Knowledge graph generation method, device and electronic device

Abstract

The embodiment of the present invention provides a knowledge graph generation method, device and electronic device, wherein the method comprises: obtaining entity data; performing event argument extraction on the entity data to obtain at least one argument data; obtaining a template container; the template container comprises at least one sub-template container; and filling the argument data into the sub-template containers respectively to generate a sub-knowledge graph in the knowledge graph. After performing event argument extraction on the entity data to obtain the argument data, the embodiment of the present invention sequentially fills the argument data into the sub-template containers of the template container to form a knowledge graph with hierarchical distribution of sub-knowledge graphs, and then the knowledge graph is displayed in an electronic device without being limited by the screen space, thereby improving the efficiency of using the screen space.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of computer technology, and in particular, to a knowledge graph generation method, device, and electronic device. Background Art

[0002] Knowledge Graph, also known as knowledge domain visualization or knowledge domain mapping map, is a series of various graphs that show the development process and structural relationship of knowledge. It uses visualization technology to describe knowledge resources and their carriers, and mine, analyze, construct, draw and display knowledge and their interrelationships.

[0003] However, with the development of the Internet and computer technology, the amount of information on the Internet has grown rapidly, and the structural relationships and content in knowledge graphs have continued to expand, resulting in poor user browsing experience when displaying knowledge graphs on electronic devices with limited screen space such as smartphones. Summary of the invention

[0004] An embodiment of the present invention provides a knowledge graph generation method, which generates a knowledge graph with hierarchical distribution of sub-knowledge graphs based on entity data, and then the knowledge graph can be displayed in layers in the screen space of an electronic device, thereby improving the user's knowledge graph browsing experience.

[0005] Correspondingly, an embodiment of the present invention also provides a knowledge graph generation device and an electronic device to ensure the implementation and application of the above method.

[0006] In order to solve the above problems, an embodiment of the present invention discloses a knowledge graph generation method, which specifically includes:

[0007] Get entity data;

[0008] Extracting event arguments from the entity data to obtain at least one argument data;

[0009] Acquire a template container; the template container includes at least one sub-template container;

[0010] The argument data are filled into the sub-template containers respectively to generate sub-knowledge graphs in the knowledge graph; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph.

[0011] Optionally, extracting event arguments from the entity data to obtain at least one argument data includes:

[0012] Performing word segmentation processing on the entity data to obtain word segmentation;

[0013] An event entity is determined based on the word segmentation, and event arguments are extracted from the entity data based on the event entity to obtain argument data corresponding to the event entity.

[0014] Optionally,

[0015] The argument data includes at least one of image data, time data, character data and summary data corresponding to the event entity.

[0016] Optionally, the sub-template container includes an image data area, a time area, and a summary data area, and the filling of the argument data into the sub-template container respectively to generate a sub-knowledge graph in the knowledge graph includes:

[0017] Filling the image data corresponding to the event entity into the image data area of ​​the sub-template container;

[0018] Filling the time data corresponding to the event entity into the time area of ​​the sub-template container; and

[0019] The summary data corresponding to the event entity is filled into the summary data area of ​​the sub-template container.

[0020] Optionally, part of the argument data is fixedly displayed in the knowledge graph; wherein, the part of the argument data at least includes time data.

[0021] Optionally, the method further comprises:

[0022] Generate related prompt words according to part of the argument data;

[0023] The associated prompt words are filled into the sub-knowledge graph, and the associated prompt words are fixedly displayed in the knowledge graph.

[0024] The embodiment of the present invention also discloses a knowledge graph generation method, including:

[0025] Acquire a knowledge graph; the knowledge graph is composed of a sub-knowledge graph generated by a server after extracting event arguments based on entity data to obtain at least one argument data and then filling the sub-template container of the template container with the data; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph;

[0026] The sub-knowledge graphs in the knowledge graph are displayed in layers in the screen space.

[0027] Optionally, the method further comprises:

[0028] In response to a browsing operation on the knowledge graph, determining a target sub-knowledge graph from the sub-knowledge graphs of the knowledge graph;

[0029] Adjust the target sub-knowledge graph to the highest level of the knowledge graph.

[0030] Optionally, the method further comprises:

[0031] When the sub-knowledge graph is partially displayed in the screen space, providing an expansion control in the sub-knowledge graph;

[0032] In response to a touch operation on the expansion control in the sub-knowledge graph, the sub-knowledge graph is expanded to display the entire sub-knowledge graph.

[0033] The embodiment of the present invention also discloses a knowledge graph generation device, including:

[0034] An entity data acquisition module, used to acquire entity data;

[0035] An event argument extraction module, used to extract event arguments from the entity data to obtain at least one argument data;

[0036] A template container acquisition module, used to acquire a template container; the template container includes at least one sub-template container;

[0037] The argument data filling module is used to fill the argument data into the sub-template container respectively to generate a sub-knowledge graph in the knowledge graph; wherein the sub-knowledge graph is hierarchically distributed in the knowledge graph.

