CN112364181A - Insurance product matching degree determination method and device - Google Patents
Insurance product matching degree determination method and device Download PDFInfo
- Publication number
- CN112364181A CN112364181A CN202011354996.8A CN202011354996A CN112364181A CN 112364181 A CN112364181 A CN 112364181A CN 202011354996 A CN202011354996 A CN 202011354996A CN 112364181 A CN112364181 A CN 112364181A
- Authority
- CN
- China
- Prior art keywords
- insurance
- node
- target
- product
- insurance product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000013598 vector Substances 0.000 claims abstract description 126
- 230000008569 process Effects 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 6
- 201000010099 disease Diseases 0.000 description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 5
- 239000000969 carrier Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 208000009453 Thyroid Nodule Diseases 0.000 description 1
- 208000024770 Thyroid neoplasm Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/383—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Abstract
The invention discloses a method and a device for determining the matching degree of insurance products, wherein at least one target insurance information node which is once associated with a target insurance product node is determined in an insurance knowledge graph, a first characteristic vector and a second characteristic vector of the target insurance product node are sequentially determined according to the target insurance information node, then a third characteristic vector of other insurance products is determined by combining the first characteristic vector and a connecting value corresponding to a connecting result of other insurance product nodes and each target insurance information node in the insurance knowledge graph, and the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to other insurance product nodes is determined by the second characteristic vector and the third characteristic vector. According to the invention, the matching degree of different insurance products can be accurately determined through the target insurance information node which is once associated with the target insurance product node and the connection condition of other insurance product nodes and the target insurance information node.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for determining the matching degree of an insurance product.
Background
With the improvement of the insurance consciousness of the people, the insurance products gradually become important guarantee products of the people for the risks possibly born in the future.
The insurance product is a special product, and the complexity degree of the insurance product far exceeds that of a common daily product. An insurance product may include a large amount of insurance information, such as insurance conditions, guarantee liability terms, disease information associated with the insurance product, insurance general knowledge information, underwriting information, security information, and insurance company information. In an actual application scenario, a customer may be interested in a certain insurance product, and therefore, other insurance products with high matching degree with the insurance product interested by the customer need to be searched out from a large amount of insurance products and recommended to the customer for comparison and reference, so how to accurately determine the matching degree between the insurance products and the insurance products becomes a problem that an insurance product provider needs to solve urgently.
Disclosure of Invention
In view of the above problems, the present invention provides a method and an apparatus for determining matching degree of insurance products, which overcomes or at least partially solves the above problems, and the technical solution is:
an insurance product matching degree determination method includes:
obtaining a target insurance product node;
determining at least one target insurance information node which is once associated with a target insurance product node in an insurance knowledge graph, wherein the insurance knowledge graph comprises insurance product nodes, insurance information nodes and edges connecting the nodes, each insurance information node corresponds to a preset weight value, each insurance product node corresponds to an insurance product, and each insurance information node corresponds to insurance information;
determining a first feature vector of the target insurance product node according to the weight value corresponding to the at least one target insurance information node respectively;
determining a second feature vector of the target insurance product node according to the first feature vector and the number of insurance product nodes connected with each target insurance information node;
for other insurance product nodes in the insurance knowledge graph except the target insurance product node: determining third eigenvectors of other insurance product nodes according to the first eigenvector and a connection value corresponding to a connection result of whether the other insurance product nodes are connected with each target insurance information node;
and determining the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to the other insurance product nodes according to the second feature vector and the third feature vectors of the other insurance product nodes in the insurance knowledge graph.
Optionally, the determining a second feature vector of the target insurance product node according to the first feature vector and the number of insurance product nodes connected to each target insurance information node includes:
for any one of the target insurance information nodes: multiplying the weight value corresponding to the target insurance information node in the first characteristic vector by the number of insurance product nodes connected with the target insurance information node to obtain the characteristic value of the target insurance information node;
and determining a second feature vector of the target insurance product node according to the feature value of each target insurance information node.
Optionally, the determining the third feature vector of the other insurance product node according to the second feature vector and a connection value corresponding to a connection result of whether the other insurance product node is connected to each target insurance information node includes:
for any one of the other insurance product nodes in the insurance knowledge graph other than the target insurance product node: and correspondingly multiplying the connection value corresponding to the connection result of the other insurance product nodes and each target insurance information node by the weight value corresponding to each target insurance information node in the first characteristic vector to determine the third characteristic vector of the other insurance product nodes.
Optionally, the determining, according to the second feature vector and the third feature vector of the other insurance product nodes in the insurance knowledge graph, a matching degree between the insurance product corresponding to the target insurance product node and the insurance product corresponding to the other insurance product nodes includes:
and inputting the second feature vector and third feature vectors of the other insurance product nodes in the insurance knowledge graph into a preset matching degree determination model, and obtaining the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to the other insurance product nodes, which are output by the preset matching degree determination model.
Optionally, the target insurance product node includes an insurance product node corresponding to an insurance product interacted by a target user, and/or an insurance product node corresponding to an insurance product interacted by a user, of which the similarity with the user image data of the target user reaches a preset similarity threshold.
Optionally, the setting process of the weight value corresponding to the insurance information node in the insurance knowledge graph includes:
determining a first weight coefficient of each insurance information body in the insurance knowledge graph, wherein the insurance information body comprises at least one insurance information node;
determining a second weight coefficient of each insurance information node in the insurance knowledge graph;
for any of the insurance information nodes: and determining a weight value corresponding to the insurance information node according to the second weight coefficient of the insurance information node and the first weight coefficient of the insurance information body in which the insurance information node is positioned.
Optionally, each insurance information ontology corresponds to a preset third weight coefficient, and the determining the first weight coefficient of each insurance information ontology in the insurance knowledge graph includes:
for any of the insurance information ontologies: and determining the first weight coefficient of the insurance information ontology in the insurance knowledge graph according to the third weight coefficient corresponding to the insurance information ontology, the first number of insurance information nodes included in the insurance information ontology and the second number of insurance information nodes included in the insurance knowledge graph.
