A knowledge management method, device, computer device and computer program product

Abstract

This disclosure provides a knowledge management method, apparatus, computer equipment, and computer program product, relating to the fields of artificial intelligence and data processing technology. The knowledge management method includes: acquiring input knowledge data; performing semantic understanding based on the knowledge data to obtain knowledge entities and corresponding knowledge topics; determining a knowledge association network based on the knowledge entities and knowledge topics, the knowledge association network including knowledge entities, the relationships between knowledge entities, and the correspondence between knowledge entities and knowledge topics; and displaying the knowledge association network, wherein knowledge entities corresponding to the same knowledge topic are displayed in clusters.

Description

Technical Field

[0001] This specification relates to the fields of artificial intelligence and data processing technology, and in particular to a knowledge management method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] With the development of internet technology, users have increasingly diverse channels for obtaining information. They can acquire knowledge content through various means such as public web pages, social media platforms, online documents, and audio-visual platforms, and then collect and store this information. For example, users can save web links, text and image information, audio information, and video information using the platform's collection function. When they need to use the relevant knowledge, they can then retrieve the collected information from the corresponding platform to read, use, or share it. However, knowledge content from different sources is scattered across different platforms, making unified management impossible. Users also cannot quickly understand the connections and structure between different pieces of knowledge, resulting in low efficiency in knowledge utilization.

[0003] In view of this, some embodiments of this specification provide a knowledge management method, apparatus, computer device, computer-readable storage medium, and computer program product, which aim to manage knowledge in a unified manner, improve the efficiency of knowledge utilization, and organize and display knowledge content in a structured and related manner to help users understand relevant knowledge from a holistic perspective. Summary of the Invention

[0004] This specification provides one or more embodiments of a knowledge management method, the method comprising: acquiring input knowledge data; performing semantic understanding based on the knowledge data to obtain knowledge entities and knowledge topics corresponding to the knowledge entities; determining a knowledge association network based on the knowledge entities and knowledge topics, the knowledge association network including knowledge entities, the association relationships between knowledge entities, and the correspondence between knowledge entities and knowledge topics; and displaying the knowledge association network, wherein knowledge entities corresponding to the same knowledge topic are displayed in clusters.

[0005] According to one or more embodiments of this specification, a method is provided to perform semantic understanding based on knowledge data to obtain knowledge entities and knowledge topics corresponding to the knowledge entities, including: performing semantic understanding on knowledge data using a large model, extracting knowledge entities from the knowledge data, determining the knowledge content corresponding to the knowledge entities, and the knowledge topic corresponding to at least one knowledge entity.

[0006] According to one or more embodiments of this specification, the association relationship between knowledge entities includes the association strength. Displaying the knowledge association network includes: determining the display position of knowledge entities based on the association strength between knowledge entities and the correspondence between knowledge entities and knowledge topics, so that knowledge entities corresponding to the same knowledge topic are clustered together for display, knowledge entities with high association strength are displayed close together, and the association strength between knowledge entities is displayed.

[0007] According to one or more embodiments of this specification, the knowledge association network further includes knowledge content corresponding to the knowledge entity, and the method further includes: in response to a selection operation on the knowledge entity, determining a target knowledge entity; in response to a sharing operation on the target knowledge entity, analyzing and processing the knowledge content corresponding to the target knowledge entity to obtain the target knowledge content.

[0008] According to one or more embodiments of this specification, the method analyzes and processes the knowledge content corresponding to the target knowledge entity to obtain the target knowledge content, including: using a large model to analyze and process the knowledge content corresponding to the target knowledge entity to obtain the target knowledge content; generating a preset data object based on the target knowledge content and at least one of the following information for direct calling by other large models: the target knowledge entity, the relationship between target knowledge entities, and prompt information for indicating the calling of the target knowledge content.

[0009] According to one or more embodiments of this specification, the method further includes: displaying knowledge content corresponding to the knowledge entity in response to a triggering operation on the knowledge entity; and determining retrieval results based on the knowledge content in the knowledge association network in response to a knowledge retrieval operation.

[0010] According to one or more embodiments of this specification, the method further includes: determining action suggestion information and corresponding triggering conditions based on knowledge data; obtaining status information, which includes at least one of the following: environmental information, contact information, and user status information; and generating reminder information based on the action suggestion information when the status information matches the triggering conditions.

[0011] According to one or more embodiments of this specification, the method for determining action suggestion information and corresponding triggering conditions based on knowledge data includes: determining whether the knowledge data meets the action suggestion generation conditions based on a preset analysis strategy; if so, extracting action suggestion information based on the knowledge data, wherein the action suggestion information includes action content, action conditions, and at least one of the following: action theme, recommendation reason, and knowledge category; and determining the triggering conditions corresponding to the action suggestion information based on the action conditions.

[0012] According to one or more embodiments of this specification, a method for obtaining input knowledge data includes: in response to a user input operation, obtaining knowledge data, wherein the knowledge data includes at least one of web links, text, voice, images, and videos.

[0013] This specification also provides a knowledge management device in one or more embodiments, the device comprising: a knowledge input module for acquiring input knowledge data; a semantic understanding module for performing semantic understanding based on the knowledge data to obtain knowledge entities and knowledge topics corresponding to the knowledge entities; an association network determination module for determining a knowledge association network based on the knowledge entities and knowledge topics, the knowledge association network including knowledge entities, the association relationships between knowledge entities, and the correspondence between knowledge entities and knowledge topics; and an association network display module for displaying the knowledge association network, wherein knowledge entities corresponding to the same knowledge topic are displayed in clusters.

[0014] One or more embodiments of this specification also provide a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it is able to implement the knowledge management method described in some embodiments of this specification.

[0015] One or more embodiments of this specification also provide a computer-readable storage medium storing computer instructions that, when executed by a processor, can implement the knowledge management method described in some embodiments of this specification.

[0016] One or more embodiments of this specification also provide a computer program product, including a computer program that, when at least a portion of the computer program is executed by a processor, can implement the knowledge management method described in some embodiments of this specification.