[0038] Optionally, the event argument extraction module is used to perform word segmentation on the entity data to obtain word segments; determine the event entity based on the word segmentation, and extract event arguments from the entity data based on the event entity to obtain argument data corresponding to the event entity.

[0039] Optionally, the argument data includes at least one of image data, time data, character data and summary data corresponding to the event entity.

[0040] Optionally, the sub-template container includes an image data area, a time area and a summary data area, and the argument data filling module is used to fill the image data corresponding to the event entity into the image data area of ​​the sub-template container; fill the time data corresponding to the event entity into the time area of ​​the sub-template container; and fill the summary data corresponding to the event entity into the summary data area of ​​the sub-template container.

[0041] Optionally, part of the argument data is fixedly displayed in the knowledge graph; wherein, the part of the argument data at least includes time data.

[0042] Optionally, the device further includes: an associated prompt word display module, which is used to generate associated prompt words according to part of the argument data; fill the associated prompt words into the sub-knowledge graph, and fixedly display the associated prompt words in the knowledge graph.

[0043] The embodiment of the present invention also discloses a knowledge graph generation device, including:

[0044] A knowledge graph acquisition module is used to acquire a knowledge graph; the knowledge graph is composed of a sub-knowledge graph generated by a server after extracting event arguments based on entity data to obtain at least one argument data and then filling the sub-template container of the template container with the data; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph;

[0045] The knowledge graph display module is used to display the sub-knowledge graphs in the knowledge graph in a hierarchical manner in the screen space.

[0046] Optionally, the device also includes: a sub-knowledge graph adjustment module, which is used to respond to a browsing operation on the knowledge graph, determine a target sub-knowledge graph from the sub-knowledge graphs of the knowledge graph; and adjust the target sub-knowledge graph to the highest level of the knowledge graph.

[0047] Optionally, the device also includes: a sub-knowledge graph expansion module, which is used to provide an expansion control in the sub-knowledge graph when the sub-knowledge graph is partially displayed in the screen space; in response to a touch operation on the expansion control in the sub-knowledge graph, expand the sub-knowledge graph to display the entire sub-knowledge graph.

[0048] An embodiment of the present invention further discloses a readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device can execute the knowledge graph generation method as described in any one of the embodiments of the present invention.

[0049] An embodiment of the present invention also discloses an electronic device, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, including a method for generating a knowledge graph as described in any one of the embodiments of the present invention.

[0050] The embodiments of the present invention include the following advantages:

[0051] In an embodiment of the present invention, entity data of an entity is obtained, event arguments are extracted from the entity data to obtain at least one argument data, and the argument data are respectively filled into the sub-template containers of the template container to generate a knowledge graph with hierarchical distribution of sub-knowledge graphs. In an embodiment of the present invention, after event arguments are extracted from the entity data to obtain argument data, the sub-template containers of the template container are sequentially filled into the sub-template containers of the template container to form a knowledge graph with hierarchical distribution of sub-knowledge graphs, so that when the knowledge graph is displayed on an electronic device, it will not be limited by the screen space, thereby improving the efficiency of using the screen space. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a flowchart of the steps of an embodiment of a knowledge graph generation method of the present invention;

[0053] Figure 2 is a schematic diagram of a knowledge graph of the present invention;

[0054] Figure 3 It is a flowchart of the steps of an optional embodiment of a knowledge graph generation method of the present invention;

[0055] Figure 4 It is a flowchart of steps of another optional embodiment of the knowledge graph generation method of the present invention;

[0056] Figure 5 It is a structural block diagram of an embodiment of a knowledge graph generation device of the present invention;

[0057] Figure 6 It is a structural block diagram of an optional embodiment of a knowledge graph generation device of the present invention;

[0058] Figure 7 A structural block diagram of an electronic device for generating a knowledge graph according to an exemplary embodiment;

[0059] Figure 8 It is a structural schematic diagram of an electronic device for generating a knowledge graph according to another exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0061] Reference Figure 1 , shows a flow chart of steps of an embodiment of a knowledge graph generation method of the present invention, which may specifically include the following steps:

[0062] Step 102: Obtain entity data.

[0063] Among them, entity data refers to data related to an entity. An entity refers to an objectively existing and distinguishable matter, a specific thing or concept. Specifically, an entity may include at least a person entity and an event entity, etc., and the corresponding entity data is data associated with the person entity or the event entity. Exemplarily, the entity may be an actor, and the corresponding entity data is the actor's acting experience, or the entity may be a news event, and the corresponding entity data is a description of the news event related to the news event. Among them, a person entity usually includes one or more corresponding event entities, so the entity data of a person entity may be composed of entity data corresponding to an event entity associated with the person entity.