Optionally, the determining the second weight coefficient of each insurance information node in the insurance knowledge graph includes:
for any of the insurance information nodes: and determining a second weight coefficient of the insurance information node according to the third number of the insurance product nodes connected with the insurance information node in the insurance knowledge graph and the fourth number of the insurance product nodes included in the insurance knowledge graph.
Optionally, the determining, according to the second weight coefficient of the insurance information node and the first weight coefficient of the insurance information body in which the insurance information node is located, a weight value corresponding to the insurance information node includes:
and multiplying the second weight coefficient of the insurance information node with the first weight coefficient of the insurance information body in which the insurance information node is positioned, and determining the weight value corresponding to the insurance information node.
An insurance product matching degree determination apparatus comprising: a target insurance product node obtaining unit, a target insurance information node determining unit, a first feature vector determining unit, a second feature vector determining unit, a third feature vector determining unit and an insurance product matching degree determining unit,
the target insurance product node obtaining unit is used for obtaining a target insurance product node;
the target insurance information node determining unit is used for determining at least one target insurance information node which is once associated with a target insurance product node in an insurance knowledge graph, wherein the insurance knowledge graph comprises insurance product nodes, insurance information nodes and edges connecting the nodes, each insurance information node corresponds to a preset weight value, each insurance product node corresponds to an insurance product, and each insurance information node corresponds to insurance information;
the first feature vector determining unit is configured to determine a first feature vector of the target insurance product node according to the weight values respectively corresponding to the at least one target insurance information node;
the second feature vector determining unit is configured to determine a second feature vector of the target insurance product node according to the first feature vector and the number of insurance product nodes connected to each target insurance information node;
the third feature vector determination unit is configured to, for insurance product nodes other than the target insurance product node in the insurance knowledge graph: determining third eigenvectors of other insurance product nodes according to the first eigenvector and a connection value corresponding to a connection result of whether the other insurance product nodes are connected with each target insurance information node;
and the insurance product matching degree determining unit is used for determining the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to the other insurance product nodes according to the second characteristic vector and the third characteristic vectors of the other insurance product nodes in the insurance knowledge graph.
By means of the technical scheme, the insurance product matching degree determining method and device provided by the invention are characterized in that at least one target insurance information node which is once associated with a target insurance product node is determined in an insurance knowledge graph, a first characteristic vector and a second characteristic vector of the target insurance product node are sequentially determined according to the target insurance information node, and then third characteristic vectors of other insurance products are determined by combining the first characteristic vector and connection values corresponding to connection results of other insurance product nodes and all target insurance information nodes in the insurance knowledge graph, so that the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to other insurance product nodes is determined through the second characteristic vector and the third characteristic vector. According to the invention, the matching degree of different insurance products can be accurately determined through the target insurance information node which is once associated with the target insurance product node and the connection condition of other insurance product nodes and the target insurance information node.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart illustrating a method for determining the matching degree of an insurance product according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a connection between a target insurance product node and an insurance information node in an insurance knowledge graph according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a setting process of a weight value corresponding to an insurance information node in an insurance knowledge graph according to an embodiment of the present invention;
FIG. 4 is a flow chart illustrating another insurance product match determination method according to an embodiment of the present invention;
FIG. 5 is a flow chart illustrating another insurance product match determination method according to an embodiment of the present invention;
FIG. 6 is a flow chart illustrating another insurance product match determination method according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram illustrating an insurance product matching degree determination apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a method for determining matching degree of an insurance product provided by an embodiment of the present invention may include:
and S100, obtaining a target insurance product node.
Optionally, the target insurance product node may include an insurance product node corresponding to an insurance product interacted by the target user.
Wherein the user-interacted insurance products may include at least one of user browsing, attention, collection and purchase of the insurance products interacted with by the user.
Optionally, the target insurance product node may include an insurance product node corresponding to an insurance product interacted by a user whose similarity with the user image data of the target user reaches a preset similarity threshold.
It can be understood that the embodiment of the invention can determine the similarity between different users according to the user portrait data by the existing user similarity algorithm. The embodiment of the present invention will not be further described and introduced for determining the user similarity.
The embodiment of the invention can determine the insurance product node corresponding to the insurance product interacted by the target user and the insurance product node corresponding to the insurance product interacted by the user, the similarity of which and the user image data of the target user reaches the preset similar threshold value, as the target insurance product node. The embodiment of the invention can obtain at least one target insurance product node.
S200, determining at least one target insurance information node which is once associated with the target insurance product node in the insurance knowledge graph.
Wherein, the Knowledge map (Knowledge Graph) can describe Knowledge resources and carriers thereof by using a visualization technology, and mine, analyze, construct, draw and display Knowledge and the mutual relation among the Knowledge resources and the carriers. The insurance knowledge graph in the embodiment of the invention comprises insurance product nodes, insurance information nodes and edges connecting the nodes, wherein each insurance information node corresponds to a preset weight value, each insurance product node corresponds to an insurance product, and each insurance information node corresponds to an insurance information.
Optionally, the embodiment of the invention may pre-construct the insurance knowledge graph.
The embodiment of the invention can define the ontology concept of each insurance product in the insurance knowledge graph, wherein each insurance product node corresponds to one insurance product. For example, node "darwinian No. 3" represents the insurance product "darwinian No. 3".
The embodiment of the invention can define the ontology concept of each insurance information in the insurance knowledge graph, wherein each insurance information node corresponds to one insurance information. Optionally, the body of the insurance product may include: the insurance system comprises a guarantee responsibility body, an insurance condition body, a disease body, an insurance common sense body, an insurance body, a security body and an insurance company body. For example: a 'serious disease responsibility' node corresponding to the guarantee responsibility body, a 'thyroid nodule' node corresponding to the disease body and the like.
The embodiment of the invention can define the relationship between the ontology and the ontology in the insurance knowledge graph. Specifically, the embodiment of the invention can input the edges representing the relationship between the nodes corresponding to the ontologies when the insurance knowledge graph is constructed. For example: and if the 'responsibility included' relationship exists between the body of the insurance product and the body of the insurance information, the insurance product node corresponding to the insurance product in the insurance knowledge graph and the insurance information node corresponding to the insurance information can be connected by the 'responsibility included' edge.
