Page summarization method and device, equipment and storage medium

Abstract

The invention belongs to the field of computers, and discloses a page summarization method and device, equipment and a storage medium. The method comprises the steps of obtaining page information corresponding to a target page in response to a global page summarization instruction triggered based on the target page; determining a scene category corresponding to the page information; and summarizing the page information according to the scene category to obtain page summarized information. According to the invention, the page information is summarized according to the scene category corresponding to the page information, so that the page summarized information is obtained. Compared with an existing mode of summarizing only by relying on the user to read the page content, the page summarizing method and device have the advantages that the page can be summarized according to the scene category corresponding to the page, and the page summarizing accuracy and the reading efficiency of the user are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a page summary method, device, equipment and storage medium. Background Art

[0002] In recent years, with the rapid development of Internet technology, the Internet has become an important channel for people to obtain information. However, the Internet information is redundant and has a huge amount of information, which greatly reduces the efficiency of people obtaining information. Therefore, how to improve users' reading efficiency has become a technical problem that needs to be solved urgently.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a page summary method, device, equipment and storage medium, aiming to solve the technical problem in the prior art that the amount of information data is huge and the content is redundant, resulting in low efficiency of users obtaining information.

[0005] To achieve the above object, the present invention provides a page summary method, which comprises the following steps:

[0006] In response to a global page summary instruction triggered based on a target page, obtaining page information corresponding to the target page;

[0007] Determining a scene category corresponding to the page information;

[0008] The page information is summarized according to the scene category to obtain page summary information.

[0009] Optionally, the step of determining the scene category corresponding to the page information includes:

[0010] Determining sensory modality content and / or webpage media type in the page information;

[0011] The scene category corresponding to the page information is determined according to the sensory modality content and / or the webpage media type.

[0012] Optionally, the step of summarizing the page information according to the scene category to obtain page summary information includes:

[0013] Determine the number of characters corresponding to the page information;

[0014] When the number of characters exceeds a preset number of characters, abbreviating the page information according to the preset number of characters to obtain target abbreviated information;

[0015] The target abbreviation information is summarized according to the scene category to obtain page summary information.

[0016] Optionally, the step of abbreviating the page information according to the preset number of characters to obtain target abbreviated information includes:

[0017] Extracting target information that meets a preset abbreviation condition from the page information;

[0018] abbreviate the target information according to the abbreviation strategy corresponding to the target information to obtain an abbreviation result;

[0019] Determine abbreviation information according to the page information and the abbreviation result;

[0020] When the number of characters in the abbreviation information is less than or equal to the preset number of characters, the abbreviation information is the target abbreviation information.

[0021] Optionally, after the step of summarizing the page information according to the scene category to obtain page summary information, the following steps are included:

[0022] Obtain optimization suggestions from users based on the page summary information feedback;

[0023] The page summary information is modified and optimized based on the optimization suggestion and the page information.

[0024] Optionally, the step of summarizing the page information according to the scene category to obtain page summary information includes:

[0025] Acquire historical web browsing information, and determine user characteristics based on the historical web browsing information;

[0026] Determining summary requirements based on the user characteristics;

[0027] The page information is summarized according to the scenario category and the summary requirement to obtain page summary information.

[0028] Optionally, the step of summarizing the page information according to the scene category to obtain page summary information includes:

[0029] When the scene category is an audio or video category, performing text conversion on the page information to obtain text information corresponding to the page information;

[0030] Extracting key information from the text information;

[0031] Summarizing the key information to obtain summary information;

[0032] The highlight information in the summary information is extracted, and page summary information is generated according to the highlight information and the summary information.

[0033] Optionally, when the scene category is an audio or video category, the step of performing text conversion on the page information to obtain text information corresponding to the page information includes:

[0034] When the scene category is audio and video, determining whether the audio and video file in the page information contains subtitle information;

[0035] If the audio and video file contains subtitle information, the subtitle information in the audio and video file is extracted to obtain text information corresponding to the page information.

[0036] Optionally, the step of summarizing the page information according to the scene category to obtain page summary information includes:

[0037] When the scenario category is a multimodal category, determining a preset modal weight;

[0038] Respectively extracting modal information corresponding to each modality in the page information;

[0039] The page information is summarized according to the preset modal weight and the modal information to obtain page summary information.

[0040] Optionally, the step of summarizing the page information according to the preset modal weight and the modal information to obtain page summary information includes:

[0041] Summarizing each of the modal information to obtain summary information;

[0042] Generate page summary information of the page information according to the preset modal weight and the summary information.

