File digest display method and apparatus

Abstract

A file digest display method and apparatus, which may be applied to a first device or a component (such as a chip system) having or supporting a function of the first device. The method may comprise: displaying an operation item of a first file in a first interface, and, in response to an operation on the operation item of the first file by a first user, displaying content of a first digest of the first file. The first file has a first mark in the first interface, the first mark indicating that the first file has a generated digest. In this way, a user can quickly determine that the first file has a generated digest by means of the first mark in the first interface, and directly perform an operation on the file in the current first interface, so as to quickly and conveniently view digest content of the first file. The interaction operation is simple, and the human-computer interaction efficiency is high.

Description

Method and apparatus for displaying document summary

[0001] This application claims priority to Chinese Patent Application No. 202411098716.X, filed with the State Intellectual Property Office of China on August 9, 2024, entitled “Method and Apparatus for Displaying Document Abstract”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a method and apparatus for displaying document summaries. Background Technology

[0003] Currently, users can generate file summaries using various tools on their devices when viewing file summaries. For example, a user can drag a file into an AI assistant and enter a prompt to generate a summary; the AI ​​assistant can then output a summary of the file based on that prompt. Alternatively, users can enter complex commands to summarize the file in input boxes that support intelligent dialogue, such as commands containing "@" and the file name, to trigger the device to generate a summary of the file.

[0004] However, in the current solution, the interactive operations required for users to view the summary are cumbersome, resulting in a poor user experience. Summary of the Invention

[0005] This application provides a method and apparatus for displaying document summaries, which simplifies the interactive operation of users viewing summaries.

[0006] To achieve the above objectives, this application adopts the following technical solution:

[0007] In a first aspect, this application provides a document summary display method, applicable to a first device or a component having or supporting the functions of the first device (such as a chip system). The method includes: displaying operation items for a first document in a first interface, and, in response to an operation by a first user on the operation items of the first document, displaying the content of a first summary of the first document. The first document has a first marker in the first interface, the first marker indicating that the first document has a generated summary.

[0008] Using this method, users can quickly determine that the first file has a generated summary by using the first marker in the first interface, and directly operate the file in the current first interface to conveniently and quickly view the summary content of the first file. The interactive operation is simple and the human-computer interaction efficiency is high.

[0009] In one possible design, the method further includes: in response to the operation of sharing the first file with the second user, sending the first file and the first summary to the second user's second device.

[0010] Using this method, after receiving a document, the second device can display a first summary of the first document to the second user. In some examples, the second user can decide whether to download the first document based on the second summary. In other examples, the second user can quickly view the first summary, improving the efficiency of information retrieval.

[0011] In one possible design, before displaying the operation items for the first file on the first interface, the method further includes: sending the first file to a third device; and receiving the first digest from the third device, wherein the first digest is obtained by the third device processing the first file.

[0012] Using this method, the first device can generate a first summary of the first document by leveraging the summary generation capabilities of other devices. Thus, even if the capabilities of the first device are insufficient, the function of quickly viewing the summary can still be achieved.

[0013] In one possible design, displaying the content of a first summary of the first file in response to an operation by a first user on an operation item of the first file includes: if the first user has permission to view the first file, displaying the content of the first summary in response to an operation by the first user on an operation item of the first file.

[0014] Using this method, only users with viewing permissions for the first file can view the first summary, which can prevent information in the document from being leaked to users without permission and improve information security.

[0015] In one possible design, the first device stores the first file and the first summary.

[0016] Using this method, the first summary of the first file is obtained by the first device after preprocessing. There is no need to generate the summary temporarily in response to the user's viewing request. This can improve the responsiveness of the user's viewing summary, reduce latency, and achieve a "click-and-get" summary viewing experience.

[0017] In one possible design, the first device stores the first digest, including storing the first digest in a digest field corresponding to the first file.

[0018] Using this method, a relationship can be established between the first file and the first summary. Subsequently, if the first file is moved, modified, or renamed, the user does not need to manually trigger the generation of the first file's summary again, simplifying the interactive operations required to generate the summary.

[0019] In one possible design, the first device also stores a second file, and the first interface further includes operation items for the second file. The second file does not have a marker in the first interface to indicate that the second file has a summary, or the second file has a second marker in the first interface to indicate that the second file does not have a summary.

[0020] Using this method, users can quickly determine that the second file does not have a generated summary by observing the second marker of the second file in the first interface, or by the absence of a corresponding marker in the first interface. Users can then perform subsequent operations accordingly, such as instructing the first device to generate a summary of the second file.

[0021] In one possible design, the second marker indicates that the second file supports the generation of a digest, and that the digest of the second file has not yet been generated.

[0022] In one possible design, the second tag indicates that the second file does not support the generation of a digest.

[0023] Using this method, the user can perform subsequent operations based on the second tag. For example, for a file that supports the generation of a digest but has not yet generated a digest, the user can instruct the first device to generate a digest of the file.

[0024] In one possible design, before displaying the operation item for the first file on the first interface, the method further includes: satisfying a first condition to generate a digest based on the file for which a digest is to be generated, wherein the file for which a digest is to be generated includes the first file; the first condition includes at least one of the following conditions: the first device has sufficient power; the first device is in a locked state; the resources of the first device meet the conditions for executing the digest generation; sufficient power of the first device includes the first device being in a charging state, or the power of the first device being greater than a first threshold.

[0025] Using this method, the first device can perform the summary generation step under certain conditions, which can improve the user's experience of viewing the summary. For example, it can ensure that summary generation has as many resources as possible, thereby improving the efficiency of summary generation. Furthermore, generating the summary in the lock screen state can avoid the resource consumption of user interaction when generating the summary in the unlocked screen state.

[0026] In one possible design, the file to be digested includes a third file, and the method further includes: during the process of generating a digest from the third file, if the first condition is not met, stopping the generation of the digest from the third file. Thus, timely stopping the generation of the digest by the first device can reduce the power consumption of the first device.

[0027] In one possible design, the file to be digested includes a fourth file, and the method further includes: during the process of generating a digest from the fourth file, if it is detected that the first condition is not met, continue generating a digest of the fourth file, and stop executing the digest generation step after generating the digest of the fourth file. In this way, the first device can ensure that the digest of the current fourth file is successfully generated, and promptly stop generating other digests after generating this digest, thereby reducing the power consumption of the first device.

[0028] In one possible design, after displaying the operation items for the first file on the first interface, the interface further includes: updating the first file; after updating the first file and before generating an updated summary based on the updated first file, displaying a fifth marker on the first interface, the fifth marker indicating that the first file supports the generation of a summary and that the summary of the first file has not yet been generated.

[0029] In this way, the first device can dynamically update the tags of the files in the interface so that users can identify whether the files have a summary or whether they support the generation of a summary through the updated tags in the interface.

[0030] In one possible design, the method further includes: processing the first file in response to the first user's summary generation operation on the first file to obtain the first summary. Thus, the first device can generate a summary based on the user's summary generation intention. Subsequently, the user can quickly view the summary by operating on the operation items of the first file.

[0031] In one possible design, the method further includes: in response to an operation that modifies the first file, processing the modified first file to obtain an updated summary. Thus, the first device can automatically update the summary corresponding to the first file after it is modified, supporting subsequent user needs for quickly viewing the summary.

[0032] In one possible design, the first device includes a first folder, and the files in the first folder support the generation of summaries. Thus, users can place all the summaries they need to generate in the first folder. The first device can perform the summary generation step when the summary generation conditions are met. For example, when the battery is sufficient and the screen is locked, the first device automatically generates summaries for the files in the first folder.

