Intelligent archive management method and system based on knowledge graph

Abstract

The embodiment of the invention provides an intelligent archive management method based on a knowledge graph. The method comprises the steps of obtaining at least one data source; a knowledge graph is determined based on the at least one data source, the knowledge graph comprises nodes and edges, the nodes comprise at least one master node and at least one secondary node, the edges comprise first-class edges and second-class edges, the attributes of the first-class edges comprise the similarity between the two nodes, and the attributes of the second-class edges represent the master-slave relation between the two connected nodes; obtaining current user characteristics and current retrieval contents, and determining a display range through the knowledge graph based on the current user characteristics and the current retrieval contents; related users are determined based on the current user features and the current retrieval content, and a display sequence is determined based on the current user features and the related user features.

Description

Technical Field

[0001] This specification relates to the field of management, and in particular to an intelligent archive management method and system based on a knowledge graph. Background Art

[0002] With the rapid development of information technology, a large amount of data is generated and accumulated. How to efficiently manage and utilize this data has become an important challenge for institutions and individuals. Especially in the field of archive management, the traditional management method based on folders and tags can no longer meet the growing amount of data and diverse user needs.

[0003] Therefore, we hope to provide an intelligent archive management method based on knowledge graph, which can intelligently display and recommend relevant archive content according to user characteristics and search content, which not only improves the accuracy and pertinence of information display, but also improves the efficiency of archive management and user experience, allowing users to find required information more quickly, thereby improving overall user satisfaction and usage efficiency. Summary of the invention

[0004] This manual provides an intelligent archive management method based on knowledge graph, which not only improves the accuracy and pertinence of information display, but also improves the efficiency of archive management and user experience, allowing users to find required information more quickly, thereby improving overall user satisfaction and usage efficiency.

[0005] One of the embodiments of the present specification provides an intelligent archive management method based on a knowledge graph, the method comprising: obtaining at least one data source; determining a knowledge graph based on the at least one data source, the knowledge graph comprising nodes and edges, the nodes comprising at least one main node and at least one secondary node, the edges comprising a first type of edge and a second type of edge, the attributes of the first type of edge comprising the similarity between two nodes, the attributes of the second type of edge representing the master-slave relationship between the two connected nodes; obtaining current user features and current search content, determining a display range through the knowledge graph based on the current user features and the current search content; determining related users based on the current user features and the current search content, and determining a display order based on the current user features and the related user features.

[0006] One of the embodiments of the present specification provides an intelligent archive management system based on a knowledge graph, the system comprising: a first acquisition module, used to acquire at least one data source; a graph determination module, used to determine a knowledge graph based on the at least one data source, the knowledge graph comprising nodes and edges, the nodes comprising at least one main node and at least one secondary node, the edges comprising a first type of edge and a second type of edge, the attributes of the first type of edge comprising a similarity between two nodes, and the attributes of the second type of edge representing a master-slave relationship between the two connected nodes; a second acquisition module, used to acquire current user features and current search content, and determine a display range through the knowledge graph based on the current user features and the current search content; a sequence determination module, used to determine related users based on the current user features and the current search content, and determine a display sequence based on the current user features and related user features.

[0007] One of the embodiments of the present specification provides an intelligent archive management device based on a knowledge graph, the device comprising a processor and a memory; the memory is used to store instructions, and when the instructions are executed by the processor, the device causes the device to implement the intelligent archive management method based on the knowledge graph as described in any of the above items.

[0008] One of the embodiments of this specification provides a computer-readable storage medium, characterized in that the storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs any one of the above-mentioned knowledge graph-based intelligent archive management methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0010] Figure 1 It is a schematic diagram of an application scenario of an intelligent archive management system based on a knowledge graph according to some embodiments of this specification;

[0011] Figure 2 It is a module diagram of an intelligent archive management system based on knowledge graph according to some embodiments of this specification;

[0012] Figure 3 is an exemplary flow chart of an intelligent archive management method based on a knowledge graph according to some embodiments of this specification;

[0013] Figure 4 It is an exemplary schematic diagram of determining the display order according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0016] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 Schematic diagram of an application scenario of an intelligent archive management system based on a knowledge graph according to some embodiments of this specification. Figure 1 As shown, the scenario 100 involved in the knowledge graph-based intelligent archive management system may include a processor 110, a storage device 120, a network 130, and a user terminal 140.