Wherein a one-time association refers to a direct connection between two nodes. The target insurance information node is an insurance information node directly connected to the target insurance product node. For ease of understanding, the one-degree association is described herein in connection with FIG. 2: as shown in fig. 2, the target insurance product node is directly connected to the insurance information node q, the insurance information node e and the insurance information node r, the insurance information node q, the insurance information node e and the insurance information node r are all associated with the target insurance product node for one time, the insurance information node w is indirectly connected to the target insurance product node through the insurance information node q, the insurance information node w is not associated with the first insurance product node for one time (for two-degree association), and the insurance information node y is indirectly connected to the target insurance product node through the insurance information node t and the insurance information node r in sequence, so that the insurance information node y is not associated with the first insurance product node for one time (for three-degree association).
The embodiment of the invention can set the corresponding weight value for the insurance information node in the insurance knowledge graph. Optionally, as shown in fig. 3, a process of setting a weight value corresponding to an insurance information node in an insurance knowledge graph according to an embodiment of the present invention may include:
and S10, determining a first weight coefficient of each insurance information body in the insurance knowledge graph, wherein the insurance information body comprises at least one insurance information node.
Optionally, in the embodiment of the present invention, the first weight coefficient of each insurance information ontology in the insurance knowledge graph may be determined according to the first number of insurance information nodes included in the insurance information ontology and the second number of insurance information nodes included in the insurance knowledge graph.
Specifically, the embodiment of the present invention may be implemented by a formula:
and determining a first weight coefficient of each insurance information body in the insurance knowledge graph. Wherein value1I is the number of insurance information body in the insurance knowledge map, totaliA first number, total, of insurance information nodes comprised by an insurance information body numbered iallFor insurance included in the insurance knowledge graphA second number of information nodes.
Optionally, each insurance information ontology corresponds to a preset third weight coefficient, and in the setting process of the weight value corresponding to the insurance information node in another insurance knowledge graph provided in the embodiment of the present invention, step S10 may include: for any insurance information body: and determining the first weight coefficient of the insurance information ontology in the insurance knowledge graph according to the third weight coefficient corresponding to the insurance information ontology, the first number of insurance information nodes included in the insurance information ontology and the second number of insurance information nodes included in the insurance knowledge graph.
According to the embodiment of the invention, the corresponding third weight coefficient can be set for each insurance information body according to the importance degree of each insurance information body determined by the actual experience of the technical personnel.
Specifically, the embodiment of the present invention may be implemented according to a formula:
determining a first weight coefficient of the insurance information ontology in the insurance knowledge graph. Wherein value1I is the number of the insurance information body in the insurance knowledge map, totaliA first number, total, of insurance information nodes comprised by an insurance information body numbered iallIs the second number, k, of insurance information nodes included in the insurance knowledge graphiAnd the third weight coefficient is corresponding to the insurance information body with the number i.
And S20, determining a second weight coefficient of each insurance information node in the insurance knowledge graph.
Optionally, the embodiment of the present invention may be implemented for any insurance information node: and determining a second weight coefficient of the insurance information node according to the number of insurance product nodes connected with the insurance information node in the insurance knowledge graph.
Optionally, in another process of setting a weight value corresponding to an insurance information node in an insurance knowledgegraph provided in the embodiment of the present invention, step S20 may include: for any insurance information node: and determining a second weight coefficient of the insurance information node according to the third number of the insurance product nodes connected with the insurance information node in the insurance knowledge graph and the fourth number of the insurance product nodes included in the insurance knowledge graph.
Specifically, the embodiment of the present invention may be implemented by a formula:
a second weight factor for the insurance information node is determined. Wherein value2Product for the second weight coefficientallIs the fourth number of insurance product nodes included in the insurance knowledge graph, j is the number of the insurance information node, productjA third number of insurance product nodes connected to the insurance information node numbered j in the insurance knowledge graph.
S30, for any insurance information node: and determining a weight value corresponding to the insurance information node according to the second weight coefficient of the insurance information node and the first weight coefficient of the insurance information body in which the insurance information node is positioned.
Optionally, in the embodiment of the present invention, the second weight coefficient of the insurance information node and the first weight coefficient of the insurance information body in which the insurance information node is located may be added to determine the weight value corresponding to the insurance information node.
Optionally, in another process of setting a weight value corresponding to an insurance information node in an insurance knowledgegraph provided in the embodiment of the present invention, step S30 may include: and multiplying the second weight coefficient of the insurance information node with the first weight coefficient of the insurance information body in which the insurance information node is positioned, and determining the weight value corresponding to the insurance information node.
Specifically, the embodiment of the present invention may be implemented by a formula:
value＝value1×value2
determining the corresponding right of the insurance information nodeAnd (4) weighing values. Wherein, value is the weight value corresponding to the insurance information node, value1A first weight coefficient, value, of the insurance information body in which the insurance information node is located2Is the second weight coefficient of the insurance information node.
According to the embodiment of the invention, the corresponding weight values are preset for the insurance information nodes in the insurance knowledge graph in advance, so that the importance degree of the insurance information nodes can be determined according to the weight values, and scientific and accurate quantitative indexes can be conveniently provided for subsequent matching of insurance products.
S300, determining a first feature vector of the target insurance product node according to the weight values respectively corresponding to the at least one target insurance information node.
Specifically, the embodiment of the present invention may sequentially arrange the weight values corresponding to the target insurance information nodes that are determined to be once associated with the target insurance product node in the insurance knowledge graph, and determine the first feature vector of the target insurance product node. For example: the target insurance product node is associated with a target insurance information node a, a target insurance information node b, a target insurance information node c and a target insurance information node d at one time, the weight value corresponding to the target insurance information node a is 0.3, the weight value corresponding to the target insurance information node b is 0.6, the weight value corresponding to the target insurance information node c is 0.2, the weight value corresponding to the target insurance information node d is 0.9, the target insurance information node a, the target insurance information node b, the target insurance information node c and the target insurance information node d are sequentially arranged according to the sequence of the target insurance information node a, the target insurance information node b, the target insurance information node c and the target insurance information node d, and the determined first feature vector of the target insurance product node is feature _ value1＝[0.3，0.6，0.2，0.9]。
S400, determining a second feature vector of the target insurance product node according to the first feature vector and the number of insurance product nodes connected with each target insurance information node.