[0043] Optionally, the page summary method further includes:

[0044] In response to an information summary instruction triggered based on a target page, determining a summary range corresponding to the information summary instruction;

[0045] Extracting the information to be summarized according to the summary scope;

[0046] Summarize the information to be summarized and generate a summary result.

[0047] In addition, to achieve the above object, the present invention also provides a page summary device, the device comprising:

[0048] A response module, configured to respond to a global page summary instruction triggered based on a target page and obtain page information corresponding to the target page;

[0049] A determination module, used to determine the scene category corresponding to the page information;

[0050] The summary module is used to summarize the page information according to the scene category to obtain page summary information.

[0051] In addition, to achieve the above-mentioned purpose, the present invention also proposes a page summary device, which includes: a memory, a processor, and a page summary program stored in the memory and executable on the processor, wherein the page summary program is configured to implement the steps of the page summary method described above.

[0052] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a page summary program is stored, and when the page summary program is executed by a processor, the steps of the page summary method described above are implemented.

[0053] The present invention responds to a global page summary instruction triggered based on a target page, obtains page information corresponding to the target page; determines the scene category corresponding to the page information; summarizes the page information according to the scene category to obtain page summary information. Since the present invention summarizes the page information according to the scene category corresponding to the page information, the page summary information is obtained. Compared with the existing method that can only rely on users to read the page content for summary, the above method of the present invention can summarize the page according to the scene category corresponding to the page, thereby improving the accuracy of the page summary and the user's reading efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a structural diagram of a page summary device of a hardware operating environment involved in an embodiment of the present invention;

[0055] Figure 2 A schematic diagram of a flow chart of a first embodiment of a page summary method of the present invention;

[0056] Figure 3-Figure 6 A schematic diagram of a page of the first embodiment of the page summary method of the present invention;

[0057] Figure 7 A schematic diagram of a flow chart of a second embodiment of a page summary method of the present invention;

[0058] Figure 8 A schematic diagram of a flow chart of a third embodiment of a page summary method of the present invention;

[0059] Fig. 9 It is a structural block diagram of the first embodiment of the page summary device of the present invention.

[0060] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0061] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0062] Reference Figure 1 , Figure 1 A schematic diagram of the device structure of a page summary of the hardware operating environment involved in the embodiment of the present invention.

[0063] like Figure 1 As shown, the page summary device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0064] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the page summary device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0065] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a page summary program.

[0066] exist Figure 1In the page summary device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the page summary device of the present invention can be set in the page summary device, and the page summary device calls the page summary program stored in the memory 1005 through the processor 1001, and executes the page summary method provided by the embodiment of the present invention.

[0067] Based on the above-mentioned page summarizing device, an embodiment of the present invention provides a page summarizing method, referring to Figure 2 , Figure 2 This is a flow chart of the first embodiment of the page summary method of the present invention.

[0068] In this embodiment, the page summary method includes the following steps:

[0069] Step S10: in response to a global page summary instruction triggered based on a target page, obtaining page information corresponding to the target page.

[0070] It should be noted that the execution subject of this embodiment may be a page summary device, in which a page summary program (also referred to as an intelligent assistant or intelligent large model) is provided, and the page summary program may be a pre-trained human-computer interaction model based on an intelligent language model and / or an intelligent drawing model, and the page summary device may be a computing service device with data processing, network communication and program running functions, such as a mobile phone, a tablet computer, a personal computer, etc. The following takes the page summary device as an example to illustrate this embodiment and the following embodiments.

[0071] It should be noted that the target page may include an interface containing certain content, such as a web page, a document page, and a multimedia page opened through a browser. The global page summary instruction may be a command to summarize part or all of the content in the target page. The page information corresponding to the target page may be information directly or indirectly contained in the target page. For example, information displayed in the target page and information corresponding to a link in the page.

[0072] Step S20: Determine the scene category corresponding to the page information.

[0073] It should be noted that the scene category may include categories of different sensory modal information, such as text, image, audio, video, etc. The scene category corresponding to the page information may be determined by identifying the scene category corresponding to the page information through the media type in the page information or image recognition technology.

[0074] Further, in order to accurately identify the scene category corresponding to the page information, the step S20 may include: determining the sensory modality content and / or webpage media type in the page information;

[0075] The scene category corresponding to the page information is determined according to the sensory modality content and / or the webpage media type.

