Information processing method and device, electronic equipment and storage medium

Abstract

The present disclosure provides an information processing method and device, electronic equipment and storage medium, relates to the technical field of computers, in particular to the technical field of knowledge graph, intelligent search and the like. The specific implementation scheme is as follows: an information retrieval request is acquired, wherein the retrieval request contains a retrieval word and a target field to which a retrieval result belongs; the retrieval word is matched with description information of each node of a first information graph to determine a target node; the size of a sub-graph to be acquired is determined according to the target field; and the sub-graph with the target node as a center node is acquired and displayed from the first information graph based on the identification of the target node and the size of the sub-graph to be acquired.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the fields of knowledge graphs and intelligent search, specifically to an information processing method, apparatus, electronic device and storage medium. Background Technology

[0002] With the rapid development of information technology, a large amount of document data is generated and stored. Therefore, it is often necessary to retrieve and obtain target documents from a large amount of document data. As a result, it is very important to know how to mine the knowledge in documents, improve the efficiency of document retrieval, and provide suggestions for decision-making. Summary of the Invention

[0003] This disclosure aims to at least partially address one of the technical problems in the related art.

[0004] Therefore, the purpose of this disclosure is to provide an information processing method, apparatus, electronic device, and storage medium that can make search results more intuitive, enhance the richness and completeness of search results, and improve user satisfaction and user experience.

[0005] According to a first aspect of this disclosure, an information processing method is provided, comprising:

[0006] Obtain an information retrieval request, wherein the retrieval request includes search terms and the target domain to which the search results belong;

[0007] The search terms are matched with the description information of each node in the first information graph to determine the target node;

[0008] Based on the target domain, determine the size of the sub-map to be acquired;

[0009] Based on the identifier of the target node and the size of the sub-graph to be acquired, the sub-graph centered on the target node is acquired from the first information graph and displayed.

[0010] According to a second aspect of this disclosure, an information processing apparatus is provided, comprising:

[0011] The first acquisition module is used to acquire an information retrieval request, wherein the retrieval request includes search terms and the target domain to which the search results belong;

[0012] The first determining module is used to match the search terms with the description information of each node in the first information graph to determine the target node;

[0013] The second determining module is used to determine the size of the sub-map to be acquired based on the target domain;

[0014] The second acquisition module is used to acquire and display a sub-graph centered on the target node from the first information graph based on the identifier of the target node and the size of the sub-graph to be acquired.

[0015] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the information processing method as described in the first aspect.

[0019] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided that stores computer instructions for causing the computer to perform the information processing method as described in the first aspect.

[0020] According to a fifth aspect of this disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the information processing method as described in the first aspect.

[0021] The information processing methods, apparatus, electronic devices, and storage media provided in this disclosure have the following beneficial effects:

[0022] By searching for target nodes matching the search terms in the information graph, and then, based on the target domain, obtaining a sub-graph of appropriate size centered on the target node in the information graph as the search result, the search results become more intuitive, improve the flexibility of information processing, increase the richness and completeness of the search results, and enhance user satisfaction and user experience.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0024] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, which are provided for a better understanding of the present invention and are not intended to limit the scope of this disclosure, wherein:

[0025] Figure 1 This is a flowchart illustrating an information processing method according to an embodiment of the present disclosure;

[0026] Figure 2 This is a schematic diagram of the structure of a first information graph provided in this disclosure;

[0027] Figure 3 This is a flowchart illustrating an information processing method according to another embodiment of the present disclosure;

[0028] Figure 4 This is a flowchart illustrating an information processing method according to another embodiment of the present disclosure;

[0029] Figure 5 This is a schematic diagram of the structure of a reference spectrum provided in this disclosure;

[0030] Figure 6 This is a schematic diagram of the structure of an information processing apparatus according to an embodiment of the present disclosure;

[0031] Figure 7 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present disclosure is shown. Detailed Implementation

[0032] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0033] The embodiments disclosed herein relate to technical fields such as knowledge graphs and intelligent search.

[0034] A knowledge graph, known in the library and information science field as knowledge domain visualization or knowledge domain mapping map, is a series of different graphics that display the development process and structural relationships of knowledge. It uses visualization technology to describe knowledge resources and their carriers, and to mine, analyze, construct, draw and display knowledge and the interrelationships between them.