Optionally, in the embodiment of the present invention, for any target insurance information node in each target insurance information node: and obtaining the characteristic value of the target insurance information node according to the weight value corresponding to the target insurance information node in the first characteristic vector and the number score value of the insurance product nodes connected with the target insurance information node.
Optionally, based on the method shown in fig. 1, as shown in fig. 4, in another insurance product matching degree determining method provided in the embodiment of the present invention, step S400 may include:
s410, for any target insurance information node in all target insurance information nodes: and multiplying the weight value corresponding to the target insurance information node in the first characteristic vector by the number of insurance product nodes connected with the target insurance information node to obtain the characteristic value of the target insurance information node.
And S420, determining a second feature vector of the target insurance product node according to the feature value of each target insurance information node.
For example: based on the first feature vector as feature _ value1＝[0.3，0.6，0.2，0.9]For example, if the weight value corresponding to the target insurance information node a is 0.3, the weight value corresponding to the target insurance information node b is 0.6, the weight value corresponding to the target insurance information node c is 0.2, the weight value corresponding to the target insurance information node d is 0.9, the number of insurance product nodes connected to the target insurance information node a is 1, the number of insurance product nodes connected to the target insurance information node b is 2, the number of insurance product nodes connected to the target insurance information node c is 3, and the number of insurance product nodes connected to the target insurance information node d is 2, the second feature vector of the target insurance product node is feature _ value2＝[0.3，1.2，0.6，1.8]。
S500, for other insurance product nodes except the target insurance product node in the insurance knowledge graph: and determining the third characteristic vectors of other insurance product nodes according to the first characteristic vector and the connection value corresponding to the connection result of whether the other insurance product nodes are connected with each target insurance information node.
Optionally, in the embodiment of the present invention, when the connection result between the other insurance product node and the target insurance information node is connection, the set connection value is 1. The embodiment of the invention can set the connection value to be 0 when the connection result of other insurance product nodes and the target insurance information node is not connected.
Optionally, based on the method shown in fig. 1, as shown in fig. 5, in another insurance product matching degree determining method provided in the embodiment of the present invention, step S500 may include:
s510, for any other insurance product node in other insurance product nodes except the target insurance product node in the insurance knowledge graph: and correspondingly multiplying the connection value corresponding to the connection result of the other insurance product nodes and each target insurance information node by the weight value corresponding to each target insurance information node in the first characteristic vector to determine the third characteristic vector of the other insurance product nodes.
For example: assume that the connection value is 1 when the connection result is connection, and the connection value is 0 when the connection result is disconnection. Based on the first feature vector as feature _ value1＝[0.3，0.6，0.2，0.9]In the example of (1), if the other insurance product node is not connected to the target insurance information node b but connected to the target insurance information node a, the target insurance information node c, and the target insurance information node d, the third feature vector of the other insurance product node is feature _ value3＝[0.3，0，0.2，0.9]。
S600, determining the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to the other insurance product nodes according to the second characteristic vector and the third characteristic vectors of the other insurance product nodes in the insurance knowledge graph.
Optionally, based on the method shown in fig. 1, as shown in fig. 6, in another insurance product matching degree determining method provided in the embodiment of the present invention, step S600 may include:
and S610, inputting the second feature vector and the third feature vector of the other insurance product nodes in the insurance knowledge graph into a preset matching degree determination model, and obtaining the matching degree of the insurance product corresponding to the target insurance product node and the insurance product corresponding to the other insurance product nodes, which are output by the preset matching degree determination model.
The preset matching degree determination model may be a model for calculating a matching value by applying a vector similarity algorithm. The vector similarity algorithm may include at least one algorithm of a cosine similarity (cosine) algorithm, a Euclidean distance (Euclidean) algorithm, and a Manhattan distance (Manhattan distance) algorithm.
The invention provides a insurance product matching degree determining method, which comprises the steps of determining at least one target insurance information node which is once associated with a target insurance product node in an insurance knowledge graph, sequentially determining a first characteristic vector and a second characteristic vector of the target insurance product node according to the target insurance information node, determining a third characteristic vector of other insurance products by combining the first characteristic vector and a connection value corresponding to a connection result of other insurance product nodes and each target insurance information node in the insurance knowledge graph, and determining the matching degree of an insurance product corresponding to the target insurance product node and an insurance product corresponding to the other insurance product node through the second characteristic vector and the third characteristic vector. According to the invention, the matching degree of different insurance products can be accurately determined through the target insurance information node which is once associated with the target insurance product node and the connection condition of other insurance product nodes and the target insurance information node.
According to the method, after a user interacts with one insurance product, the matching degree of the insurance product and other insurance products is determined through the method for determining the matching degree of the insurance product, the other insurance products can be sorted from large to small according to the matching degree, the other insurance products which are sorted before the preset sequence position are recommended to the user, the user can conveniently compare and refer to the similar insurance products, and the insurance product which is suitable for the user is selected.
Corresponding to the above method embodiment, an embodiment of the present invention further provides an insurance product matching degree determining apparatus, which has a structure shown in fig. 7 and may include: a target insurance product node obtaining unit 100, a target insurance information node determining unit 200, a first feature vector determining unit 300, a second feature vector determining unit 400, a third feature vector determining unit 500, and an insurance product matching degree determining unit 600.
And a target insurance product node obtaining unit 100 for obtaining a target insurance product node.
Optionally, the target insurance product node may include an insurance product node corresponding to an insurance product interacted by the target user.
Wherein the user-interacted insurance products may include at least one of user browsing, attention, collection and purchase of the insurance products interacted with by the user.