[0076] It should be noted that the determining of the sensory modality content in the page information may be identifying different sensory modalities contained in the page information, such as text, image, audio, video, etc. The webpage media type may be metadata information of the webpage, such as tags, attributes or embedded code, <video>and <audio>Tags and CSS classes. Such media type information may indicate whether a web page contains multimodal content. The scene category corresponding to the page information may be determined based on the sensory modal content and / or the web page media type when the sensory modal content is audio and / or video, or when the web page media type is <video>and / or <audio>When the tags are used to characterize audio and video files, it is determined that the scene category is audio and video, and when the sensory modality content is text, or the webpage media type is <h1>and / or When the tags used to characterize the text content are used, it is determined that the scene category is a text category.

[0077] Step S30: Summarize the page information according to the scene category to obtain page summary information.

[0078] It should be noted that summarizing the page information according to the scene category may be summarizing the page information corresponding to the scene category in different summarizing methods according to the scene category. For example, when the scene category is text, summarizing the page information according to the scene category may be summarizing the text; when the scene category is audio and video, summarizing the page information according to the scene category may be first converting the audio and video page information into text content and then summarizing the text.

[0079] In a specific implementation, the page summary program can be integrated into the browser, and a page summary button can be provided in the toolbar of the browser. Figure 3 , Figure 3 This is a page schematic diagram of the first embodiment of the page summary method of the present invention. Figure 3 In the browser toolbar, there is a page summary button on top. When the user clicks the page summary button, the browser can call the page summary program to obtain the page information in the target page corresponding to the page summary button, and summarize the page information to obtain the page summary result. In order to facilitate the user to view, the page summary result can be displayed in the target page. For details, please refer to Figure 4 and Figure 5 , the page summary results can be displayed in the target page through a floating window or split screen display.

[0080] Furthermore, the intelligent large model has a maximum tokens limit. In order to prevent the input page information from exceeding the maximum tokens limit of the model, the step S30 may include: determining the number of characters corresponding to the page information;

[0081] When the number of characters exceeds a preset number of characters, abbreviating the page information according to the preset number of characters to obtain target abbreviated information;

[0082] The target abbreviation information is summarized according to the scene category to obtain page summary information.

[0083] It should be noted that the number of characters may be the number of characters corresponding to the page information. The preset number of characters may be the maximum number of tokens that the intelligent big model can recognize. The abbreviating of the page information according to the preset number of characters to obtain the target abbreviation information may be to abbreviate the page information and limit the abbreviated target abbreviation information to the maximum number of tokens that the intelligent big model can recognize. To ensure that the intelligent big model can accurately recognize the input page information. The abbreviation of the page information may be to remove duplicate information and other information of non-substantial content in the page information, such as: advertisements, format information, etc. in the page. After deleting the non-substantial information in the above-mentioned page information, if the number of characters of the deleted page information still exceeds the preset number of characters, feature extraction is performed on the deleted page information, and the target abbreviation information is determined based on the extracted features.

[0084] Furthermore, in order to abbreviate only information that is irrelevant to or has low relevance to the subject of the page information when abbreviating the page information, the step of abbreviating the page information according to the preset number of characters to obtain target abbreviated information includes:

[0085] Extracting target information that meets a preset abbreviation condition from the page information;

[0086] abbreviate the target information according to the abbreviation strategy corresponding to the target information to obtain an abbreviation result;

[0087] Determine abbreviation information according to the page information and the abbreviation result;

[0088] When the number of characters in the abbreviation information is less than or equal to the preset number of characters, the abbreviation information is the target abbreviation information.

[0089] It should be noted that the preset abbreviation condition may be a condition corresponding to information that can be abbreviated in advance, for example, a summary that does not belong to the page information, information containing preset sensitive and commercial terms, information that does not reflect the theme of the page information, advertising information, links to other information, etc. Different target information corresponds to different abbreviation methods, for example, the abbreviation strategy for advertising information is deletion, and the abbreviation strategy for other paragraph information that does not belong to the summary of the page information is feature extraction, etc. The abbreviation strategy corresponding to different information can be customized according to the type of target information that may exist in the page information. The determination of the abbreviation information based on the page information and the abbreviation result may be the determination of the abbreviation information based on the abbreviation result and the remaining information after deleting the target information from the page information. When the number of characters in the abbreviation information is less than or equal to the preset number of characters, the abbreviation information is used as the target abbreviation information. When the number of characters in the abbreviation information is greater than the preset number of characters, feature extraction can be performed on the abbreviation information, and the extracted features are used as the target abbreviation information.

[0090] Furthermore, in order to make the output page summary information more in line with the user's expectations, after step S30, it further includes: obtaining optimization suggestions from the user based on the page summary information feedback;

[0091] The page summary information is modified and optimized based on the optimization suggestion and the page information.