[0035] Intelligent search engines are a new generation of search engines that combine artificial intelligence technology. In addition to providing traditional functions such as fast retrieval and relevance ranking, they can also provide functions such as user role registration, automatic identification of user interests, semantic understanding of content, intelligent information filtering and push.

[0036] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0037] The information processing method, apparatus, electronic device, and storage medium of this disclosure are described below with reference to the accompanying drawings.

[0038] It should be noted that the execution subject of the information processing method in this embodiment is an information processing device, which can be implemented by software and / or hardware. The device can be configured in an electronic device, which may include, but is not limited to, a terminal, a server, etc.

[0039] Figure 1 This is a flowchart illustrating an information processing method according to an embodiment of the present disclosure.

[0040] like Figure 1 As shown, the information processing method includes:

[0041] S101: Obtain information retrieval request.

[0042] The search request may include search terms and the target domain to which the search results belong.

[0043] It should be noted that the target domain of the search results can be any discipline, industry, technology, product, service, or any other field with a specific set of knowledge or information. The target domain included in the search request can be selected by the user or identified based on the search terms entered by the user; this disclosure does not limit this. For example, if the search term is "rainstorm," it means that the user needs to search for information related to rainstorms, and the target domain of the requested search results can be the meteorological field.

[0044] In this embodiment of the disclosure, the user can enter search terms and select the target search area in the search engine, so that the search engine can obtain the information retrieval request.

[0045] S102: Match the search terms with the description information of each node in the first information graph to determine the target node.

[0046] The first information graph refers to the knowledge graph corresponding to the graph database used by the search engine to retrieve information. The first information graph is an attribute graph that can contain multiple nodes. Any two nodes can be connected by one or more edges, which represent the relationships between nodes, such as causality or subordination. Each node or edge can correspond to multiple attributes, which can include descriptive information about the node.

[0047] It should be noted that, in this disclosure, the first information graph is used to describe the relationships between multiple documents. Therefore, in addition to nodes representing entities such as people, places, and events, the first information graph may also include nodes representing documents. Any document node can establish a relationship with the corresponding entity node through edges based on the entities contained within the document.

[0048] The following is combined with Figure 2 The structure of the first information graph is illustrated by an example. For example... Figure 2 As shown, Figure 2 Based on meteorological related entities (i.e. Figure 2 The description information includes nodes for events such as heavy rain, typhoons, telecommunications outages, and floods, as well as multiple documents (i.e.,...). Figure 2 The information map is constructed from documents such as "Emergency Plan for Internet Outage.pdf" and "Emergency Plan for Flood Disaster.pdf". Figure 2 In this context, nodes representing entities can be connected by directed edges, and the relationship between two entities (i.e.,...) can be represented by... Figure 2 The relationships and similarities shown are marked on the edges. Nodes representing documents are... Figure 2 At the end of the path, the document name can be marked on the document node as descriptive information.

[0049] In this embodiment of the disclosure, an index can be built in the search engine based on the description information of each node of the first information graph. The search terms are matched with the description information of each node of the first information graph through the index, the correlation degree between the search terms and each node is calculated, and the correlation degree is sorted. Then, the node with the highest correlation degree can be determined as the target node.

[0050] S103: Determine the size of the sub-map to be acquired based on the target domain.

[0051] It is understandable that the information of a single node in a graph is limited, and returning the target node as a search result to the user will not yield good search results. Therefore, in this disclosure, other nodes associated with the target node can be obtained from the first information graph, and a sub-graph containing multiple nodes can be used as the search result to provide more comprehensive information and improve the accuracy and completeness of the search.

[0052] In this embodiment of the disclosure, subgraphs of different sizes can be determined and returned as search results for different domains. This is because the concepts, entities, and relationships involved in some domains may be relatively simple and direct, and smaller subgraphs can fully reflect the information associated with the search terms. Reducing the size of the search results can save computing resources and improve processing efficiency. Therefore, a correspondence between different domains and subgraph sizes can be established in advance. Then, after determining the target node, the corresponding relationship can be queried according to the requested target domain to determine the size of the subgraph to be obtained. This allows for dynamic determination of the amount of data contained in the search results, improving the flexibility of information processing.

[0053] S104: Based on the identifier of the target node and the size of the sub-graph to be acquired, acquire and display the sub-graph centered on the target node from the first information graph.

[0054] The identifier of the target node refers to the information that can uniquely locate the node in the first information graph, which can be the name of the node, etc.

