Method and device for automatically generating patent intelligence based on knowledge graph

Abstract

The invention belongs to the technical field of patent intelligence analysis, and particularly relates to an automatic patent intelligence generation method and device based on a knowledge graph. The method comprises the following steps: S1, acquiring an aircraft structure knowledge graph stored through a tree structure; s2, determining the position of a structure node to be processed; s3, grouping the structure nodes of the structure tree, and determining a keyword set of each group; s4, enabling each keyword set to correspond to different positions of the patent text, and constructing a combined retrieval strategy for the patent text; s5, obtaining a single retrieval result of each structure node; s6, determining a composite retrieval result; and S7, according to the patent intelligence analysis template, extracting patent contents from the composite retrieval result corresponding to each structure node and the substructure node thereof, and constructing a patent intelligence tree. Omnibearing patent information retrieval and generation of the aircraft structure are realized, and the coverage range and analysis accuracy of patent information are improved.

Description

Technical Field

[0001] The present application belongs to the field of patent intelligence analysis technology, and in particular, relates to a method and device for automatically generating patent intelligence based on a knowledge graph. Background Art

[0002] At present, patent intelligence collection for aircraft usually requires providing keywords, then conducting patent searches, and extracting patent intelligence from the search results. However, when conducting patent searches, there are defects such as confusing search conditions, slow search efficiency, and low accuracy of search results. In addition, in the process of obtaining patent intelligence, the amount of patent data is large, and the correspondence between the obtained patent intelligence and the key technologies of the aircraft is unclear. Summary of the invention

[0003] In order to solve the above problems, the first aspect of the present application provides a method for automatically generating patent intelligence based on a knowledge graph, which mainly includes: Step S1, obtaining an aircraft structure knowledge graph stored in a tree structure; Step S2: determine the position of the initially selected structure node to be processed in the knowledge graph, and use the structure node and all its substructure nodes as the structure nodes to be processed; Step S3, dividing all structure nodes between the structure node to be processed and the root node into multiple groups according to the growth order of the tree structure, and constructing a keyword set for each group using the name of each structure node in each group as a keyword; Step S4, mapping each keyword set to different positions in the patent text to construct a combined search strategy for the patent text; Step S5, using the patent text retrieved by the combined search strategy as a single search result of the structure node to be processed; Step S6, combining the single search result of the structure node to be processed with the single search results of all its substructure nodes as the composite search result of the initially selected structure node to be processed; Step S7: construct an intelligence tree using the structure node to be processed and all its substructure nodes, extract patent content from the composite search results corresponding to each structure node and its substructure nodes according to the patent intelligence analysis template, and mount it on the structure node of the intelligence tree.

[0004] Preferably, step S3 further includes: The keywords are modified based on a pre-built term comparison dictionary, which is used to map aircraft terms to patent usage terms.

[0005] Preferably, step S4 further comprises: Step S41, the keywords of the structure node farthest from the root node of the structure knowledge graph are matched to the title of the patent text, the keyword set consisting of one or more structure nodes with the second farthest distance from the root node of the structure knowledge graph is matched to the abstract of the patent text, and the keyword set consisting of one or more structure nodes closest to the root node of the structure knowledge graph is matched to the description of the patent text; Step S42: The search strategies constructed by the multiple keyword sets are connected with each other using the relationship “and”, and the keywords in each keyword set are connected with the relationship “or”.

[0006] Preferably, step S6 further comprises: From the bottom up, for each structure node, the search data of all its child structure nodes are removed, and the remaining search data is used as the modified single search result of the structure node. The modified single search results of each structure node are combined as the composite search result.

[0007] Preferably, step S7 further comprises: Step S71: for each structure node A, determine the patent catalog of the structure node A and each sub-structure node B directly connected to the structure node A, wherein the patent catalog of the sub-structure node B directly connected to the structure node A is the set of patent catalogs of the sub-structure node B and all sub-nodes C of the sub-structure node B, and the patent catalog of the structure node A is extracted from the corrected single search result of the structure node A, and the patent catalog contains multiple patent records, and each patent record includes at least two fields: patent application date and patent publication country; Step S72: Based on the patent catalogs of the structure node A and each substructure node B directly connected to the structure node A, conduct patent technology composition analysis, annual patent application volume distribution analysis, and patent regional deployment distribution analysis.