[0092] It should be noted that the optimization suggestion may be an AI prompt word (Prompt) fed back by the user based on the page summary information. The prompt is a natural language processing technology that can help the artificial intelligence model better understand and respond to the user's input through prompts and incentives. The modification and optimization of the page summary information based on the optimization suggestion and the page information may be to generate page summary information that meets the user's expectations based on the AI ​​prompt word and the page information.

[0093] Furthermore, different types and identities of users have different focuses on summarization. For example, when programmers summarize page information corresponding to software-related search problems, they generally focus on how to solve the search problems step by step. When designers summarize page information corresponding to search problems, they generally focus on whether the search problems can be realized. Therefore, in order to meet the needs of different users for page summarization, the step S30 may include: obtaining historical web browsing information, and determining user characteristics according to the historical web browsing information;

[0094] Determining summary requirements based on the user characteristics;

[0095] The page information is summarized according to the scenario category and the summary requirement to obtain page summary information.

[0096] It should be noted that the determination of user characteristics based on the historical web browsing information may be to determine the user's browsing type based on the historical web browsing information, and the user's browsing characteristics may be determined based on the user's browsing type. The determination of summary requirements based on the user characteristics may be to determine the user's focus when summarizing information based on the user characteristics. For example, if the user frequently browses for how to solve a problem, the summary requirement may be to summarize the solution steps corresponding to the search problem; if the user frequently browses for related information, the summary requirement may be to summarize the various news information in the page information. The summarization of the page information based on the scenario category and the summary requirement may be to focus on retaining and summarizing the information corresponding to the summary requirement when summarizing the page information, so that the generated page summary result meets the summary requirement.

[0097] Furthermore, in order to meet the diverse summarization needs of users, for example, summarizing only part of the content in a page or document or a certain audio or video file, the page summarization method further includes:

[0098] In response to an information summary instruction triggered based on a target page, determining a summary range corresponding to the information summary instruction;

[0099] Extracting the information to be summarized according to the summary scope;

[0100] Summarize the information to be summarized and generate a summary result.

[0101] It should be noted that the summary range may include the location information of the information to be summarized selected by the user in the target page, which may be a certain area in the target page or the number of rows where the information to be summarized is located. Extracting the information to be summarized according to the summary range may be obtaining the information corresponding to the summary range, that is, the information to be summarized. Summarizing the information to be summarized and generating a summary result may be taking the information to be summarized as page information, and referring to the above-mentioned determination of the scene category corresponding to the page information, summarizing the page information according to the scene category, and obtaining the step of page summary information, which will not be repeated in this embodiment.

[0102] In the specific implementation, please refer to Figure 6 , the user can select at least one summary range on the target page, and can select at least one summary range by circling, clicking, or selecting with the text cursor. Figure 6 As shown, the user selects two summary ranges by circling them, and the browser can obtain the information to be summarized within the two summary ranges, summarize the information to be summarized, and generate a summary result.

[0103] In response to the global page summary instruction triggered based on the target page, this embodiment obtains the page information corresponding to the target page; determines the scene category corresponding to the page information; summarizes the page information according to the scene category to obtain page summary information. Since this embodiment summarizes the page information according to the scene category corresponding to the page information to obtain page summary information. Compared with the existing method that can only rely on users to read the page content for summary, the above method of this embodiment can summarize the page according to the scene category corresponding to the page, thereby improving the accuracy of the page summary and the user's reading efficiency.

[0104] refer to Figure 7 , Figure 7 This is a flow chart of the second embodiment of the page summary method of the present invention.

[0105] Based on the above first embodiment, in this embodiment, step S30 includes:

[0106] Step S301: when the scene category is a multimodal category, determining a preset modality weight.

[0107] It should be noted that the multimodal class may be one or more of the modes of text, image, audio and / or video in the page information. The preset modal weight may be the pre-set weight of the influence of the content of different modalities on the summary result when summarizing. Different modal weights may be set for different page types. For example, in a document page, the weight of text information is greater than that of the image class; in a video website, the weight corresponding to video information is greater than that of text information. For example, in order to ensure the accuracy of the summary result, in an ordinary web page, the weight of text content may be set to be greater than the weight of audio and video content, which is greater than the weight of image content.

[0108] Step S302: extracting the modal information corresponding to each modality in the page information respectively.