[0055] In this embodiment, the identifier of the target node and the size of the subgraph to be acquired can be sent to the graph database. The graph database can then determine the location of the target node in the first information graph based on the target node's identifier, and then, based on the size of the subgraph to be acquired, extract the corresponding length from multiple paths originating from the target node in the first information graph to obtain the subgraph. The obtained subgraph can then be displayed on the user interface.

[0056] Optionally, the level m of the candidate associated nodes can be determined first based on the size of the sub-graph to be acquired. Then, based on the identifier of the target node, the information of the m-level associated nodes associated with the target node can be obtained. Based on the information of the m-level associated nodes, the sub-graph centered on the target node can be obtained from the first information graph and displayed.

[0057] The information of the first-level associated nodes may include at least one of the following: the number of associated nodes, the association relationship between the target node and the first-level associated nodes, and the association weight between the target node and the first-level associated nodes.

[0058] It should be noted that when the value of m is greater than or equal to 2, in the first information graph, each (m-1)th level node may be associated with multiple (m-1)th level associated nodes. Therefore, the information of the (m-1)th level associated node may include at least one of the following: the number of associated nodes, the corresponding (m-1)th level associated node, the association relationship with the (m-1)th level associated node, and the association weight with the (m-1)th level associated node.

[0059] In this embodiment of the disclosure, the scale of the sub-graph may include the number of associated nodes to be acquired, the level of the associated nodes, the type of the associated nodes, etc., so that the level m of the candidate associated nodes can be determined according to the scale of the sub-graph to be acquired. After locating the target node in the first information graph based on the identifier of the target node, the information of the associated nodes can be confirmed step by step from the target node according to the path direction. That is, first determine the information of the first-level associated nodes, then determine the information of the second-level associated nodes based on each first-level associated node, and so on, until the information of the m-th level associated nodes is obtained. Then, a sub-graph with the target node as the center node can be generated based on the information of the associated nodes.

[0060] In this embodiment of the disclosure, based on the level of the sub-graph generated by the target, associated nodes are obtained level by level with the target node as the center to obtain the sub-graph, which can improve the orderliness of the sub-graph generation and improve the reliability and efficiency of information processing.

[0061] It should be noted that, in this disclosure, after obtaining the sub-map and displaying it to the user, the user can perform operations such as viewing detailed content, expanding the map, and downloading it, in order to increase the flexibility and practicality of the sub-map and better meet the user's needs in knowledge acquisition and decision-making, thereby improving the user experience.

[0062] Optionally, if any node in the sub-map is detected to be selected, the attribute information of that node can be obtained and displayed.

[0063] The attribute information may include at least one of the following: the content of any node, storage address, source, update time, etc.

[0064] In this embodiment, users can select any node on the sub-graph in the display interface via touch or click, thereby detecting the selection of any node in the sub-graph. Then, based on the identifier of that node, its attribute information can be obtained from the first information graph. This obtained attribute information is then displayed at the corresponding position of that node in the sub-graph via pop-ups or other means. This allows users to gain a deeper understanding of the specific content and meaning of each node in the graph, improving the completeness of the search results and enhancing the user experience.

[0065] Optionally, upon receiving an extension instruction for any node in the sub-graph, the at least one-level associated node of that node and the association relationship between that node and the at least one-level associated node can be obtained from the first information graph and displayed.

[0066] It should be noted that the level of the associated nodes obtained when expanding the subgraph can be selected by the user according to actual needs and sent to the search engine in the expansion instruction, or it can be a fixed value preset in the search engine, etc. This disclosure does not limit this.

[0067] In this embodiment, if a user is interested in the content of a certain node in the subgraph and needs to obtain more related information, they can click on any node in the subgraph on the display interface and select the expansion function. The search engine then receives the instruction to expand any node in the subgraph. It then retrieves at least one node in the first information graph that is associated with that node but does not belong to the currently generated subgraph. Based on the relationship between the at least one node and any other node, it constructs edges connecting these nodes in the subgraph to obtain the expanded subgraph, which is then displayed. This improves the flexibility of information processing, enhances the information completeness of the generated subgraph, better meets user needs, and improves the user experience.

[0068] Optionally, upon receiving a storage instruction for a subgraph, and if the subgraph contains at least one document-type node, the subgraph can be stored, and the document associated with at least one document-type node can be retrieved and stored based on the storage address associated with the at least one document-type node.

[0069] The attribute information of document-type nodes can include the storage address of the corresponding document in a file storage system or server, and the complete document can be obtained from the file storage system through the storage address.

