Knowledge graph generation method and device

Abstract

The invention discloses a knowledge graph generation method and device, and belongs to the technical field of communication. The method comprises the steps that a learning tool set is determined, the learning tool set comprises a plurality of learning tools corresponding to electronic devices of all users in a preset user set, and the preset user set comprises a first user and at least one second user associated with the first user; in response to a first input of a first user, obtaining first search content; searching the first search content through a learning tool group to obtain a first search result; and generating a knowledge graph by taking the first search content and the first search result as knowledge points.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to a method and apparatus for generating a knowledge graph. Background Art

[0002] With the continuous development of technology, it has become a relatively common function in electronic devices to construct a targeted knowledge graph through intelligent electronic devices to assist users in learning. When an electronic device constructs a knowledge graph, it usually relies on the learning tools installed on the electronic device as search tools to obtain knowledge points. However, the learning tools installed in electronic devices are usually relatively single, and the search results for some search contents may be inaccurate, resulting in poor reliability of the knowledge graph and being unfavorable for users to learn. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a method and apparatus for generating a knowledge graph, which can improve the accuracy of search results by combining the search results of multiple learning tools without the need to install multiple learning tools, thereby improving the reliability of the knowledge graph and being beneficial to assisting users in learning.

[0004] In a first aspect, the embodiments of this application provide a method for generating a knowledge graph, and the method includes:

[0005] Determine a learning tool group, where the learning tool group includes multiple learning tools corresponding to the electronic devices of all users in a preset user set, and the preset user set includes a first user and at least one second user associated with the first user;

[0006] In response to a first input of the first user, obtain a first search content;

[0007] Search the first search content through the learning tool group to obtain a first search result;

[0008] Use the first search content and the first search result as knowledge points to generate a knowledge graph.

[0009] In a second aspect, the embodiments of this application provide an apparatus for generating a knowledge graph, and the apparatus includes:

[0010] A first determination module, configured to determine a learning tool group, where the learning tool group includes multiple learning tools corresponding to the electronic devices of all users in a preset user set, and the preset user set includes a first user and at least one second user associated with the first user;

[0011] A first acquisition module, configured to obtain a first search content in response to a first input of the first user;

[0012] A search module, configured to search the first search content through the learning tool group to obtain a first search result;

[0013] The first generation module is configured to generate a knowledge graph by using the first search content and the first search result as knowledge points.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory. The memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0015] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the method described in the first aspect.

[0017] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the method described in the first aspect.

[0018] In the embodiment of the present application, a preset user set can be constructed according to the first user and at least one second user associated with the first user. A learning tool group is obtained by combining multiple learning tools corresponding to the electronic devices of all users in the preset user set. Thus, the first search content input by the first user can be searched based on the learning tool group to obtain a more accurate first search result. The first search content and the corresponding first search result can be used as knowledge points to generate a knowledge graph. In this way, without installing multiple learning tools, the accuracy of the search result can be improved by combining the search results of multiple learning tools, and further the reliability of the knowledge graph can be improved, which is beneficial to assisting users in learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic flowchart of a knowledge graph generation method provided by an embodiment of the present application;

[0020] Figure 2a is a schematic diagram of an interface of a knowledge graph generation method provided by an embodiment of the present application;

[0021] Figure 2b is a second schematic diagram of an interface of a knowledge graph generation method provided by an embodiment of the present application;

[0022] Figure 3a is a third schematic diagram of an interface of a knowledge graph generation method provided by an embodiment of the present application;

[0023] Figure 3b It is the fourth interface schematic diagram of the knowledge graph generation method provided by the embodiments of the present application;

[0024] Figure 3c It is the fifth interface schematic diagram of the knowledge graph generation method provided by the embodiments of the present application;

[0025] Figure 4a It is the sixth interface schematic diagram of the knowledge graph generation method provided by the embodiments of the present application;

[0026] Figure 4b It is the seventh interface schematic diagram of the knowledge graph generation method provided by the embodiments of the present application;

[0027] Figure 5a It is the eighth interface schematic diagram of the knowledge graph generation method provided by the embodiments of the present application;

[0028] Figure 5b It is the ninth interface schematic diagram of the knowledge graph generation method provided by the embodiments of the present application;

[0029] Figure 6a It is the tenth interface schematic diagram of the knowledge graph generation method provided by the embodiments of the present application;

[0030] Figure 6b It is the eleventh interface schematic diagram of the knowledge graph generation method provided by the embodiments of the present application;

[0031] Figure 7 It is the schematic diagram of the knowledge graph in the knowledge graph generation method provided by the embodiments of the present application;

[0032] Figure 8 It is the schematic diagram of the target knowledge point in the knowledge graph generation method provided by the embodiments of the present application;

[0033] Figure 9a It is the schematic diagram of the configuration information of the learning materials in the knowledge graph generation method provided by the embodiments of the present application;

[0034] Figure 9b It is the schematic diagram of the learning materials in the knowledge graph generation method provided by the embodiments of the present application;

[0035] Figure 10 It is the schematic diagram of the structure of the knowledge graph generation device provided by the embodiments of the present application;

[0036] Figure 11 It is the schematic diagram of the structure of the electronic device provided by the embodiments of the present application;

[0037] Figure 12 It is the schematic diagram of the hardware structure of the electronic device provided by the embodiments of the present application. Detailed implementation manners

[0038] The following will clearly describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application belong to the scope of protection of the present application.

[0039] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are usually of the same category, and the number of objects is not limited. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects, and the character " / " generally means that the related objects before and after are in an "or" relationship.

[0040] The following will, with reference to the accompanying drawings, describe in detail the knowledge graph generation method provided in the embodiments of the present application through specific embodiments and their application scenarios.

[0041] Figure 1 is a schematic flowchart of the knowledge graph generation method provided in the embodiments of the present application. The knowledge graph generation method may include:

[0042] Step 101: Determine a learning tool group, where the learning tool group includes a plurality of learning tools corresponding to the electronic devices of all users in a preset user set, and the preset user set includes a first user and at least one second user associated with the first user.