[0064] In the embodiment of the present invention, the entity data of the entity can be obtained from the designated database, or when the user enters the encyclopedia website of the entity, the content in the website can be used as the entity data of the entity, such as the actor's acting experience, the development process of major events, the version update process of books, etc. in the encyclopedia website, or it can be articles with a certain popularity on other websites, such as articles with more than 100,000 views on social networking sites. In addition, after the user specifies the entity, the search engine can be used to search for data associated with the entity as the entity data, for example, when the user searches for information about the actor Jack Black, the acting experience associated with the actor Jack Black is used as the entity data, and the embodiment of the present invention does not need to be limited to this.

[0065] As an example, entity data may at least include image data, location, character data, time data, and summary data of an event, etc. Exemplarily, assuming that the entity is an actor, the entity data may be the actor's acting experience, etc., such as [Actor Jack Black starred in the movie "Gulliver's Travels" in the United States in 2010 (attached with the movie poster of "Gulliver's Travels")]; assuming that the entity is a news event, the entity data may be the news content of the news event, such as [A Mid-Autumn Festival Gala was held in Beijing in September 2021 (attached with the promotional poster of the Mid-Autumn Festival Gala)].

[0066] Step 104: extract event arguments from the entity data to obtain at least one argument data.

[0067] Among them, event argument extraction refers to extracting the various component elements of an event (time data, location, character data (characters), summary data adapted to the event, etc.) from the event description, and the elements are argument data.

[0068] In an embodiment of the present invention, after event argument extraction is performed on entity data, one or more argument data may be obtained. For example, assuming that the entity data [actor Jack Black, starred in his first film "Born to Win" in 1992; starred in the comedy film "Kingsman" in 1996; starred in the comedy love movie "Losing Love" in 2000...] is obtained, after event argument extraction is performed on the entity data, the argument data obtained may include [starred in his first film "Born to Win" in 1992], [starred in the comedy film "Kingsman" in 1996], [starred in the comedy love movie "Losing Love" in 2000]...

[0069] Step 106: Acquire a template container; the template container includes at least one sub-template container.

[0070] Step 108: Fill the argument data into the sub-template containers respectively to generate sub-knowledge graphs in the knowledge graph; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph.

[0071] Among them, the template container is a pre-set data container, the template container includes one or more sub-template containers, the sub-template container includes a blank area, and the blank area of ​​the sub-template container is filled with argument data to generate a sub-knowledge graph in the knowledge graph, thereby obtaining the knowledge graph of the entity.

[0072] For example, refer to Figure 2 , obtain the actor Jack Black's acting experience 202 on the encyclopedia website as entity data, and after extracting event arguments from the entity data, obtain the argument data of the actor Jack Black, and fill these argument data into the sub-template container in chronological order (timeline), thereby obtaining a knowledge graph about the actor Jack Black sorting events in chronological order, that is, a knowledge graph 204 formed by the sub-knowledge graphs sorted in chronological order 1992, 1996, 2000...

[0073] Among them, hierarchical distribution means that the sub-knowledge graphs in the knowledge graph are not at the same level at the same time. Exemplarily, assuming that the knowledge graph includes four sub-knowledge graphs A, B, C, and D, the four sub-knowledge graphs A, B, C, and D can be stacked in sequence, and the sub-knowledge graph A is placed at the highest level, so that when the knowledge graph is displayed, the sub-knowledge graph A currently placed at the highest level will be displayed. It can be understood that by distributing the knowledge graph of sub-knowledge graphs in a hierarchical manner, the knowledge graph can be displayed in a limited screen space. For example, a smartphone with a smaller screen space can display as much content as possible in a limited screen space based on a knowledge graph of hierarchical distribution of sub-knowledge graphs. It should be noted that in addition to the above-mentioned method of stacking sub-knowledge graphs in sequence, other hierarchical methods can also be used for display, such as displaying two sub-knowledge graphs in one layer, and the embodiments of the present invention do not need to be limited to this.

[0074] In the above-mentioned knowledge graph generation method, the entity data of the entity is obtained, event arguments are extracted from the entity data to obtain at least one argument data, the argument data are respectively filled into the sub-template container of the template container, a sub-knowledge graph in the knowledge graph of the entity is generated, and the sub-knowledge graph in the knowledge graph is displayed in a hierarchical manner in an electronic device. After the embodiment of the present invention extracts the event arguments from the entity data to obtain the argument data, it is filled into the sub-template container of the template container in an orderly manner to form a knowledge graph with hierarchical distribution of sub-knowledge graphs, and then the knowledge graph is displayed in an electronic device without being limited by the screen space, thereby improving the efficiency of using the screen space.

[0075] Reference Figure 3 , shows a flow chart of steps of an optional embodiment of a knowledge graph generation method of the present invention, which may specifically include the following steps:

[0076] Step 302: Obtain entity data.

[0077] Step 304: perform word segmentation processing on the entity data to obtain word segments;

[0078] Step 306: determine the event entity based on the word segmentation, and extract event arguments from the entity data based on the event entity to obtain argument data corresponding to the event entity.