[0008] The second aspect of the present application provides a patent intelligence automatic generation device based on knowledge graph, which mainly includes: An aircraft structure knowledge graph acquisition module is used to acquire an aircraft structure knowledge graph stored in a tree structure; A module for determining a structure node to be processed, used to determine the position of the initially selected structure node to be processed in the knowledge graph, and to take the structure node and all its substructure nodes as the structure nodes to be processed; A keyword set acquisition module is used to divide all structure nodes between the structure node to be processed and the root node into multiple groups according to the growth order of the tree structure, and construct a keyword set for each group using the name of each structure node in each group as a keyword; A combined search strategy formulation module is used to map each keyword set to different positions in the patent text to construct a combined search strategy for the patent text; A single search result collection module, used to use the patent text searched by the combined search strategy as a single search result of the structure node to be processed; A composite search result determination module, used for combining the single result of the structure node to be processed with the single search results of all its substructure nodes as the composite search result of the structure node to be processed that is initially selected; The intelligence tree generation module is used to construct an intelligence tree using the structure node to be processed and all its substructure nodes, extract patent content from the composite search results corresponding to each structure node and its substructure nodes according to the patent intelligence analysis template, and mount it on the structure node of the intelligence tree.

[0009] Preferably, the device further comprises: A keyword correction module is used to correct the keywords based on a pre-built word comparison dictionary, wherein the word comparison dictionary is used to map aircraft terms to patent usage terms.

[0010] Preferably, the combined search strategy formulation module includes: A keyword corresponding unit, used to correspond the keywords of the structure node farthest from the root node of the structure knowledge graph to the title of the patent text, correspond the keyword set consisting of one or more structure nodes with the second farthest distance from the root node of the structure knowledge graph to the abstract of the patent text, and correspond the keyword set consisting of one or more structure nodes closest to the root node of the structure knowledge graph to the description of the patent text; The search strategy automatic generation unit is used to connect the search strategies constructed by multiple keyword sets with each other using the relationship "and", and to connect the keywords in each keyword set with the relationship "or".

[0011] Preferably, the composite search result determination module includes: The deduplication processing unit is used to remove the search data of all substructure nodes of each structure node from the bottom up, and use the remaining search data as the modified single search result of the structure node. The modified single search results of each structure node are combined as the composite search result.

[0012] Preferably, the intelligence tree generation module includes: A patent catalog extraction unit is used to determine, for each structure node A, the patent catalog of the structure node A and each sub-structure node B directly connected to the structure node A, wherein the patent catalog of the sub-structure node B directly connected to the structure node A is the set of patent catalogs of the sub-structure node B and all sub-nodes C of the sub-structure node B, and the patent catalog of the structure node A is extracted from the corrected single search result of the structure node A, wherein the patent catalog contains multiple patent records, and each patent record includes at least two fields: patent application date and patent publication country; The data analysis unit is used to perform patent technology composition analysis, annual patent application volume distribution analysis, and patent regional deployment distribution analysis based on the patent catalog of the structure node A and each substructure node B directly connected to the structure node A.

[0013] This application realizes the comprehensive patent information retrieval and generation of aircraft structures, improving the coverage and analysis accuracy of patent information. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flowchart of a preferred embodiment of the method for automatically generating patent intelligence based on knowledge graph of the present application.

[0015] Figure 2 This application Figure 1 Schematic diagram of the aircraft structure knowledge graph structure of the illustrated embodiment.

[0016] Figure 3 This application Figure 1 Schematic diagram of analysis results of patent technology composition of the illustrated embodiment. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical scheme and advantages of the implementation of this application clearer, the technical scheme in the implementation of this application will be described in more detail in combination with the drawings in the implementation of this application. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described implementation is a part of the implementation of this application, not all of the implementations. The implementation described below with reference to the drawings is exemplary and is intended to be used to explain this application, and cannot be understood as a limitation on this application. Based on the implementation in this application, all other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. The implementation of this application is described in detail below in combination with the drawings.

[0018] The first aspect of the present application provides a method for automatically generating patent intelligence based on a knowledge graph, such as Figure 1 As shown, it mainly includes: Step S1, obtaining an aircraft structure knowledge graph stored in a tree structure.