[0019] In some embodiments, the processor 110 may be used to process information and / or data related to the application scenario 100. For example, the processor 110 may determine a network graph based on at least one data source. In some embodiments, the processor 110 may be local or remote. For example, the processor 110 may access information and / or data stored in the storage device 120 or the user terminal 140 via the network 130. For another example, the processor 110 may be directly connected to the storage device 120 or the user terminal 140 to access the stored information and / or data.

[0020] The processor 110 may be used to determine a knowledge graph for at least one data source. In some embodiments, the processor may also determine a display range and a display order. The knowledge graph may correspond to at least one data source. The archive may include multiple forms of data sources.

[0021] The storage device 120 can be used to store data and / or instructions related to the intelligent management of archives based on the knowledge graph. In some embodiments, the storage device 120 can store data obtained / acquired from the user terminal 140. In some embodiments, the storage device 120 can store data and / or instructions used by the processor 110 to execute or use to complete the exemplary method described in this application. In some embodiments, the storage device 120 can be implemented on a cloud platform. After the processor 110 determines the knowledge graph, it can send it to the storage device 120 via the network and store the knowledge graph in the storage device 120.

[0022] In some embodiments, the storage device 120 may be connected to the network 130 to communicate with one or more components of the scene 100 (e.g., the processor 110, the user terminal 140). One or more components of the scene 100 may access data or instructions stored in the storage device 120 via the network 130. In some embodiments, the storage device 120 may be directly connected to or communicate with one or more components of the scene 100 (e.g., the processor 110, the user terminal 140). In some embodiments, the storage device 120 may be part of the processor 110. In some embodiments, the storage device 120 may be a separate memory. The storage device 140 may store historical data, for example, a machine learning model, historical data, etc.

[0023] Network 130 may facilitate the exchange of information and / or data. In some embodiments, one or more components of scene 100 (eg, processor 110, user terminal 140) may send information and / or data to other components of scene 100 via network 130.

[0024] The user terminal 140 may be a device terminal used by the user. The user terminal 140 may be a computer, a mobile phone, a tablet or other device. The user terminal 140 may include a display for displaying the obtained display order. In some embodiments, the user terminal 140 may include an input terminal for inputting the user's current search content.

[0025] Figure 2 It is a module diagram of the knowledge graph-based intelligent archive management system shown in some embodiments of this specification.

[0026] like Figure 2As shown, the archive intelligent management system 200 based on the knowledge graph may include a first acquisition module 210, a graph determination module 220, a second acquisition module 230, and a sequence determination module 240.

[0027] The first acquisition module 210 is used to acquire at least one data source.

[0028] The graph determination module 220 is used to determine the knowledge graph based on the data source, the knowledge graph includes nodes and edges, the nodes include at least one main node and at least one secondary node, the edges include first-class edges and second-class edges, the attributes of the first-class edges include the similarity between two nodes, and the attributes of the second-class edges represent the master-slave relationship between the two connected nodes.

[0029] The second acquisition module 230 is used to obtain the current user characteristics and the current search content, and determine the display range through the knowledge graph based on the current user characteristics and the current search content.

[0030] In some embodiments, the display range includes a first range and a second range, and the second acquisition module 230 further includes: a keyword determination module, used to determine the current search keyword based on the current search content; a first range determination module, used to take the content corresponding to the nodes that meet the first range condition as the first range, and the first range condition is that the similarity between the node and the current search keyword exceeds a first similarity threshold; a second range determination module, used to take the content corresponding to the nodes that meet the second range condition as the second range, and the second range condition is all secondary nodes connected to all first nodes in the first range by second-type edges.

[0031] In some embodiments, the display range further removes the nodes in the third range from the nodes in the first range and the second range, and the second acquisition module 230 further includes: a label determination module, which is used to determine the current user label through a label determination model based on the current user feature; a vector determination module, which is used to determine the node feature vector based on the nodes in the first range and the second range; a comparison module, which is used to compare the similarity between the current user label and the node feature vector; a third range determination module, which is used to determine the corresponding secondary node when the similarity between the node feature vector and the current user label is higher than a second similarity threshold, and take the corresponding secondary node corresponding to the corresponding secondary node and the collection of all its subordinate nodes as the third range.

[0032] The order determination module 240 is used to determine related users based on the current user characteristics and the current search content, and to determine a display order based on the current user characteristics and related user characteristics.