[0017] The beneficial effects that the embodiments of this specification may bring include, but are not limited to: (1) acquiring input knowledge data, performing semantic understanding based on the knowledge data, obtaining knowledge entities and knowledge topics corresponding to the knowledge entities, and determining a knowledge association network based on the knowledge entities and knowledge topics. The knowledge association network includes knowledge entities, the relationship between knowledge entities, and the correspondence between knowledge entities and knowledge topics. The knowledge association network is displayed, and knowledge entities corresponding to the same knowledge topic are displayed in clusters. This allows for unified management of knowledge, improves the efficiency of knowledge utilization, and organizes and displays knowledge content in a structured manner, helping users to understand relevant knowledge from an overall perspective; (2) by constructing a knowledge association network, the input scattered knowledge data can be organized according to knowledge topics and knowledge entities, so that different knowledge contents can form a relationship, making it convenient for users to centrally manage the knowledge information they have accumulated; (3) by generating a knowledge association network and determining the search results based on the knowledge content in the knowledge association network, the knowledge content collected by users from different sources can be stored in association, which is convenient for large models to understand and use in a unified manner. There is no need to repeatedly search for and understand knowledge content from different sources, which improves the efficiency of knowledge utilization; (4) because the knowledge association network is displayed in the interface, The content includes knowledge entities and the relationships between knowledge entities. Knowledge entities corresponding to the same topic are displayed in clusters. Users can flexibly combine different knowledge points in the visualized knowledge organization structure. They do not need to return to various platforms to find the knowledge to be shared. Instead, they can directly select the content to be shared from the perspective of the knowledge system, realize flexible sharing of single knowledge points, related knowledge or complete topic knowledge, and improve the accuracy, completeness and efficiency of knowledge sharing. (5) By responding to the sharing operation of the target knowledge entity, the target knowledge content is obtained by analyzing and processing the knowledge content corresponding to the target knowledge entity. Thus, the scattered knowledge content to be shared can be integrated into the target knowledge content with complete semantic association. The recipient does not need to understand the knowledge content from multiple sources to quickly obtain complete knowledge information, which improves the information integrity and comprehensibility in the knowledge dissemination process. (6) By analyzing and processing the knowledge content corresponding to the target knowledge entity, the target knowledge content is obtained, and a preset data object is generated based on the target knowledge content. Thus, it can be directly called by other large models, skipping the step restriction that the recipient needs to understand before using it. There is no need to re-analyze and organize the original knowledge content, which improves the efficiency of knowledge dissemination.(7) By determining action suggestion information and corresponding triggering conditions based on knowledge data, status information is obtained. When the status information matches the triggering conditions, a reminder message is generated based on the action suggestion information. In this way, the various knowledge data collected by the user, after being understood by the large model, does not just remain in storage, but is actively searched for and edited from the knowledge to generate reminder messages, thereby guiding the user's actions, in conjunction with various real-time information and needs of the user. It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced can be any one or a combination of the above, or any other possible beneficial effects. Attached Figure Description

[0018] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. The same numbers in the drawings denote the same structures or steps.

[0019] Figure 1 This is an exemplary flowchart of a knowledge management method according to some embodiments of this specification.

[0020] Figure 2 This is a schematic diagram of a knowledge management display interface according to some embodiments of this specification.

[0021] Figure 3 This is a schematic diagram of another knowledge management display interface shown according to some embodiments of this specification.

[0022] Figure 4 This is a schematic diagram of a knowledge-related network display interface based on some embodiments of this specification.

[0023] Figure 5 This is a schematic diagram of the knowledge content display interface shown in some embodiments of this specification.

[0024] Figure 6 This is a schematic diagram of the search interface shown according to some embodiments of this specification.

[0025] Figure 7 This is a schematic diagram of the search results display interface according to some embodiments of this specification.

[0026] Figure 8 This is an exemplary flowchart illustrating a knowledge-sharing method according to some embodiments of this specification.

[0027] Figure 9 This is a schematic diagram of a knowledge sharing interface shown according to some embodiments of this specification.

[0028] Figure 10This is an exemplary flowchart illustrating a knowledge data-based reminder method according to some embodiments of this specification.

[0029] Figure 11 This is a schematic diagram of the reminder information display interface according to some embodiments of this specification.

[0030] Figure 12 This is a schematic diagram of an action suggestion information management interface according to some embodiments of this specification.

[0031] Figure 13 This is an exemplary block diagram of a knowledge management device according to some embodiments of this specification. Detailed Implementation

[0032] To more clearly illustrate the technical solutions of the embodiments in this specification, the embodiments will be described in detail below with reference to the accompanying drawings. Obviously, the content described below are some examples or embodiments of this specification. For those skilled in the art, without creative effort, the technical solutions or means disclosed in this specification can be applied to other scenarios based on this technical content.

[0033] It should be understood that the terms "system," "device," "unit," and / or "module" used in this specification are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0034] Unless otherwise specified, the technical terms used to describe components, elements, etc. in this specification are not singular but may include plural. Generally speaking, terms such as "comprising" or "including" only indicate that explicitly identified steps, elements, or components are included, and these steps, elements, and components do not constitute an exclusive list, as the described method or apparatus may also include other steps or components.

[0035] This specification uses flowcharts to illustrate the operational steps performed by the apparatus or system of related embodiments. However, unless otherwise specified, the order in which these steps are described should not be construed as a limitation on the order of execution. Those skilled in the art can adjust the order of these steps based on the knowledge and information conveyed by the embodiments in this specification. Such adjustments include, but are not limited to, reversing the order of steps, merging multiple steps, and splitting a step.

[0036] With the development of internet technology, users have increasingly diverse channels for obtaining information. They can acquire knowledge content through various means such as public web pages, social media platforms, online documents, and audio / video platforms, and then collect and store this information. In some related embodiments, users can store web page links, text and image information, audio information, and video information through the platform's collection function. When they need to use the relevant knowledge, they can then retrieve the collected information from the corresponding platform for reading, use, or sharing. However, knowledge content from different sources is scattered across different platforms, making unified management impossible. Users also cannot quickly understand the connections and structures between different pieces of knowledge, resulting in low knowledge utilization efficiency. Furthermore, since knowledge content from different sources typically exists in raw information form (such as text, images, and videos), it cannot be uniformly understood and used by large models. This forces large models to repeatedly perform information retrieval and understanding processing when generating corresponding content based on user-collected knowledge, further reducing knowledge utilization efficiency.