[0019] Figure 2 A simplified schematic diagram of the aircraft structure knowledge graph is given. Figure 2 In the structure tree, the fixed-wing aircraft is the root node, which can also be called the first-level node. The fuselage, wings, and engines are the second-level nodes. The skin, frame, and cabin are the third-level nodes. The 7075 aluminum alloy material, carbon fiber material, truss frame, box frame, torsional stiffness, etc. are the fourth-level nodes. The yield strength parameters, density parameters, etc. are the fifth-level nodes, which are also the last-level nodes. In the aircraft structure knowledge graph, the last-level node is the attribute parameter of the previous-level node, that is, the yield strength ≥310MPa is the strength attribute parameter of the 7075 aluminum alloy material or carbon fiber material.

[0020] Step S2: determine the position of the initially selected structure node to be processed in the knowledge graph, and use the structure node and all its substructure nodes as the structure nodes to be processed.

[0021] The structure nodes to be processed are usually specified by the user. One or more nodes can be specified. For example, Figure 2 The skin in the structure node is used as the structure node to be processed. When the system performs analysis, although the user only specifies the skin, all the child nodes of the skin need to be analyzed as well. Figure 2 The 7075 aluminum alloy material, carbon fiber material, etc. are also used as structural nodes to be processed.

[0022] Step S3: Divide all structure nodes between the structure node to be processed and the root node into multiple groups according to the growth order of the tree structure, and construct a keyword set for each group using the name of each structure node in each group as a keyword.

[0023] This step processes each structure node to be processed separately. For example, for the structure node selected above, all structure nodes between it and the root node fixed-wing aircraft include skin, fuselage, and fixed-wing aircraft. The above three nodes are divided into multiple groups. For example, skin is the first group. In this group, skin is located in the keyword set of the first group as a keyword. Fuselage and fixed-wing aircraft are the second group. In this group, fuselage and fixed-wing aircraft are located in the keyword set of the second group as keywords.

[0024] For another example, for the 7075 aluminum alloy material, which is a structural node to be processed, all structural nodes between it and the root node fixed-wing aircraft include 7075 aluminum alloy, skin, fuselage, and fixed-wing aircraft. The above four nodes are divided into multiple groups. For example, 7075 aluminum alloy is the first group, in which 7075 aluminum alloy is located in the keyword set of the first group as a keyword, skin and fuselage are the second group, in which skin and fuselage are located in the keyword set of the second group as keywords, and fixed-wing aircraft is the third group, in which fixed-wing aircraft is located in the keyword set of the third group as a keyword.

[0025] In some optional implementations, step S3 further includes: The keywords are modified based on a pre-built term comparison dictionary, which is used to map aircraft terms to patent usage terms.

[0026] Although a set of keywords is obtained in step S3, these keywords may not be applicable to patent search or may be too simple and cannot cover accurate and comprehensive characterization of relevant structures, such as Figure 2 In the patent terminology, in addition to the airfoil, keywords such as wing configuration can also be used to represent it. For example, aerodynamic force can also be expanded to keywords such as flow field pressure, lift, and drag. This embodiment first constructs a word comparison dictionary, which contains multiple mapping relationships. Each mapping relationship includes two feature sets that can be mapped to each other. The first feature set uses special terms in aircraft design, and the second feature set uses special terms in patent writing. The keywords in the two feature sets have a certain overlap. Afterwards, based on the word comparison dictionary, the aircraft term is corrected to one or more patent usage terms.

[0027] In some optional embodiments, before modifying the keyword, the structural name matching degree between each patent usage term and the parent node or child node of the structural node where the keyword is located is calculated for each patent usage term mapped to the keyword in the word reference dictionary, and only the patent usage terms with a matching degree below a threshold are used to modify the keyword.

[0028] As mentioned above, the keyword aerodynamics is mapped to multiple patent usage terms, such as flow field pressure, lift, drag, etc. If in the aircraft structure knowledge graph, the aerodynamic structure node contains sub-nodes such as lift and drag, after calculation in this embodiment, it is obvious that the patent usage term lift has a 100% match with the sub-node lift node of the aerodynamic structure node, and the patent usage term drag has a 100% match with the sub-node drag node of the aerodynamic structure node. Therefore, these two terms need to be shielded, and on the basis of the keyword aerodynamics, only the patent usage term flow field pressure is added as a keyword.

[0029] In this embodiment, the matching degree calculation can be performed using cosine similarity, Jaccard similarity coefficient, etc. The threshold used in the comparison process can be manually modified, and the value is usually between 60% and 90%.

[0030] Step S4: correspond each keyword set to different positions in the patent text to construct a combined search strategy for the patent text.

