step to be executed is directed, the method further comprises: Displaying a companion mode setting page, and in the companion mode setting page, displaying an event time setting control for the current operation step to be executed; In response to a setting operation for the event time setting control, determining the event time of the event to which the current operation step to be executed is directed; According to the event time of the event to which the current operation step to be executed is directed and the time constraint information, determining the reminder time matched with the time constraint information.

16. The method of any one of claims 13-15, further comprising: ​ When the current operation step to be executed ends and a trigger condition of a next operation step to be executed is not reached, a failure reason of a failure of executing the current operation step to be executed is displayed.

17. A content collection apparatus, the apparatus comprising: a content display module configured to display, in an application, solution content including strategy information for achieving a specified goal; a content collection module configured to, in response to a collection operation for the solution content, display a collection result of adding the solution content to a collection folder of the application; and an operation scheme display module configured to, in response to a presentation trigger event for the solution content, display, in the application, an operation scheme extracted from the solution content, the operation scheme including operation steps extracted from the strategy information.

18. A computer device, comprising a memory and a processor, the memory storing a computer program, and the processor, when executing the computer program, implements steps of the method in any one of claims 1 to 16.

19. A computer readable storage medium, storing a computer program, and the computer program, when executed by a processor, implements steps of the method in any one of claims 1 to 16.

20. A computer program product, comprising a computer program, and the computer program, when executed by a processor, implements steps of the method in any one of claims 1 to 16.

Images