[0037] To this end, some embodiments of this specification propose a knowledge management method, which includes: acquiring input knowledge data, performing semantic understanding based on the knowledge data, obtaining knowledge entities and knowledge topics corresponding to the knowledge entities, and determining a knowledge association network based on the knowledge entities and knowledge topics. The knowledge association network includes knowledge entities, the relationships between knowledge entities, and the correspondence between knowledge entities and knowledge topics. The knowledge association network is displayed, and knowledge entities corresponding to the same knowledge topic are displayed in clusters. This unified management of knowledge improves the efficiency of knowledge utilization and provides a structured organization and associated display of knowledge content, helping users understand relevant knowledge from a holistic perspective.

[0038] Figure 1 This is an exemplary flowchart of a knowledge management method according to some embodiments of this specification. Figure 1The illustrated process 100 can be executed by a computer device, for example, by a knowledge management device 1300 deployed on the computer device. In some embodiments, the computer device can be a terminal device, including but not limited to desktop computers, smartphones, laptops, VR (Virtual Reality) devices, tablets, smart TVs, in-vehicle terminals, etc. In other embodiments, the computer device can also be a server. The server can include a local server or a cloud server; depending on different service needs, a local server corresponding to a specific region can be deployed in one or more regions. In some embodiments, the server can be a single computer or a computing cluster composed of multiple computers, thereby providing more powerful computing power and more efficient response to user service requests. In some embodiments, part of process 100 can be executed by the computer device acting as a terminal device, while another part can be executed by the computer device acting as a server. Figure 1 As shown, process 100 may include the following steps.

[0039] Step 110: Obtain the input knowledge data. In some embodiments, step 110 can be implemented by the knowledge input module 1310.

[0040] In some embodiments, knowledge data may be user-input data. A computer device may acquire knowledge data in response to user input. This knowledge data may include at least one of web links, text, voice, images, and videos. Figure 2 This is a schematic diagram of a knowledge management display interface according to some embodiments of this specification. For example, as shown below... Figure 2 As shown, when users are browsing web pages, reading articles, viewing images (or videos), or chatting using social media, they can input the content they are browsing or the corresponding web page link into the input box in the knowledge management display interface and click the "Fetch and Save" icon. The computer device can then respond to this input operation and retrieve the corresponding knowledge data.

[0041] In some embodiments, knowledge data may also be data automatically acquired using a preset acquisition tool. For example, a user can pre-configure data acquisition conditions, such as setting the conditions to acquire knowledge data containing specific key content or from a specific data source. A computer device can use an automatic acquisition tool (e.g., a data acquisition tool) to access a target data source according to the pre-configured data acquisition conditions, acquire knowledge data from the target data source, or extract knowledge data containing specific key content from the target data source. The target data source may be a public webpage, online document, data platform, etc. It is understood that in the specific embodiments of this specification, the collection, use, or processing of data (e.g., knowledge data and environmental information, contact information, user status information, etc. mentioned below) requires the data subject's permission or consent when one or more embodiments of this specification are applied to specific products or technologies. Furthermore, the collection, use, or processing of related data must strictly comply with the relevant laws, regulations, and standards of the data source country, implementation country, and other relevant countries and regions. De-identification technology ensures that the final data used is securely processed de-identified data, protecting the rights and interests of the data subject and data security.

[0042] Step 120: Perform semantic understanding based on the knowledge data to obtain knowledge entities and the knowledge topics corresponding to the knowledge entities. In some embodiments, step 120 can be implemented by the semantic understanding module 1320.

[0043] In some embodiments, a computer device can utilize a large model to perform semantic understanding of knowledge data, extract knowledge entities from the knowledge data, determine the knowledge content corresponding to the knowledge entities, and the knowledge topic corresponding to at least one knowledge entity. The large model can be a large language model or a multimodal large model. For example, a large language model can be a natural language processing model built on a deep learning architecture, used for semantic understanding, content generation, and knowledge reasoning of text-based knowledge data. The large language model can be built on a Transformer architecture, using a self-attention mechanism to model words, sentences, and contextual relationships in the input text, thereby understanding the semantic connections between text content. A multimodal large model can be an artificial intelligence model capable of jointly understanding different forms of data, used for comprehensive analysis of knowledge data in multiple forms such as text, images, audio, and video. For example, a multimodal large model can include a text encoder, an audio encoder, a visual encoder, and a fusion module. The text encoder can extract semantic features from text data, the visual encoder can extract visual features from image or video data, the audio encoder can extract acoustic or semantic features from audio data, and the fusion module can fuse features from different modalities to obtain a comprehensive semantic representation. Through a multimodal large model, unified understanding and knowledge reasoning can be achieved for knowledge data in various forms, including text, images, speech, and video.

[0044] In some embodiments, a knowledge entity can refer to an object or concept with independent semantic meaning within knowledge content, used to represent the specific knowledge object involved in the knowledge data. For example, a knowledge entity can include people, organizations, locations, products, technologies, events, methods, items, specific concepts, etc. For instance, in knowledge data about computing power subsidies, "computing power subsidies," "TOC promotion," and "traffic allocation strategy" can serve as knowledge entities. In some embodiments, knowledge content can be information obtained by a large model after semantically understanding the knowledge data, used to describe knowledge entities. Knowledge content can also be content fragments directly extracted from knowledge data to describe knowledge entities. In some embodiments, a knowledge topic can be information obtained by a large model after semantically understanding the knowledge data, used to represent the knowledge domain, content direction, or core concept involved in the knowledge data. In some embodiments, knowledge entities extracted based on knowledge data can include one or more, and knowledge topics determined based on knowledge data can include one or more. Knowledge entities can correspond one-to-one with knowledge content, and one knowledge topic can correspond to one or more knowledge entities.

[0045] In some embodiments, the computer device can input knowledge data and a first preset prompt into a large model. The large model can parse the knowledge data according to the first preset prompt, extract one or more knowledge entities from the knowledge data, generate knowledge content corresponding to each knowledge entity, and determine the knowledge topic corresponding to each knowledge entity. For example, when the knowledge data is a webpage link, the large model can call a browser's crawling function or a webpage content acquisition interface to access the corresponding webpage according to the webpage link, obtain content information such as text content, image content, audio information, or video information from the webpage, and then perform semantic understanding on the obtained content information according to the first preset prompt, extract knowledge entities, and determine the knowledge content and knowledge topic corresponding to each knowledge entity. The first preset prompt can be used to instruct the large model to analyze the knowledge data and determine the knowledge entities, the knowledge content corresponding to each knowledge entity, and the correspondence between the knowledge topic and the knowledge entity. For example, the first preset prompt message could be: "Please analyze the input information and extract the knowledge entities and knowledge topics from the input information according to the following task requirements, determine the knowledge content corresponding to each knowledge entity, and one or more knowledge entities corresponding to the knowledge topic. The specific task requirements are: specific requirements for extracting knowledge entities ×××; specific requirements for determining knowledge topics ×××; specific requirements for determining knowledge content ×××. The output format is ×××."