[0070] It should be noted that a subgraph may contain multiple document class nodes. Users can send storage commands through the storage control corresponding to the subgraph to download and store all documents associated with all document class nodes within the subgraph. Alternatively, users can click the storage control corresponding to any document class node to download the document associated with that document class node.

[0071] In this embodiment of the disclosure, by downloading and storing the documents associated with the document-type nodes contained in the sub-graph, the efficiency of information acquisition and integration of retrieval results can be improved, providing users with a more convenient and efficient work and study experience.

[0072] In this embodiment, an information retrieval request is first obtained. The search terms contained in the information retrieval request are matched with the description information of each node in the first information graph to determine the target node. Then, based on the target domain contained in the information retrieval request, the size of the sub-graph to be obtained is determined. Finally, based on the identifier of the target node and the size of the sub-graph to be obtained, the sub-graph centered on the target node is obtained from the first information graph and displayed. Thus, by searching for target nodes that match the search terms in the information graph, and then obtaining a sub-graph of the appropriate size centered on the target node in the information graph based on the retrieved target domain, the retrieval results are obtained. This makes the retrieval results more intuitive, improves the flexibility of information processing, increases the richness and completeness of the retrieval results, and improves user satisfaction and user experience.

[0073] Figure 3 This is a schematic flowchart of an information processing method proposed in another embodiment of this disclosure.

[0074] like Figure 3 As shown, the information processing method includes:

[0075] S301: Obtain information retrieval request.

[0076] The description of S301 in this embodiment can be found in the above embodiments, and will not be repeated here.

[0077] S302: Determine the name of each first node of type entity in the first information graph as the description information of that first node.

[0078] The name of the first node refers to the concept or thing that the entity itself represents. It has a clear referential nature and can accurately identify and distinguish different entities. For example, Figure 2 The images depict heavy rain, typhoons, telecommunications disruptions, floods, etc.

[0079] S303: The keywords of the documents associated with each second node of type document in the first information graph are determined as the descriptive information of that second node.

[0080] In this embodiment of the disclosure, important words, features, or phrases can be extracted from each document by means of manual extraction, machine extraction, or automated extraction using artificial intelligence (AI) technology. These keywords are then used as descriptive information for the second node corresponding to the document in the first information graph.

[0081] Optionally, if there are multiple keywords associated with any second node in a document, the frequency and position of each keyword in any second node can be determined, and then the descriptive information sequence of any second node can be determined based on the frequency and position of each keyword in any second node.

[0082] In other words, when a document associated with any second node contains multiple keywords, the frequency of each keyword and its position within the document can be determined. Then, based on the frequency and position (importance) of each keyword, the matching degree between each keyword and the document is comprehensively determined. Finally, the keywords are ranked according to their matching degree to obtain a sequence of descriptive information; keywords ranked higher have higher weights and are more important in the descriptive information of the second node.

[0083] In this embodiment of the disclosure, by determining the frequency and position of the keywords extracted from the document within the document, the keywords are sorted and used as a sequence of descriptive information for the document class nodes corresponding to the document in the first information graph. This improves the accuracy and reliability of the descriptive information of the document class nodes and further provides conditions for improving the accuracy of subsequent node matching results.

[0084] In this embodiment of the disclosure, by determining the descriptive information of different types of nodes in the information graph in different ways, the accuracy of the information graph can be improved, which provides a condition for improving the accuracy of subsequent node matching results.

[0085] S304: If the search term matches a keyword in at least two second nodes in the first information graph, determine the order of a keyword in the description information sequence of at least two second nodes, and the length of the description information sequence of at least two second nodes.

[0086] The length of the description information sequence of the second node can refer to the number of keywords in the description information of the second node.

[0087] Understandably, when a search term matches a keyword in at least two second nodes of the first information graph, the degree of match between the search term and each of the two second nodes varies depending on the position of the keyword in the description information sequence of the second node. Furthermore, the more keywords contained in the description information sequence of a second node, the more dispersed the importance or weight of each keyword relative to the second node becomes. Therefore, if a keyword appears in the same order in the description information sequences of two second nodes, the longer the description information sequence corresponding to the second node, the weaker the match between the search term and that second node.

[0088] S305: Based on the length of the description information sequence associated with at least two nodes and the order of a keyword in the description information sequence, determine one of the at least two second nodes as the target node.