[0031] As mentioned above, the keywords of all the structural nodes between the structural node to be processed and the root node are grouped. These keywords may appear in different positions of the patent text, such as the title, abstract, and specification. Step S4 is used to match the keywords with the positions, thereby constructing a combined search strategy.

[0032] In some optional implementations, step S4 further includes: Step S41, the keywords of the structure node farthest from the root node of the structure knowledge graph are matched to the title of the patent text, the keyword set consisting of one or more structure nodes with the second farthest distance from the root node of the structure knowledge graph is matched to the abstract of the patent text, and the keyword set consisting of one or more structure nodes closest to the root node of the structure knowledge graph is matched to the description of the patent text; Step S42: The search strategies constructed by the multiple keyword sets are connected with each other using the relationship “and”, and the keywords in each keyword set are connected with the relationship “or”.

[0033] In step S41, the structural nodes that are farther from the root node, that is, the structural nodes that are closer to the node to be processed, the patents related to these nodes are the most needed patents, and the relevant keywords should usually appear in the title. For example, for the skin, a structural node to be processed given in the above example, if the patent name contains skin, then this type of patent is usually what we need. However, the appearance of skin in the title does not mean that this type of patent is related to the aircraft, so other keywords are needed for further limitation. For example, in step S41, the keywords of the structural nodes closest to the root node are mapped to the specification position of the patent text, and the keywords of the nodes between the root node and the structural node to be processed are mapped to the abstract position of the patent text, such as mapping the parent node fuselage of the skin to the abstract position, and mapping the parent node fixed-wing aircraft of the fuselage to the specification position.

[0034] Then in step S42, such a combination of keywords is connected to form a combined search strategy. For example, a combined search strategy expression is: TI=(skin OR covering layer) AND AB=(fuselage) AND DES=(fixed-wing aircraft). In this expression, TI is the title, AB is the abstract, DES is the specification, OR represents an OR connection relationship, and AND represents an AND connection relationship.

[0035] It is understandable that the above example only provides one combination of the combined search strategy. In actual use, certain keywords can also be mapped to other positions or combined positions in the patent text. The combined position here can, for example, be to set the body to appear in the title or abstract.

[0036] Step S5: taking the patent text retrieved by the combined search strategy as a single search result of the structural node to be processed.

[0037] As shown in step S2, in addition to the given structure node to be processed, its child nodes are also used as structure nodes to be processed. Each structure node is searched using the corresponding combined search strategy to obtain the search results of the corresponding structure node and marked as a single search result. For example, for the structure node of skin, 10,000 patent data were searched, for its child structure node 7075 aluminum alloy, 3,000 patent data were searched, and for the child structure node carbon fiber, 20,000 patent data were searched.

[0038] Step S6: Combining the single search result of the structure node to be processed with the single search results of all its sub-structure nodes as the composite search result of the initially selected structure node to be processed.

[0039] In this step, the search results of all the structural nodes to be processed are summarized as the composite search results of the initially selected structural nodes. That is, in the above example, the single search result of the skin, the single search result of the 7075 aluminum alloy, and the single search result of the carbon fiber are collectively used as the composite search result of the skin.

[0040] In some optional implementations, step S6 further includes: From the bottom up, for each structure node, the search data of all its child structure nodes are removed, and the remaining search data is used as the modified single search result of the structure node. The modified single search results of each structure node are combined as the composite search result.

[0041] In this embodiment, during the compounding process of a single search result, duplicate patents need to be eliminated. For example, if the initially selected structure node to be processed is the skin, then the 10,000 search results for the skin partially overlap with the 3,000 search results for 7075 aluminum alloy, and partially overlap with the 20,000 search results for carbon fiber. Therefore, it is necessary to remove duplicate data from the 10,000 data for the skin. Figure 2 First, based on the search results of 7075 aluminum alloy and carbon fiber, the search results of skin are corrected; based on the search results of truss structure and box structure, the search results of frame are corrected; based on the search results of cockpit and cargo hold, the search results of cabin are corrected; finally, based on the search results of skin, aluminum alloy, carbon fiber, truss structure, box structure, frame, cockpit, cargo hold and cabin, the search results of fuselage are corrected.

[0042] Step S7: construct an intelligence tree using the structure node to be processed and all its substructure nodes, extract patent content from the composite search results corresponding to each structure node and its substructure nodes according to the patent intelligence analysis template, and mount it on the structure node of the intelligence tree.