[0033] In some embodiments, the sequence determination module 240 further includes: a candidate user determination module, used to determine the candidate user based on the current search content and historical user characteristics; a similarity determination module, used to determine the similarity between the current user and the candidate user; a related user determination module, used to determine the related user based on the similarity between the current user and the candidate user; a display module, used to determine the display order based on the similarity between the current user and the related user, the user characteristics of the related user, the current search keyword, and the display range.

[0034] It should be understood that the above modules are only simple examples of the relevant modules mainly involved in this specification, and do not represent the display of all relevant contents of this application. There are also some modules and units that are not shown in this module diagram, and they are not illustrated one by one here. Moreover, the above modules and units are not completely independent, and may also be cross-involved.

[0035] Figure 3 300 is an exemplary flow chart of a method for intelligent archive management based on a knowledge graph according to some embodiments of this specification. Process 300 may be executed by a processor. Figure 3 As shown, process 300 may include the following steps:

[0036] Step 310: Obtain at least one data source.

[0037] The data source may include a website page, an article, or a video. At least one data source is obtained as an archive, and tags are added based on the data source for later selection. The data source may be obtained through a network connection to a database or server.

[0038] Step 320, determine a knowledge graph based on at least one data source.

[0039] A knowledge graph may refer to a graphical structure of at least one data source content and the relationship between data sources. A knowledge graph includes nodes and edges. There may be multiple knowledge graphs.

[0040] Each node in the knowledge graph includes at least one main node and at least one secondary node. The name of each node can correspond to a keyword of a data source. The keyword can be a word / term in the title of the data source or a word / term with the highest frequency in the data source. For example, for the article "How to Stir-fry Braised Pork", "Stir-fry Braised Pork" can be used as the node name.

[0041] Each master node may include at least one level of secondary nodes, i.e., a first-level secondary node. In some embodiments, a first-level secondary node may also include at least a second-level secondary node. Each first-level secondary node may correspond to at least one step or part included in the master node. Each second-level secondary node may correspond to at least one step or part of its upper-level node (i.e., a first-level secondary node).

[0042] Each node includes node attributes. The attributes of the main node include the data source form of the corresponding main node, the geographical location of the release, etc. The data source form includes video, text, pictures, etc. The attributes of each sub-node can include the proportion of the content corresponding to it in the data source to the content corresponding to the previous node, as well as the corresponding content size of each sub-node. For example, the proportion of the number of minutes corresponding to the first-level sub-node "Boil in Water" to the total number of minutes of the main node video "Stir-fried Braised Pork".

[0043] Every two nodes are connected by an edge. In some embodiments, edges of different levels can be connected. For example, each main node can be connected by an edge, and each primary secondary node and each main node can be connected by an edge. The edge can include a first-class edge and a second-class edge. The first-class edge refers to the connection between two nodes whose similarity exceeds the node similarity threshold. The second-class edge refers to the connection between two nodes that can form a containment and contained relationship. The attributes of the first-class edge may include the similarity between the two nodes. The similarity between the two nodes may refer to the degree of similarity of the semantics, structure, and / or attributes of the two node names. The node similarity threshold can be determined manually. The attributes of the second-class edge can represent the master-slave relationship between the two connected nodes.

[0044] Step 330, obtain the current user characteristics and the current search content, and determine the display range through the knowledge graph based on the current user characteristics and the current search content.

[0045] User characteristics may refer to the user's basic information, the user's working hours, browsing history, click behavior, etc. Click behavior may include clicks based on recommendations, active clicks, dwell time, etc. The user's basic characteristics may refer to the user's age, the user's geographical location, gender, hobbies, etc. The current user characteristics may refer to the user characteristics of the currently retrieved user. User characteristics may be obtained by obtaining user registration information and website information. The current user may refer to the object that is currently being retrieved or is about to be pushed. The current user characteristics may refer to the user characteristics of the current user.