[0046] In some embodiments, the computer device can also determine the source of the knowledge data. For example, the knowledge data may originate from a website, or from videos, images, audio, etc. The first preset prompt information can also be used to instruct the large model to analyze the source of the knowledge data and output that source information. When the user subsequently views the knowledge entity and its corresponding knowledge content, they can trace the original source of the knowledge content, improving the reliability and completeness of knowledge utilization.

[0047] In some embodiments, the computer device may also display a notification message indicating that the knowledge data parsing is complete. This notification message may include the number of knowledge entities extracted, the number of knowledge topics, and the source of the knowledge data. Figure 3 This is a schematic diagram of another knowledge management display interface according to some embodiments of this specification. For example, as shown below... Figure 3 As shown, once the knowledge data has been parsed, the computer device can display a notification message "Included in the database | Source page + 8 entities + 3 topics" on the knowledge management display interface.

[0048] Step 130: Determine the knowledge association network based on knowledge entities and knowledge topics. In some embodiments, step 130 can be implemented by the association network determination module 1330.

[0049] In some embodiments, a knowledge association network can refer to a data structure used to represent the relationships between different knowledge entities and the correspondence between knowledge topics and knowledge entities. A knowledge association network can include knowledge entities, the relationships between knowledge entities, and the correspondence between knowledge entities and knowledge topics. By constructing a knowledge association network, input, scattered knowledge data can be organized according to knowledge topics and knowledge entities, forming relationships between different knowledge contents, facilitating centralized management of users' accumulated knowledge information.

[0050] In some embodiments, the association between knowledge entities can be characterized by the strength of the association. A computer device can determine the strength of the association between different knowledge entities based on their semantic features. For example, the computer device can use a large model to convert knowledge entities into semantic vectors, and determine the strength of the association between different knowledge entities based on the distance and direction between the semantic vectors. For instance, the cosine similarity between semantic vectors can be calculated to determine the strength of the association. The higher the cosine similarity, the stronger the association; the lower the cosine similarity, the weaker the association.

[0051] In some embodiments, a computer device can use knowledge topics and knowledge entities as nodes in a network, and the correspondence between knowledge topics and knowledge entities, as well as the association between knowledge entities, as connections between nodes, thereby forming a knowledge association network containing multi-layered association information. In some embodiments, as new knowledge data is continuously input, the computer device can update the existing knowledge association network. For example, the computer device can obtain new knowledge entities and new knowledge topics corresponding to new knowledge data. If the new knowledge topic already exists in the existing knowledge association network, the new knowledge topic is merged with the existing knowledge topics in the existing knowledge association network, and the new knowledge entity corresponding to the new knowledge topic is associated with the existing knowledge topic in the knowledge association network. When the new knowledge topic does not exist in the existing knowledge association network, a new knowledge topic and the knowledge entity corresponding to that knowledge topic can be created in the existing knowledge association network. The computer device can also calculate the association between new knowledge entities, as well as the association between new knowledge entities and other existing knowledge entities in the knowledge association network, and update the knowledge association network. In this way, knowledge data from different sources can be gradually integrated into the same knowledge association network, forming a personalized knowledge association network containing multiple knowledge topics and multiple knowledge entities.

[0052] Step 140: Display the knowledge association network. In some embodiments, step 140 may be implemented by the association network display module 1340.

[0053] In some embodiments, the computer device can visualize the knowledge association network. For example, it can display knowledge topics, knowledge entities, the correspondence between knowledge topics and knowledge entities, and the associations between knowledge entities; or it can display only knowledge entities and the associations between them. Knowledge entities corresponding to the same knowledge topic can be grouped together, forming a relatively concentrated knowledge area on the display interface, allowing users to understand the complete content of a knowledge item or category from a point-to-surface perspective. The associations between knowledge entities can be represented by association strength, which can be indicated by lines. Different association strengths can be presented using lines of different forms (e.g., different colors, shapes, thicknesses, etc.).

[0054] In some embodiments, the computer device can determine the display position of knowledge entities based on the strength of association between knowledge entities and the correspondence between knowledge entities and knowledge topics, so that knowledge entities corresponding to the same knowledge topic are displayed together, knowledge entities with high association strength are displayed closer together, and the strength of association between knowledge entities is displayed. For example, the computer device can allocate candidate display areas for knowledge entities belonging to the same knowledge topic, so that knowledge entities corresponding to the same knowledge topic are displayed together, and determine the display position of knowledge entities in the candidate display areas according to the strength of association between knowledge entities, so that knowledge entities with high association strength are displayed closer together.

[0055] Figure 4 This is a schematic diagram of a knowledge association network display interface according to some embodiments of this specification. For example, such as... Figure 4 As shown, the knowledge association network can be displayed in the form of a knowledge nebula. Each spherical icon represents a knowledge entity. Knowledge entities corresponding to the same knowledge topic are clustered together, and the strength of the association between knowledge entities is represented by different forms of lines.

[0056] In some embodiments, the knowledge association network may further include knowledge content corresponding to the knowledge entity. The knowledge content may be information describing the knowledge entity obtained after the large model performs semantic understanding of the knowledge data, or it may be content fragments directly extracted from the knowledge data to describe the knowledge entity. The computer device may display the knowledge content corresponding to the knowledge entity in response to a triggering operation on the knowledge entity. The triggering operation may include any one of the following: single-click, double-click, multiple clicks, long press, drag, etc., on the knowledge entity. Figure 5 This is a schematic diagram of a knowledge content display interface according to some embodiments of this specification. For example, when a user clicks... Figure 4 When the knowledge entity icon "computing power subsidy" is shown, the computer device can display as follows: Figure 5The knowledge content display interface shown can present knowledge content corresponding to "computing power subsidies". In some embodiments, the knowledge content display interface can also display the source of the knowledge content. Users can click on the icon or link corresponding to the source, and the computer device can respond to the operation and display the knowledge data corresponding to the knowledge content.