[0079] In an embodiment of the present invention, encyclopedia content corresponding to a person entity or an event entity is extracted from an encyclopedia website as entity data, or articles with a certain popularity corresponding to a person entity or an event entity are extracted from other websites as entity data, and the entity data is processed by word segmentation to obtain multiple word segments, and then the event entity can be determined based on the word segmentation, and then event arguments are extracted from the entity data based on the event entity to obtain image data, time data, person data, summary data, etc. corresponding to the event entity as argument data corresponding to the event entity.

[0080] For example, assuming that you search for the person entity [Zhang San] on an encyclopedia website, you can obtain the encyclopedia content corresponding to the person entity. The encyclopedia content can be used as the entity data of the person entity [Zhang San]. If you perform word segmentation on the entity data of the person entity [Zhang San], you can get multiple word segments, such as 200, technology company, manager, 2005, general manager, etc. Then, based on the word segmentation, you can determine the event entities [Served as a manager of a technology company in 2000] and [Served as the general manager of a technology company in 2005]. Then, based on the event entities, you can perform event argument extraction on the entity data, and further get the image data, summary data, etc. corresponding to the event entities [Served as a manager of a technology company in 2000] and [Served as the general manager of a technology company in 2005] as argument data.

[0081] It can be understood that the entity data is segmented to obtain word segmentation, and the event entity is determined based on the word segmentation, so that the event argument can be extracted from the entity data based on the event entity to obtain the argument data corresponding to the event entity. This can facilitate the subsequent filling of the entity data into the sub-template container according to the event entity to obtain the sub-knowledge graph in the knowledge graph. Displaying an event entity through a sub-knowledge graph is conducive to users obtaining information in a targeted manner.

[0082] Step 308: Acquire a template container; the template container includes at least one sub-template container.

[0083] Step 310: Fill the argument data into the sub-template containers respectively to generate a sub-knowledge graph in the knowledge graph of the entity; wherein the sub-knowledge graph is hierarchically distributed in the knowledge graph.

[0084] In an exemplary embodiment, the sub-template container includes an image data area, a time area, and a summary data area. The step 310 of filling the argument data into the sub-template container respectively to generate a sub-knowledge graph in the knowledge graph of the entity may include the following steps:

[0085] Fill the image data corresponding to the event entity into the image data area of ​​the sub-template container; fill the time data corresponding to the event entity into the time area of ​​the sub-template container; and fill the summary data corresponding to the event entity into the summary data area of ​​the sub-template container.

[0086] In the embodiment of the present invention, the sub-template container of the template container may include one or more blank areas, wherein the blank areas may include at least an image data area, a time area, and a summary data area, etc. The blank areas may be filled with corresponding content, such as a person's photo in the image data area, an event occurrence event in the time area, and summary data in the summary data area, thereby generating a sub-knowledge graph corresponding to the event entity.

[0087] In an exemplary embodiment, part of the argument data is fixedly displayed in the knowledge graph; wherein the part of the argument data at least includes time data.

[0088] In the specific implementation, in order to let users better understand the life story of a person or the context of an event corresponding to a certain entity, you can choose to display the argument metadata that is more relevant to the entity and the event in a fixed manner in the knowledge graph.

[0089] As a specific example, part of the argument data may be time data, which is fixedly displayed in the knowledge graph, so that users can quickly understand the life story or event context of the entity. In addition, users can select or slide the time data to select the corresponding sub-knowledge graph as the target sub-knowledge graph for display. Figure 2 ,In the figure, the knowledge graphs 204 and 206, the events occurring in 1992, 1996, 2000, .. . are ,fixedly displayed in the knowledge graph, even if the currently displayed sub-knowledge ,graph has changed.

[0090] In an exemplary embodiment, the method may further include the following steps:

[0091] Generate related prompt words according to part of the argument data;

[0092] The associated prompt words are filled into the sub-knowledge graph, and the associated prompt words are fixedly displayed in the knowledge graph.

[0093] In an embodiment of the present invention, considering that partial argument data of different entities are fixedly displayed in the knowledge graph, which can allow users to better understand the life story of a person or the context of events, only one argument data, such as time data, can only allow users to understand a time corresponding to an event entity. Therefore, an embodiment of the present invention can also generate related prompt words based on partial argument data, fill the related prompt words into the sub-knowledge graph, and fixedly display the related prompt words and partial argument data together in the knowledge graph.

[0094] For example, refer to Figure 2, assuming that the character entity [Jack Black] participated in the movie "Born to Win" in 1992, and part of the argument data is 1992, based on 1992 combined with Jack Black's relevant personal content, such as his date of birth being August 28, 1969, it can be determined that Jack Black was 23 years old in 1992. Then [23 years old] can be used as the associated prompt information corresponding to the part of the argument data

[1992] and fixedly displayed in the knowledge graph.

[0095] In the above exemplary embodiment, part of the argument metadata and related prompt information are fixedly displayed in the knowledge graph, which is presented to the user in a focused and attractive way for browsing, so that the user can quickly obtain effective information.