[0043] In step 101, the first user may be the user corresponding to the first electronic device, and the knowledge graph generation method may be executed by the first electronic device. The second user may be a user associated with the first user. For example, the second user may be a contact of the first user, or a group member in the same group as the first user, or a friend of the first user in an instant messaging application, etc., which is not specifically limited here.

[0044] Based on the strong relationship between friends built by adding friends, or the weak relationship between the same or associated group members, taking the strong and weak relationships as the basis, according to the selection input of the first user, at least one second user is selected to build an interconnected and mutually trusted link between learning applications with the first user, that is, a preset user set can be obtained. For example Figure 2aAs shown, in the preset user set display interface 200 of the first electronic device, the preset user set 210 can be displayed in the form of a chain. The preset user set 210 may include a first user 211 and at least one second user 212 associated with the first user 211.

[0045] Users within the preset user set can share and use each other's corresponding learning tools. A learning tool group can be determined based on the preset user set. The learning tool group may include applications installed on all users' electronic devices, websites or applets that have been used, websites or applets that have been authorized, etc.

[0046] It can be understood that a user's electronic device may include the user's mobile phone, tablet computer, laptop, learning machine, smart watch and other devices. In other words, a user can correspond to multiple electronic devices at the same time, and the learning tool group can aggregate the learning tools corresponding to the user's multiple electronic devices.

[0047] Step 102, in response to the first input of the first user, obtain the first search content.

[0048] In step 102, the first input of the first user in the search box can be received, and in response to the first input, the first search content can be obtained. As Figure 2b shown, the first search content 221 can be "Pythagorean theorem".

[0049] Step 103, search the first search content through the learning tool group to obtain the first search result.

[0050] In step 103, as Figure 2b shown, when the first search content 221 is input into the search box corresponding to the preset user set, or the first search content 221 is dragged into the area of the preset user set 210, the first search content 221 can be searched through the learning tool group. Exemplarily, at least one second user's second electronic device can be used as a relay node, and the learning tool corresponding to the second electronic device is used to search the first search content, and at the same time the learning tool corresponding to the first electronic device is used to search the first search content to obtain the results of each learning tool.

[0051] Exemplarily, the first search content input by the first user on the first electronic device can be spread to each user node in the preset user set, so that the first search content can be transmitted to each learning tool in the preset user set for searching. The results searched by multiple terminals and distributedly can be transmitted back to the preset user set, and the preset user set will de-duplicate the returned results according to the similarity comparison and present them in the form of a list on the first electronic device.

[0052] In some examples, these results can be presented so that the first user can select a certain result as the final first search result and display the first search result 222 corresponding to the first search content 221 in a preset display area. In other examples, the first electronic device can also recommend the optimal result as the first search result 222 by itself and display it.

[0053] Step 104: Generate a knowledge graph using the first search content and the first search result as knowledge points.

[0054] In step 104, the first search content and the first search result can be determined as a knowledge point. After obtaining multiple knowledge points using the same method, a knowledge graph can be generated based on these knowledge points.

[0055] In the embodiments of the present application, a preset user set can be constructed according to the first user and at least one second user associated with the first user. A learning tool group can be obtained from the multiple learning tools corresponding to the electronic devices of all users in the preset user set. Thus, the first search content input by the first user can be searched based on the learning tool group to obtain a more accurate first search result. The first search content and the corresponding first search result can be used as knowledge points to generate a knowledge graph. In this way, without installing multiple learning tools, the accuracy of the search result can be improved by combining the search results of multiple learning tools, and then the reliability of the knowledge graph can be improved, which is beneficial to assisting users in learning.

[0056] In some embodiments, searching for the first search content through the learning tool group to obtain the first search result includes:

[0057] Searching for the first search content through the learning tool group to obtain multiple initial results corresponding to the multiple learning tools;

[0058] Determine the similarity between the multiple initial results;

[0059] Determine the initial results whose similarity meets the preset similarity condition as the first search result.

[0060] In this embodiment, the first search content can be searched through multiple learning tools in the learning tool group to obtain the initial result corresponding to each learning tool, that is, multiple initial results can be obtained.

[0061] Multiple initial results can be compared one by one to calculate the similarity between them. It can be understood that if the initial results obtained by most of the multiple learning tools are the same or similar, and the initial results obtained by a small number of learning tools are significantly different from the other initial results, then it can be considered that the initial results with significant differences may be wrong answers. Based on this, the initial results whose similarity meets the preset similarity condition can be determined as the first search result. For example, the initial result with the highest similarity is determined as the first search result, or for example, several initial results with relatively high similarity are fused and determined as the first search result.

[0062] In this way, a more accurate first search result can be determined based on the similarity between the multiple initial results corresponding to multiple learning tools, further improving the accuracy of the first search result, and further improving the reliability of the knowledge graph, which is beneficial to assisting users in learning.

[0063] In some embodiments, after determining the learning tool group, the method further includes:

[0064] Displaying multiple learning tools in the learning tool group;

[0065] Receiving a second input for the multiple learning tools;

[0066] In response to the second input, determining a target learning tool from the multiple learning tools;

[0067] Searching for the first search content through the learning tool group to obtain a first search result, including:

[0068] Searching for the first search content through the target learning tool to obtain a first search result.

[0069] In this embodiment, as Figure 3a shown, after determining the learning tool group, multiple learning tools can be displayed in the learning tool group display interface 300. A second input from the first user for the multiple learning tools can be received, and in response to the second input, a target learning tool can be determined from the multiple learning tools. For example, the first user can click on some of the multiple learning tools, or for example, as Figure 3b shown, the first user can circle some of the multiple learning tools in the learning tool group display interface 300 to obtain the selected target learning tool 310.

[0070] The first search content can be searched through the target learning tool to obtain a first search result. Exemplarily, as Figure 3c shown, the target learning tool 310 can be used to search for the first search content 321, such as "Pythagorean theorem", to obtain and display the first search result 322.