[0043] With the search results, all the structural nodes to be processed can be analyzed.

[0044] For example, for the initially selected fuselage structure node, step S6 gives the composite search results of the fuselage, as well as the composite search results of its three substructure nodes, namely the composite search results of the skin, the composite search results of the frame, the composite search results of the cabin section, and these search results can form the patent information of the fuselage and mount it on the fuselage structure node of the information tree. Similarly, for the initially selected fuselage structure node, its extended skin substructure node can be constructed based on the composite search results of the skin, the composite search results of the aluminum alloy in the skin substructure node, and the composite search results of the carbon fiber, and the patent information of the skin can be mounted on the skin structure node of the information tree. In this way, the patent information of all the structural nodes to be processed can be constructed to form a patent information tree for the initially selected structure to be processed.

[0045] In step S1, the present application automatically constructs a patent intelligence tree based on the aircraft structure knowledge graph based on the initially selected structure nodes to be processed. The architecture of the patent intelligence tree here is a part of the aircraft structure knowledge graph, and is a relatively complete part. For example, for the fuselage, all its child nodes are consistent with the aircraft structure knowledge graph. In an alternative implementation, in order to reconstruct a new patent intelligence tree from the aircraft structure knowledge graph, it is also possible to initially select multiple new structure trees with continuous connection relationships in step S1 to directly construct a new patent intelligence tree. For example, the first-level node fuselage and the second-level nodes skin and frame are selected. At this time, the system will automatically ignore the second-level node cabin and only use the skin and frame as the second-level nodes of the fuselage. The patent intelligence formed only shows the patent proportion of the skin and frame. Of course, for the skin and frame, the system still regards them as the initially selected structure nodes to be processed and continues to analyze their child nodes.

[0046] In some optional implementations, step S7 further includes: Step S71: for each structure node A, determine the patent catalog of the structure node A and each sub-structure node B directly connected to the structure node A, wherein the patent catalog of the sub-structure node B directly connected to the structure node A is the set of patent catalogs of the sub-structure node B and all sub-nodes C of the sub-structure node B, and the patent catalog of the structure node A is extracted from the corrected single search result of the structure node A, and the patent catalog contains multiple patent records, and each patent record includes at least two fields: patent application date and patent publication country; Step S72: Based on the patent catalogs of the structure node A and each substructure node B directly connected to the structure node A, conduct patent technology composition analysis, annual patent application volume distribution analysis, and patent regional deployment distribution analysis.

[0047] This embodiment provides a detailed process of generating patent intelligence based on a template. For example, Figure 2As shown, the structural node A here is the fuselage, the structural node B is the skin, the frame, and the cabin, and the structural node C is aluminum alloy and carbon fiber. First, the patent catalog of the skin contains all the retrieved patents of the skin, aluminum alloy, and carbon fiber, that is, the composite search results of the skin, for example, 500 items. Similarly, the patent catalog of the frame includes the patents in the composite search results of the frame, for example, 600 items. The patent catalog of the cabin includes the patents in the composite search results of the cabin, for example, 700 items. The search results of the fuselage include the patents in the revised single search results of the fuselage, for example, 200 items, that is, the number of patents after removing the composite search results of the skin, the composite search results of the frame, and the composite search results of the cabin from the 2000 composite search results of the fuselage. This makes the number of patent distribution analysis performed in step S72 more accurate, and the revised single search results of the fuselage can be used as other patent data in the fuselage excluding the skin, frame, and cabin, such as Figure 3 shown.

[0048] Other patent application distribution analysis and regional distribution analysis are similar to the above structural composition analysis process. They can be directly obtained based on the application date field and application country field in the patent catalog using the built-in functions of the Excel table.