[0089] It should be noted that when the lengths of the description information sequences associated with at least two nodes are the same, the order of the keywords matching the search term in the at least two description information sequences can be compared, and the second node corresponding to the description information sequence with the highest order can be determined as the target node.

[0090] Alternatively, when the keywords matching the search term are in the same order in at least two description information sequences, the lengths of at least two description information sequences can be compared, and the second node corresponding to the shortest description information sequence can be determined as the target node.

[0091] Alternatively, if the length and order are different, the weights corresponding to the length and order can be determined respectively, and the target node can be determined by weighted fusion of at least two second nodes.

[0092] In this embodiment of the disclosure, based on the order of the keywords matched by the search term in multiple descriptive information sequences and the length of each descriptive information sequence, a node is selected as the target node from multiple document class nodes matched by the search term. This improves the reliability of the target node and further enhances the efficiency of information processing and the accuracy of the search results.

[0093] S306: Determine the size of the sub-map to be acquired based on the target domain.

[0094] S307: Based on the identifier of the target node and the size of the sub-graph to be acquired, acquire and display the sub-graph centered on the target node from the first information graph.

[0095] The descriptions of S306 and S307 in this embodiment can be found in the above embodiments, and will not be repeated here.

[0096] In this embodiment, the name of each first node of type entity in the first information graph is determined as the description information of that first node, and the keywords of the documents associated with each second node of type document in the first information graph are determined as the description information of that second node. This improves the accuracy of the information graph and provides a basis for improving the accuracy of subsequent node matching results. Furthermore, when the search term matches a keyword of at least two second nodes in the first information graph, the order of a keyword in the description information sequences of at least two second nodes and the length of the description information sequences of at least two second nodes are first determined. Then, based on the length of the description information sequences associated with at least two nodes and the order of a keyword in the description information sequences, one of the at least two second nodes is determined as the target node. This improves the reliability of the target node and further enhances the efficiency of information processing and the accuracy of the search results.

[0097] Figure 4 This is a schematic flowchart of an information processing method proposed in another embodiment of this disclosure.

[0098] like Figure 4 As shown, the information processing method includes:

[0099] S401: Obtain information retrieval request.

[0100] For a detailed description of S401, please refer to the above embodiments, which will not be repeated here.

[0101] S402: Construct a reference map based on expert knowledge related to various fields.

[0102] Among them, the expert knowledge related to various fields refers to the basic principles and theories in various fields, as well as the knowledge and experience accumulated over a long period of time. This expert knowledge can be obtained through expert systems, historical records, human experience, etc., related to various fields.

[0103] In this embodiment of the disclosure, expert knowledge related to various fields can be input into a graph database, and the relationships between different professional terms can be extracted through methods such as automatic machine extraction to construct a reference graph. For example... Figure 5 As shown, Figure 5 This is a schematic diagram of the reference atlas. Figure 5In this system, the reference map is constructed based on expert knowledge related to the meteorological field. It uses various meteorological terms, such as heavy rain, typhoons, telecommunications disruptions, and floods, as nodes in the reference map. Furthermore, directed edges are established to connect the corresponding nodes based on the relationships between any two terms, such as causal relationships or similarity relationships.

[0104] It should be noted that for expert knowledge related to multiple fields, multiple corresponding reference maps can be constructed separately, or expert knowledge related to at least two fields can be cross-referenced to construct a single reference map, etc. This disclosure does not limit this.

[0105] It should be noted that the constructed reference map can be updated in real time by inputting new expert knowledge into the graph database.

[0106] S403: Construct a second information graph based on the acquired information resources and associated keywords.

[0107] Information resources can refer to documents in formats such as Word, Portable Document Format (PDF), and PowerPoint (PPT).

[0108] The nodes in the second information graph include information resources and keywords.

[0109] In this embodiment, all information resources are first stored in a file storage system or server. Then, for the text content of each information resource, extraction techniques are used to obtain associated keywords. A corresponding node labeled as a document type is constructed for each information resource, and the storage address of the information resource in the file storage system or server is recorded as an attribute on the node. The document type nodes and the entity nodes corresponding to the extracted keywords are loaded into a graph database, and an association relationship is established between the document type nodes and keyword nodes in the graph database according to the correspondence between documents and keywords, thereby obtaining a second information graph.

[0110] S404: The reference map and the second information map are fused to obtain the first information map.