[0057] In some embodiments, the computer device may also determine search results based on knowledge content in a knowledge association network in response to a knowledge retrieval operation. Figure 6 This is a schematic diagram of the search interface shown according to some embodiments of this specification. Figure 7 This is a schematic diagram of a search results display interface according to some embodiments of this specification. For example, such as... Figure 6 As shown, the graphical user interface of the computer device can display a search interface, which may include a search box. The user can enter the question "**How ​​to sign a contract cost-effectively" in the search box and click the search icon. The computer device can respond to this operation, using a large model to search for knowledge entities, knowledge topics, and corresponding knowledge content related to the user's search question in the knowledge association network. After semantic analysis and organization, the search results are generated and presented as shown in the image. Figure 7 The search results are displayed in the interface shown. Because the knowledge association network is a personal knowledge database built upon the user's historical input of web pages, text, images, audio, video, and other knowledge data, computer devices can perform more targeted searches based on the user's accumulated knowledge, returning search results that better match the user's knowledge background and areas of interest, thus improving the accuracy and personalization of the search results. By generating a knowledge association network and determining search results based on the knowledge content within it, knowledge content from different sources collected by the user can be linked and stored, facilitating unified understanding and related use by a large model. This eliminates the need for repeated information retrieval and understanding processing of knowledge content from different sources, improving knowledge utilization efficiency.

[0058] In some embodiments, users may also select knowledge entities to share in order to disseminate stored personalized knowledge content. Figure 8 This is an exemplary flowchart illustrating a knowledge-sharing method according to some embodiments of this specification. Figure 8 The process 800 shown can be executed by a computer device, for example, by the knowledge sharing module 1350 module in the knowledge management device 1300 deployed on the computer device. Figure 8 As shown, in some embodiments, process 800 may include the following steps.

[0059] Step 810: In response to the selection operation on the knowledge entity, determine the target knowledge entity.

[0060] In some embodiments, the computer device can, in response to a selection operation on one or more knowledge entities, identify the selected knowledge entity as the target knowledge entity. The selection operation on a knowledge entity can include any of the following: single-click, double-click, multiple clicks, long-press, drag, or selection. In some embodiments, the computer device can also highlight the target knowledge entity in the knowledge association network display interface. For example, changing the border color of the knowledge entity icon or adding a highlight effect to the border can help users distinguish the target knowledge entity (i.e., the selected knowledge entity) from the unselected knowledge entities. Because the content displayed in the knowledge association network display interface includes knowledge entities and the relationships between them, and knowledge entities corresponding to the same topic are displayed in clusters, users can flexibly combine different knowledge points in a visualized knowledge organization structure. For example, users can select several highly related knowledge entities to share, or select knowledge entities corresponding to the same topic to share. Through this method, users no longer need to return to various platforms to search for knowledge to share, but can directly select content to share from the perspective of the knowledge system, achieving flexible sharing of single knowledge points, related knowledge, or complete topic knowledge, improving the accuracy, completeness, and efficiency of knowledge sharing.

[0061] Step 820: In response to the sharing operation of the target knowledge entity, analyze and process the knowledge content corresponding to the target knowledge entity to obtain the target knowledge content.

[0062] In some embodiments, a share icon may be displayed in the knowledge association network display interface, and the sharing operation for the target knowledge entity may be a trigger operation on the share icon. For example, clicking the share icon.

[0063] In some embodiments, a computer device can utilize a large model to analyze and process the knowledge content corresponding to the target knowledge entity to obtain the target knowledge content. For example, in response to a click on the share icon, the computer device can input each target knowledge entity, the knowledge content corresponding to each target knowledge entity, and a second preset prompt into the large model. The second preset prompt can instruct the large model to reorganize the knowledge based on the target knowledge entity and its corresponding knowledge content, forming logically coherent and readable content. The large model can understand, analyze, and reorganize each target knowledge entity and its corresponding knowledge content according to the second preset prompt, removing duplicate content, supplementing necessary contextual information, and generating target knowledge content according to a preset structure. For example, when a user selects multiple knowledge entities related to "artificial intelligence computing," the large model can understand, analyze, and reorganize the knowledge content corresponding to the selected knowledge entities, reorganizing multiple scattered knowledge fragments into a complete knowledge introduction around "artificial intelligence computing," forming target knowledge content, so that the recipient does not need to search and organize knowledge from multiple sources again. By responding to the sharing operation of the target knowledge entity, the target knowledge content is obtained by analyzing and processing the knowledge content corresponding to the target knowledge entity. This allows the scattered knowledge content to be shared to be integrated into target knowledge content with complete semantic association. The recipient can quickly obtain complete knowledge information without having to understand the knowledge content from multiple sources separately, thus improving the integrity and comprehensibility of information in the knowledge dissemination process.

[0064] In some embodiments, after determining the target knowledge content, the computer device can generate a preset data object based on the target knowledge content and at least one of the following information, for direct use by other large models: target knowledge entities, the relationships between target knowledge entities, and prompt information indicating the invocation of the target knowledge content. The prompt information indicating the invocation of the target knowledge content can be a preset prompt word. For example, the prompt information could be "You are a [username / entity name], please answer the user's question according to the following requirements: 1. Use this knowledge content to answer the question first; 2. Use [language name / language]; 3. Avoid overly technical language." In some embodiments, the preset data object can be a data structure generated according to a preset format, used to carry information such as the target knowledge content. In some embodiments, the preset data object may also include the knowledge topic corresponding to the target knowledge entity and the correspondence between the target knowledge entity and the knowledge topic. For example, a computer device can write target knowledge content, target knowledge entities, the relationships between target knowledge entities, prompts indicating the invocation of target knowledge content, the knowledge topics corresponding to target knowledge entities, and the correspondence between target knowledge entities and knowledge topics into a data structure in a preset format (e.g., JSON format), thereby forming a preset data object. This allows other large models to directly invoke the preset data object and read the information within it without re-parsering and organizing the original knowledge content. In some embodiments, to facilitate knowledge sharing between different devices or different large models, the computer device can also encapsulate the preset data object for invocation. For example, the preset data object can be encapsulated using a command-line interface (CLI) to generate a corresponding invocation entry point, enabling other large models to obtain the preset data object based on this entry point and read the information within it. Figure 9 This is a schematic diagram of a knowledge-sharing interface according to some embodiments of this specification. For example, a computer device can encapsulate a preset data object using a command-line interface to generate, for instance... Figure 9 The command-line instruction containing the URL link shown serves as a knowledge-sharing password. This command-line instruction encapsulates a network request command for retrieving a preset data object and its corresponding URL address. Users can directly copy this command-line instruction and paste it into the receiving end's large model. The receiving end's large model executes the network request command to access the URL address, thereby retrieving the preset data object and reading the information within it.