[0071] In this way, after obtaining the learning tool group, the target learning tools that meet the user's needs can be screened out to search the first search content, so as to eliminate some learning tools that are not trusted by the user. On the one hand, it can save some computing resources for subsequent matching of the first search results. On the other hand, it can make the first search results more meet the user's needs, realizing the personalization of the knowledge graph.

[0072] In some embodiments, before determining the learning tool group, the method further includes:

[0073] Displaying the contact information of the first user;

[0074] Receiving a third input to the contact information;

[0075] In response to the third input, determining at least one second user from the contact information;

[0076] Constructing a preset user set according to the first user and at least one second user.

[0077] In this embodiment, as Figure 4a shown, the contact information of the first user can be displayed on the contact display interface 400. The contact information may include the address book of the first user, instant messaging applications, and friend information in other social web pages or mini-programs, etc. The contact information may refer to the information of a single user, and may include group information composed of multiple users, such as groups like "colleagues", "family members", "friends", etc.

[0078] The third input of the first user to the contact information can be received. In response to the third input, at least one second user can be determined from the contact information. For example, the first user can select some contacts from the displayed contact information as at least one second user to form a study group with the first user and construct a preset user set. In some examples, the first user can also verify the credibility of the selected users. For example, the selected users are all within the user's friend range.

[0079] As Figure 4b shown, the first user can construct a preset user set 410 with at least one second user. The learning tools corresponding to the electronic devices of all users in the preset user set can be shared.

[0080] In some examples, wrong questions can also be shared among the users in the preset user set. The shared wrong questions and the corresponding answers are used as knowledge points to generate a knowledge graph for the purpose of checking for gaps and making up for deficiencies.

[0081] In this way, contacts can be selected as at least one second user to construct a preset user set with the first user, laying a foundation for aggregating multiple learning tools in the preset user set to form a learning tool group.

[0082] In some embodiments, after constructing a preset user set according to a first user and at least one second user, the method further includes:

[0083] Receiving a fifth input to the preset user set;

[0084] In response to the fifth input, performing a first process, the first process including any one of the following:

[0085] Adding a second user;

[0086] Deleting a second user;

[0087] Replacing a second user.

[0088] In this embodiment, as Figure 4b shown, a fifth input from a user to the preset user set 410 can be received, and in response to the fifth input, a user in the preset user set can be added, a user in the preset user set can be deleted, or a user in the preset user set can be replaced.

[0089] Exemplarily, by long pressing a certain node in the preset user set, "Add", "Delete", and "Replace" controls can be displayed, and when the first user clicks on the corresponding control, the corresponding function can be executed.

[0090] In some examples, the first user can also drag the icon of a new user into the preset user set area to become a new node of the preset user set, so as to achieve the purpose of adding a second user.

[0091] In this way, the users in the preset user set can be edited to achieve the purpose of optimizing the preset user set, so as to aggregate a learning tool group that better meets the user's needs, improving the personalization and reliability of the knowledge graph.

[0092] In some embodiments, generating a knowledge graph further includes:

[0093] Obtaining wrong question information, where the wrong question information includes at least one of the wrong question information corresponding to the first user and the wrong question information corresponding to the second user;

[0094] Using the wrong question information as knowledge points to generate a knowledge graph.

[0095] In this embodiment, the wrong question information corresponding to the first user can be obtained. As Figure 5a and Figure 5b shown, the first user can take a photo of the wrong question or perform a real-time preview through the wrong question scanning interface 500, extract, summarize, and collect the wrong questions in the viewfinder, and refine the words, phrases, and sentences to obtain the wrong question information 510. In some examples, the first user can use the learning tool corresponding to the first electronic device to search for the wrong questions to obtain the answers to the wrong questions, which together form the wrong question information.

[0096] It is also possible to obtain the wrong-question information corresponding to the second user. For example, the first electronic device can obtain the wrong-question information shared by the second user through the second electronic device. Among them, the wrong-question information corresponding to the second user can be obtained by the second electronic device in the same manner as described above, and specific limitations are not provided here.

[0097] The wrong-question information of the first user and / or the second user can be used as knowledge points to generate a knowledge graph.

[0098] In this way, the sources of the knowledge points in the knowledge graph can also include the wrong-question information of the first user and / or the second user, making the knowledge points in the knowledge graph more comprehensive and further improving the reliability of the knowledge graph.

[0099] In some embodiments, when the users corresponding to the wrong-question information are N users and N is an integer greater than 1, using the wrong-question information as knowledge points to generate a knowledge graph includes:

[0100] Comparing the wrong-question information corresponding to the N users one by one to determine the target wrong-question information, where any two wrong-question information in the target wrong-question information are different;

[0101] Using the target wrong-question information as knowledge points to generate a knowledge graph.

[0102] In this embodiment, it can be understood that each user may have the situation of getting the same question wrong. Based on this, when the users corresponding to the wrong-question information include multiple users, that is, when the knowledge graph needs to include the wrong-question information of multiple users, the wrong-question information corresponding to the N users can be compared one by one first, and the duplicate wrong-question information among the N users can be removed to obtain the de-duplicated target wrong-question information, and this target wrong-question information is used as knowledge points to generate a knowledge graph.

[0103] In this way, the same knowledge points in the knowledge graph can be screened out, making the knowledge graph more concise and accurate, and further improving the reliability of the knowledge graph.

[0104] In some embodiments, generating a knowledge graph further includes:

[0105] Obtaining the search information shared by M second users, where the search information includes the second search content and the second search result, and the second search result is obtained by the learning tool corresponding to the electronic device of the second user searching the second search content, and M is a positive integer;

[0106] Using the search information as knowledge points to generate a knowledge graph.

[0107] In this embodiment, multiple second users can share their respective corresponding search information in a group chat or other publicly visible web pages, where the search information can be shared in the form of links, text content, screenshots, etc. It can be understood that the search information may include the second search content input by the second user, as well as the second search results obtained by searching the second search content through the learning tool corresponding to the electronic device of the second user.