Optionally, the target insurance product node may include an insurance product node corresponding to an insurance product interacted by a user whose similarity with the user image data of the target user reaches a preset similarity threshold.
It can be understood that the embodiment of the invention can determine the similarity between different users according to the user portrait data by the existing user similarity algorithm. The embodiment of the present invention will not be further described and introduced for determining the user similarity.
The target insurance product node obtaining unit 100 may determine an insurance product node corresponding to an insurance product interacted by the target user and an insurance product node corresponding to an insurance product interacted by the user, of which the similarity with the user image data of the target user reaches a preset similar threshold, as target insurance product nodes. The embodiment of the invention can obtain at least one target insurance product node.
A target insurance information node determination unit 200 for determining at least one target insurance information node once associated with the target insurance product node in the insurance knowledgegraph.
Wherein, the Knowledge map (Knowledge Graph) can describe Knowledge resources and carriers thereof by using a visualization technology, and mine, analyze, construct, draw and display Knowledge and the mutual relation among the Knowledge resources and the carriers. The insurance knowledge graph in the embodiment of the invention comprises insurance product nodes, insurance information nodes and edges connecting the nodes, wherein each insurance information node corresponds to a preset weight value, each insurance product node corresponds to an insurance product, and each insurance information node corresponds to an insurance information.
Optionally, the embodiment of the invention may pre-construct the insurance knowledge graph.
The embodiment of the invention can define the ontology concept of each insurance product in the insurance knowledge graph, wherein each insurance product node corresponds to one insurance product.
The embodiment of the invention can define the ontology concept of each insurance information in the insurance knowledge graph, wherein each insurance information node corresponds to one insurance information. Optionally, the body of the insurance product may include: the insurance system comprises a guarantee responsibility body, an insurance condition body, a disease body, an insurance common sense body, an insurance body, a security body and an insurance company body.
The embodiment of the invention can define the relationship between the ontology and the ontology in the insurance knowledge graph. Specifically, the embodiment of the invention can input the edges representing the relationship between the nodes corresponding to the ontologies when the insurance knowledge graph is constructed.
Wherein a one-time association refers to a direct connection between two nodes. The target insurance information node is an insurance information node directly connected to the target insurance product node.
The embodiment of the invention can set the corresponding weight value for the insurance information node in the insurance knowledge graph. Optionally, the device for determining matching degree of an insurance product according to an embodiment of the present invention may further include: the device comprises a first weight coefficient determining unit, a second weight coefficient determining unit and a weight value determining unit.
The first weight coefficient determining unit is used for determining a first weight coefficient of each insurance information body in the insurance knowledge graph, and each insurance information body comprises at least one insurance information node.
Optionally, the first weight coefficient determining unit may determine the first weight coefficient of each insurance information ontology in the insurance knowledge graph according to the first number of insurance information nodes included in the insurance information ontology and the second number of insurance information nodes included in the insurance knowledge graph.
Specifically, the first weight coefficient determination unit may determine the first weight coefficient by the formula:
and determining a first weight coefficient of each insurance information body in the insurance knowledge graph. Wherein value1I is the number of insurance information body in the insurance knowledge map, totaliA first number, total, of insurance information nodes comprised by an insurance information body numbered iallIs the second number of insurance information nodes included in the insurance knowledgegraph.
Optionally, each insurance information body corresponds to a preset third weight coefficient, and the first weight coefficient determining unit may be specifically configured to, for any insurance information body: and determining the first weight coefficient of the insurance information ontology in the insurance knowledge graph according to the third weight coefficient corresponding to the insurance information ontology, the first number of insurance information nodes included in the insurance information ontology and the second number of insurance information nodes included in the insurance knowledge graph.
According to the embodiment of the invention, the corresponding third weight coefficient can be set for each insurance information body according to the importance degree of each insurance information body determined by the actual experience of the technical personnel.
Specifically, the first weight coefficient determining unit may determine the first weight coefficient according to the formula:
determining a first weight coefficient of the insurance information ontology in the insurance knowledge graph. Wherein value1I is the number of the insurance information body in the insurance knowledge map, totaliA first number, total, of insurance information nodes comprised by an insurance information body numbered iallIs the second number, k, of insurance information nodes included in the insurance knowledge graphiAnd the third weight coefficient is corresponding to the insurance information body with the number i.
And the second weight coefficient determining unit is used for determining the second weight coefficient of each insurance information node in the insurance knowledge graph.
Optionally, the second weight coefficient determining unit may: and determining a second weight coefficient of the insurance information node according to the number of insurance product nodes connected with the insurance information node in the insurance knowledge graph.
Optionally, the second weight coefficient determining unit may be specifically configured to, for any insurance information node: and determining a second weight coefficient of the insurance information node according to the third number of the insurance product nodes connected with the insurance information node in the insurance knowledge graph and the fourth number of the insurance product nodes included in the insurance knowledge graph.
Specifically, the second weight coefficient determination unit may determine the second weight coefficient by the formula:
a second weight factor for the insurance information node is determined. Wherein value2Product for the second weight coefficientallIs the fourth number of insurance product nodes included in the insurance knowledge graph, j is the number of the insurance information node, productjA third number of insurance product nodes connected to the insurance information node numbered j in the insurance knowledge graph.
A weight value determination unit, configured to, for any insurance information node: and determining a weight value corresponding to the insurance information node according to the second weight coefficient of the insurance information node and the first weight coefficient of the insurance information body in which the insurance information node is positioned.
Optionally, the weight value determining unit may add the second weight coefficient of the insurance information node and the first weight coefficient of the insurance information body in which the insurance information node is located, and determine the weight value corresponding to the insurance information node.
Optionally, the weight value determining unit may be specifically configured to multiply the second weight coefficient of the insurance information node by the first weight coefficient of the insurance information body in which the insurance information node is located, and determine the weight value corresponding to the insurance information node.