[0065] In some embodiments, the computer device may also provide reminders to the user based on knowledge data, so as to guide the user's actions by combining the user's real-time information and needs. Figure 10 This is an exemplary flowchart illustrating a knowledge data-based reminder method according to some embodiments of this specification. Figure 10The illustrated process 1000 can be executed by a computer device, for example, by the reminder module 1370 in the knowledge management device 1300 deployed on the computer device. Figure 10 As shown, in some embodiments, process 1000 may include the following steps.

[0066] Step 1010: Determine action suggestion information and corresponding triggering conditions based on knowledge data.

[0067] In some embodiments, the computer device can utilize a large model to determine action suggestion information and corresponding triggering conditions based on knowledge data. For example, the computer device can input knowledge data and a third preset prompt into the large model, which can then perform semantic analysis and processing on the knowledge data based on the third preset prompt, and determine the action suggestion information and corresponding triggering conditions.

[0068] In some embodiments, the third preset prompt information may include a preset analysis strategy, and the computer device may use a large model to determine whether the knowledge data meets the conditions for generating action suggestions based on the preset analysis strategy. The preset analysis strategy may include judgment criteria for determining whether the knowledge data meets the conditions for generating action suggestions. For example, the preset analysis strategy may be: "Please determine whether this content contains the value of 'reminding the user to do something at a certain time'." Judgment criteria include: 1. It contains specific behavioral suggestions (e.g., what to eat, what to do, what to avoid); 2. The behavior has a natural time trigger (e.g., waking up, before meals, before bed, a certain time, etc.); 3. It has practical significance for the user's daily life.

[0069] In some embodiments, when the conditions for generating action suggestions are met, the computer device can extract action suggestion information based on knowledge data and determine the triggering conditions corresponding to the action suggestion information based on the action conditions. The action suggestion information may include action content, action conditions, and at least one of the following: action theme, recommendation reason, and knowledge category. For example, action content may include eating, running, sleeping, exercising, etc. Action conditions may include reaching a preset time point, reaching a preset geographical location, detecting user fatigue, detecting insufficient user exercise, etc.; the action theme may include a general description of the action content; the recommendation reason may include a description of the reason for performing the action; the knowledge category may include health knowledge, wellness knowledge, learning knowledge, and lifestyle habit knowledge, etc. In some embodiments, the triggering condition may be the same as the action condition. For example, the triggering condition may be reaching a preset geographical location or detecting user fatigue or insufficient user exercise. In other embodiments, the triggering condition may be different from the action condition, and the triggering condition may be determined based on the action condition. For example, the trigger condition is reaching a preset time (e.g., 12:00), and the action condition can be a certain time before reaching the preset time (e.g., 11:45), so that a reminder message can be sent in advance so that the user can perform the action on time at the preset time.

[0070] For example, the third preset prompt information may also include action suggestion information output requirements, strategies for determining trigger conditions based on action conditions, and output format requirements. When the action suggestion generation conditions are met, the large model can output action suggestion information according to the action suggestion information output requirements and output format requirements, and determine the trigger conditions corresponding to the action suggestion information according to the strategy for determining trigger conditions. For example, the output requirements for action suggestion information may include: "When the action suggestion generation conditions are met, output 5 recommendation cards in JSON format; otherwise, output an empty array. Each card format includes: Action content (character count requirement **, concise and clear, clearly stating ***), Action conditions (time triggering method / location triggering method, and describe the specific triggering time / location in ** format), Action theme (character count requirement **, starting with ** description), Recommendation reason (character count requirement **, clearly stating why it is recommended at this time / location), Knowledge category (e.g., health knowledge, wellness knowledge, learning knowledge, lifestyle knowledge, etc.)." For example, the strategy for determining triggering conditions based on action conditions may include: "When the action conditions meet *** requirements, the action conditions are the triggering conditions; when the action conditions do not meet *** requirements, the reminder time of the triggering condition should be ** minutes earlier than the reminder time of the action conditions." For example, the output format requirements may include: "Only output a JSON array, in the format: [{...},{...}] or []; do not include any other text."

[0071] Step 1020: Obtain status information.

[0072] In some embodiments, status information may include at least one of the following: environmental information, contact information, and user status information. Environmental information may include time information, location information, weather information, ambient temperature information, air quality information, etc. Contact information may include the user's interaction status with different contacts; for example, contact information may include contact identifiers, the relationship between the user and the contact, the frequency of interaction between the user and the contact, etc. Computer devices can obtain contact information by accessing the user terminal's address book. User status information may include physiological status information, device usage status information, etc. For example, physiological status information may include information such as heart rate, sleep status, body temperature, and blood oxygen saturation; computer devices can obtain physiological status information using smart wearable devices. Device usage status information may include information such as the terminal device's usage time, battery status, and screen usage status.

[0073] Step 1030: When the status information matches the triggering conditions, generate a reminder message based on the action suggestion information.