[0096] Reference Figure 4 , shows a flowchart of another optional embodiment of a knowledge graph generation method of the present invention, which may specifically include the following steps:

[0097] Step 402, obtaining a knowledge graph; the knowledge graph is composed of a sub-knowledge graph generated by the server after extracting event arguments based on entity data and obtaining at least one argument data, and then filling the sub-template container of the template container with the data; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph;

[0098] Step 404: Display the sub-knowledge graphs in the knowledge graph in a hierarchical manner in the screen space.

[0099] In an embodiment of the present invention, when a user browses certain entity data on an electronic device, the knowledge graph corresponding to the entity data can be obtained. For example, when a user browses the acting experience of actor Zhang San on an encyclopedia website, in addition to the conventional listing of actor Zhang San's acting experience, the user can also choose to use the knowledge graph to display actor Zhang San's acting experience. In this case, the knowledge graph corresponding to actor Zhang San's acting experience will be displayed in the screen space of the electronic device.

[0100] In the above-mentioned knowledge graph generation method, a knowledge graph of hierarchically distributed sub-knowledge graphs is displayed in the screen space of an electronic device. Since the knowledge graph is composed of multiple hierarchically distributed sub-knowledge graphs, more content can be expressed in the same screen space when displayed on the electronic device, thereby improving the utilization efficiency of the screen space.

[0101] In an exemplary embodiment, the method may further include the following steps:

[0102] In response to a browsing operation on the knowledge graph, determining a target sub-knowledge graph from the sub-knowledge graphs of the knowledge graph;

[0103] Adjust the target sub-knowledge graph to the highest level of the knowledge graph.

[0104] In an embodiment of the present invention, a knowledge graph may include multiple hierarchically distributed sub-knowledge graphs. In order to facilitate users to browse the desired sub-knowledge graphs, the user's browsing operations on the knowledge graph can be detected in the electronic device, such as sliding operations or clicking operations, etc. In response to the browsing operations, the sub-knowledge graph selected by the user can be used as the target sub-knowledge graph, and the target sub-knowledge graph can be adjusted to the highest level of the knowledge graph, so that the user can browse the target sub-knowledge graph.

[0105] As an example, see Figure 2 , assuming that the sub-knowledge graph of 1992 is currently displayed, if the user clicks on 1996 in the knowledge graph 204, then the sub-knowledge graph 206 of 1996 will be displayed.

[0106] Optionally, the embodiment of the present invention can also be configured to automatically switch and display the sub-knowledge graphs in the knowledge graph in chronological order, thereby reducing user operations, and the embodiment of the present invention does not need to be limited to this.

[0107] In an exemplary embodiment, the method may further include the following steps:

[0108] When the sub-knowledge graph is partially displayed in the screen space, providing an expansion control in the sub-knowledge graph;

[0109] In response to a touch operation on the expansion control in the sub-knowledge graph, the sub-knowledge graph is expanded to display the entire sub-knowledge graph.

[0110] In the specific implementation, when the knowledge graph is displayed on the screen space of an electronic device, in order to achieve a better visual effect, the sub-knowledge graphs in the knowledge graph are usually of the same size and adapted to the screen space of the electronic device. Then, there may be some argument metadata with more content, such as the movie in which the actor participated is more popular, then the summary data in the argument metadata will also be more, and the size of the corresponding sub-knowledge graph will also be larger. At this time, for these sub-knowledge graphs, only part of them can be displayed on the screen space of the electronic device, such as Figure 2 204 in the figure only partially displays the sub-knowledge graph, and at the same time, an expansion control [View full text] is provided in the sub-knowledge graph.

[0111] If the user wants to fully view the partially displayed sub-knowledge graph, he can touch the expansion control, such as Figure 2By performing a touch operation such as clicking or pressing the expansion control in the [View full text], the sub-knowledge graph will be expanded in the screen space of the electronic device, as shown in the following example. Figure 2 As shown in 208.

[0112] By applying the embodiment of the present invention, a template container is created. After the entity data of the entity is subjected to event argument extraction to obtain argument data, argument data including image data, time data, and summary data are filled into the sub-template container of the template container in the order of time data to obtain a sub-knowledge graph in the knowledge graph, thereby forming a knowledge graph of related person entities or event entities. Among them, since the knowledge graph is obtained by filling in the time data, each time data in the knowledge graph browsed by the user can correspond to the content event of the time data, presenting the user with a focused and attractive browsing experience, thereby improving the utilization rate of the screen controls and facilitating the user to quickly obtain effective information.

[0113] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0114] Reference Figure 5 , shows a structural block diagram of an embodiment of a knowledge graph generation device of the present invention, which may specifically include the following modules:

[0115] An entity data acquisition module 502, used to acquire entity data;

[0116] An event argument extraction module 504 is used to extract event arguments from the entity data to obtain at least one argument data;

[0117] The template container acquisition module 506 is used to acquire a template container; the template container includes at least one sub-template container;

[0118] The argument data filling module 508 is used to fill the argument data into the sub-template container respectively to generate a sub-knowledge graph in the knowledge graph; wherein the sub-knowledge graph is hierarchically distributed in the knowledge graph.