Specifically, the weight value determining unit may determine the weight value by a formula:
value＝value1×value2
and determining a weight value corresponding to the insurance information node. Wherein, value is the weight value corresponding to the insurance information node, value1A first weight coefficient, value, of the insurance information body in which the insurance information node is located2Is the second weight coefficient of the insurance information node.
According to the embodiment of the invention, the corresponding weight values are preset for the insurance information nodes in the insurance knowledge graph in advance, so that the importance degree of the insurance information nodes can be determined according to the weight values, and scientific and accurate quantitative indexes can be conveniently provided for subsequent matching of insurance products.
The first feature vector determining unit 300 is configured to determine a first feature vector of the target insurance product node according to the weight values respectively corresponding to the at least one target insurance information node.
Specifically, the first feature vector determining unit 300 may sequentially arrange weight values corresponding to the target insurance information nodes that are determined to be associated with the target insurance product node at one time in the insurance knowledge graph, and determine the first feature vector of the target insurance product node.
And a second feature vector determining unit 400, configured to determine a second feature vector of each target insurance product node according to the first feature vector and the number of insurance product nodes connected to the target insurance information node.
Optionally, the second feature vector determining unit 400 may be specifically configured to: for any one of the target insurance information nodes: and multiplying the weight value corresponding to the target insurance information node in the first characteristic vector by the number of insurance product nodes connected with the target insurance information node to obtain the characteristic value of the target insurance information node. And determining a second feature vector of the target insurance product node according to the feature value of each target insurance information node.
A third feature vector determination unit 500, configured to, for insurance product nodes other than the target insurance product node in the insurance knowledge graph: and determining the third characteristic vectors of other insurance product nodes according to the first characteristic vector and the connection value corresponding to the connection result of whether the other insurance product nodes are connected with each target insurance information node.
Optionally, the third feature vector determining unit 500 may be specifically configured to, for any one of the other insurance product nodes in the insurance knowledge graph except for the target insurance product node: and correspondingly multiplying the connection value corresponding to the connection result of the other insurance product nodes and each target insurance information node by the weight value corresponding to each target insurance information node in the first characteristic vector to determine the third characteristic vector of the other insurance product nodes.
An insurance product matching degree determining unit 600, configured to determine, according to the second feature vector and the third feature vector of the other insurance product nodes in the insurance knowledge graph, a matching degree between the insurance product corresponding to the target insurance product node and the insurance product corresponding to the other insurance product nodes.
Optionally, the insurance product matching degree determining unit 600 may be specifically configured to input the second feature vector and the third feature vector of the other insurance product nodes in the insurance knowledge graph into a preset matching degree determining model, and obtain the matching degree of the insurance product corresponding to the target insurance product node and the insurance product corresponding to the other insurance product nodes, which are output by the preset matching degree determining model.
The preset matching degree determination model may be a model for calculating a matching value by applying a vector similarity algorithm. The vector similarity algorithm may include at least one algorithm of a cosine similarity (cosine) algorithm, a Euclidean distance (Euclidean) algorithm, and a Manhattan distance (Manhattan distance) algorithm.
The invention provides an insurance product matching degree determining device, which determines at least one target insurance information node which is once associated with a target insurance product node in an insurance knowledge graph, sequentially determines a first characteristic vector and a second characteristic vector of the target insurance product node according to the target insurance information node, determines a third characteristic vector of other insurance products by combining the first characteristic vector and a connection value corresponding to a connection result of other insurance product nodes and each target insurance information node in the insurance knowledge graph, and further determines the matching degree of an insurance product corresponding to the target insurance product node and an insurance product corresponding to the other insurance product node through the second characteristic vector and the third characteristic vector. According to the invention, the matching degree of different insurance products can be accurately determined through the target insurance information node which is once associated with the target insurance product node and the connection condition of other insurance product nodes and the target insurance information node.
The insurance product matching degree determining device comprises a processor and a memory, wherein the target insurance product node obtaining unit 100, the target insurance information node determining unit 200, the first feature vector determining unit 300, the second feature vector determining unit 400, the third feature vector determining unit 500, the insurance product matching degree determining unit 600 and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, and the matching degree of different insurance products can be accurately determined by adjusting the kernel parameters.
An embodiment of the present invention provides a storage medium on which a program is stored, the program implementing the insurance product matching degree determination method when executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein the method for determining the matching degree of the insurance product is executed when the program runs.
The embodiment of the invention provides electronic equipment, which comprises at least one processor, at least one memory and a bus, wherein the memory and the bus are connected with the processor; the processor and the memory complete mutual communication through a bus; the processor is used for calling the program instructions in the memory to execute the insurance product matching degree determination method. The electronic device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to execute a program initialized with the steps of the insurance product match-degree determination method described above when executed on an electronic device.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus, electronic devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, an electronic device includes one or more processors (CPUs), memory, and a bus. The electronic device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. An insurance product matching degree determination method is characterized by comprising the following steps:
obtaining a target insurance product node;
determining at least one target insurance information node which is once associated with a target insurance product node in an insurance knowledge graph, wherein the insurance knowledge graph comprises insurance product nodes, insurance information nodes and edges connecting the nodes, each insurance information node corresponds to a preset weight value, each insurance product node corresponds to an insurance product, and each insurance information node corresponds to insurance information;
determining a first feature vector of the target insurance product node according to the weight value corresponding to the at least one target insurance information node respectively;
determining a second feature vector of the target insurance product node according to the first feature vector and the number of insurance product nodes connected with each target insurance information node;
for other insurance product nodes in the insurance knowledge graph except the target insurance product node: determining third eigenvectors of other insurance product nodes according to the first eigenvector and a connection value corresponding to a connection result of whether the other insurance product nodes are connected with each target insurance information node;
and determining the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to the other insurance product nodes according to the second feature vector and the third feature vectors of the other insurance product nodes in the insurance knowledge graph.
2. The method according to claim 1, wherein determining the second eigenvector of each target insurance product node from the first eigenvector and the number of insurance product nodes connected to the target insurance information node comprises:
for any one of the target insurance information nodes: multiplying the weight value corresponding to the target insurance information node in the first characteristic vector by the number of insurance product nodes connected with the target insurance information node to obtain the characteristic value of the target insurance information node;
and determining a second feature vector of the target insurance product node according to the feature value of each target insurance information node.