[0046] In some embodiments, the current search keyword is determined based on the user's current search content, and the display range is determined through the knowledge graph based on the current search keyword and the current user characteristics. The display range may refer to the content corresponding to the node in the knowledge graph that is finally displayed to the user. The display range may include a first range and a second range. In some embodiments, the content corresponding to the node that meets the first range condition is used as the first range. In some embodiments, the content corresponding to the node that meets the second range condition is used as the second range. The first range condition may be that the similarity between the node and the search keyword exceeds the first similarity threshold. In some embodiments, the first similarity threshold may be the same as the node similarity threshold. Among them, the nodes within the first range may be primary nodes and / or secondary nodes. For example, the user's search keyword is "make braised pork", which may correspond to the node name "fry braised pork", and all nodes connected to "fry braised pork" through the first type of edge (for example, "cook braised pork") are used as the first range. The second range condition may be all secondary nodes connected to all first nodes within the first range by the second type of edge.

[0047] In some embodiments, the display range may also be a collection of nodes in the first range and the second range minus the nodes in the third range. In some embodiments, the user tag is determined based on the user feature, the similarity between the user tag and the nodes in the first range and the second range is compared, and the third range is further determined based on the similarity. The third range is a collection of nodes corresponding to content that the user is already familiar with.

[0048] In some embodiments, user tags are determined by a tag determination model based on user characteristics. User tags may refer to keywords corresponding to content that the user is already familiar with. For example, user tags may be words that are the same or similar to node names in the knowledge graph.

[0049] The label determination model can be a machine learning model, such as a recurrent neural network, Transformer, etc. The label determination model is used to capture the temporal characteristics of user behavior. The label determination model includes a temporal determination layer and a label determination layer. The input of the temporal determination layer is user characteristics including the user's basic information, the user's working hours, browsing history, click behavior, and the user's geographic location, and the output is a user feature temporal sequence. For the user feature temporal sequence, a sliding window method is used to extract subsequences. The feature temporal sequence in the sliding window is used as the input of the label determination layer, and the label related to the window can be output, that is, the label of the content that the current user is already familiar with can be determined.

[0050] The label determination model can be obtained through training samples. The training samples are obtained through historical data. The training samples can be historical user features, and the trained labels are the cumulative time series of historical users browsing content.

[0051] In some embodiments, the current user tag is obtained through a tag determination model based on the current user characteristics.

[0052] The current user tag can be used to determine the content that the user is already familiar with.

[0053] In some embodiments, for nodes within the first range and the second range, the nodes can be represented as node feature vectors through a text embedding model (such as Word2Vec, BERT, etc.) or a graph embedding model (such as GraphSAGE, DeepWalk, etc.) as the corresponding feature representation.

[0054] In some embodiments, cosine similarity or other similarity measurement methods may be used to compare the similarity between the current user tag and the node feature vector.

[0055] In some embodiments, when the similarity between the node feature vector and the current user tag is higher than the corresponding second similarity threshold, the corresponding secondary node is determined, and the corresponding secondary node corresponds to the upper node and the collection of all its lower nodes as the third range. The second similarity threshold can correspond to the secondary node attribute, the node and the user tag similarity, and the corresponding preset relationship can be manually determined. The higher the similarity between the node and the user tag, the higher the proportion in the corresponding secondary node attribute, and the lower the second similarity threshold can be.

[0056] For example, the user wants to search for "how to stew braised pork", and the steps of stewing braised pork include the selection of meat, blanching meat, the selection of braised soup, and the process of stewing meat. All nodes containing "stew braised pork" and "make braised pork" are taken as the first scope, and the secondary nodes A-1 "blanching meat" and A-2 "blanching meat" contained in the main node A "stew braised pork" and the main node B "make braised pork" are taken as the second scope. Further, the user tag is "blanching meat", and the proportion of the attribute of the secondary node A-1 "blanching meat" contained in the main node A "stew braised pork" is 60%, and the proportion of the attribute of the secondary node A-2 "blanching meat" contained in the main node B "make braised pork" is 90%, and the second similarity threshold is 65%, then the main node B and the secondary node B-1 contained in it are both taken as the third scope. Remove the main node B and all its subordinate secondary nodes from the first scope and the second scope as the display scope.

[0057] In some cases, there is a larger description of the content to be searched, and the results at this time cannot meet our search requirements, and we need to further narrow the scope manually for another search. However, through some embodiments of the present application, when selecting some nodes in the knowledge graph, the content that the user already knows or is familiar with can be filtered out, so as to provide accurate push to the user.

[0058] In some embodiments, the node name may also be iteratively updated according to the word name in the current user tag corresponding to the node within the third range.

[0059] Step 340: determine related users based on the current user characteristics and the current search content, and determine the display order based on the current user characteristics and the related user characteristics.