[0109] It should be noted that the extracting of the modal information corresponding to each modality in the page information may be extracting the information corresponding to each modality in the page information. For example, if there are two modal contents, text and video, in the page information, the modal information corresponding to the text content and the modal information corresponding to the video content are obtained respectively.

[0110] Step S303: Summarize the page information according to the preset modal weight and the modal information to obtain page summary information.

[0111] It should be noted that summarizing the page information according to the preset modal weight and the modal information may be summarizing the modal information corresponding to each modality respectively to obtain a modal summary result, and then generating page summary information according to the weight of each modality in the preset modal weight and the modal summary result. Specifically, it may be performing feature extraction on each modal summary result to obtain a feature extraction result corresponding to each modality, and then extracting page summary information from all feature extraction results based on the weight corresponding to each modality. It may also be based on a pre-trained intelligent big model, inputting the preset modal weight and the modal information corresponding to each modality into the intelligent big model to obtain page summary information output by the intelligent big model.

[0112] In this embodiment, when the scene category is a multimodal category, a preset modal weight is determined; modal information corresponding to each modality in the page information is extracted respectively; the page information is summarized according to the preset modal weight and the modal information to obtain page summary information. In this embodiment, when the page information contains multiple modalities, the page information can be summarized according to the weights corresponding to each modality to obtain a more accurate page summary result.

[0113] refer to Figure 8 , Figure 8 This is a flow chart of the third embodiment of the page summary method of the present invention.

[0114] Based on the above embodiments, in this embodiment, step S30 includes:

[0115] Step S305: When the scene category is audio or video, the page information is converted into text to obtain text information corresponding to the page information.

[0116] It should be noted that the text conversion of the page information may be to perform voice recognition on the audio and video page information to obtain text information corresponding to the audio and video page information.

[0117] Further, in order to improve the efficiency of summarizing the audio and video page information, the step S305 may include: when the scene category is the audio and video category, determining whether the audio and video file in the page information contains subtitle information;

[0118] If the audio and video file contains subtitle information, the subtitle information in the audio and video file is extracted to obtain text information corresponding to the page information.

[0119] It should be noted that the determination of whether the audio and video file in the page information contains subtitle information can be that when the scene category is a video category, a frame image corresponding to the video is obtained, image recognition is performed on the frame image, and whether the frame image contains text information is determined. When the frame image contains text information, the positions of the text information in multiple frame images are compared to see if they are consistent. When the positions of the text information in a preset number of frame images are consistent, it is determined that the video file in the page information contains subtitle information, and the position where the text information is consistent is used as the subtitle position; when the audio and video file contains subtitle information, the subtitle information at the subtitle position in each frame image is extracted in sequence according to the time sequence of the video to obtain the text information corresponding to the page information.

[0120] Step S306: extract key information from the text information.

[0121] It should be noted that the extracting of key information from the text information may be extracting key information from the text information. For example, extracting key features and core points from the text information. This may be an important point of view, a storyline, a song theme, etc.

[0122] Step S307: Summarize the key information to obtain summary information.

[0123] It should be noted that the summarizing of the key information may be summarizing the extracted key information into concise sentences or paragraphs, using clear and concise language to express the information, to obtain the summarized information.

[0124] Step S308: extracting highlight information from the summary information, and generating page summary information according to the highlight information and the summary information.

[0125] It should be noted that the extracting of the highlight information in the summary information may be to determine the highlight, uniqueness or eye-catching part of the audio or video, which may be the theme of the audio or video, wonderful clips, outstanding acting skills or impressive music, etc. The generating of the page summary information according to the highlight information and the summary information may be based on the summary information and highlighting the highlight information to obtain the page summary information corresponding to the page information.

[0126] In this embodiment, when the scene category is audio and video, the page information is converted into text to obtain text information corresponding to the page information; key information in the text information is extracted; the key information is summarized to obtain summary information; highlight information in the summary information is extracted, and page summary information is generated based on the highlight information and the summary information. In this embodiment, when the scene category is audio and video, the page information is converted into text, newly extracted, summarized, and the like to generate page summary information, which can accurately summarize audio and video information, avoid users spending more time watching videos frame by frame to obtain video content, and can improve the efficiency of users obtaining information.

[0127] Reference Fig. 9 , Fig. 9 It is a structural block diagram of the first embodiment of the page summary device of the present invention.

[0128] like Fig. 9 As shown, the page summary device proposed in the embodiment of the present invention includes:

[0129] A response module 10, configured to obtain page information corresponding to the target page in response to a global page summary instruction triggered based on the target page;

[0130] A determination module 20, used to determine the scene category corresponding to the page information;

[0131] The summarizing module 30 is used to summarize the page information according to the scene category to obtain page summary information.