[0108] The search information shared by the second user can be obtained and used as knowledge points to generate a knowledge graph.

[0109] In this way, the sources of the knowledge points in the knowledge graph can also include the search information shared by the second user, making the knowledge points in the knowledge graph more comprehensive and further improving the reliability of the knowledge graph.

[0110] In some embodiments, when the search information includes first search information and second search information, where the second users corresponding to the first search information and the second search information are different, and the second search content of the first search information and the second search information is the same, before using the search information as knowledge points to generate a knowledge graph, the method further includes:

[0111] Display the first search information and the second search information;

[0112] Receive a fourth input;

[0113] In response to the fourth input, when the display positions of the first search information and the second search information coincide, compare the first search information and the second search information to obtain a difference result;

[0114] Display the difference result.

[0115] In this embodiment, the first search information and the second search information shared by different users searching for the same second search content can be obtained.

[0116] Such as Figure 6a shown, the first search information 601 and the second search information 602 can be displayed.

[0117] Receive a fourth input, where the fourth input can be an input in which the first user drags the first search information 601 towards the second search information 602, or an input in which the first user drags the second search information 602 towards the first search information 601.

[0118] Such as Figure 6bAs shown, in response to the fourth input, when the display positions of the first search information 601 and the second search information 602 coincide, the first search information and the second search information are compared to obtain a difference result 603 and displayed. So that the first user can view the difference result, and then can determine the search result corresponding to the second search content based on the difference result, and generate a knowledge graph with it as a knowledge point.

[0119] In this way, for different search information corresponding to the same second search content, the difference results can be automatically compared and displayed, so as to determine more accurate search information according to the difference results, further improve the reliability of the knowledge graph, and be conducive to assisting users in learning.

[0120] In some embodiments, generating a knowledge graph further includes:

[0121] Obtain the knowledge points corresponding to the first user, where the knowledge points include at least one of the following: knowledge points obtained from files corresponding to the learning progress of the first user and having an appearance frequency greater than a first threshold; knowledge points associated with the target input of the first user;

[0122] Generate a knowledge graph based on the knowledge points.

[0123] In this embodiment, knowledge points with an appearance frequency greater than the first threshold can be obtained from files corresponding to the learning progress of the first user. For example, high-frequency knowledge points with an appearance frequency greater than the first threshold can be obtained from the texts or syllabuses already learned by the first user. These knowledge points are also added to the knowledge graph of the first user.

[0124] It is also possible to obtain knowledge points associated with the target input of the first user in response to the target input of the first user. In other words, the knowledge points manually input by the first user can be added to the knowledge graph of the first user.

[0125] In this way, the sources of the knowledge points in the knowledge graph can also include high-frequency knowledge points in files corresponding to the learning progress of the first user, and / or knowledge points manually added by the first user, so that the knowledge points in the knowledge graph are more comprehensive, further improving the reliability of the knowledge graph.

[0126] In some embodiments, generating a knowledge graph includes:

[0127] Taking the source of the knowledge points as the first-level nodes, and taking the knowledge points of the same source as the second-level nodes associated with the first-level nodes corresponding to the source, to generate a knowledge graph.

[0128] In this embodiment, as Figure 7As shown, the knowledge graph 700 may include first-level nodes in black and second-level nodes in white. By way of example, the source of knowledge points can be used as the first-level nodes. For example, the first-level nodes may include dictation notebooks, wrong-question notebooks, textbooks, collected content, etc.; the second-level nodes may include specific knowledge point content, and the second-level nodes are associated with the first-level nodes. Knowledge points from the same source can be used as the second-level nodes associated with the corresponding first-level nodes.

[0129] In some examples, when the first user clicks on a certain first-level node, all the collections of knowledge points under that first-level node can be viewed.

[0130] In this way, knowledge points can be classified to generate an associated knowledge graph, which is convenient for users to quickly find the corresponding knowledge points and is helpful for assisting users in learning.

[0131] In some embodiments, when the knowledge points include knowledge points of multiple disciplines, generating a knowledge graph includes:

[0132] Taking the discipline corresponding to the knowledge points as the first-level nodes, taking the sources of the knowledge points under the same discipline as the second-level nodes associated with the first-level nodes corresponding to the discipline, and taking the knowledge points from the same source as the third-level nodes associated with the second-level nodes corresponding to the source, to generate a knowledge graph.

[0133] In this embodiment, the knowledge points may include knowledge points of multiple disciplines. Taking the knowledge graph corresponding to English listening training as an example, wrong-question information or search information of disciplines such as Chinese, English, and mathematics can be obtained. For non-English information, it can be translated into English first, and then the corresponding words, phrases, and sentences can be added to the knowledge graph.

[0134] This knowledge graph can be a three-level graph. Among them, the discipline corresponding to the knowledge points can be used as the first-level nodes, the sources of the knowledge points under the same discipline can be used as the second-level nodes associated with the first-level nodes corresponding to the discipline, and the knowledge points from the same source can be used as the third-level nodes associated with the second-level nodes corresponding to the source.

[0135] In this way, the knowledge graph can be a three-level graph of multiple disciplines, which combines the knowledge points of multiple disciplines skillfully, with richer and more comprehensive content, and is convenient for users to study uniformly.

[0136] In some embodiments, after generating the knowledge graph, the method further includes:

[0137] Determining target knowledge points from the knowledge graph;

[0138] Responding to the configuration input of the first user to determine the configuration information of learning materials;

[0139] Generating learning materials according to the target knowledge points and the configuration information, so that the first user can use the learning materials for learning.

[0140] In this embodiment, the target knowledge point can be determined from the knowledge graph. For example, the first user can select the corresponding knowledge point as the target knowledge point by clicking on the relevant node. Another example is that, as Figure 8 shown, the first user can circle the knowledge graph 700, and then determine the circled target knowledge point 710.