[0033] In one possible design, the method further includes: receiving a fifth file from a fourth device; and sending a second digest to the fourth device, the second digest being obtained by the first device processing the fifth file.

[0034] Using this method, the first device can assist the fourth device in generating a digest, thereby reducing the computing power consumption of the fourth device.

[0035] In one possible design, the first summary is obtained from M summaries of M first semantic blocks in the first file; the M first semantic blocks are obtained by performing layout understanding on the first file, and each first semantic block has complete semantics; the summary of each first semantic block is obtained by performing artificial intelligence (AI) processing on the first semantic block, where M is an integer greater than 1.

[0036] Using this method, the first device considers the semantics of the document content when performing layout understanding, ensuring the semantic integrity of each semantic block and improving the accuracy of the summary. Furthermore, based on layout understanding, the first device can discard some unimportant information in the document, reducing the computational load for generating the summary and improving its efficiency.

[0037] In one possible design, each first semantic block includes multiple second semantic blocks, and the summary of each first semantic block is obtained by artificial intelligence (AI) processing of the first semantic block, including: the summary of the first semantic block is determined based on the summaries of the multiple second semantic blocks included in the first semantic block.

[0038] In this way, by understanding the information in the multi-layered semantic blocks of a file, the generated summary can conform to the file's hierarchical structure, allowing users to quickly understand the summary content of the file.

[0039] In one possible design, the first interface includes a file management interface, which displays operation items for the first file, including: displaying a file list in the file management interface, the file list including entries corresponding to one or more files; the one or more files including the first file.

[0040] Using this method, users can operate (such as long-press) on file entries in the file management interface. The first device responds to this operation and displays a summary of the file, enabling users to quickly view the file summary and improving human-computer interaction efficiency.

[0041] In one possible design, the first interface includes a chat interface with a third user; displaying operation items for the first file in the first interface includes: after receiving the first file and the first summary from the third user's device, displaying operation items for the first file in the first interface.

[0042] Using this method, the first device can receive a first file and a first summary of the first file shared by other devices, and can quickly view the first summary by operating on the operation items of the first file, so as to quickly understand the content of the first file.

[0043] In one possible design, the first file satisfies at least one of the following conditions: the first file is of text, audio, or video type; the size of the first file is less than a second threshold; the first file is of text type and the number of words in the first file is less than a third threshold; the first file is of audio type and the duration of the first file is less than a fourth threshold; the first file is of video type and the duration of the first file is less than a fifth threshold.

[0044] Using this method, the first device can generate a first summary of the first file after determining that the first file meets at least one of the above conditions, thereby reducing the probability of failure in generating the summary of the first file.

[0045] In one possible design, the method further includes displaying the content of the first file in response to a user's operation on the first control in the first interface. Using this method, the first device can display a summary of the document in response to a user's operation (such as long-pressing the document) before opening the document's content. In this way, the user can quickly understand the content of the corresponding document through the summary, effectively improving the efficiency of information retrieval.

[0046] In one possible design, the first device can pre-generate both a detailed summary and a concise summary. The first device can display one summary by default and then switch to displaying the other summary in response to user interaction. For example, as mentioned above, the first device defaults to displaying the concise summary and then switches to displaying the detailed summary. Similarly, the first device defaults to displaying the detailed summary and can then switch to displaying the concise summary. In this way, the first device can switch between displaying summaries of different levels of detail based on user interaction, thus meeting the user's browsing needs.

[0047] In one possible design, the first device pre-generates a summary, and subsequently, in response to user actions, generates another summary and switches to display the other summary.

[0048] In one possible design, the operation on the action item includes, but is not limited to: long-pressing the action item or keeping the focus on the action item. Keeping the focus on the action item can be an input such as keeping the focus on the action item using a mouse or remote control.

[0049] In a second aspect, a document summary display device is provided, which can be applied to a first device or a component (such as a chip system) having or supporting the functions of the first device, the device may include:

[0050] The display unit is configured to display operation items for a first file on a first interface; and in response to an operation by a first user on the operation items of the first file, to display the content of a first summary of the first file. The first file has a first marker on the first interface, the first marker indicating that the first file has a generated summary.

[0051] In one possible design, the device further includes a communication unit for sending the first file and the first summary to a second device of the second user in response to an operation of sharing the first file with a second user.

[0052] In one possible design, the communication unit is further configured to send the first file to a third device before displaying the operation item of the first file in the first interface; and to receive the first digest from the third device, the first digest being obtained by the third device processing the first file.

[0053] In one possible design, displaying the content of a first summary of the first file in response to an operation by a first user on an operation item of the first file includes: if the first user has permission to view the first file, displaying the content of the first summary in response to an operation by the first user on an operation item of the first file.

[0054] In one possible design, the first device stores the first file and the first summary.

[0055] In one possible design, the first device stores the first digest, including storing the first digest in a digest field corresponding to the first file.

[0056] In one possible design, the first device also stores a second file, and the first interface further includes operation items for the second file. The second file does not have a marker in the first interface to indicate that the second file has a summary, or the second file has a second marker in the first interface to indicate that the second file does not have a summary.

[0057] In one possible design, the second marker indicates that the second file supports the generation of a digest, and that the digest of the second file has not yet been generated.

[0058] In one possible design, the second tag indicates that the second file does not support the generation of a digest.

[0059] In one possible design, the device further includes a processing unit for generating a summary based on a file to be summarized, before displaying the operation item of the first file in the first interface, satisfying a first condition, wherein the file to be summarized includes the first file; the first condition includes at least one of the following conditions: the first device has sufficient power; the first device is in a locked state; the resources of the first device meet the conditions for performing summary generation; wherein, sufficient power of the first device includes the first device being in a charging state, or the power of the first device being greater than a first threshold.

[0060] In one possible design, the file to be digested includes a third file, and the processing unit is further configured to: during the process of generating a digest based on the third file, if the first condition is not met, stop generating the digest of the third file.

[0061] In one possible design, the file to be digested includes a fourth file, and the processing unit is further configured to: during the process of generating a digest based on the fourth file, if the first condition is not met, continue generating a digest of the fourth file, and stop executing the digest generation step after generating the digest of the fourth file.

[0062] In one possible design, the processing unit is further configured to: process the first file in response to the first user's operation to generate a summary of the first file, thereby obtaining the first summary.

[0063] In one possible design, the processing unit is further configured to: in response to an operation that modifies the first file, process the modified first file to obtain an updated summary.

[0064] In one possible design, the first device includes a first folder, the files in which a summary can be generated.

[0065] In one possible design, the communication unit is further configured to: receive a fifth file from a fourth device; and send a second digest to the fourth device, the second digest being obtained by the first device processing the fifth file.

[0066] In one possible design, the first summary is obtained from M summaries of M first semantic blocks in the first file; the M first semantic blocks are obtained by performing layout understanding on the first file, and each first semantic block has complete semantics; the summary of each first semantic block is obtained by performing artificial intelligence (AI) processing on the first semantic block, where M is an integer greater than 1.

[0067] In one possible design, each first semantic block includes multiple second semantic blocks, and the summary of each first semantic block is obtained by artificial intelligence (AI) processing of the first semantic block, including: the summary of the first semantic block is determined based on the summaries of the multiple second semantic blocks included in the first semantic block.

[0068] In one possible design, the first interface includes a file management interface, which displays operation items for the first file, including: displaying a file list in the file management interface, the file list including entries corresponding to one or more files; the one or more files including the first file.

[0069] In one possible design, the first interface includes a chat interface with a third user; displaying operation items for the first file in the first interface includes: after receiving the first file and the first summary from the third user's device, displaying operation items for the first file in the first interface.