[0060] For details on determining the display order, see Figure 4 Related content.

[0061] In some embodiments of this specification, by establishing a knowledge graph, data sources and other archives are integrated and associated in an automated manner to form a graph structure representing entities and relationships, which is conducive to better understanding and mining the connections and meanings between data.

[0062] Figure 4 It is an exemplary schematic diagram of determining the display order according to some embodiments of this specification. Process 400 may be executed by a processor.

[0063] Related users may refer to users related to the current user based on the search keyword. In some embodiments, related users may refer to users who have searched for the current search keyword and have similar basic features to the current user. Display order may refer to the arrangement sequence of data sources recommended for the current user.

[0064] In some embodiments, historical user features 420 are obtained, and historical user tags 421 are determined based on the historical user features 420. The process of obtaining historical user tags can refer to the process of obtaining current user tags. In some embodiments, based on the current search keyword 411 and the historical user tags 421, cosine similarity or other similarity measurement methods are used to determine the similarity between the current search keyword 411 and the historical user tags 421, and the historical users whose similarity between the current search keyword 411 and the historical user tags 421 is greater than a third similarity threshold are determined as candidate users 430. The current search keyword 411 can be determined by the current search content 410, and the related information determined can refer to Figure 3 Detailed content. The third similarity threshold can be set manually. Historical users can refer to users who have had network behaviors (for example, searching, browsing, clicking, etc.) in big data. Candidate users refer to users who have had network behaviors on the current search content. First, based on the current search keyword, the users who have searched for the current keyword can be determined to narrow the scope of related users. Unless otherwise specified in this manual, related user features, candidate user features, and historical user features can all refer to corresponding user features, and the acquisition methods can refer to the acquisition method of current user features.

[0065] In some embodiments, the related user 460 may be determined based on the similarity 450 between the current user 440 and the candidate user 430. In some embodiments, the historical candidate user feature time series sequence of the candidate user may be determined through the time series determination layer of the tag determination model based on the candidate user feature, and the similarity 450 between the current user and the candidate user may be determined through the similarity determination model based on the historical candidate user feature time series sequence and the current user feature time series sequence, and the candidate user whose similarity is greater than the fourth similarity threshold may be regarded as the related user. The acquisition method and content of the candidate user feature may refer to the acquisition method and content of the user feature.

[0066] In some embodiments, based on the similarity 450 between the current user and related users, the user characteristics 470 of the related users, the current search keywords 411, and the display range 471, a sequential determination model is used to determine the click sequence of the current user on the data source corresponding to the node feature vector within the display range, and the click sequence is used as the display order 480.

[0067] The sequential determination model may be a machine learning model and may be obtained through training.

[0068] By analyzing the similarities between users, the current user's click behavior can be predicted based on the existing click behavior of similar users based on the current search keywords, and personalized recommendations can be provided to each user to better meet the user's needs and interests. By collecting and analyzing the user's historical behavior and rating data, the system can more accurately understand the user's likes and preferences and improve the accuracy of recommendations. Based on the current user characteristics and related user characteristics, the display order of information can be determined, which can make it easier for users to find content of interest, and can provide users with smarter and more personalized archive management services, improve user experience and efficiency, and improve user browsing efficiency and satisfaction.

[0069] In some embodiments, the user's working hours may correspond to the data source form of the master node. The user characteristics may be used to know whether the user will choose to browse data in a specific data source form at a specific time (e.g., working hours). In some embodiments, the user's geographical location may correspond to the geographical location published by the data source. In some embodiments, the basic information in the relevant user characteristics and the geographical location may be assigned a higher weight as an important reference for the display order.

[0070] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced may be any one or a combination of the above, or any other beneficial effects that may be obtained.

[0071] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0072] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0073] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some embodiments currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0074] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0075] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0076] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0077] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for intelligent archive management based on knowledge graph, characterized in that: The method comprises: Obtain at least one data source; Determine a knowledge graph based on the at least one data source, the knowledge graph comprising nodes and edges, the nodes comprising at least one primary node and at least one secondary node, the edges comprising a first-class edge and a second-class edge, the attributes of the first-class edge comprising a similarity between two nodes, and the attributes of the second-class edge representing a master-slave relationship between two connected nodes; Acquire current user characteristics and current search content, and determine a display range through the knowledge graph based on the current user characteristics and the current search content; The related users are determined based on the current user characteristics and the current search content, and the display order is determined based on the current user characteristics and the related user characteristics.