[0119] In an exemplary embodiment, the event argument extraction module 504 is used to perform word segmentation processing on the entity data to obtain word segments; determine the event entity based on the word segments, and extract event arguments from the entity data based on the event entity to obtain argument data corresponding to the event entity.

[0120] In an exemplary embodiment, the argument data includes at least one of image data, time data, character data and summary data corresponding to the event entity.

[0121] In an exemplary embodiment, the sub-template container includes an image data area, a time area and a summary data area, and the argument data filling module 508 is used to fill the image data corresponding to the event entity into the image data area of ​​the sub-template container; fill the time data corresponding to the event entity into the time area of ​​the sub-template container; and fill the summary data corresponding to the event entity into the summary data area of ​​the sub-template container.

[0122] In an exemplary embodiment, part of the argument data is fixedly displayed in the knowledge graph; wherein the part of the argument data at least includes time data.

[0123] In an exemplary embodiment, the device further includes: an associated prompt word display module, which is used to generate associated prompt words based on part of the argument data; fill the associated prompt words into the sub-knowledge graph, and fixedly display the associated prompt words in the knowledge graph.

[0124] In summary, in an embodiment of the present invention, entity data of an entity is obtained, event arguments are extracted from the entity data to obtain at least one argument data, the argument data are respectively filled into sub-template containers of a template container, a sub-knowledge graph in the knowledge graph of the entity is generated, and the sub-knowledge graph in the knowledge graph is displayed in a hierarchical manner in an electronic device. After the embodiment of the present invention extracts event arguments from the entity data to obtain argument data, it is filled into the sub-template containers of the template container in an orderly manner to form a knowledge graph with hierarchical distribution of sub-knowledge graphs, and then the knowledge graph is displayed in an electronic device without being limited by screen space, thereby improving the efficiency of using the screen space.

[0125] Reference Figure 6 , shows a structural block diagram of an embodiment of a knowledge graph generation device of the present invention, which may specifically include the following modules:

[0126] The knowledge graph acquisition module 602 is used to acquire a knowledge graph; the knowledge graph is composed of a sub-knowledge graph generated by the server after extracting event arguments based on entity data and obtaining at least one argument data, and then filling the sub-template container of the template container with the data; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph;

[0127] The knowledge graph display module 604 is used to display the sub-knowledge graphs in the knowledge graph in a hierarchical manner in the screen space.

[0128] In an exemplary embodiment, the device also includes: a sub-knowledge graph adjustment module, which is used to respond to a browsing operation on the knowledge graph, determine a target sub-knowledge graph from the sub-knowledge graphs of the knowledge graph; and adjust the target sub-knowledge graph to the highest level of the knowledge graph.

[0129] In an exemplary embodiment, the device also includes: a sub-knowledge graph expansion module, which is used to provide an expansion control in the sub-knowledge graph when the sub-knowledge graph is partially displayed in the screen space; in response to a touch operation on the expansion control in the sub-knowledge graph, expand the sub-knowledge graph to display the entire sub-knowledge graph.

[0130] In summary, in an embodiment of the present invention, a knowledge graph of hierarchically distributed sub-knowledge graphs is displayed in the screen space of an electronic device. Since the knowledge graph is composed of multiple hierarchically distributed sub-knowledge graphs, more content can be expressed in the same screen space when displayed on the electronic device, thereby improving the utilization efficiency of the screen space.

[0131] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0132] Figure 7 7 is a block diagram of an electronic device 500 for generating a knowledge graph according to an exemplary embodiment. For example, the electronic device 700 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, a smart wearable device, etc.

[0133] Reference Figure 7 , the electronic device 700 may include one or more of the following components: a processing component 702 , a memory 704 , a power component 706 , a multimedia component 708 , an audio component 710 , an input / output (I / O) interface 712 , a sensor component 714 , and a communication component 716 .

[0134] The processing component 702 generally controls the overall operation of the electronic device 700, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 702 may include one or more modules to facilitate the interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate the interaction between the multimedia component 708 and the processing component 702.

[0135] The memory 704 is configured to store various types of data to support operations on the device 700. Examples of such data include instructions for any application or method operating on the electronic device 700, contact data, phone book data, messages, pictures, videos, etc. The memory 704 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0136] The power component 706 provides power to the various components of the electronic device 700. The power component 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 700.

[0137] The multimedia component 708 includes a screen that provides an output interface between the electronic device 700 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front camera and / or a rear camera. When the electronic device 700 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0138] The audio component 710 is configured to output and / or input audio signals. For example, the audio component 710 includes a microphone (MIC), and when the electronic device 700 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 704 or sent via the communication component 716. In some embodiments, the audio component 710 also includes a speaker for outputting audio signals.