[0070] In one possible design, the first file satisfies at least one of the following conditions: the first file is of text, audio, or video type; the size of the first file is less than a second threshold; the first file is of text type and the number of words in the first file is less than a third threshold; the first file is of audio type and the duration of the first file is less than a fourth threshold; the first file is of video type and the duration of the first file is less than a fifth threshold.

[0071] Thirdly, this application provides a document summary display device, including a functional module, unit, or means for performing the methods in any possible design of any aspect of this application described above. This module can be implemented by software or hardware, or by a combination of software and hardware. It may include a processing unit and a communication unit, without limitation.

[0072] Fourthly, the present application provides a document summary display device, comprising: a processor configured to perform the method of any of the above-described aspects.

[0073] Optionally, the device may further include the memory and / or the communication interface.

[0074] The communication interface is coupled to the processor and is used for inputting and / or outputting information.

[0075] The memory is used to store computer programs, and the processor is configured to perform a method of any of the above-described designs, which can be implemented as: a method for executing a computer program stored in the memory to perform any of the above-described designs.

[0076] Alternatively, the processor can be a hardware-implemented circuit, such as an artificial intelligence (AI) processor, to improve operating speed. This application does not limit the specific implementation of the processor.

[0077] Optionally, the document summary display device can be a complete device or a module within the device, such as a chip.

[0078] Fifthly, the present application provides a computer-readable storage medium including computer instructions that, when executed on a device, cause the device to perform any of the possible designs described above.

[0079] Sixthly, the present application provides a computer program product that, when run on a device, causes the device to execute the method in any possible design of any of the above aspects.

[0080] Seventhly, this application provides a circuit system (or chip system) including a processing circuit configured to perform the methods in any possible design of any of the above aspects. The processing circuit can be implemented as a corresponding circuit component, such as one or more processors. Alternatively, it can be implemented as a processor and a memory. Yet another example is a processor and a transceiver.

[0081] Eighthly, an electronic device is provided, comprising: a display screen, a processor, and a memory, the display screen, the memory, and the processor being coupled together, the memory being used to store program code including instructions, and the processor reading the instructions from the memory to cause the electronic device to perform the method as described in any of the preceding aspects and any of the designs therein.

[0082] Ninthly, this application provides a chip system including at least one processor and at least one interface circuit, the at least one interface circuit being used to perform transceiver functions and send instructions to at least one processor, and when at least one processor executes instructions, at least one processor performs the method as described in the first aspect and any of the designs therein. Attached Figure Description

[0083] Figure 1 is a schematic diagram of the system architecture provided in an embodiment of this application;

[0084] Figure 2 is a schematic diagram of the architecture of the device provided in an embodiment of this application;

[0085] Figures 3-6 are schematic diagrams of the interfaces provided in the embodiments of this application;

[0086] Figures 7 and 8 are schematic diagrams of scenarios provided in the embodiments of this application;

[0087] Figures 9-11 are schematic diagrams of the interfaces provided in the embodiments of this application;

[0088] Figure 12 is a schematic diagram of a scenario provided in an embodiment of this application;

[0089] Figure 13 is a flowchart illustrating the document summary display method provided in an embodiment of this application;

[0090] Figure 14 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0091] Figure 15 is a schematic diagram of the structure of a chip system provided in an embodiment of this application. Detailed Implementation

[0092] The technical solutions of the embodiments of this application are described below with reference to the accompanying drawings. In the description of the embodiments of this application, the terminology used in the following embodiments is for the purpose of describing specific embodiments only and is not intended to be a limitation of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one” and “one or more” refer to one or more (including two).

[0093] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized. The term "connection" includes direct connections and indirect connections, unless otherwise stated. "First" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated.

[0094] In the embodiments of this application, the words "exemplarily" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of the words "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0095] In the technical solutions of this application, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. For example, in the technical solutions of this application, the collection of user instructions is carried out with the user's authorization, which will be uniformly stated here and will not be repeated below.

[0096] "For use" can mean "dedicated to" or "available for use", but is not limited to "dedicated to".

[0097] This application provides a method for displaying a file summary. The terminal can store a first file and a first summary of the first file. Users can quickly view the first summary of the first file by operating on the icon of the first file, thereby improving the efficiency of users in obtaining information.

[0098] This method can be applied to systems with summary generation capabilities. Figure 1 shows an example of the system architecture applicable to the embodiments of this application. As shown in Figure 1, the system may include a layout understanding module, a file distribution module, a file analysis service, and a model. The file analysis service may also be called a file system intelligent analysis service, or a file intelligence service, or a file service, and the name is not limited.

[0099] The layout understanding module, file distribution module, and file analysis service can be deployed on the first device. There can be one or more models. For example, the models may include models deployed on a computer and models deployed locally on the first device.

[0100] The file analysis service can be used to pass the corresponding file to the layout understanding module after detecting the addition or modification of a local file on the first device. For example, the file analysis service is a background service that runs continuously.

[0101] The layout understanding module can be used to understand the layout of a document, and then to create a hierarchical graph model of the document, forming nodes at multiple levels. Layout understanding and hierarchical graph modeling can be understood as segmenting the document according to semantic dimensions. For example, for a PowerPoint presentation, the first level of nodes is each page of the presentation; the second level of nodes is each semantic block on each page; and the third level of nodes is the specific multimodal content within each block. Multimodal content includes, but is not limited to, text, tables, and images.

[0102] For example, a Word document can be segmented into document level, outline level, and multimodal level. The document level corresponds to the entire document. The outline level corresponds to subpages, and the multimodal level corresponds to specific content within a subpage. Alternatively, the outline level corresponds to subheadings, and the multimodal level corresponds to specific content within those subheadings.

[0103] Figure 1 illustrates the multiple nodes obtained from the hierarchical graph modeling. The root node corresponds to the document layer. The root node includes two child nodes of the outline layer. The left child node of the outline layer includes two child nodes of the multimodal layer. The right child node of the outline layer includes one child node of the multimodal layer.

[0104] Child nodes can also be called subgraphs or semantic blocks, with no restrictions on the name.

[0105] The file distribution module can be used to distribute the corresponding parts of child nodes to the corresponding devices for processing, and the devices can then generate summaries using the larger model. For example, the content of the left-hand child nodes in the outline layer can be distributed to a computer, which will then generate a summary of that content. Conversely, the content of the right-hand child nodes in the outline layer can be distributed to the local machine, where a summary of that content will be generated.

[0106] For example, the model could be a large language model, or simply a large model. Electronic devices use large models to process files and output a summary of the files.

[0107] As one possible implementation, the layout understanding module performs hierarchical graph modeling on the file to obtain multiple nodes. The electronic device then processes each node from bottom to top using a large model to obtain a summary. In other words, the file is divided into multiple semantic blocks, a summary for each semantic block is generated, and a summary of the entire file is generated based on the summaries of each semantic block. For nodes at a certain level, the input of the large model includes the summaries of the child nodes of that node. For leaf nodes without child nodes, the input of the large model includes the multimodal information corresponding to that leaf node.

[0108] For example, as shown in Figure 1, for leaf node 2 (a type of child node), the electronic device inputs the graph corresponding to this leaf node into the large model to obtain a summary of the graph. Similarly, for leaf node 4 (a type of child node), the electronic device inputs the text corresponding to this leaf node into the large model to obtain a summary of the text. For leaf node 5 (a type of child node), the electronic device inputs the table corresponding to this leaf node into the large model to obtain a summary of the table.