[0111] In this embodiment, the identical nodes in the reference graph and the second information graph can be identified first, and these identical nodes in the two graphs can be merged into a single node in the first information graph. For edges (i.e., relationships with other nodes) that the same node is associated with in both the reference graph and the second information graph, if either edge is included in both the reference graph and the second information graph, they can be merged into a single edge in the first information graph. Alternatively, if at least one edge is included in only the reference graph or the second information graph, then in the merged first information graph, the identical node will still be associated with that at least one edge and the other nodes connected by that edge.

[0112] For example, in the reference graph, node A and node B are connected by an edge representing association a, and node B and node C are connected by an edge representing association b. In the second information graph, node A and node B are connected by an edge representing association a, and node B and node D are connected by an edge representing association c. It can be seen that both the reference graph and the second information graph contain node A and node D. The fused first information graph can contain nodes A, B, C, and D, with an edge representing association a between A and B, an edge representing association b between B and C, and an edge representing association c between B and D.

[0113] The following is combined with Figure 2 and Figure 5 The illustration demonstrates how the reference map and the second information map are integrated. The second information map contains a node named "Flood" and the associated relationships between nodes corresponding to the document "Flood Disaster Emergency Plan, PDF". Figure 5 The reference graph shown also contains a node named "Flood," therefore, the merged first information graph can contain the association between the "Flood" node and the nodes in the "Flood Disaster Emergency Plan, pdf" document. This process continues until the first information graph contains all nodes and edges from both the reference and second information graphs, at which point the fusion process ends, and the merged first information graph is shown below. Figure 2 As shown.

[0114] S405: Match the search terms with the description information of each node in the first information graph to determine the target node.

[0115] S406: Determine the size of the sub-map to be acquired based on the target domain.

[0116] S407: Based on the identifier of the target node and the size of the sub-graph to be acquired, acquire and display the sub-graph centered on the target node from the first information graph.

[0117] The descriptions of S405 to S407 above can be found in the above embodiments, and will not be repeated here.

[0118] In this embodiment, a reference graph is first constructed based on expert knowledge related to various fields. Then, a second information graph is constructed based on the acquired information resources and associated keywords. Finally, the reference graph and the second information graph are merged to obtain a first information graph. Thus, by integrating industry expert knowledge to construct an information graph describing the content and relationships of information resources, the reliability and accuracy of the information graph are improved, and the content of the graph is further enriched, making it more complete and comprehensive.

[0119] Figure 6 This is a schematic diagram of the structure of an information processing device according to an embodiment of the present disclosure.

[0120] like Figure 6 As shown, the information processing device 600 includes:

[0121] The first acquisition module 601 is used to acquire an information retrieval request, wherein the retrieval request includes the search terms and the target domain to which the search results belong;

[0122] The first determining module 602 is used to match the search terms with the description information of each node in the first information graph to determine the target node;

[0123] The second determining module 603 is used to determine the size of the sub-map to be acquired based on the target domain;

[0124] The second acquisition module 604 is used to acquire and display the sub-graph with the target node as the center node from the first information graph based on the identifier of the target node and the size of the sub-graph to be acquired.

[0125] In some possible embodiments, the second acquisition module 604 may specifically be used for:

[0126] Determine the level m of the candidate associated nodes based on the size of the subgraph to be acquired;

[0127] Based on the identifier of the target node, obtain the information of the m-level associated nodes related to the target node. The information of the first-level associated nodes includes at least one of the following: the number of associated nodes, the association relationship between the target node and the first-level associated nodes, and the association weight between the target node and the first-level associated nodes.

[0128] Based on the information of the m-level associated nodes, obtain and display the sub-graph with the target node as the center node from the first information graph.

[0129] In some possible embodiments, the second acquisition module 604 may also be used for:

[0130] When any node in the sub-map is detected to be selected, the attribute information of that node is obtained and displayed. The attribute information includes at least one of the following: the content of that node, its storage address, its source, and its update time.

[0131] In some possible embodiments, the second acquisition module 604 may also be used for:

[0132] Upon receiving an extension instruction for any node in the sub-graph, the system retrieves and displays from the first information graph at least one first-level associated node and the association relationship between the node and the first first-level associated node.

[0133] In some possible embodiments, the second acquisition module 604 may also be used for:

[0134] Upon receiving a storage instruction for a subgraph, and if the subgraph contains at least one document-type node, the subgraph is stored, and based on the storage address associated with the at least one document-type node, the document associated with the at least one document-type node is retrieved and stored.