[0139] I / O interface 712 provides an interface between processing component 702 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0140] The sensor assembly 714 includes one or more sensors for providing various aspects of status assessment for the electronic device 700. For example, the sensor assembly 714 can detect the open / closed state of the device 700, the relative positioning of components, such as the display and keypad of the electronic device 700, and the sensor assembly 714 can also detect the position change of the electronic device 700 or a component of the electronic device 700, the presence or absence of contact between the user and the electronic device 700, the orientation or acceleration / deceleration of the electronic device 700, and the temperature change of the electronic device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 714 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0141] The communication component 716 is configured to facilitate wired or wireless communication between the electronic device 700 and other devices. The electronic device 700 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 714 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 714 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0142] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0143] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 704 including instructions, and the instructions can be executed by a processor 720 of an electronic device 700 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0144] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute a knowledge graph generation method, the method comprising: obtaining entity data; performing event argument extraction on the entity data to obtain at least one argument data; obtaining a template container; the template container comprising at least one sub-template container; filling the argument data into the sub-template containers respectively to generate a sub-knowledge graph in the knowledge graph; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph.

[0145] Optionally, the extracting event arguments from the entity data to obtain at least one argument data includes: performing word segmentation on the entity data to obtain word segmentation; determining an event entity based on the word segmentation, and extracting event arguments from the entity data based on the event entity to obtain argument data corresponding to the event entity.

[0146] Optionally, the sub-template container includes an image data area, a time area and a summary data area, and the argument data are filled into the sub-template containers respectively to generate a sub-knowledge graph in the knowledge graph, including: filling the image data corresponding to the event entity into the image data area of ​​the sub-template container; filling the time data corresponding to the event entity into the time area of ​​the sub-template container; and filling the summary data corresponding to the event entity into the summary data area of ​​the sub-template container.

[0147] Optionally, part of the argument data is fixedly displayed in the knowledge graph; wherein, the part of the argument data at least includes time data.

[0148] Optionally, the method further includes: generating associated prompt words according to part of the argument data; filling the associated prompt words into the sub-knowledge graph, and fixedly displaying the associated prompt words in the knowledge graph.

[0149] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute a knowledge graph generation method, the method comprising: obtaining a knowledge graph; the knowledge graph is composed of a sub-knowledge graph generated by a server after performing event argument extraction based on entity data to obtain at least one argument data, and then filling the sub-template container of the template container into the corresponding sub-knowledge graph; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph; and the sub-knowledge graphs in the knowledge graph are displayed in a hierarchical manner in the screen space.

[0150] Optionally, the method further includes: in response to a browsing operation on the knowledge graph, determining a target sub-knowledge graph from the sub-knowledge graphs of the knowledge graph; and adjusting the target sub-knowledge graph to the highest level of the knowledge graph.

[0151] Optionally, the method also includes: when the sub-knowledge graph is partially displayed in the screen space, providing an expansion control in the sub-knowledge graph; in response to a touch operation on the expansion control in the sub-knowledge graph, expanding the sub-knowledge graph to display the entire sub-knowledge graph.

[0152] Figure 8 It is a structural diagram of an electronic device 800 for generating a knowledge graph according to another exemplary embodiment of the present invention. The electronic device 800 may be a server, which may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 822 (for example, one or more processors) and a memory 832, and one or more storage media 830 (for example, one or more mass storage devices) storing applications 842 or data 844. Among them, the memory 832 and the storage medium 830 may be short-term storage or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processor 822 may be configured to communicate with the storage medium 830 and execute a series of instruction operations in the storage medium 830 on the server.

[0153] The server may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input and output interfaces 858, one or more keyboards 856, and / or one or more operating systems 841, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0154] An electronic device includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations: obtaining entity data; performing event argument extraction on the entity data to obtain at least one argument data; obtaining a template container; the template container includes at least one sub-template container; filling the argument data into the sub-template containers respectively to generate a sub-knowledge graph in the knowledge graph; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph.

[0155] Optionally, the extracting event arguments from the entity data to obtain at least one argument data includes: performing word segmentation on the entity data to obtain word segmentation; determining an event entity based on the word segmentation, and extracting event arguments from the entity data based on the event entity to obtain argument data corresponding to the event entity.

[0156] Optionally, the sub-template container includes an image data area, a time area and a summary data area, and the argument data are filled into the sub-template containers respectively to generate a sub-knowledge graph in the knowledge graph, including: filling the image data corresponding to the event entity into the image data area of ​​the sub-template container; filling the time data corresponding to the event entity into the time area of ​​the sub-template container; and filling the summary data corresponding to the event entity into the summary data area of ​​the sub-template container.

[0157] Optionally, part of the argument data is fixedly displayed in the knowledge graph; wherein, the part of the argument data at least includes time data.

[0158] Optionally, the method further includes: generating associated prompt words according to part of the argument data; filling the associated prompt words into the sub-knowledge graph, and fixedly displaying the associated prompt words in the knowledge graph.