2. The intelligent archive management method based on knowledge graph according to claim 1 is characterized in that: The determining of the display order based on the current user characteristics and the related user characteristics further includes: Determine candidate users based on the current search content and historical user characteristics; Determining the similarity between the current user and the candidate user; Determine the relevant user based on the similarity between the current user and the candidate user; The display order is determined based on the similarity between the current user and related users, user characteristics of the related users, the current search keyword, and the display range.

3. The intelligent archive management method based on knowledge graph according to claim 2 is characterized in that: The display range includes a first range and a second range, and the determining the display range through the knowledge graph based on the current user feature and the current search content includes: Determine the current search keyword based on the current search content; The content corresponding to the node that meets the first range condition is taken as the first range, wherein the first range condition is that the similarity between the node and the current search keyword exceeds a first similarity threshold; The content corresponding to the nodes satisfying the second range condition is taken as the second range, where the second range condition is all secondary nodes connected to all first nodes in the first range by second-type edges.

4. The intelligent archive management method based on knowledge graph according to claim 3 is characterized in that: The display range is also a collection of nodes in the first range and the second range excluding the nodes in the third range, and determining the third range includes: Determine a current user tag through a tag determination model based on the current user feature; Determine a node feature vector based on nodes within the first range and the second range; Comparing the similarity between the current user tag and the node feature vector; When the similarity between the node feature vector and the current user tag is higher than a second similarity threshold, a corresponding secondary node is determined, and a collection of an upper node corresponding to the corresponding secondary node and all its lower nodes is taken as a third range.

5. An intelligent archive management system based on knowledge graph, characterized in that: The system comprises: A first acquisition module, used to acquire at least one data source; a graph determination module, configured to determine a knowledge graph based on the at least one data source, wherein the knowledge graph includes nodes and edges, wherein the nodes include at least one primary node and at least one secondary node, and the edges include first-class edges and second-class edges, wherein the attributes of the first-class edges include the similarity between two nodes, and the attributes of the second-class edges represent the master-slave relationship between the two connected nodes; A second acquisition module is used to acquire current user characteristics and current search content, and determine a display range through the knowledge graph based on the current user characteristics and the current search content; The sequence determination module is used to determine related users based on the current user characteristics and the current search content, and to determine the display sequence based on the current user characteristics and related user characteristics.

6. The intelligent archive management system based on knowledge graph according to claim 5 is characterized in that: The sequence determination module further includes: A candidate user determination module, used to determine candidate users based on the current search content and historical user characteristics; A similarity determination module, used to determine the similarity between the current user and the candidate user; A related user determination module, configured to determine the related user based on the similarity between the current user and the candidate user; The display module is used to determine the display order based on the similarity between the current user and related users, the user characteristics of the related users, the current search keywords, and the display range.

7. The intelligent archive management system based on knowledge graph according to claim 6 is characterized in that: The display range includes a first range and a second range, and the second acquisition module further includes: A keyword determination module, used to determine the current search keyword based on the current search content; A first range determination module, configured to take the content corresponding to the node satisfying the first range condition as the first range, wherein the first range condition is that the similarity between the node and the current search keyword exceeds a first similarity threshold; The second range determination module is used to take the content corresponding to the nodes satisfying the second range condition as the second range, wherein the second range condition is all the secondary nodes connected to all the first nodes in the first range by the second type of edges.

8. The intelligent archive management system based on knowledge graph according to claim 7 is characterized in that: The display range further removes the nodes in the third range from the nodes in the first range and the second range, and the second acquisition module further includes: A tag determination module, used to determine a current user tag through a tag determination model based on the current user characteristics; A vector determination module, used to determine a node feature vector based on nodes within the first range and the second range; A comparison module, used to compare the similarity between the current user tag and the node feature vector; The third range determination module is used to determine the corresponding secondary node when the similarity between the node feature vector and the current user tag is higher than the second similarity threshold, and take the collection of the upper node corresponding to the corresponding secondary node and all its lower nodes as the third range.

9. A knowledge graph-based intelligent archive management device, comprising a processor and a memory; the memory is used to store instructions, characterized in that: When the instruction is executed by the processor, the device implements the intelligent archive management method based on knowledge graph as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer runs the intelligent archive management method based on knowledge graph as described in any one of claims 1 to 4.

Images