3. The method according to claim 2, wherein the determining the third eigenvector of the other insurance product node according to the second eigenvector and the connection value corresponding to the connection result of whether the other insurance product node is connected to each target insurance information node comprises:
for any one of the other insurance product nodes in the insurance knowledge graph other than the target insurance product node: and correspondingly multiplying the connection value corresponding to the connection result of the other insurance product nodes and each target insurance information node by the weight value corresponding to each target insurance information node in the first characteristic vector to determine the third characteristic vector of the other insurance product nodes.
4. The method according to claim 1, wherein the determining the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to the other insurance product nodes according to the second feature vector and the third feature vectors of the other insurance product nodes in the insurance knowledge graph comprises:
and inputting the second feature vector and third feature vectors of the other insurance product nodes in the insurance knowledge graph into a preset matching degree determination model, and obtaining the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to the other insurance product nodes, which are output by the preset matching degree determination model.
5. The method according to claim 1, wherein the target insurance product node comprises an insurance product node corresponding to an insurance product interacted by a target user, and/or an insurance product node corresponding to a user-interacted insurance product of which the similarity of user image data of the target user reaches a preset similarity threshold.
6. The method according to claim 1, wherein the setting process of the weight value corresponding to the insurance information node in the insurance knowledge graph comprises:
determining a first weight coefficient of each insurance information body in the insurance knowledge graph, wherein the insurance information body comprises at least one insurance information node;
determining a second weight coefficient of each insurance information node in the insurance knowledge graph;
for any of the insurance information nodes: and determining a weight value corresponding to the insurance information node according to the second weight coefficient of the insurance information node and the first weight coefficient of the insurance information body in which the insurance information node is positioned.
7. The method of claim 6, wherein each insurance information ontology corresponds to a preset third weight coefficient, and the determining the first weight coefficient of each insurance information ontology in the insurance knowledge graph comprises:
for any of the insurance information ontologies: and determining the first weight coefficient of the insurance information ontology in the insurance knowledge graph according to the third weight coefficient corresponding to the insurance information ontology, the first number of insurance information nodes included in the insurance information ontology and the second number of insurance information nodes included in the insurance knowledge graph.
8. The method of claim 6, wherein determining the second weight coefficient for each of the insurance information nodes in the insurance knowledgegraph comprises:
for any of the insurance information nodes: and determining a second weight coefficient of the insurance information node according to the third number of the insurance product nodes connected with the insurance information node in the insurance knowledge graph and the fourth number of the insurance product nodes included in the insurance knowledge graph.
9. The method according to claim 6, wherein the determining the weight value corresponding to the insurance information node according to the second weight coefficient of the insurance information node and the first weight coefficient of the insurance information ontology in which the insurance information node is located comprises:
and multiplying the second weight coefficient of the insurance information node with the first weight coefficient of the insurance information body in which the insurance information node is positioned, and determining the weight value corresponding to the insurance information node.
10. An insurance product matching degree determination apparatus, comprising: a target insurance product node obtaining unit, a target insurance information node determining unit, a first feature vector determining unit, a second feature vector determining unit, a third feature vector determining unit and an insurance product matching degree determining unit,
the target insurance product node obtaining unit is used for obtaining a target insurance product node;
the target insurance information node determining unit is used for determining at least one target insurance information node which is once associated with a target insurance product node in an insurance knowledge graph, wherein the insurance knowledge graph comprises insurance product nodes, insurance information nodes and edges connecting the nodes, each insurance information node corresponds to a preset weight value, each insurance product node corresponds to an insurance product, and each insurance information node corresponds to insurance information;
the first feature vector determining unit is configured to determine a first feature vector of the target insurance product node according to the weight values respectively corresponding to the at least one target insurance information node;
the second feature vector determining unit is configured to determine a second feature vector of the target insurance product node according to the first feature vector and the number of insurance product nodes connected to each target insurance information node;
the third feature vector determination unit is configured to, for insurance product nodes other than the target insurance product node in the insurance knowledge graph: determining third eigenvectors of other insurance product nodes according to the first eigenvector and a connection value corresponding to a connection result of whether the other insurance product nodes are connected with each target insurance information node;
and the insurance product matching degree determining unit is used for determining the matching degree of the insurance product corresponding to the target insurance product node and the insurance products corresponding to the other insurance product nodes according to the second characteristic vector and the third characteristic vectors of the other insurance product nodes in the insurance knowledge graph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011354996.8A CN112364181A (en) | 2020-11-27 | 2020-11-27 | Insurance product matching degree determination method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011354996.8A CN112364181A (en) | 2020-11-27 | 2020-11-27 | Insurance product matching degree determination method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112364181A true CN112364181A (en) | 2021-02-12 |
Family