[0159] An electronic device includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include instructions for performing the following operations: obtaining a knowledge graph; the knowledge graph is composed of a sub-knowledge graph generated by a server after performing event argument extraction based on entity data to obtain at least one argument data and then filling the sub-template container of a template container into the corresponding sub-knowledge graph; wherein the sub-knowledge graphs are distributed in layers in the knowledge graph; and the sub-knowledge graphs in the knowledge graph are displayed in layers in the screen space.

[0160] Optionally, the method further includes: in response to a browsing operation on the knowledge graph, determining a target sub-knowledge graph from the sub-knowledge graphs of the knowledge graph; and adjusting the target sub-knowledge graph to the highest level of the knowledge graph.

[0161] Optionally, the method also includes: when the sub-knowledge graph is partially displayed in the screen space, providing an expansion control in the sub-knowledge graph; in response to a touch operation on the expansion control in the sub-knowledge graph, expanding the sub-knowledge graph to display the entire sub-knowledge graph.

[0162] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0163] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0164] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0165] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0166] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0167] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0168] The above is a detailed introduction to a knowledge graph generation method, a knowledge graph generation device and an electronic device provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A knowledge graph generation method, characterized in that: include: Get entity data; Extracting event arguments from the entity data to obtain at least one argument data; The extracting event arguments from the entity data to obtain at least one argument data includes: Performing word segmentation processing on the entity data to obtain word segmentation; Determine an event entity based on the word segmentation, and extract event arguments from the entity data based on the event entity to obtain argument data corresponding to the event entity; The argument data includes at least one of image data, time data, character data and summary data corresponding to the event entity; Acquire a template container; the template container is a preset data container; the template container includes at least one sub-template container; the sub-template container includes one or more blank areas, wherein the blank areas at least include an image data area, a time area, and a summary data area; The argument data are filled into the sub-template containers respectively to generate sub-knowledge graphs in the knowledge graph; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph, and are fully or partially displayed on the screen space of the electronic device according to the size of the sub-knowledge graphs.

2. The method according to claim 1, characterized in that The step of filling the argument data into the sub-template containers respectively to generate a sub-knowledge graph in the knowledge graph includes: Filling the image data corresponding to the event entity into the image data area of ​​the sub-template container; Filling the time data corresponding to the event entity into the time area of ​​the sub-template container; and The summary data corresponding to the event entity is filled into the summary data area of ​​the sub-template container.

3. The method according to claim 2, characterized in that Part of the argument data is fixedly displayed in the knowledge graph; wherein the part of the argument data at least includes time data.

4. The method according to claim 2, characterized in that: The method further comprises: Generate related prompt words according to part of the argument data; The associated prompt words are filled into the sub-knowledge graph, and the associated prompt words are fixedly displayed in the knowledge graph.

5. A knowledge graph generation method, characterized in that: include: Get the knowledge graph; The knowledge graph is composed of a sub-knowledge graph generated by a server after extracting event arguments based on entity data to obtain at least one argument data and then filling the sub-template container of the template container with the corresponding data; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph; In response to a browsing operation on the knowledge graph, determining a target sub-knowledge graph from the sub-knowledge graphs of the knowledge graph; Adjusting the target sub-knowledge graph to the highest level of the knowledge graph; The sub-knowledge graphs in the knowledge graph are displayed in layers in the screen space.

6. The method according to claim 5, characterized in that The method further comprises: When the sub-knowledge graph is partially displayed in the screen space, providing an expansion control in the sub-knowledge graph; In response to a touch operation on the expansion control in the sub-knowledge graph, the sub-knowledge graph is expanded to display the entire sub-knowledge graph.

7. A knowledge graph generation device, characterized in that: include: An entity data acquisition module, used to acquire entity data; An event argument extraction module, used to extract event arguments from the entity data to obtain at least one argument data; The extracting event arguments from the entity data to obtain at least one argument data includes: performing word segmentation processing on the entity data to obtain word segmentation; determining an event entity based on the word segmentation, and extracting event arguments from the entity data based on the event entity to obtain argument data corresponding to the event entity; A template container acquisition module, used to acquire a template container; the template container is a pre-set data container; the template container includes at least one sub-template container; the sub-template container includes one or more blank areas, wherein the blank area includes at least an image data area, a time area and a summary data area; The argument data filling module is used to fill the argument data into the sub-template container respectively to generate a sub-knowledge graph in the knowledge graph; wherein the sub-knowledge graph is hierarchically distributed in the knowledge graph.

8. A knowledge graph generation device, characterized in that: include: A knowledge graph acquisition module is used to acquire a knowledge graph; the knowledge graph is composed of a sub-knowledge graph generated by a server after extracting event arguments based on entity data to obtain at least one argument data and then filling the sub-template container of the template container with the data; wherein the sub-knowledge graphs are hierarchically distributed in the knowledge graph; The knowledge graph display module is used to display the sub-knowledge graphs in the knowledge graph in a hierarchical manner in the screen space.

9. An electronic device, characterized in that: It includes a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, including for executing the knowledge graph generation method as described in any one of method claims 1-6.

10. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the knowledge graph generation method as described in any one of method claims 1-6.

Images