[0109] As shown in Figure 1, for child node 3, the electronic device inputs the summaries corresponding to child node 4 (text) and child node 5 (table) into the larger model to obtain the summary corresponding to child node 3. For the root node, the electronic device inputs the summaries corresponding to child node 3 and child node 1 into the larger model to obtain the summary of the root node. In this way, by understanding the information of the file's multi-level nodes from bottom to top, the generated summary can conform to the file's hierarchical structure, allowing users to quickly understand the summary's overview content.

[0110] For example, the terminal can be a mobile phone, tablet computer, handheld computer, netbook, and various other devices such as personal digital assistant (PDA) and artificial intelligence (AI) devices.

[0111] For example, Figure 2 shows a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0112] As shown in Figure 2, the electronic device 500 (also known as a terminal) may include a processor 510 and a memory 520.

[0113] Processor 510 may include one or more processing units, such as: application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0114] The controller can generate operation control signals based on the instruction opcode and timing signals to complete the control of instruction fetching and execution.

[0115] The processor 510 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 510 is a cache memory. This memory can store instructions or data that the processor 510 has just used or that are used repeatedly. If the processor 510 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 510, and thus improves the efficiency of the system.

[0116] In some embodiments, processor 510 may include one or more interfaces. These one or more interfaces may be used to connect processor 510 to memory 520, etc.

[0117] In some embodiments of this application, the processor 510 can be used to generate a summary of a file and bind the file to the summary. Thus, even if a file is moved, renamed, or edited, the user can quickly view the latest summary. Please refer to the following description for details.

[0118] The memory 520 can be used to store computer executable program code, which includes instructions. The memory 520 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as image playback), etc. The data storage area may store data created during the use of the electronic device 500, etc. The processor 510 executes various functional applications and data processing of the electronic device 500 by running instructions stored in the memory 520 and / or instructions stored in memory located within the processor.

[0119] If electronic device 500 is a terminal, it may also include a display screen 530. Electronic device 500 can implement display functions through a GPU, display screen 530, and application processor. The GPU is a microprocessor for image processing, connected to the display screen 530 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering. Processor 510 may include one or more GPUs, which execute program instructions to generate or modify display information.

[0120] The display screen 530 is used to display images, videos, etc. The display screen 530 includes a display panel. The display panel may be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a miniature LED, a microLED, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 500 may include one or N displays 530, where N is a positive integer greater than 1.

[0121] In some embodiments of this application, the terminal's display screen 530 can be used to display various interfaces, such as a document summary.

[0122] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device. In other embodiments of this application, the electronic device may include more or fewer components than those shown in FIG. 2, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0123] The technical solutions provided in the embodiments of this application will be described below with reference to the accompanying drawings and scenarios.

[0124] Scene 1

[0125] The first device can preprocess the content of locally stored files to generate summary content, allowing users to quickly view the file summary. Optionally, file types include, but are not limited to, text, audio, and video files. For example, a text file could be a Word or PPT document, an ebook, or another type of text file. Alternatively, a file could be a specific document, such as Xmind or Evernote. Another example is a multimedia file such as an MP3 or MP4 file, or a short video. The text type can also be referred to as a document type; the name is unrestricted.

[0126] For example, as shown in Figure 3(a), interface 101 displays local files on the phone. In response to a user long-pressing the "Design for Next Generation Products" document (marked with a dashed box), the phone can display interface 102 as shown in Figure 3(b), and display a summary of the document on interface 102. For example, the summary is displayed in window 107.

[0127] In some examples in this paper, users can trigger the first device to display a summary of a file by manipulating file operation items. For instance, file operation items can be table entries in a file viewing interface. As shown in Figure 4A, the file list enclosed by the dashed box includes files Yy1-Yy4 and the product meeting table entry. Similarly, in Figure 9(b), the operation item for "Next Generation Product Design" can be control 305. And in Figure 10(a), the operation item for "Next Generation Product Design" can be a dialog box enclosed by the dashed box. This paper does not limit the specific implementation or display style of the operation items.

[0128] Optionally, the phone displays a brief summary in interface 102 by default. In response to the user clicking the "Details" option 103, the phone can display a detailed summary.

[0129] Optionally, the interface 102 may also include a "Read Full Text" option 104. In response to the user clicking the "Read Full Text" option 104, the mobile phone can display the document. For example, it can display the first page of the document. Alternatively, it can display the subsequent content after swiping or turning pages.

[0130] For example, the mobile phone displays a summary in window 107, which can be achieved by: a first device providing a content display service, and a server providing a preview function. After detecting that the user has long-pressed a document, the first device can invoke this service to present some content in window 107. In this way, there is no need to jump to the corresponding application to open the summary or document, which can improve the efficiency of displaying the summary or document.

[0131] Optionally, the interface 102 may also include an "Open in app" option 105. In response to the user clicking the "Open in app" option 105, the phone can jump to the corresponding app to display the summary or document.

[0132] Optionally, the interface 102 may also include a "share" option 106. In response to the user clicking the "share" option 106, the mobile phone can share the document and the summary with other users.

[0133] Interface 102 may also include other controls, such as a voice playback control, which allows the phone to play a summary via voice in response to the user clicking the control.

[0134] The actions that trigger the first device to display a summary are not limited to long presses. For example, after detecting a user's long press on a document, the first device can display a card with multiple options, such as "Show Summary" and "Rename." After detecting a user clicking the "Show Summary" option, the first device displays a summary of the document.

[0135] Using the above method, the first device can display a summary of a document in response to a user's action (such as long-pressing the document) before the document's content is opened. This allows users to quickly understand the document's content through the summary, effectively improving information retrieval efficiency. Furthermore, the user's interaction path to obtain the summary is shorter, and the interaction method is simpler and more natural. Moreover, since the document's summary is pre-processed by the first device, it does not need to be generated temporarily in response to the user's viewing request; therefore, it can quickly respond to the user's summary viewing operation and display the summary, reducing the latency for the user to view the summary.

[0136] As one possible implementation, the first device can display icons for the corresponding files according to different user interface (UI) styles. For example, in Figure 3(a), the style one icon includes a circle and a star-like graphic inside the circle, indicating that a summary of the file has been generated. In some examples, hovering or long-pressing the icon will display the file's summary information on the phone.

[0137] For example, in Figure 3(a), the icon of Style 2 indicates that a summary cannot be generated for the file. The icon of Style 2 does not contain the circle and star markings. In other embodiments, the icon of Style 2 may also contain the circle and star markings, wherein the background of the circle is different from that of the icons of Style 1 and Style 3, to help users distinguish files.

[0138] For example, the icon in Style 3 indicates that the file can have a summary generated (the file supports having a summary generated), but the summary is not yet complete. The icon style after the summary is completed is Style 1. Optionally, Style 2 can be omitted. In this way, different UI styles can represent the differentiated status of files. Files that have already had summaries generated will be specially identified (marked) to help users distinguish files that can have their summaries viewed, thus improving the interactive experience.

[0139] Using this method, users can operate on a file in the file viewing interface (such as long-pressing), and the first device can respond to the operation by displaying a summary of the file, enabling users to quickly view the file summary and improving human-computer interaction efficiency.

[0140] File viewing interfaces, such as, but not limited to, file manager interfaces, document search interfaces, or memo interfaces. For example, in response to a user long-pressing the icon of a file found in the search interface, the first device pops up a preview interface and displays a summary of the file in the preview interface. As another example, if the first device detects that a user long-presses a document embedded in a memo, it displays a summary of that document.

[0141] In this article, the file viewing interface can be any interface that provides a file access point, allowing users to quickly view file summaries. The file viewing interface may include a file list. The file viewing interface can also be called a file management interface. The file list can also be called a file inventory; the name is not limited.