[0141] The configuration input of the first user can be received, and in response to the configuration input of the first user, the configuration information of the learning material can be determined. As Figure 9a shown, taking the learning material as a listening training story as an example, the configuration information can include information such as character naming, story scene, background music, story duration, and story word count. In some examples, the configuration information can further include more advanced configuration information such as the proportion of each character, the order of character appearance, the appearance time, and the story conflict.

[0142] The learning material for the first user to learn can be generated according to the target knowledge point and the configuration information. As Figure 9b shown, taking the learning material as a listening training story as an example, the character naming in the configuration information can include Elsa and Peppa, and the story duration can be 15 minutes. Based on this, the learning material 910 can be generated, and the story can be named "The Encounter of Elsa and Peppa". Among them, the keyword sentences can be generated based on the Generative Pre-Trained Transformer (GPT) to generate a story line with logical relationships. By adding some prompt words and setting personalized options such as characters and scenes, the user can conduct listening training in a familiar story scene, reducing the user's memory cost.

[0143] In this way, the target knowledge point can be selected from the knowledge graph of the first user, and the learning material for the first user can be generated in combination with the configuration information. In this way, the first user can learn based on the targeted and interesting learning material, improving the user's learning enthusiasm and personalization, and being more conducive to assisting the user in learning.

[0144] In some embodiments, when the learning material is a listening training story, after generating the learning material according to the target knowledge point and the configuration information, the method further includes:

[0145] Display the first control on the learning material playback page;

[0146] Receive the sixth input to the first control;

[0147] In response to the sixth input, continue writing the listening training story.

[0148] In this embodiment, taking the learning material as a listening training story as an example, when the first user is training listening, only the listening card can be displayed on the learning material playback interface, and the listening training story can be played. When the first user is training vocabulary, the story content can be displayed on the learning material playback interface without playing the audio.

[0149] The first control can also be displayed on the learning material playback page, and the sixth input from the first user to the first control can be received. In response to the sixth input, the listening training story can be continued. Exemplarily, a "continue writing" control can be displayed on the learning material playback page. After the first user finishes listening to the listening training story, if interested, the first user can click the "continue writing" control to continue writing the listening training story.

[0150] It can be understood that when continuing to write the listening training story, the original configuration information can be used, or new configuration information can be re-set to continue writing a new listening training story for the first user to learn.

[0151] In this way, the interestingness of the learning material is improved, which is conducive to motivating the user's learning enthusiasm.

[0152] In some embodiments, when the learning material is a listening training story, after generating the learning material according to the target knowledge point and the configuration information, the method further includes:

[0153] When a preset condition is met, a target listening story is recommended to the first user, and the target listening story has the same theme as the learning material;

[0154] Among them, the preset condition includes any one of the following: generating learning materials of the same theme continuously within a preset time period; receiving a seventh input to the second control displayed on the learning material playback page.

[0155] In this embodiment, if the user continuously generates learning materials of the same theme within a preset time period, for example, continuously generates listening training stories of the same theme type for a week, then more target listening stories of the same theme can be recommended to the first user based on these contents.

[0156] The second control can also be displayed on the learning material playback page, and the seventh input from the first user to the second control can be received. In response to the seventh input, a target listening story is recommended to the first user. Exemplarily, a "recommend" control can be displayed on the learning material playback page. After the first user finishes listening to the listening training story, if interested in the story of this theme, the first user can click the "recommend" control to recommend a target listening story with the same theme to the first user.

[0157] In this way, some target listening stories of the same theme can be recommended to the first user to organize and generate a listening special training, provide some intensive training for the user, and be more conducive to assisting the user's learning.

[0158] In some embodiments, after generating learning materials according to the target knowledge points and configuration information, the method further includes:

[0159] Obtaining the learning result of the first user on the learning materials;

[0160] Generating an identifier corresponding to the learning result;

[0161] Displaying the identifier.

[0162] In this embodiment, the learning result of the first user on the learning materials can be obtained, such as whether the learning is completed or not, and if completed, what is the corresponding completion degree, etc. An identifier corresponding to the learning result can be generated and displayed. Exemplarily, corresponding learner medals can be generated according to the learning result to encourage the enthusiasm of users.

[0163] In some examples, the identifier can further include preview information, and the preview information can include information such as new characters, scenes, plot summaries, etc. unlocked by the next listening story.

[0164] In this way, the interest of the learning materials is further improved, which is conducive to motivating the learning enthusiasm of users.

[0165] For the knowledge graph generation method provided by the embodiments of the present application, the execution subject can be a knowledge graph generation device. In the embodiments of the present application, taking the knowledge graph generation device executing the knowledge graph generation method as an example, the knowledge graph generation device provided by the embodiments of the present application is described.

[0166] As Figure 10 shown, the knowledge graph generation device 1000 may include:

[0167] A first determination module 1001, configured to determine a learning tool group, where the learning tool group includes a plurality of learning tools corresponding to the electronic devices of all users in a preset user set, and the preset user set includes the first user and at least one second user associated with the first user;

[0168] A first acquisition module 1002, configured to acquire first search content in response to a first input of the first user;

[0169] A search module 1003, configured to search the first search content through the learning tool group to obtain a first search result;

[0170] A first generation module 1004, configured to generate a knowledge graph by using the first search content and the first search result as knowledge points.

[0171] In the embodiments of the present application, a preset user set can be constructed according to a first user and at least one second user associated with the first user, and a learning tool group can be obtained from the multiple learning tools corresponding to the electronic devices of all users in the preset user set. Thus, the first search content input by the first user can be searched based on the learning tool group to obtain a more accurate first search result, and the first search content and the corresponding first search result can be used as knowledge points to generate a knowledge graph. In this way, without installing multiple learning tools, the accuracy of the search result can be improved by combining the search results of multiple learning tools, thereby improving the reliability of the knowledge graph and facilitating user learning.