[0074] In some embodiments, the computer device can match status information with triggering conditions. When a match is successful, the computer device can use a large model to generate a reminder message based on action suggestion information. For example, the triggering condition could be that the time reaches 11:45. The computer device can obtain time information from the system time. When the time information obtained from the system time is 11:45, the computer device determines that the status information matches the triggering condition and inputs the action suggestion information and a fourth preset prompt message into the large model. The fourth preset prompt message can be used to instruct the large model to analyze the action suggestion information and generate a reminder message according to preset display requirements. For example, the fourth preset prompt message could be "Please generate a reminder message based on the action suggestion information. The reminder message must at least describe the specific action content and the reason for the action, and the word count should be within **". Figure 11 These are schematic diagrams illustrating the reminder information display interface according to some embodiments of this specification. For example... Figure 11 As shown, the reminder message could be, "Finish dinner before 6:00 PM to allow your stomach 4 hours to digest and improve sleep quality." The reminder message can be displayed as a desktop widget in the reminder message display interface. By determining action suggestions and corresponding trigger conditions based on knowledge data, and acquiring status information, a reminder message is generated based on the action suggestions when the status information matches the trigger conditions. In this way, the various knowledge data collected by the user, after being understood by the large model, does not simply remain in storage, but is actively searched for and edited from the knowledge base to generate reminder messages, thereby guiding the user's actions, in conjunction with various real-time information and needs of the user.

[0075] In some embodiments, the computer device may also classify and manage the action suggestion information based on the knowledge categories in the action suggestion information, and generate an action suggestion information management interface. Figure 12 This is a schematic diagram of an action suggestion information management interface according to some embodiments of this specification. For example... Figure 12 As shown, the action suggestion information management interface includes knowledge category icons. When a user clicks on a knowledge category icon, the action suggestion information management interface can display thumbnails of multiple action suggestion information corresponding to that knowledge category icon. When a user clicks on a thumbnail of an action suggestion information, the complete information of the action suggestion information can be displayed.

[0076] This manual also provides a knowledge management device. Figure 13 This is an exemplary block diagram of a knowledge management device according to some embodiments of this specification. In some embodiments, the knowledge management device 1300 may be deployed on a computer device. Figure 13 As shown, in some embodiments, the knowledge management device 1300 may include a knowledge input module 1310, a semantic understanding module 1320, an association network determination module 1330, and an association network display module 1340.

[0077] The knowledge input module 1310 can be used to acquire input knowledge data.

[0078] The semantic understanding module 1320 can be used to perform semantic understanding based on knowledge data to obtain knowledge entities and the knowledge topics corresponding to the knowledge entities.

[0079] The association network determination module 1330 can be used to determine a knowledge association network based on knowledge entities and knowledge topics. The knowledge association network includes knowledge entities, the association relationships between knowledge entities, and the correspondence between knowledge entities and knowledge topics.

[0080] The association network display module 1340 can be used to display a knowledge association network, in which knowledge entities corresponding to the same knowledge topic are displayed in clusters.

[0081] In some optional embodiments, the knowledge input module 1310 can also be used to acquire knowledge data in response to user input operations, the knowledge data including at least one of web links, text, voice, images, and videos.

[0082] In some optional embodiments, the semantic understanding module 1320 can also be used to perform semantic understanding on knowledge data using a large model, extract knowledge entities from the knowledge data, determine the knowledge content corresponding to the knowledge entities, and the knowledge topic corresponding to at least one knowledge entity.

[0083] In some optional embodiments, the association network display module 1340 can also be used to determine the display position of knowledge entities based on the association strength between knowledge entities and the correspondence between knowledge entities and knowledge topics, so that knowledge entities corresponding to the same knowledge topic are clustered together and displayed, knowledge entities with high association strength are displayed close together, and the association strength between knowledge entities is displayed.

[0084] In some optional embodiments, the knowledge association network also includes knowledge content corresponding to the knowledge entity, and the knowledge management device 1300 may also include a knowledge sharing module 1350, which is used to determine the target knowledge entity in response to the selection operation of the knowledge entity; and to analyze and process the knowledge content corresponding to the target knowledge entity in response to the sharing operation of the target knowledge entity to obtain the target knowledge content.

[0085] In some optional embodiments, the knowledge sharing module 1350 can also be used to analyze and process the knowledge content corresponding to the target knowledge entity using a large model to obtain the target knowledge content; and generate a preset data object based on the target knowledge content and at least one of the following information for other large models to directly call: the target knowledge entity, the relationship between the target knowledge entities, and a prompt message for indicating the call to the target knowledge content.

[0086] In some optional embodiments, the knowledge management device 1300 may further include a knowledge retrieval module 1360, which is used to display the knowledge content corresponding to the knowledge entity in response to a triggering operation on the knowledge entity; and to determine the retrieval results based on the knowledge content in the knowledge association network in response to a knowledge retrieval operation.

[0087] In some optional embodiments, the knowledge management device 1300 may further include a reminder module 1370, which is used to determine action suggestion information and corresponding triggering conditions based on knowledge data; acquire status information, which includes at least one of the following: environmental information, contact information, and user status information; and generate reminder information based on the action suggestion information when the status information matches the triggering conditions.

[0088] In some optional embodiments, the reminder module 1370 can also be used to determine whether the knowledge data meets the conditions for generating action suggestions based on a preset analysis strategy; if it does, extract action suggestion information based on the knowledge data, the action suggestion information including action content, action conditions and at least one of the following: action topic, recommendation reason, knowledge category; and determine the triggering conditions corresponding to the action suggestion information based on the action conditions.

[0089] For more information on each module, please refer to [link / reference]. Figures 1-12 The relevant explanations will not be repeated here. It should be understood that... Figure 13The apparatus, system, and modules illustrated can be implemented in various ways. For example, in some embodiments, they can be implemented by hardware, software, or a combination of both. The hardware portion can be implemented using dedicated logic; the software portion can be stored in memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated-design hardware. Those skilled in the art will understand that the methods, apparatus, and systems described above can be implemented using computer-executable instructions and / or included in the control code of a processor, such as code provided in the memory of a programmable device on a media such as a disk, CD, or DVD-ROM. The apparatus and modules described in this specification can be implemented not only by hardware circuitry such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips or transistors, or programmable hardware devices such as field-programmable gate arrays or programmable logic devices, but also by software, for example, executed by various types of processors, or by a combination of the aforementioned hardware circuitry and software (e.g., firmware).

[0090] It should be noted that the above descriptions of the devices, systems, and modules are for convenience only and should not be construed as limiting this specification to the embodiments described. It is understood that those skilled in the art, after understanding the principle of the device, can arbitrarily combine the various modules without departing from this principle to form sub-devices connected to other modules. Alternatively, some modules can be split to obtain more modules or multiple units under a single module. Such modifications are all within the scope of this specification.

[0091] Some embodiments of this specification also provide a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it can implement this specification. Figures 1-12 The method shown.