[0142] The above example uses the summary display on a mobile phone. Figure 4A shows an example of the summary display on a computer. As shown in Figure 4A, when the mouse hovers over the name of the file "Product Meeting.mp3" for a certain period of time, the computer can display the text summary of the file "Meeting Minutes" in area 201.

[0143] Optionally, the computer may also display a "Copy" option 202 in area 201. In response to the user clicking the "Copy" option 202, the computer can copy the contents of the summary to the clipboard for later use.

[0144] Optionally, the computer may also display an "Add to To-Do" option 204 in zone 201. In response to the user clicking the "Add to To-Do" option 204, the computer may add the summary to the calendar or memo to remind the user of the to-do item.

[0145] In some embodiments, the first device may determine files that support digest generation. "Files supporting digest generation" can be understood or replaced as: the file meets the requirements for digest generation. Files supporting digest generation satisfy at least one of the following conditions: the file type is text, audio, or video; the file size is less than a second threshold; the file is text and the number of words is less than a third threshold; the file is audio and the duration is less than a fourth threshold; the file is video and the duration is less than a fifth threshold.

[0146] For example, the first device does not support generating summaries for design documents or other special types of documents. Similarly, ebooks are too large, so the first device does not support generating summaries for them. Documents with fewer than 20,000 words can have summaries generated, but documents with 20,000 or more words cannot. Furthermore, for long video files, local computing power may be insufficient to generate summaries, therefore the first device does not support this feature. For short videos, if the first device has sufficient computing power to generate a summary, it can be determined that it supports this feature.

[0147] The thresholds in this article are merely examples. Each threshold can be flexibly determined based on the computing power of the first device or other factors, and is not limited thereto.

[0148] The first device may also use other methods to determine the files that support the generation of summaries.

[0149] The above example uses the scenario where "the first device determines that a file beyond its own capabilities is not supported for generating a summary." In other embodiments, the first device may also determine some files that are not supported for generating a summary based on other factors. For example, if a document contains too few words to warrant generating a summary, the first device may determine that it is not supported for generating a summary for that document.

[0150] The above example uses icon style to distinguish whether a file has a summary. The first device can also use other methods to distinguish whether a file can generate a summary; there are no restrictions, as long as they can help users distinguish whether a file has a summary. For example, it can distinguish by file name. As shown in Figure 4B, the first device can display mark 203 on the interface to indicate that a summary of the product meeting document has been generated.

[0151] The above example uses a file list in the form shown in Figure 4A. In other embodiments, the file list can take other forms and is not limited. For example, in Figure 4C, the file list is displayed as thumbnails. Each file has a corresponding label to help the user distinguish whether a file has a summary.

[0152] As one possible implementation, for files that do not support digest generation, the first device can also display the reason why a digest is not generated. For example, in Figure 4C, when the mouse hovers over the operation item for file Yy3, the computer can pop up window 205, which displays "This file type is not suitable for generating a digest." In this way, the user can know that the reason why the file has no digest is that the file type is inappropriate.

[0153] As one possible implementation, the user can select files that support digest generation. For example, in Figure 5(a), the user can select three files and right-click, triggering a computer display window 501, which may include a "Generate Digest" option. In response to the user clicking the "Generate Digest" option, the computer updates the icons of the three files to the style shown in Figure 5(b), indicating that the three files support digest generation but the digest has not yet been completed. After the digest is generated, the computer can update the icons of the corresponding files. As shown in Figure 5(c), the computer updates the style of the icons of the three files to style one, indicating that the digests of the three files have been generated. In this way, the first device can dynamically update the file markers in the interface so that the user can identify whether a file has a digest or supports digest generation through the updated markers in the interface.

[0154] As one possible implementation, the first device can create a specific folder, where all files within that folder can generate summaries. For example, a user can drag a file Yy3 from folder xx1 (as shown in Figure 6(b)) to folder xx3 (an example of the first folder) in Figure 6(a). After detecting the newly added file Yy3 in the xx3 folder, the first device can process the file Yy3 and generate a corresponding summary. As shown in Figure 6(c), after generating the summary of file Yy3, the first device can update the style of the icon for file Yy3 to indicate that the summary for file Yy3 has been generated.

[0155] The above examples illustrate how file tags can represent files that have already had a digest generated, files that do not support digest generation, and files that support digest generation but have not yet generated a digest. In other embodiments, file tags can be different and are not limited, as long as they allow users to quickly distinguish whether a file has a generated digest. For example, files can be categorized as files with digests and files without digests. The first device marks files with digests on the interface. For files without digests, the first device can mark the file on the interface, meaning there is a second tag on the interface indicating that the file does not have a digest. Alternatively, for files without digests, there is no tag on the interface indicating that the file has a digest. The tags for files with digests and files without digests are different so that users can distinguish between files with and without digests through the interface. Optionally, the first device can also display the reason why a file has no digest.

[0156] For example, subsequently, the first device can process the file without a digest to generate a digest for that file. Alternatively, the first device may never process the file without a digest to obtain one.

[0157] As described above, in some embodiments, the first device can divide the document into multiple sub-images by performing layout understanding on the document. Semantically related parts are grouped into the same sub-image. For example, in Figure 7, the upper half of the first page of the document is a sub-image 601. The lower half of the first page and the upper half of the second page are a sub-image 602. The contents of the third and fourth pages are a sub-image 603.

[0158] The first device can process each subgraph to obtain a summary corresponding to each subgraph, and determine the summary of the file based on the summaries of each subgraph. For example, for subgraph 601, the first device inputs the content of subgraph 601 (such as text, tables, etc.) into the large model, and the large model outputs a summary of subgraph 601. Similarly, the first device obtains summaries of subgraph 602 and subgraph 603. The first device inputs the summaries of subgraphs 601-603 into the large model, and the large model outputs a summary of the file.

[0159] For example, the summaries of subfigures 601-603 can correspond to the summaries of the subtitles / subpages shown in Figure 8. For instance, the first device inputs the summaries of the text, tables, and figures in subfigure 601 into the large model, and the large model outputs the summaries of subfigure 601.

[0160] Using this method, the first device considers the semantics of the document content when performing layout understanding, ensuring the semantic integrity of each subgraph and improving the accuracy of the summary. Furthermore, based on layout understanding, the first device can discard some unimportant information from the document, reducing the computational load for generating the summary and improving its efficiency.

[0161] In some embodiments, the abbreviated and detailed summaries mentioned above may correspond to different prompts for the large model. The prompt can be used to provide the large model with contextual information about the input and the parameters of the input model. For example, if the abbreviated summary corresponds to prompt 1, the large model can generate a 300-word abbreviated summary based on prompt 1. If the detailed summary corresponds to prompt 2, the large model can generate a 500-word detailed summary based on prompt 2. The specific word count for the abbreviated and detailed summaries can be set and is not limited.

[0162] As one possible implementation, the first device can pre-generate both a detailed summary and a brief summary. The first device can display one summary by default, and subsequently switch to displaying the other summary in response to user interaction. For example, in the above example, the first device defaults to displaying the brief summary, and subsequently switches to displaying the detailed summary. Or, for instance, the first device defaults to displaying the detailed summary, and subsequently switches to displaying the brief summary.

[0163] In other implementations, the first device pre-generates a summary, and subsequently, in response to user actions, generates another summary and switches to display the other summary.

[0164] This article does not limit the method of generating or displaying the abstract. For example, other models can be used to generate the abstract. For example, the abstract can be displayed in other interfaces that conform to user habits.

[0165] In some embodiments, after the first device generates a file summary, it can bind the summary to the file. As one possible implementation, the first device stores this binding relationship in a database. For example, Table 1 shows an example of such a database. In Table 1, the summary can be stored in a summary field corresponding to the file name to form an association between the file and the summary.