[0172] In some embodiments, the search module 1003 can also be used for:

[0173] Search the first search content through the learning tool group to obtain multiple initial results corresponding to the multiple learning tools;

[0174] Determine the similarity between the multiple initial results;

[0175] Determine the initial results whose similarity meets the preset similarity condition as the first search result.

[0176] In this way, a more accurate first search result can be determined based on the similarity between the multiple initial results corresponding to the multiple learning tools, further improving the accuracy of the first search result, and then further improving the reliability of the knowledge graph, which is beneficial to assisting user learning.

[0177] In some embodiments, the knowledge graph generation device 1000 may further include:

[0178] A first display module for displaying the multiple learning tools in the learning tool group;

[0179] A first receiving module for receiving a second input to the multiple learning tools;

[0180] A second determination module for determining a target learning tool from the multiple learning tools in response to the second input;

[0181] The search module 1003 can also be used for:

[0182] Search the first search content through the target learning tool to obtain a first search result.

[0183] In this way, after obtaining the learning tool group, a target learning tool that meets the user's needs can be selected to search the first search content, so as to eliminate some learning tools that are not trusted by the user. On the one hand, some computing resources for subsequent first search result matching can be saved, and on the other hand, the first search result can better meet the user's needs, realizing the personalization of the knowledge graph.

[0184] In some embodiments, the knowledge graph generation device 1000 may further include:

[0185] A second display module for displaying the contact information of the first user;

[0186] A second receiving module for receiving a third input to the contact information;

[0187] A third determination module for determining at least one second user from the contact information in response to the third input;

[0188] A construction module for constructing a preset user set according to the first user and at least one second user.

[0189] In this way, contacts can be selected as at least one second user to construct a preset user set with the first user, laying a foundation for aggregating multiple learning tools in the preset user set to form a learning tool group.

[0190] In some embodiments, the first generation module 1004 may further be configured to:

[0191] Obtain wrong question information, where the wrong question information includes at least one of the wrong question information corresponding to the first user and the wrong question information corresponding to the second user;

[0192] Use the wrong question information as knowledge points to generate a knowledge graph.

[0193] In this way, the source of the knowledge points in the knowledge graph may further include the wrong question information of the first user and / or the second user, so that the knowledge points in the knowledge graph are more comprehensive, further improving the reliability of the knowledge graph.

[0194] In some embodiments, when the users corresponding to the wrong question information are N users and N is an integer greater than 1, the first generation module 1004 may further be configured to:

[0195] Compare the wrong question information corresponding to the N users one by one to determine target wrong question information, where any two wrong question information in the target wrong question information are different;

[0196] Use the target wrong question information as knowledge points to generate a knowledge graph.

[0197] In this way, the same knowledge points in the knowledge graph can be screened out, making the knowledge graph more concise and accurate, further improving the reliability of the knowledge graph.

[0198] In some embodiments, the first generation module 1003 may further be configured to:

[0199] Obtain the search information shared by M second users. The search information includes the second search content and the second search result. The second search result is obtained by the learning tool corresponding to the electronic device of the second user searching for the second search content. M is a positive integer;

[0200] Use the search information as knowledge points to generate a knowledge graph.

[0201] In this way, the source of the knowledge points in the knowledge graph can also include the search information shared by the second user, so that the knowledge points in the knowledge graph are more comprehensive, further improving the reliability of the knowledge graph.

[0202] In some embodiments, when the search information includes the first search information and the second search information, where the second users corresponding to the first search information and the second search information are different, and the second search content of the first search information and the second search information is the same, the knowledge graph generation device 1000 may further include:

[0203] A third display module, configured to display the first search information and the second search information;

[0204] A fourth receiving module, configured to receive a fourth input;

[0205] A comparison module, configured to, in response to the fourth input, when the display positions of the first search information and the second search information coincide, compare the first search information and the second search information to obtain a difference result;

[0206] A fourth display module, configured to display the difference result.

[0207] In this way, for different search information corresponding to the same second search content, the difference results can be automatically compared and displayed, so as to determine more accurate search information according to the difference results, further improving the reliability of the knowledge graph and being beneficial to assisting users in learning.

[0208] The knowledge graph generation device in the embodiments of the present application may be an electronic device or a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal or other devices other than terminals. Exemplarily, the electronic device may be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a Mobile Internet Device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. It may also be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0209] The knowledge graph generation device in the embodiments of the present application may be a device with an operating system. The operating system may be an Android operating system, an IOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0210] The knowledge graph generation device provided by the embodiments of the present application can implement Figure 1 each process implemented by the method embodiments in FIGS. 7 to 9. To avoid repetition, details are not described here again.

[0211] Optionally, as Figure 11 shown, the embodiments of the present application further provide an electronic device 1100, including a processor 1101 and a memory 1102. A program or instruction that can run on the processor 1101 is stored on the memory 1102. When the program or instruction is executed by the processor 1101, it implements each step of the above-mentioned knowledge graph generation method embodiment and can achieve the same technical effect. To avoid repetition, details are not described here again.

[0212] It should be noted that the electronic device in the embodiments of the present application includes the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0213] Figure 12 is a schematic diagram of the hardware structure of the electronic device provided by the embodiments of the present application.

[0214] The electronic device 1200 includes, but is not limited to, components such as a radio frequency unit 1201, a network module 1202, an audio output unit 1203, an input unit 1204, a sensor 1205, a display unit 1206, a user input unit 1207, an interface unit 1208, a memory 1209, and a processor 1210.

[0215] Those skilled in the art can understand that the electronic device 1200 may further include a power source (such as a battery) for supplying power to each component. The power source can be logically connected to the processor 1210 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. Figure 12 The structure of the electronic device shown does not limit the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0216] Among them, the processor 1210 can be used to:

[0217] Determine a learning tool group, where the learning tool group includes a plurality of learning tools corresponding to the electronic devices of all users in a preset user set, and the preset user set includes a first user and at least one second user associated with the first user;

[0218] In response to a first input of the first user, obtain first search content;

[0219] Search the first search content through the learning tool group to obtain a first search result;

[0220] Use the first search content and the first search result as knowledge points to generate a knowledge graph.