[0132] In response to the global page summary instruction triggered based on the target page, this embodiment obtains the page information corresponding to the target page; determines the scene category corresponding to the page information; summarizes the page information according to the scene category to obtain page summary information. Since this embodiment summarizes the page information according to the scene category corresponding to the page information to obtain page summary information, compared with the existing method that can only rely on users to read the page content, the above method of this embodiment can summarize the page according to the scene category corresponding to the page, thereby improving the accuracy of the page summary and the user's reading efficiency.

[0133] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0134] In addition, for technical details not fully described in this embodiment, reference may be made to the page summarization method provided in any embodiment of the present invention, and will not be repeated here.

[0135] Based on the first embodiment of the page summarizing device of the present invention, a second embodiment of the page summarizing device of the present invention is proposed.

[0136] In this embodiment, the determination module 20 is further used to determine the sensory modality content and / or webpage media type in the page information;

[0137] The scene category corresponding to the page information is determined according to the sensory modality content and / or the webpage media type.

[0138] Furthermore, the summarizing module 30 is also used to determine the number of characters corresponding to the page information;

[0139] When the number of characters exceeds a preset number of characters, abbreviating the page information according to the preset number of characters to obtain target abbreviated information;

[0140] The target abbreviation information is summarized according to the scene category to obtain page summary information.

[0141] Furthermore, the summarizing module 30 is further used to extract target information that meets a preset abbreviation condition from the page information;

[0142] abbreviate the target information according to the abbreviation strategy corresponding to the target information to obtain an abbreviation result;

[0143] Determine abbreviation information according to the page information and the abbreviation result;

[0144] When the number of characters in the abbreviation information is less than or equal to the preset number of characters, the abbreviation information is the target abbreviation information.

[0145] Furthermore, the summary module 30 is also used to obtain optimization suggestions from users based on the page summary information feedback;

[0146] The page summary information is modified and optimized based on the optimization suggestion and the page information.

[0147] Furthermore, the summarizing module 30 is also used to obtain historical web browsing information and determine user characteristics based on the historical web browsing information;

[0148] Determining summary requirements based on the user characteristics;

[0149] The page information is summarized according to the scenario category and the summary requirement to obtain page summary information.

[0150] Furthermore, the summary module 30 is further configured to convert the page information into text when the scene category is an audio or video category, so as to obtain text information corresponding to the page information;

[0151] Extracting key information from the text information;

[0152] Summarizing the key information to obtain summary information;

[0153] The highlight information in the summary information is extracted, and page summary information is generated according to the highlight information and the summary information.

[0154] Furthermore, the summary module 30 is further configured to determine whether the audio and video files in the page information contain subtitle information when the scene category is an audio and video category;

[0155] If the audio and video file contains subtitle information, the subtitle information in the audio and video file is extracted to obtain text information corresponding to the page information.

[0156] Furthermore, the summary module 30 is further configured to determine a preset modality weight when the scene category is a multimodal category;

[0157] Respectively extracting modal information corresponding to each modality in the page information;

[0158] The page information is summarized according to the preset modal weight and the modal information to obtain page summary information.

[0159] Furthermore, the summarizing module 30 is further used to summarize each of the modal information to obtain summary information;

[0160] Generate page summary information of the page information according to the preset modal weight and the summary information.

[0161] Furthermore, the summarizing module 30 is further configured to determine a summary range corresponding to the information summarizing instruction in response to the information summarizing instruction triggered based on the target page;

[0162] Extracting the information to be summarized according to the summary scope;

[0163] Summarize the information to be summarized and generate a summary result.

[0164] Other embodiments or specific implementations of the page summary device of the present invention can refer to the above-mentioned method embodiments, which will not be described in detail here.

[0165] In addition, an embodiment of the present invention further provides a storage medium, on which a page summary program is stored. When the page summary program is executed by a processor, the steps of the page summary method described above are implemented.

[0166] It should be noted that, in this article, the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0167] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0168] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0169] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0170] The present invention discloses A1, a page summary method, which comprises the following steps:

[0171] In response to a global page summary instruction triggered based on a target page, obtaining page information corresponding to the target page;

[0172] Determining a scene category corresponding to the page information;

[0173] The page information is summarized according to the scene category to obtain page summary information.

[0174] A2. In the page summarization method described in A1, the step of determining the scene category corresponding to the page information comprises:

[0175] Determining sensory modality content and / or webpage media type in the page information;

[0176] The scene category corresponding to the page information is determined according to the sensory modality content and / or the webpage media type.