[0049] The second aspect of the present application provides a patent intelligence automatic generation device based on a knowledge graph corresponding to the above method, which mainly includes: An aircraft structure knowledge graph acquisition module is used to acquire an aircraft structure knowledge graph stored in a tree structure; A module for determining a structure node to be processed, used to determine the position of the initially selected structure node to be processed in the knowledge graph, and to take the structure node and all its substructure nodes as the structure nodes to be processed; A keyword set acquisition module is used to divide all structure nodes between the structure node to be processed and the root node into multiple groups according to the growth order of the tree structure, and construct a keyword set for each group using the name of each structure node in each group as a keyword; A combined search strategy formulation module is used to map each keyword set to different positions in the patent text to construct a combined search strategy for the patent text; A single search result collection module, used to use the patent text searched by the combined search strategy as a single search result of the structure node to be processed; A composite search result determination module, used for combining the single result of the structure node to be processed with the single search results of all its substructure nodes as the composite search result of the structure node to be processed that is initially selected; The intelligence tree generation module is used to construct an intelligence tree using the structure node to be processed and all its substructure nodes, extract patent content from the composite search results corresponding to each structure node and its substructure nodes according to the patent intelligence analysis template, and mount it on the structure node of the intelligence tree.

[0050] In some optional embodiments, the device further comprises: A keyword correction module is used to correct the keywords based on a pre-built word comparison dictionary, wherein the word comparison dictionary is used to map aircraft terms to patent usage terms.

[0051] In some optional implementations, the combined search strategy formulation module includes: A keyword corresponding unit, used to correspond the keywords of the structure node farthest from the root node of the structure knowledge graph to the title of the patent text, correspond the keyword set consisting of one or more structure nodes with the second farthest distance from the root node of the structure knowledge graph to the abstract of the patent text, and correspond the keyword set consisting of one or more structure nodes closest to the root node of the structure knowledge graph to the description of the patent text; The search strategy automatic generation unit is used to connect the search strategies constructed by multiple keyword sets with each other using the relationship "and", and to connect the keywords in each keyword set with the relationship "or".

[0052] In some optional implementations, the composite search result determination module includes: The deduplication processing unit is used to remove the search data of all substructure nodes of each structure node from the bottom up, and use the remaining search data as the modified single search result of the structure node. The modified single search results of each structure node are combined as the composite search result.

[0053] In some optional implementations, the intelligence tree generation module includes: A patent catalog extraction unit is used to determine, for each structure node A, the patent catalog of the structure node A and each sub-structure node B directly connected to the structure node A, wherein the patent catalog of the sub-structure node B directly connected to the structure node A is the set of patent catalogs of the sub-structure node B and all sub-nodes C of the sub-structure node B, and the patent catalog of the structure node A is extracted from the corrected single search result of the structure node A, wherein the patent catalog contains multiple patent records, and each patent record includes at least two fields: patent application date and patent publication country; The data analysis unit is used to perform patent technology composition analysis, annual patent application volume distribution analysis, and patent regional deployment distribution analysis based on the patent catalog of the structure node A and each substructure node B directly connected to the structure node A.

[0054] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for automatically generating patent intelligence based on knowledge graph, characterized in that: include: Step S1, obtaining an aircraft structure knowledge graph stored in a tree structure; Step S2: determine the position of the initially selected structure node to be processed in the knowledge graph, and use the structure node and all its substructure nodes as the structure nodes to be processed; Step S3, dividing all structure nodes between the structure node to be processed and the root node into multiple groups according to the growth order of the tree structure, and constructing a keyword set for each group using the name of each structure node in each group as a keyword; Step S4, mapping each keyword set to different positions in the patent text to construct a combined search strategy for the patent text; Step S5, using the patent text retrieved by the combined search strategy as a single search result of the structure node to be processed; Step S6, combining the single search result of the structure node to be processed with the single search results of all its substructure nodes as the composite search result of the initially selected structure node to be processed; Step S7: construct an intelligence tree using the structure node to be processed and all its substructure nodes, extract patent content from the composite search results corresponding to each structure node and its substructure nodes according to the patent intelligence analysis template, and mount it on the structure node of the intelligence tree.

2. The method for automatically generating patent intelligence based on knowledge graph according to claim 1, characterized in that: Step S3 further includes: The keywords are modified based on a pre-built term comparison dictionary, which is used to map aircraft terms to patent usage terms.

3. The method for automatically generating patent intelligence based on knowledge graph according to claim 1, characterized in that: Step S4 further comprises: Step S41, the keywords of the structure node farthest from the root node of the structure knowledge graph are matched to the title of the patent text, the keyword set consisting of one or more structure nodes with the second farthest distance from the root node of the structure knowledge graph is matched to the abstract of the patent text, and the keyword set consisting of one or more structure nodes closest to the root node of the structure knowledge graph is matched to the description of the patent text; Step S42: connect the search strategies constructed by multiple keyword sets with each other using the relationship “and”, and connect the keywords in each keyword set with the relationship “or”.