[0135] In some possible embodiments, the first determining module 602 may also be used for:

[0136] The name of each first node of type entity in the first information graph is determined as the description information of that first node;

[0137] The keywords of the documents associated with each second node of type document in the first information graph are determined as the descriptive information of that second node.

[0138] In some possible embodiments, the first determining module 602 may also be used for:

[0139] If a document associated with any second node has multiple keywords, determine the frequency and position of each keyword in any second node;

[0140] Based on the frequency and position of each keyword in any second node, determine the sequence of descriptive information for that second node.

[0141] In some possible embodiments, the first determining module 602 may specifically be used for:

[0142] If the search term matches a keyword in at least two second nodes in the first information graph, determine the order of the keyword in the description information sequence of at least two second nodes, and the length of the description information sequence of at least two second nodes.

[0143] Based on the length of the description information sequence associated with at least two nodes, and the order of a keyword in the description information sequence, one of the at least two second nodes is identified as the target node.

[0144] In some possible embodiments, the first determining module 602 may also be used for:

[0145] A reference map is constructed based on expert knowledge from various fields.

[0146] Based on the acquired information resources and associated keywords, a second information graph is constructed, wherein the nodes in the second information graph include information resources and keywords;

[0147] The reference map and the second information map are fused to obtain the first information map.

[0148] It should be noted that the foregoing explanation of the information processing method also applies to the information processing device of this embodiment, and will not be repeated here.

[0149] In this embodiment, an information retrieval request is first obtained. The search terms contained in the information retrieval request are matched with the description information of each node in the first information graph to determine the target node. Then, based on the target domain contained in the information retrieval request, the size of the sub-graph to be obtained is determined. Finally, based on the identifier of the target node and the size of the sub-graph to be obtained, the sub-graph centered on the target node is obtained from the first information graph and displayed. Thus, by searching for target nodes that match the search terms in the information graph, and then obtaining a sub-graph of the appropriate size centered on the target node in the information graph based on the retrieved target domain, the retrieval results are obtained. This makes the retrieval results more intuitive, improves the flexibility of information processing, increases the richness and completeness of the retrieval results, and improves user satisfaction and user experience.

[0150] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0151] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0152] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0153] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0154] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as information processing methods. For example, in some embodiments, the information processing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the information processing method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform information processing methods by any other suitable means (e.g., by means of firmware).

[0155] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0157] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0158] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0159] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0160] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service ecosystem, addressing the shortcomings of traditional physical hosts and VPS (Virtual Private Server, or simply "VPS") services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0161] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0162] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. In the description of this disclosure, the words "if" and "suppose" as used may be interpreted as "when," "when," "in response to determination," or "in the circumstances."

[0163] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An information processing method, comprising: Obtain an information retrieval request, wherein the retrieval request includes search terms and the target domain to which the search results belong; Matching the search terms with the description information of each node in the first information graph to determine the target node includes: The name of each first node of type entity in the first information graph is determined as the description information of that first node; The keywords of the documents associated with each second node of type document in the first information graph are determined as the description information of the second node. In the case that there are multiple keywords of the documents associated with any second node, the frequency and position of each keyword in any second node are determined. Based on the frequency and position of each keyword in any second node, the description information sequence of any second node is determined. Based on the target domain, determine the size of the sub-map to be acquired; Based on the identifier of the target node and the size of the sub-graph to be acquired, the sub-graph centered on the target node is acquired from the first information graph and displayed.

2. The method as described in claim 1, wherein, The step of obtaining and displaying a sub-graph centered on the target node from the first information graph based on the identifier of the target node and the size of the sub-graph to be obtained includes: Based on the size of the sub-graph to be acquired, determine the level m of the candidate associated nodes; Based on the identifier of the target node, information on m-level associated nodes related to the target node is obtained, wherein the information of the first-level associated nodes includes at least one of the following: number of associated nodes, association relationship between the target node and the first-level associated nodes, and association weight between the target node and the first-level associated nodes. Based on the information of the m-level associated nodes, a sub-graph centered on the target node is obtained from the first information graph and displayed.

3. The method of claim 1, wherein, After obtaining and displaying the sub-map centered on the target node from the first information map, the method further includes: When any node in the sub-graph is detected to be selected, the attribute information of that node is obtained and displayed, wherein the attribute information includes at least one of the following: the content, storage address, source, and update time of that node.