[0177] A3. The page summarizing method as described in A1, wherein the step of summarizing the page information according to the scene category to obtain page summary information comprises:

[0178] Determine the number of characters corresponding to the page information;

[0179] When the number of characters exceeds a preset number of characters, abbreviating the page information according to the preset number of characters to obtain target abbreviated information;

[0180] The target abbreviation information is summarized according to the scene category to obtain page summary information.

[0181] A4. The page summarization method as described in A3, wherein the step of abbreviating the page information according to the preset number of characters to obtain target abbreviated information comprises:

[0182] Extracting target information that meets a preset abbreviation condition from the page information;

[0183] abbreviate the target information according to the abbreviation strategy corresponding to the target information to obtain an abbreviation result;

[0184] Determine abbreviation information according to the page information and the abbreviation result;

[0185] When the number of characters in the abbreviation information is less than or equal to the preset number of characters, the abbreviation information is the target abbreviation information.

[0186] A5. The page summarizing method as described in A1, after the step of summarizing the page information according to the scene category to obtain the page summary information, comprises:

[0187] Obtain optimization suggestions from users based on the page summary information feedback;

[0188] The page summary information is modified and optimized based on the optimization suggestion and the page information.

[0189] A6. The page summarizing method as described in A1, wherein the step of summarizing the page information according to the scene category to obtain page summary information comprises:

[0190] Acquire historical web browsing information, and determine user characteristics based on the historical web browsing information;

[0191] Determining summary requirements based on the user characteristics;

[0192] The page information is summarized according to the scenario category and the summary requirement to obtain page summary information.

[0193] A7. In the page summarizing method described in A1, the step of summarizing the page information according to the scene category to obtain page summary information comprises:

[0194] When the scene category is an audio or video category, performing text conversion on the page information to obtain text information corresponding to the page information;

[0195] Extracting key information from the text information;

[0196] Summarizing the key information to obtain summary information;

[0197] The highlight information in the summary information is extracted, and page summary information is generated according to the highlight information and the summary information.

[0198] A8. The page summarization method as described in A7, wherein when the scene category is audio or video, the step of converting the page information into text to obtain text information corresponding to the page information comprises:

[0199] When the scene category is audio and video, determining whether the audio and video file in the page information contains subtitle information;

[0200] If the audio and video file contains subtitle information, the subtitle information in the audio and video file is extracted to obtain text information corresponding to the page information.

[0201] A9. The page summarizing method as described in any one of A1 to A7, wherein the step of summarizing the page information according to the scene category to obtain page summary information comprises:

[0202] When the scenario category is a multimodal category, determining a preset modal weight;

[0203] Respectively extracting modal information corresponding to each modality in the page information;

[0204] The page information is summarized according to the preset modal weight and the modal information to obtain page summary information.

[0205] A10. The page summarizing method as described in A9, wherein the step of summarizing the page information according to the preset modal weight and the modal information to obtain page summary information comprises:

[0206] Summarizing each of the modal information to obtain summary information;

[0207] Generate page summary information of the page information according to the preset modal weight and the summary information.

[0208] A11. The page summary method according to any one of A1 to A7, wherein the page summary method further comprises:

[0209] In response to an information summary instruction triggered based on a target page, determining a summary range corresponding to the information summary instruction;

[0210] Extracting the information to be summarized according to the summary scope;

[0211] Summarize the information to be summarized and generate a summary result.

[0212] The present invention discloses B12, a page summary device, the page summary device comprising:

[0213] A response module, configured to respond to a global page summary instruction triggered based on a target page and obtain page information corresponding to the target page;

[0214] A determination module, used to determine the scene category corresponding to the page information;

[0215] The summary module is used to summarize the page information according to the scene category to obtain page summary information.

[0216] B13, the page summarizing device as described in B12, wherein the determining module is further used to determine the sensory modality content and / or webpage media type in the page information;

[0217] The scene category corresponding to the page information is determined according to the sensory modality content and / or the webpage media type.

[0218] B14, the page summary device as described in B12, wherein the summary module is further used to determine the number of characters corresponding to the page information;

[0219] When the number of characters exceeds a preset number of characters, abbreviating the page information according to the preset number of characters to obtain target abbreviated information;

[0220] The target abbreviation information is summarized according to the scene category to obtain page summary information.