[0092] Some embodiments of this specification also provide a computer-readable storage medium storing computer instructions that, when executed by a processor, can implement this specification. Figures 1-12 The method shown.

[0093] Some embodiments of this specification also provide a computer program product, including a computer program that, when at least a portion of the computer program is executed by a processor, can implement this specification. Figures 1-12The method is illustrated. In some embodiments, the computer program product may refer only to a computer program, which may be carried on a storage medium or a processing device. In other embodiments, the computer program product may also be a storage medium or a processing device containing the aforementioned computer program. The processing device may include one or more processors, and the storage medium.

[0094] In some embodiments, the processor may be a combination of one or more of the following processors: central processing unit (CPU), application-specific integrated circuit (ASIC), application-specific instruction set processor (ASIP), graphics processing unit (GPU), physical processing unit (PPU), digital signal processor (DSP), field-programmable gate array (FPGA), programmable logic device (PLD), programmable logic controller (PLC), reduced instruction set computer (RISC), and microprocessor.

[0095] In some embodiments, the storage medium may include one or more combinations of the following: mass storage, removable storage, volatile read-write memory, and read-only memory (ROM). Exemplary mass storage may include disks, optical disks, solid-state drives, etc. Exemplary removable storage may include flash drives, floppy disks, optical disks, memory cards, compressed hard disks, magnetic tapes, etc. Exemplary volatile read-write memory may include random access memory (RAM). Exemplary RAM may include dynamic random access memory (DRAM), dual data rate synchronous dynamic random access memory (DDRSDRAM), static random access memory (SRAM), silicon controlled retrieval memory (T-RAM), and zero-capacitance memory (Z-RAM), etc. Exemplary read-only memory may include masked read-only memory (MROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), compressed hard disk read-only memory (CD-ROM), and digital multifunction hard disk read-only memory, etc.

[0096] The basic concepts have been described above. It is obvious that the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, various modifications, improvements, and corrections may be made to this specification by those skilled in the art. Such modifications, improvements, and corrections are taught in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

Claims

1. A knowledge management method, characterized in that, The method includes: Acquire the input knowledge data; Based on the knowledge data, semantic understanding is performed to obtain knowledge entities and knowledge topics corresponding to the knowledge entities; A knowledge association network is determined based on the knowledge entities and the knowledge topics. The knowledge association network includes the knowledge entities, the association relationships between the knowledge entities, and the correspondence between the knowledge entities and the knowledge topics. The knowledge association network is displayed, wherein knowledge entities corresponding to the same knowledge topic are displayed in clusters.

2. The method according to claim 1, characterized in that, Based on the knowledge data, semantic understanding is performed to obtain knowledge entities and knowledge topics corresponding to the knowledge entities, including: The knowledge data is semantically understood using a large model, the knowledge entities in the knowledge data are extracted, the knowledge content corresponding to the knowledge entities is determined, and the knowledge topic corresponding to at least one of the knowledge entities is determined.

3. The method according to claim 1, characterized in that, The relationships between the knowledge entities include the strength of the relationships, and displaying the knowledge relationship network includes: Based on the correlation strength between the knowledge entities and the correspondence between the knowledge entities and the knowledge topics, the display position of the knowledge entities is determined, so that the knowledge entities corresponding to the same knowledge topic are displayed together, the knowledge entities with high correlation strength are displayed close together, and the correlation strength between the knowledge entities is displayed.

4. The method according to claim 1, characterized in that, The knowledge association network also includes knowledge content corresponding to the knowledge entity, and the method further includes: In response to the selection operation on the knowledge entity, the target knowledge entity is determined; In response to the sharing operation of the target knowledge entity, the target knowledge content is analyzed and processed based on the knowledge content corresponding to the target knowledge entity to obtain the target knowledge content.

5. The method according to claim 4, characterized in that, The step of analyzing and processing the knowledge content corresponding to the target knowledge entity to obtain the target knowledge content includes: The target knowledge content is obtained by analyzing and processing the knowledge content corresponding to the target knowledge entity using a large model. Based on the target knowledge content and at least one of the following information, a preset data object is generated for direct use by other large models: the target knowledge entity, the relationship between the target knowledge entities, and a prompt message indicating the invocation of the target knowledge content.

6. The method according to claim 4, characterized in that, The method further includes: In response to a trigger operation on the knowledge entity, the knowledge content corresponding to the knowledge entity is displayed; In response to a knowledge retrieval operation, the retrieval results are determined based on the knowledge content in the knowledge association network.

7. The method according to claim 1, characterized in that, The method further includes: Based on the knowledge data, action suggestion information and corresponding triggering conditions are determined. Obtain status information, which includes at least one of the following: environment information, contact information, and user status information; When the status information matches the triggering condition, a reminder message is generated based on the action suggestion information.

8. The method according to claim 7, characterized in that, The process of determining action suggestion information and corresponding triggering conditions based on the knowledge data includes: Based on a preset analysis strategy, determine whether the knowledge data meets the conditions for generating action suggestions; If the conditions are met, the action suggestion information is extracted based on the knowledge data. The action suggestion information includes action content, action conditions, and at least one of the following: action theme, recommendation reason, and knowledge category. The triggering conditions corresponding to the action suggestion information are determined based on the action conditions.

9. The method according to claim 1, characterized in that, The acquisition of input knowledge data includes: In response to user input, the knowledge data is acquired, which includes at least one of web links, text, voice, images, and videos.

10. A knowledge management device, characterized in that, The device includes: The knowledge input module is used to acquire input knowledge data; The semantic understanding module is used to perform semantic understanding based on the knowledge data to obtain knowledge entities and knowledge topics corresponding to the knowledge entities. The association network determination module is used to determine a knowledge association network based on the knowledge entities and the knowledge topics, wherein the knowledge association network includes the knowledge entities, the association relationships between the knowledge entities, and the correspondence between the knowledge entities and the knowledge topics; The association network display module is used to display the knowledge association network, wherein knowledge entities corresponding to the same knowledge topic are displayed in clusters.

11. A computer device, characterized in that, The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it is able to implement the method as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, enable the implementation of the method as described in any one of claims 1 to 9.

13. A computer program product, characterized in that, It includes a computer program that, when at least a portion of the computer program is executed by a processor, enables the implementation of the method as described in any one of claims 1 to 9.

Images