[0166] Table 1 is just an example; the database can store more or less information, or use other formats for storage.

[0167] Table 1

[0168] After the first device generates a summary of a file, it can display the summary to the user based on the relationship between the summary and the file. For example, if the phone detects that the user long-presses the document "Design of the Next Generation Product" shown in Figure 3(a), the phone queries the database shown in Table 1 to obtain the summary of the document "Meeting Topic: Product Meeting...", and displays the summary as shown in Figure 3(b).

[0169] In some examples, when a file is detected to have been moved, the first device can update the file's storage path. The first device can then read the digest from the database based on the association between the file and the digest, and present the digest.

[0170] In some examples, when the file "Design of Next-Generation Products" is detected to have been edited, the first device can generate a summary based on the modified file, store the modified summary in the summary field of the file, and delete the original summary. For example, the updated database is shown in Table 2. When the system detects that a user wants to view a file's summary, the first device can read the file's summary from the database and present it.

[0171] Table 2

[0172] In some examples, when a file is detected to have been renamed, the first device can update the file's name. Subsequently, the first device can read the digest from the database based on the association between the file and the digest, and then present the digest.

[0173] In some examples, when a file is detected to have been deleted, the first device can delete a summary of that file.

[0174] By using the above method, the first device associates and stores files and summaries, so that after a file is moved, modified, or renamed, the user does not need to manually trigger the generation of a summary again, thus reducing the complexity of generating a summary.

[0175] In some embodiments, the first device may generate a summary of the document under certain conditions.

[0176] As one possible implementation, the first device may determine whether to generate a summary based on at least one of the following: the battery level of the first device, the resource consumption percentage of the first device, or the screen status of the first device. For example, resource consumption includes, but is not limited to, memory and processor resource consumption.

[0177] In some examples, if the first device has sufficient battery power and is in a locked state, it can generate a document summary. When the first device is unlocked, it either does not generate a summary or pauses the summarizing task. Thus, in the unlocked state, the first device does not consume excessive resources due to the summarizing task, providing more resources for human-computer interaction and contributing to the smoothness of user operations in the unlocked state.

[0178] The first device has sufficient power, either because it is currently charging or because its power level exceeds a certain threshold.

[0179] In some examples, if the first device has sufficient battery power and its resource consumption is low while the screen is locked, the first device can generate a summary. Conversely, if the first device has insufficient battery power and its resource consumption is low while the screen is locked, it may not generate a summary or may pause the summary task. Low resource consumption can mean that the resource consumption is below a threshold. For example, if the user is using the first device with the screen on, the CPU and GPU of the first device are under high load, the summary task will be queued, and the first device will not generate a summary immediately.

[0180] In some examples, the first device can generate a summary when it has sufficient power and consumes relatively few resources.

[0181] In some examples, if the first device switches to an unlocked state and is performing a resource-intensive task while generating a summary in a locked state, the first device can terminate or pause the summary task. Otherwise, if the first device switches to an unlocked state but is not currently performing a resource-intensive task, the first device can continue performing the current summary generation task. A high resource consumption percentage can be defined as a resource consumption percentage exceeding a threshold. Optionally, if the first device pauses the summary task, it can wait until the resource consumption percentage decreases before resuming the summary task.

[0182] For example, if a user unlocks the device and opens a resource-intensive application while the device is generating a summary on its locked screen, the device can immediately terminate the summary task. Conversely, if a user unlocks the device and browses a webpage while the device is generating a summary on its locked screen, where resource consumption is low, the device can continue executing the summary task.

[0183] In some examples, if the battery level is low during the summary generation process, the first device may terminate or pause the summary task. For instance, if the battery level drops to 50% while the first device is generating a summary in a locked state, the first device may terminate the summary task to save power.

[0184] Alternatively, as a possible implementation, the first device may periodically perform a digest task, and this document does not limit the specific timing and conditions under which the first device generates a digest.

[0185] Scene 2

[0186] In this scenario, the first device can share files and file summaries with other devices, so that users on those other devices can quickly understand the content of the files based on the file summaries.

[0187] Take, for example, a scenario where a user is chatting using instant messaging software. Exemplarily, as shown in Figure 9(a), mobile phone 1 displays interface 301. In response to the user on mobile phone 1 selecting the document "Design of Next-Generation Products" and clicking the send button 302, mobile phone 1 sends the document "Design of Next-Generation Products" and a summary of the document to mobile phone 2. In some examples, after receiving the document and the summary, mobile phone 2 can display control 305 in interface 303, as shown in Figure 9(b). In response to the user clicking control 305, as shown in Figure 9(c), mobile phone 2 can expand to display the summary of the document.

[0188] In other examples, after receiving the document and its summary, mobile phone 2 can display an icon for the document in interface 401 as shown in Figure 10(a). The icon uses style one, indicating that the document has a corresponding summary. In response to the user's long-press operation on the icon, mobile phone 2 displays the document's summary in interface 402 as shown in Figure 10(b).

[0189] Using this method, after receiving a document, the device can display a summary of the document to the user, who can then decide whether to download the document based on the summary.

[0190] The above example uses an instant messaging software scenario. The solution in this application embodiment can also be applied to other file sharing scenarios, such as email sending and receiving. In other embodiments, the solution in this application embodiment can also be applied to near-field communication scenarios. For example, in a Huawei sharing scenario, in response to a user's selection of document 1, the computer shares document 1 and its corresponding summary to mobile phone 2. The user of mobile phone 2 can long-press document 1 to view its summary. Optionally, document 1 on mobile phone 2 can also have corresponding markers so that the user of mobile phone 2 can distinguish whether a file has a summary.

[0191] In one or more scenarios described in this paper (not limited to scenario two), the first device can also control the display and hiding of the summary in conjunction with file permissions. For example, in Figure 11(a), for the encrypted document "Product Meeting," hovering the mouse over the document will not trigger the first device to display the summary. This prevents information in the document from being leaked to users without permissions. Optionally, the first device can display a prompt message indicating to the user why the summary cannot be viewed. For example, window 403 may display "You do not have read permissions for this file and its summary."

[0192] Users can enter a password to decrypt the document. After decryption, as shown in Figure 11(b), when the mouse hovers over the document, the first device can display a summary of the document.

[0193] For example, a document may be a shared document. Users with permission to view the shared document can quickly view its summary. Users without permission cannot quickly view its summary.

[0194] For example, the first terminal obtains a file that the first user does not have read permissions for, and moves the file to the folder xx3 shown in Figure 6(a). Since the first user cannot read the file, the first terminal will not generate a digest, nor will it display a specific digest marker on the interface. Optionally, the first terminal can display the reason for not generating a digest, such as "You do not have read permissions for the file."

[0195] Scene 3

[0196] In this scenario, cross-device interaction, digest sharing, and computing power collaboration are supported, enabling multiple devices to collaboratively generate file digests.

[0197] For example, after a mobile phone recognizes a document that needs a summary, if its own computing power is insufficient, it can compress the document and send the compressed document to nearby collaborative devices. Collaborative devices can be high-computing devices, such as computers, in-vehicle systems, servers, or one or more devices in a home storage system. As shown in Figure 12, the mobile phone sends the file to the computer (an example of a third device), the computer generates a summary of the file, and sends the summary back to the mobile phone. The mobile phone can store the summary and bind it to the file. For example, the summary can be stored in the summary field corresponding to the file.

[0198] As one possible implementation, the first device can detect collaborating devices through a file analysis service. The first device can then select the timing for generating a digest based on the current load of each collaborating device. For example, if a high-performance computing device with low load is currently available, the first device's file distribution module can immediately instruct that high-performance computing device to generate a digest of the files on the first device. Conversely, if no high-performance computing device with low load is currently available, the first device can delay instructing the high-performance computing device to generate a file digest.