[0221] In the embodiments of the present application, a preset user set can be constructed according to the first user and at least one second user associated with the first user, and a learning tool group can be obtained by aggregating a plurality of learning tools corresponding to the electronic devices of all users in the preset user set. Thus, the first search content input by the first user can be searched through the learning tool group to obtain a more accurate first search result. The first search content and the corresponding first search result can be used as knowledge points to generate a knowledge graph. In this way, without installing multiple learning tools, the search results of multiple learning tools can be combined to improve the accuracy of the search results, and further improve the reliability of the knowledge graph, which is beneficial to assisting users in learning.

[0222] In some embodiments, the processor 1210 can also be used to:

[0223] Search the first search content through the learning tool group to obtain multiple initial results corresponding to the multiple learning tools;

[0224] Determine the similarity between multiple initial results;

[0225] Determine the initial results whose similarity meets the preset similarity condition as the first search results.

[0226] In this way, more accurate first search results can be determined based on the similarity between multiple initial results corresponding to multiple learning tools, further improving the accuracy of the first search results, and then further improving the reliability of the knowledge graph, which is beneficial to assisting users in learning.

[0227] In some embodiments, the display unit 1206 can be used to: display multiple learning tools in the learning tool group;

[0228] The user input unit 1207 can be used to: receive a second input for multiple learning tools;

[0229] The processor 1210 can also be used to:

[0230] In response to the second input, determine a target learning tool from multiple learning tools;

[0231] Search the first search content through the target learning tool to obtain the first search results.

[0232] In this way, after obtaining the learning tool group, a target learning tool that meets the user's needs can be selected to search the first search content, so as to eliminate some learning tools that are not trusted by the user. On the one hand, some computing resources for subsequent first search result matching can be saved, and on the other hand, the first search results can better meet the user's needs, realizing the personalization of the knowledge graph.

[0233] In some embodiments, the display unit 1206 can also be used to: display the contact information of the first user;

[0234] The user input unit 1207 can be used to: receive a third input for the contact information;

[0235] The processor 1210 can also be used to:

[0236] In response to the third input, determine at least one second user from the contact information;

[0237] Construct a preset user set according to the first user and at least one second user.

[0238] In this way, contacts can be selected as at least one second user to construct a preset user set with the first user, laying a foundation for aggregating multiple learning tools in the preset user set to form a learning tool group.

[0239] In some embodiments, the processor 1210 can also be used to:

[0240] Obtain wrong-question information, where the wrong-question information includes at least one of the wrong-question information corresponding to the first user and the wrong-question information corresponding to the second user;

[0241] Use the wrong-question information as knowledge points to generate a knowledge graph.

[0242] In this way, the source of the knowledge points in the knowledge graph can also include the wrong-question information of the first user and / or the second user, so that the knowledge points in the knowledge graph are more comprehensive, and the reliability of the knowledge graph is further improved.

[0243] In some embodiments, when the users corresponding to the wrong-question information are N users and N is an integer greater than 1, the processor 1210 can also be used to:

[0244] Compare the wrong-question information corresponding to the N users one by one to determine the target wrong-question information, and any two wrong-question information in the target wrong-question information are different;

[0245] Use the target wrong-question information as knowledge points to generate a knowledge graph.

[0246] In this way, the same knowledge points in the knowledge graph can be screened out, making the knowledge graph more concise and accurate, and further improving the reliability of the knowledge graph.

[0247] In some embodiments, the processor 1210 can also be used to:

[0248] Obtain the search information shared by M second users, where the search information includes the second search content and the second search result, and the second search result is obtained by the learning tool corresponding to the electronic device of the second user searching the second search content, and M is a positive integer;

[0249] Use the search information as knowledge points to generate a knowledge graph.

[0250] In this way, the source of the knowledge points in the knowledge graph can also include the search information shared by the second users, so that the knowledge points in the knowledge graph are more comprehensive, and the reliability of the knowledge graph is further improved.

[0251] In some embodiments, when the search information includes the first search information and the second search information, where the second users corresponding to the first search information and the second search information are different, and the second search content of the first search information and the second search information is the same, the display unit 1206 can be used to: display the first search information and the second search information;

[0252] The user input unit 1207 can be used to: receive a fourth input;

[0253] The processor 1210 can be used to: in response to a fourth input, when the display positions of the first search information and the second search information coincide, compare the first search information and the second search information to obtain a difference result;

[0254] The display unit 1206 can also be used to: display the difference result.

[0255] In this way, for different search information corresponding to the same second search content, the difference result can be automatically compared and displayed, so as to determine more accurate search information according to the difference result, further improving the reliability of the knowledge graph and being beneficial to assisting users in learning.

[0256] It should be understood that in the embodiments of the present application, the input unit 1204 may include a Graphics Processing Unit (GPU) 12041 and a microphone 12042. The graphics processor 12041 processes the image data of static pictures or videos obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1206 may include a display panel 12061, and the display panel 12061 can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1207 includes at least one of a touch panel 120121 and other input devices 12072. The touch panel 120121 is also called a touch screen. The touch panel 120121 can include two parts: a touch detection device and a touch controller. The other input devices 12072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be elaborated here.

[0257] The memory 1209 can be used to store software programs and various data. The memory 1209 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area may store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1209 may include a volatile memory or a non-volatile memory, or the memory 1209 may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synch link dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The memory 1209 in the embodiments of the present application includes, but is not limited to, these and any other suitable types of memories.

[0258] The processor 1210 may include one or more processing units; optionally, the processor 1210 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above modem processor may not be integrated into the processor 1210 either.

[0259] The embodiments of the present application further provide a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, it implements each process of the above-mentioned embodiment of the knowledge graph generation method and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0260] Among them, the processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media such as computer read-only memory ROM, random access memory RAM, magnetic disks, or optical discs, etc.