[0221] B15. The page summarizing device as described in B14, wherein the summarizing module is further used to extract target information that meets a preset abbreviation condition from the page information;

[0222] abbreviate the target information according to the abbreviation strategy corresponding to the target information to obtain an abbreviation result;

[0223] Determine abbreviation information according to the page information and the abbreviation result;

[0224] When the number of characters in the abbreviation information is less than or equal to the preset number of characters, the abbreviation information is the target abbreviation information.

[0225] B16, the page summary device as described in B12, wherein the summary module is further used to obtain optimization suggestions from users based on the page summary information feedback;

[0226] The page summary information is modified and optimized based on the optimization suggestion and the page information.

[0227] B17. The page summary device as described in B12, wherein the summary module is further used to obtain historical web page browsing information and determine user characteristics based on the historical web page browsing information;

[0228] Determining summary requirements based on the user characteristics;

[0229] The page information is summarized according to the scenario category and the summary requirement to obtain page summary information.

[0230] B18. The page summarizing device as described in B12, wherein the summarizing module is further used to convert the page information into text when the scene category is audio or video, so as to obtain text information corresponding to the page information;

[0231] Extracting key information from the text information;

[0232] Summarizing the key information to obtain summary information;

[0233] The highlight information in the summary information is extracted, and page summary information is generated according to the highlight information and the summary information.

[0234] The present invention discloses C19, a page summarizing device, which includes: a memory, a processor, and a page summarizing program stored in the memory and executable on the processor, wherein the page summarizing program is configured to implement the steps of the page summarizing method described in any one of A1 to A11.

[0235] The present invention discloses D20, a storage medium, on which a page summary program is stored. When the page summary program is executed by a processor, the steps of the page summary method described in any one of A1 to A11 are implemented. < / h1> < / audio> < / video> < / audio> < / video>

Claims

1. A page summary method, characterized in that: The page summary method comprises the following steps: In response to a global page summary instruction triggered based on a target page, obtaining page information corresponding to the target page; Determining a scene category corresponding to the page information; The page information is summarized according to the scene category to obtain page summary information.

2. The page summary method according to claim 1, characterized in that: The step of determining the scene category corresponding to the page information includes: Determining sensory modality content and / or webpage media type in the page information; The scene category corresponding to the page information is determined according to the sensory modality content and / or the webpage media type.

3. The page summary method according to claim 1, characterized in that: The step of summarizing the page information according to the scene category to obtain page summary information includes: Determine the number of characters corresponding to the page information; When the number of characters exceeds a preset number of characters, abbreviating the page information according to the preset number of characters to obtain target abbreviated information; The target abbreviation information is summarized according to the scene category to obtain page summary information.

4. The page summary method according to claim 3, characterized in that: The step of abbreviating the page information according to the preset number of characters to obtain target abbreviated information includes: Extracting target information that meets a preset abbreviation condition from the page information; abbreviate the target information according to the abbreviation strategy corresponding to the target information to obtain an abbreviation result; Determine abbreviation information according to the page information and the abbreviation result; When the number of characters in the abbreviation information is less than or equal to the preset number of characters, the abbreviation information is the target abbreviation information.

5. The page summary method according to claim 1, characterized in that: After the step of summarizing the page information according to the scene category to obtain page summary information, the method further includes: Obtain optimization suggestions from users based on the page summary information feedback; The page summary information is modified and optimized based on the optimization suggestion and the page information.

6. The page summary method according to claim 1, characterized in that: The step of summarizing the page information according to the scene category to obtain page summary information includes: Acquire historical web browsing information, and determine user characteristics based on the historical web browsing information; Determining summary requirements based on the user characteristics; The page information is summarized according to the scenario category and the summary requirement to obtain page summary information.

7. The page summary method according to claim 1, characterized in that: The step of summarizing the page information according to the scene category to obtain page summary information includes: When the scene category is an audio or video category, performing text conversion on the page information to obtain text information corresponding to the page information; Extracting key information from the text information; Summarizing the key information to obtain summary information; The highlight information in the summary information is extracted, and page summary information is generated according to the highlight information and the summary information.

8. A page summary device, characterized in that: The page summary device comprises: A response module, configured to respond to a global page summary instruction triggered based on a target page and obtain page information corresponding to the target page; A determination module, used to determine the scene category corresponding to the page information; The summary module is used to summarize the page information according to the scene category to obtain page summary information.

9. A page summary device, characterized in that: The device comprises: a memory, a processor, and a page summary program stored in the memory and executable on the processor, wherein the page summary program is configured to implement the steps of the page summary method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a page summary program, and when the page summary program is executed by the processor, the steps of the page summary method according to any one of claims 1 to 7 are implemented.

Images