[0199] As one possible implementation, if the devices lose connection during the collaborative generation of the summary, the first device can trigger exception handling through the file analysis service and add the file sub-nodes back to the list of summaries to be generated.

[0200] The above example uses a mobile phone instructing a computer to generate a complete summary. In other embodiments, multiple devices can collaboratively generate the summary, with each device completing a portion of the summary. For example, the mobile phone completes the summary of figures, text, and tables, the computer completes the summary of subheadings, and the home storage completes the summary of the entire document.

[0201] Using this method, the first device can generate a document summary for itself by leveraging the AI ​​capabilities of other devices. In this way, even devices with insufficient AI capabilities can achieve the function of quickly viewing the summary.

[0202] Figure 13 illustrates an example flow of a method according to an embodiment of this application. As shown in Figure 13, the method may include:

[0203] S101, The first device displays the operation item of the first file on the first interface; the first file has a first mark on the first interface, the first mark indicating that the first file has a generated summary.

[0204] This method is applicable to scenarios such as locally generated summaries and summaries obtained through communication. Taking the locally generated summary scenario as an example, the first device can store a first file and a first summary of the first file. As one possible implementation, the first device stores the first summary in the summary field corresponding to the first file. For example, the summary of the corresponding file can be stored in the summary field of the table shown in Table 1. Taking the scenario of obtaining a summary through communication as an example, the first device can receive the file and summary from the sharing party through software such as Huawei Share or chat software.

[0205] For example, as shown in Figure 3(a), the first device displays the operation item corresponding to the document "Design of Next Generation Products" (shown in dashed boxes).

[0206] S102. In response to the first user's operation on the operation item of the first file, the first device displays the content of the first summary of the first file.

[0207] The first summary is an overview of the first document.

[0208] For example, as shown in Figure 3(a), in response to a user long-pressing the "Design of Next Generation Products" file, the first device displays a summary of the file in interface 102 as shown in Figure 3(b).

[0209] Optionally, the method may further include: in response to the operation of sharing a first file, the first device sends the first file and the first summary. For example, in Figure 9(a), in response to the user selecting the file "Design of Next-Generation Products" and clicking the send button 302, mobile phone 1 sends the file and its summary to mobile phone 2. Thus, the user of mobile phone 2 can also experience a quick preview of the summary. For a detailed implementation of this method, please refer to the relevant introduction in Scenario 2, which will not be repeated here.

[0210] The first device may generate a first digest by referring to the method described herein. Optionally, before S101, the method may further include: satisfying a first condition, the first device generating a digest based on a file to be digested, wherein the file to be digested includes the first file; the first condition includes at least one of the following conditions: the first device has sufficient power; the first device is in a locked state; the resources of the first device meet the conditions for executing digest generation. Sufficient power of the first device includes the first device being in a charging state, or the power of the first device being greater than a first threshold.

[0211] The first device's resources satisfying the conditions for generating an execution summary can be understood as the first device's available resources being greater than or equal to a threshold, or the first device's used resources being less than or equal to a certain threshold. Available resources can also be called remaining resources. Used resources can also be called occupied or consumed resources. The first device can determine whether it meets the conditions for generating an execution summary based on the values ​​or percentages of available and used resources.

[0212] Optionally, resources may include multiple types; some resources can be measured by availability, while others can be measured by occupancy. For example, if available memory is greater than or equal to 5MB and processor usage is less than or equal to 50%, the first device determines that the conditions for generating an execution digest are met. Conversely, the first device determines that the conditions for generating an execution digest are not met.

[0213] As one possible implementation, the first digest is obtained from M digests of M first semantic blocks in the first file; the M first semantic blocks are obtained by performing layout understanding on the first file, and each first semantic block has complete semantics; the digest of each first semantic block is obtained by performing artificial intelligence (AI) processing on the first semantic block, where M is an integer greater than 1.

[0214] Optionally, each first semantic block includes multiple second semantic blocks, and the summary of each first semantic block is obtained by performing artificial intelligence (AI) processing on the first semantic block, including: the summary of the first semantic block is determined based on the summaries of the multiple second semantic blocks included in the first semantic block. For example, the number of second semantic blocks included in different first semantic blocks may be different.

[0215] In one possible implementation, the file to be digested includes a third file, and the method further includes: during the process of generating a digest from the third file, if the first device detects that the first condition is not met, it stops generating the digest from the third file. That is, after detecting that the condition for executing the digest is not met, the first device can immediately stop the digest generation step.

[0216] Alternatively, as a possible implementation, the file to be digested includes a fourth file, and the method further includes: during the process of generating a digest based on the fourth file, if the first device detects that the first condition is not met, it continues to generate a digest of the fourth file, and after generating the digest of the fourth file, it stops executing the digest generation step. That is, after detecting that the condition for executing the digest is not met, the first device can continue to generate a digest of the current file, and then stop the digest generation step. For example, the file to be digested includes files 1-4, and the first device generates digests sequentially according to the order of files 1-4, and is currently generating a digest of file 2. If the first device detects that the condition for executing the digest generation is not met, then the first device can continue to generate a digest of file 2. After generating a digest of file 2, the first device terminates the digest generation step.

[0217] For example, if a user unlocks the first device while it is generating a file summary in a locked and charging state, the first device can determine whether to continue the summary generation step based on its resource availability. For instance, if the first device has ample available memory and a low processor load, it can continue the summary generation step. Conversely, it can terminate or pause the summary generation step if the available memory is insufficient.

[0218] The above primarily describes the solutions provided by the embodiments of this application from a methodological perspective. It is understood that, in order to achieve the above functions, the electronic device includes hardware structures and / or software modules corresponding to the execution of each function. Based on the units and algorithm steps of the various examples described in the embodiments disclosed in this application, the embodiments of this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by a computer driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the technical solutions of the embodiments of this application.

[0219] This application provides embodiments for dividing an electronic device into functional modules based on the above method examples. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into a single processing unit. The integrated unit can be implemented in hardware or as a software functional module. It should be noted that the unit division in this application embodiment is illustrative and represents only one logical functional division; in actual implementation, other division methods may be used.

[0220] Figure 14 shows a schematic diagram of an electronic device provided in an embodiment of this application. This electronic device 1300 can be used to implement the methods executed by the electronic devices described in the above method embodiments. For example, the electronic device 1300 may include a processing unit 1301 and a communication unit 1302. Optionally, the electronic device 1300 may further include a display unit 1303.

[0221] As another possible example, processing unit 1301 is used to support electronic device 1300 in performing the processing functions of the terminal described in any one of Figures 1 to 13; communication unit 1302 is used to support electronic device 1300 in performing the communication functions of the terminal described in any one of Figures 1 to 13; and display unit 1303 is used to support electronic device 1300 in performing the display functions of each device described in any one of Figures 1 to 13.

[0222] Optionally, the electronic device 1300 shown in FIG. 14 may further include a storage unit (not shown in FIG. 14) storing a program or instructions. When the processing unit 1301 executes the program or instructions, the electronic device 1300 shown in FIG. 14 can perform the method described in the above-described method embodiments.

[0223] The technical effects of the electronic device 1300 shown in Figure 14 can be referred to the technical effects described in the above method embodiments, and will not be repeated here. The processing unit 1301 involved in the electronic device 1300 shown in Figure 14 can be implemented by a processor or processor-related circuit components, and can be a processor or processing module. The communication unit 1302 can be implemented by a transceiver or transceiver-related circuit components, and can be a transceiver or transceiver module. The display unit 1303 can be implemented by display screen-related components.