[0261] Another embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement each process of the above-mentioned knowledge graph generation method embodiment, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0262] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0263] The embodiments of the present application provide a computer program product. The program product is stored in a storage medium and is executed by at least one processor to implement each process of the above-mentioned knowledge graph generation method embodiment, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0264] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including that element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0265] Through the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases, the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0266] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them belong to the protection scope of the present application.

Claims

1. A knowledge graph generation method, characterized in that: The method comprises: Determine a learning tool group, the learning tool group including a plurality of learning tools corresponding to electronic devices of all users in a preset user set, the preset user set including a first user and at least one second user associated with the first user; In response to a first input of the first user, obtaining a first search content; Searching the first search content by using the learning tool group to obtain a first search result; The first search content and the first search result are used as knowledge points to generate a knowledge graph.

2. The method according to claim 1, characterized in that The step of searching the first search content by using the learning tool group to obtain a first search result includes: Searching the first search content by using the learning tool group to obtain a plurality of initial results corresponding to the plurality of learning tools; determining similarities between the plurality of initial results; The initial result whose similarity meets a preset similarity condition is determined as the first search result.

3. The method according to claim 1, characterized in that: After determining the learning tool set, the method further includes: displaying a plurality of learning tools in the learning tool set; receiving a second input to the plurality of learning tools; In response to the second input, determining a target learning tool from the plurality of learning tools; The step of searching the first search content by using the learning tool group to obtain a first search result includes: The first search content is searched by using the target learning tool to obtain a first search result.

4. The method according to claim 1, characterized in that: Before determining the learning tool set, the method further includes: Displaying the contact information of the first user; receiving a third input of the contact information; In response to the third input, determining the at least one second user from the contact information; The preset user set is constructed according to the first user and the at least one second user.

5. The method according to claim 1, characterized in that The generating of the knowledge graph further includes: Acquire wrong question information, where the wrong question information includes at least one of the wrong question information corresponding to the first user and the wrong question information corresponding to the second user; The wrong question information is used as knowledge points to generate a knowledge graph.

6. The method according to claim 5, characterized in that In the case that the number of users corresponding to the wrong question information is N, and N is an integer greater than 1, the step of using the wrong question information as a knowledge point to generate a knowledge graph includes: Comparing the wrong question information corresponding to the N users one by one to determine target wrong question information, wherein any two wrong question information in the target wrong question information are different; The target wrong question information is used as knowledge points to generate a knowledge graph.

7. The method according to claim 1, characterized in that The generating of the knowledge graph further includes: Acquire search information shared by M second users, the search information including second search content and second search results, the second search results being obtained by searching the second search content with a learning tool corresponding to the electronic device of the second user, and M being a positive integer; The search information is used as knowledge points to generate a knowledge graph.

8. The method according to claim 7, characterized in that In the case where the search information includes first search information and second search information, wherein the first search information and the second search information correspond to different second users, and the first search information and the second search information have the same second search content, before using the search information as a knowledge point to generate a knowledge graph, the method further includes: displaying the first search information and the second search information; receiving a fourth input; In response to the fourth input, when the display positions of the first search information and the second search information overlap, comparing the first search information with the second search information to obtain a difference result; The difference results are displayed.

9. A knowledge graph generation device, characterized in that: The device comprises: A first determining module, configured to determine a learning tool group, the learning tool group including a plurality of learning tools corresponding to electronic devices of all users in a preset user set, the preset user set including a first user and at least one second user associated with the first user; A first acquisition module, configured to acquire first search content in response to a first input of the first user; A search module, configured to search the first search content through the learning tool group to obtain a first search result; The first generating module is used to generate a knowledge graph by taking the first search content and the first search result as knowledge points.

10. The device according to claim 9, characterized in that The search module is also used for: Searching the first search content by using the learning tool group to obtain a plurality of initial results corresponding to the plurality of learning tools; determining similarities between the plurality of initial results; The initial result whose similarity meets a preset similarity condition is determined as the first search result.

11. The device according to claim 9, characterized in that The device also includes: A first display module, used for displaying a plurality of learning tools in the learning tool group; A first receiving module, configured to receive a second input of the plurality of learning tools; a second determining module, configured to determine a target learning tool from the plurality of learning tools in response to the second input; The search module is also used for: The first search content is searched by using the target learning tool to obtain a first search result.

12. The device according to claim 9, characterized in that The device also includes: A second display module, used to display the contact information of the first user; A second receiving module, configured to receive a third input of the contact information; A third determining module, configured to determine the at least one second user from the contact information in response to the third input; A construction module is used to construct the preset user set according to the first user and the at least one second user.

13. The device according to claim 9, characterized in that The first generating module is further used for: Acquire wrong question information, where the wrong question information includes at least one of the wrong question information corresponding to the first user and the wrong question information corresponding to the second user; The wrong question information is used as knowledge points to generate a knowledge graph.

14. The device according to claim 13, characterized in that When the number of users corresponding to the wrong question information is N and N is an integer greater than 1, the first generating module is further configured to: Comparing the wrong question information corresponding to the N users one by one to determine target wrong question information, wherein any two wrong question information in the target wrong question information are different; The target wrong question information is used as knowledge points to generate a knowledge graph.

15. The device according to claim 9, characterized in that The first generating module is further used for: Acquire search information shared by M second users, the search information including second search content and second search results, the second search results being obtained by searching the second search content with a learning tool corresponding to the electronic device of the second user, and M being a positive integer; The search information is used as knowledge points to generate a knowledge graph.

16. The device according to claim 15, characterized in that In a case where the search information includes first search information and second search information, wherein the first search information and the second search information correspond to different second users, and the first search information and the second search information have the same second search content, the device further includes: A third display module, used for displaying the first search information and the second search information; A fourth receiving module, configured to receive a fourth input; a comparison module, configured to, in response to the fourth input, compare the first search information with the second search information to obtain a difference result when the display positions of the first search information and the second search information overlap; The fourth display module is used to display the difference result.

Images