4. The method for automatically generating patent intelligence based on knowledge graph according to claim 1, characterized in that: Step S6 further comprises: From the bottom up, for each structure node, the search data of all its child structure nodes are removed, and the remaining search data is used as the modified single search result of the structure node. The modified single search results of each structure node are combined as the composite search result.

5. The method for automatically generating patent intelligence based on knowledge graph according to claim 4, characterized in that: Step S7 further comprises: Step S71: for each structure node A, determine the patent catalog of the structure node A and each sub-structure node B directly connected to the structure node A, wherein the patent catalog of the sub-structure node B directly connected to the structure node A is the set of patent catalogs of the sub-structure node B and all sub-nodes C of the sub-structure node B, and the patent catalog of the structure node A is extracted from the corrected single search result of the structure node A, and the patent catalog contains multiple patent records, and each patent record includes at least two fields: patent application date and patent publication country; Step S72: Based on the patent catalogs of the structure node A and each substructure node B directly connected to the structure node A, conduct patent technology composition analysis, annual patent application volume distribution analysis, and patent regional deployment distribution analysis.

6. A patent information automatic generation device based on knowledge graph, characterized in that: include: An aircraft structure knowledge graph acquisition module is used to acquire an aircraft structure knowledge graph stored in a tree structure; A module for determining a structure node to be processed, used to determine the position of the initially selected structure node to be processed in the knowledge graph, and to take the structure node and all its substructure nodes as the structure nodes to be processed; A keyword set acquisition module is used to divide all structure nodes between the structure node to be processed and the root node into multiple groups according to the growth order of the tree structure, and construct a keyword set for each group using the name of each structure node in each group as a keyword; A combined search strategy formulation module is used to map each keyword set to different positions in the patent text to construct a combined search strategy for the patent text; A single search result collection module, used to use the patent text searched by the combined search strategy as a single search result of the structure node to be processed; A composite search result determination module, used for combining the single result of the structure node to be processed with the single search results of all its substructure nodes as the composite search result of the structure node to be processed that is initially selected; The intelligence tree generation module is used to construct an intelligence tree using the structure node to be processed and all its substructure nodes, extract patent content from the composite search results corresponding to each structure node and its substructure nodes according to the patent intelligence analysis template, and mount it on the structure node of the intelligence tree.

7. The patent information automatic generation device based on knowledge graph according to claim 6, characterized in that: The device also includes: A keyword correction module is used to correct the keywords based on a pre-built word comparison dictionary, wherein the word comparison dictionary is used to map aircraft terms to patent usage terms.

8. The patent information automatic generation device based on knowledge graph according to claim 6, characterized in that: The combined search strategy formulation module includes: A keyword corresponding unit, used to correspond the keywords of the structure node farthest from the root node of the structure knowledge graph to the title of the patent text, correspond the keyword set consisting of one or more structure nodes with the second farthest distance from the root node of the structure knowledge graph to the abstract of the patent text, and correspond the keyword set consisting of one or more structure nodes closest to the root node of the structure knowledge graph to the description of the patent text; The search strategy automatic generation unit is used to connect the search strategies constructed by multiple keyword sets with each other using the relationship "and", and to connect the keywords in each keyword set with the relationship "or".

9. The patent information automatic generation device based on knowledge graph according to claim 6, characterized in that: The composite search result determination module comprises: The deduplication processing unit is used to remove the search data of all substructure nodes of each structure node from the bottom up, and use the remaining search data as the modified single search result of the structure node. The modified single search results of each structure node are combined as the composite search result.

10. The patent information automatic generation device based on knowledge graph according to claim 9, characterized in that: The intelligence tree generation module includes: A patent catalog extraction unit is used to determine, for each structure node A, the patent catalog of the structure node A and each sub-structure node B directly connected to the structure node A, wherein the patent catalog of the sub-structure node B directly connected to the structure node A is the set of patent catalogs of the sub-structure node B and all sub-nodes C of the sub-structure node B, and the patent catalog of the structure node A is extracted from the corrected single search result of the structure node A, wherein the patent catalog contains multiple patent records, and each patent record includes at least two fields: patent application date and patent publication country; The data analysis unit is used to perform patent technology composition analysis, annual patent application volume distribution analysis, and patent regional deployment distribution analysis based on the patent catalog of the structure node A and each substructure node B directly connected to the structure node A.

Images