[0224] This application also provides a chip system, as shown in FIG15, which includes at least one processor 1401 and at least one interface circuit 1402. The processor 1401 and the interface circuit 1402 are interconnected via lines. For example, the interface circuit 1402 can be used to receive signals from other devices. As another example, the interface circuit 1402 can be used to send signals to other devices (e.g., the processor 1401). Exemplarily, the interface circuit 1402 can read instructions stored in a memory and send those instructions to the processor 1401. When the instructions are executed by the processor 1401, the electronic device can perform the various steps performed by the electronic device in the above embodiments. Of course, the chip system may also include other discrete devices, and this application does not specifically limit this.

[0225] Optionally, the chip system may contain one or more processors. These processors can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor, implemented by reading software code stored in memory.

[0226] Optionally, the chip system may contain one or more memories. The memory may be integrated with the processor or disposed separately from it; this application does not limit this. For example, the memory may be a non-transient processor, such as a read-only memory (ROM), which may be integrated with the processor on the same chip or disposed separately on different chips. This application does not specifically limit the type of memory or the arrangement of the memory and processor.

[0227] For example, the chip system may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), a central processor unit (CPU), a network processor (NP), a digital signal processor (DSP), a micro controller unit (MCU), a programmable logic device (PLD), or other integrated chips.

[0228] It should be understood that each step in the above method embodiments can be completed by integrated logic circuits in the processor hardware or by instructions in software form. The method steps disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0229] This application also provides a computer storage medium storing computer instructions, which, when executed on an electronic device, cause the electronic device to perform the methods described in the above-described method embodiments.

[0230] This application provides a computer program product, which includes a computer program or instructions that, when run on a computer, cause the computer to perform the methods described in the above-described method embodiments.

[0231] In addition, this application also provides an apparatus, which may specifically be a chip, component or module. The apparatus may include a connected processor and a memory. The memory is used to store computer execution instructions. When the apparatus is running, the processor can execute the computer execution instructions stored in the memory to cause the apparatus to perform the methods in the above-described method embodiments.

[0232] In this embodiment, the electronic device, computer storage medium, computer program product or chip are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding method provided above, and will not be repeated here.

[0233] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0234] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The embodiments can be combined with or referenced to each other without conflict. The apparatus embodiments described above are merely illustrative; for example, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0235] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0236] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0237] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0238] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for displaying document summaries, characterized in that, The method is applied to a first device, and the method includes: The first interface displays operation items for the first file; the first file has a first mark on the first interface, the first mark indicating that the first file has a generated summary; In response to the first user's operation on the first file, the content of the first summary of the first file is displayed.

2. The method according to claim 1, characterized in that, Also includes: In response to the operation of sharing the first file with the second user, the first file and the first digest are sent to the second user's second device.

3. The method according to claim 1 or 2, characterized in that, Before displaying the operation items for the first file in the first interface, it also includes: Send the first file to the third device; The first digest is received from the third device, wherein the first digest is obtained by the third device processing the first file.

4. The method according to any one of claims 1-3, characterized in that, In response to an operation by the first user on the first file, the content of a first summary of the first file is displayed, including: If the first user has permission to view the first file, the content of the first summary is displayed in response to the first user's operation on the first file.

5. The method according to any one of claims 1-4, characterized in that, The first device stores the first file and the first summary.

6. The method according to claim 5, characterized in that, The first device stores the first digest, including: The first summary is stored in the summary field corresponding to the first file.

7. The method according to any one of claims 1-6, characterized in that, The first device also stores a second file, and the first interface also includes operation items for the second file. The second file does not have a marker in the first interface to indicate that the second file has a summary, or the second file has a second marker in the first interface to indicate that the second file does not have a summary.

8. The method according to claim 7, characterized in that, The second marker indicates that the second file supports the generation of a digest, and that the digest of the second file has not yet been generated.

9. The method according to claim 7, characterized in that, The second marker indicates that the second file does not support the generation of a digest.

10. The method according to any one of claims 1-9, characterized in that, Before displaying the operation items for the first file in the first interface, it also includes: If the first condition is met, a digest is generated based on the file for which a digest is to be generated, wherein the file for which a digest is to be generated includes the first file; the first condition includes at least one of the following: the first device has sufficient power; the first device is in a locked screen state; the resources of the first device meet the conditions for executing digest generation. Sufficient power for the first device includes the first device being in a charging state, or the first device having a power level greater than a first threshold.

11. The method according to claim 10, characterized in that, The file to be used to generate the summary includes a third file, and the method further includes: If the first condition is not met during the process of generating a digest from the third file, the process of generating the digest from the third file is stopped.

12. The method according to claim 10, characterized in that, The file to be used to generate the summary includes a fourth file, and the method further includes: If the first condition is not met during the process of generating a digest based on the fourth document, the process continues to generate a digest of the fourth document, and stops the digest generation step after the digest of the fourth document is generated.

13. The method according to any one of claims 1-13, characterized in that, Also includes: In response to the first user's operation to generate a summary of the first file, the first file is processed to obtain the first summary.

14. The method according to any one of claims 1-13, characterized in that, Also includes: In response to the operation of modifying the first file, the modified first file is processed to obtain an updated summary.

15. The method according to any one of claims 1-14, characterized in that, The first device includes a first folder, and the files in the first folder support the generation of summaries.

16. The method according to any one of claims 1-15, characterized in that, Also includes: Receive the fifth file from the fourth device; A second digest is sent to the fourth device, the second digest being obtained by the first device from processing the fifth file.

17. The method according to any one of claims 1-16, characterized in that, The first summary is obtained from M summaries of M first semantic blocks in the first file; the M first semantic blocks are obtained by understanding the layout of the first file, and each first semantic block has complete semantics; the summary of each first semantic block is obtained by artificial intelligence (AI) processing of the first semantic block, where M is an integer greater than 1.

18. The method according to claim 17, characterized in that, Each first semantic block includes multiple second semantic blocks, and the summary of each first semantic block is obtained by artificial intelligence (AI) processing of the first semantic block, including: the summary of the first semantic block is determined based on the summaries of the multiple second semantic blocks included in the first semantic block.

19. The method according to any one of claims 1-18, characterized in that, The first interface includes a file management interface, which displays the operation items for the first file, including: The file management interface displays a file list, which includes entries corresponding to one or more files; the one or more files include the first file.

20. The method according to any one of claims 1-4 or 14-16, characterized in that, The first interface includes a chat interface with a third user; the first interface displays operation items for the first file, including: After receiving the first file and the first summary from the third user's device, the operation items for the first file are displayed in the first interface.

21. The method according to any one of claims 1-18, characterized in that, The first file satisfies at least one of the following conditions: the first file is of text, audio, or video type; the size of the first file is less than a second threshold; the first file is of text type and the number of words in the first file is less than a third threshold; the first file is of audio type and the duration of the first file is less than a fourth threshold; the first file is of video type and the duration of the first file is less than a fifth threshold.

22. A computer-readable storage medium, characterized in that, Includes a program or instructions, which, when executed, implement the method as described in any one of claims 1 to 21.

23. A computer program product, characterized in that, It includes a program or instructions that, when the computer program product is run on a computer, cause the computer to perform the method as described in any one of claims 1 to 21.

24. A chip system, characterized in that, The chip system includes processing circuitry configured to perform the method as described in any one of claims 1 to 21.

25. An electronic device, characterized in that, The electronic device includes a processor and a memory; The memory is used to store computer execution instructions. When the device is running, the processor executes the computer execution instructions stored in the memory to cause the device to perform the method as described in any one of claims 1 to 21.

Images