4. The method of claim 1, wherein, After obtaining and displaying the sub-map centered on the target node from the first information map, the method further includes: Upon receiving an extension instruction for any node in the sub-map, the system retrieves and displays from the first information map at least one first-level associated node and the association relationship between the node and the first first-level associated node.

5. The method of claim 1, wherein, After obtaining and displaying the sub-map centered on the target node from the first information map, the method further includes: Upon receiving a storage instruction for the subgraph, and if the subgraph contains at least one document class node, the subgraph is stored, and the document associated with the at least one document class node is retrieved and stored based on the storage address associated with the at least one document class node.

6. The method of claim 1, wherein, The step of matching the search terms with the description information of each node in the first information graph to determine the target node includes: If the search term matches a keyword in at least two second nodes in the first information graph, determine the order of the keyword in the description information sequence of the at least two second nodes, and the length of the description information sequence of the at least two second nodes. Based on the length of the description information sequence associated with at least two nodes, and the order of a keyword in the description information sequence, one of the at least two second nodes is determined as the target node.

7. The method as described in any one of claims 1-6, wherein, Before matching the search terms with the description information of each node in the first information graph to determine the target node, the method further includes: A reference map is constructed based on expert knowledge from various fields. Based on the acquired information resources and associated keywords, a second information graph is constructed, wherein the nodes in the second information graph include the information resources and keywords; The reference map is fused with the second information map to obtain the first information map.

8. An information processing apparatus, comprising: The first acquisition module is used to acquire an information retrieval request, wherein the retrieval request includes search terms and the target domain to which the search results belong; The first determining module is used to match the search terms with the description information of each node in the first information graph to determine the target node, including: The name of each first node of type entity in the first information graph is determined as the description information of that first node; The keywords of the documents associated with each second node of type document in the first information graph are determined as the description information of the second node. In the case that there are multiple keywords of the documents associated with any second node, the frequency and position of each keyword in any second node are determined. Based on the frequency and position of each keyword in any second node, the description information sequence of any second node is determined. The second determining module is used to determine the size of the sub-map to be acquired based on the target domain; The second acquisition module is used to acquire and display a sub-graph centered on the target node from the first information graph based on the identifier of the target node and the size of the sub-graph to be acquired.

9. The apparatus of claim 8, wherein, The second acquisition module is specifically used for: Based on the size of the sub-graph to be acquired, determine the level m of the candidate associated nodes; Based on the identifier of the target node, information on m-level associated nodes related to the target node is obtained, wherein the information of the first-level associated nodes includes at least one of the following: number of associated nodes, association relationship between the target node and the first-level associated nodes, and association weight between the target node and the first-level associated nodes. Based on the information of the m-level associated nodes, a sub-graph centered on the target node is obtained from the first information graph and displayed.

10. The apparatus of claim 8, wherein, The second acquisition module is further configured to: When any node in the sub-graph is detected to be selected, the attribute information of that node is obtained and displayed, wherein the attribute information includes at least one of the following: the content, storage address, source, and update time of that node.

11. The apparatus of claim 8, wherein, The second acquisition module is further configured to: Upon receiving an extension instruction for any node in the sub-map, the system retrieves and displays from the first information map at least one first-level associated node and the association relationship between the node and the first first-level associated node.

12. The apparatus of claim 8, wherein, The second acquisition module is further configured to: Upon receiving a storage instruction for the subgraph, and if the subgraph contains at least one document class node, the subgraph is stored, and the document associated with the at least one document class node is retrieved and stored based on the storage address associated with the at least one document class node.

13. The apparatus of claim 8, wherein, The first determining module is specifically used for: If the search term matches a keyword in at least two second nodes in the first information graph, determine the order of the keyword in the description information sequence of the at least two second nodes, and the length of the description information sequence of the at least two second nodes. Based on the length of the description information sequence associated with at least two nodes, and the order of a keyword in the description information sequence, one of the at least two second nodes is determined as the target node.

14. The apparatus according to any one of claims 8-13, wherein, The first determining module is further configured to: A reference map is constructed based on expert knowledge from various fields. Based on the acquired information resources and associated keywords, a second information graph is constructed, wherein the nodes in the second information graph include the information resources and keywords; The reference map is fused with the second information map to obtain the first information map.

15. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the information processing method according to any one of claims 1-7.

16. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, in, The computer instructions are used to cause the computer to perform the information processing method according to any one of claims 1-7.

17. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the steps of the information processing method according to any one of claims 1-7.

Images