ID=74535300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011354996.8A Pending CN112364181A (en) | 2020-11-27 | 2020-11-27 | Insurance product matching degree determination method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112364181A (en) |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207884A (en) * | 2012-11-23 | 2013-07-17 | 浙江工业大学 | Method for matching weight iteration nodes between weighting networks |
| CN108156032A (en) * | 2017-12-22 | 2018-06-12 | 中国人民解放军战略支援部队信息工程大学 | The reference mode choosing method combined based on spectral clustering with random selection |
| CN109597856A (en) * | 2018-12-05 | 2019-04-09 | 北京知道创宇信息技术有限公司 | A kind of data processing method, device, electronic equipment and storage medium |
| US20190197134A1 (en) * | 2017-12-22 | 2019-06-27 | Oracle International Corporation | Computerized geo-referencing for images |
| CN110032606A (en) * | 2019-03-29 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of sample clustering method and device |
| CN110427563A (en) * | 2019-08-30 | 2019-11-08 | 杭州智策略科技有限公司 | A kind of professional domain system cold start-up recommended method of knowledge based map |
| CN110675954A (en) * | 2019-10-11 | 2020-01-10 | 北京百度网讯科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111104522A (en) * | 2019-12-20 | 2020-05-05 | 武汉理工大学 | Regional industry association effect trend prediction method based on knowledge graph |
| CN111241311A (en) * | 2020-01-09 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Media information recommendation method and device, electronic equipment and storage medium |
| CN111241241A (en) * | 2020-01-08 | 2020-06-05 | 平安科技（深圳）有限公司 | Case retrieval method, device and equipment based on knowledge graph and storage medium |
| CN111444357A (en) * | 2020-03-24 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Content information determination method and device, computer equipment and storage medium |
| CN111475637A (en) * | 2020-06-24 | 2020-07-31 | 支付宝(杭州)信息技术有限公司 | Data processing and training method and device for pushing knowledge points |
| CN111523918A (en) * | 2019-02-02 | 2020-08-11 | 北京极智嘉科技有限公司 | Commodity clustering method, commodity clustering device, commodity clustering equipment and storage medium |
| CN111768231A (en) * | 2020-06-24 | 2020-10-13 | 中国工商银行股份有限公司 | Product information recommendation method and device |
| KR20200123544A (en) * | 2019-04-22 | 2020-10-30 | 넷마블 주식회사 | Mehtod for extracting synonyms |
| CN111931002A (en) * | 2020-06-30 | 2020-11-13 | 华为技术有限公司 | Matching method and related equipment |
-
2020
- 2020-11-27 CN CN202011354996.8A patent/CN112364181A/en active Pending
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207884A (en) * | 2012-11-23 | 2013-07-17 | 浙江工业大学 | Method for matching weight iteration nodes between weighting networks |
| CN108156032A (en) * | 2017-12-22 | 2018-06-12 | 中国人民解放军战略支援部队信息工程大学 | The reference mode choosing method combined based on spectral clustering with random selection |
| US20190197134A1 (en) * | 2017-12-22 | 2019-06-27 | Oracle International Corporation | Computerized geo-referencing for images |
| CN109597856A (en) * | 2018-12-05 | 2019-04-09 | 北京知道创宇信息技术有限公司 | A kind of data processing method, device, electronic equipment and storage medium |
| CN111523918A (en) * | 2019-02-02 | 2020-08-11 | 北京极智嘉科技有限公司 | Commodity clustering method, commodity clustering device, commodity clustering equipment and storage medium |
| CN110032606A (en) * | 2019-03-29 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of sample clustering method and device |
| KR20200123544A (en) * | 2019-04-22 | 2020-10-30 | 넷마블 주식회사 | Mehtod for extracting synonyms |
| CN110427563A (en) * | 2019-08-30 | 2019-11-08 | 杭州智策略科技有限公司 | A kind of professional domain system cold start-up recommended method of knowledge based map |
| CN110675954A (en) * | 2019-10-11 | 2020-01-10 | 北京百度网讯科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN111104522A (en) * | 2019-12-20 | 2020-05-05 | 武汉理工大学 | Regional industry association effect trend prediction method based on knowledge graph |
| CN111241241A (en) * | 2020-01-08 | 2020-06-05 | 平安科技（深圳）有限公司 | Case retrieval method, device and equipment based on knowledge graph and storage medium |
| CN111241311A (en) * | 2020-01-09 | 2020-06-05 | 腾讯科技（深圳）有限公司 | Media information recommendation method and device, electronic equipment and storage medium |
| CN111444357A (en) * | 2020-03-24 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Content information determination method and device, computer equipment and storage medium |
| CN111475637A (en) * | 2020-06-24 | 2020-07-31 | 支付宝(杭州)信息技术有限公司 | Data processing and training method and device for pushing knowledge points |
| CN111768231A (en) * | 2020-06-24 | 2020-10-13 | 中国工商银行股份有限公司 | Product information recommendation method and device |
| CN111931002A (en) * | 2020-06-30 | 2020-11-13 | 华为技术有限公司 | Matching method and related equipment |
Non-Patent Citations (2)
| Title |
|---|
| GIANNIS NIKOLENTZOS: "Matching Node Embeddings for Graph Similarity", 《THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / MACHINE LEARNING METHODS》, vol. 31, no. 1, pages 2429 - 2435 * |
| 孙萍: "网络购物中顾客共同趋向性获取算法研究", 《中国优秀硕士学位全文数据库 信息科技》, pages 138 - 2014 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200050968A1 (en) | Interactive interfaces for machine learning model evaluations | |
| CN113610239B (en) | Feature processing method and feature processing system for machine learning | |
| CN110489558B (en) | Article aggregation method and device, medium and computing equipment | |
| CN106844407B (en) | Tag network generation method and system based on data set correlation | |
| CN111046237B (en) | User behavior data processing method and device, electronic equipment and readable medium | |
| WO2022007434A1 (en) | Visualization method and related device | |
| CN111078776A (en) | Data table standardization method, device, equipment and storage medium | |
| CN109255000B (en) | Dimension management method and device for label data | |
| TWI705411B (en) | Method and device for identifying users with social business characteristics | |
| CN111090807A (en) | Knowledge graph-based user identification method and device | |
| CN108804564A (en) | The combined recommendation method and terminal device of financial product | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| WO2020147259A1 (en) | User portait method and apparatus, readable storage medium, and terminal device | |
| CN111611228B (en) | Load balancing adjustment method and device based on distributed database | |
| CN108959289B (en) | Website category acquisition method and device | |
| CN111383072A (en) | User credit scoring method, storage medium and server | |
| CN111259975B (en) | Method and device for generating classifier and method and device for classifying text | |
| CN111597336A (en) | Processing method and device of training text, electronic equipment and readable storage medium | |
| CN112100400A (en) | Node recommendation method and device based on knowledge graph | |
| CN111488386A (en) | Data query method and device | |
| CN113988878B (en) | Graph database technology-based anti-fraud method and system | |
| CN111488479A (en) | Hypergraph construction method, hypergraph construction device, computer system and medium | |
| CN112364181A (en) | Insurance product matching degree determination method and device | |
| CN114357184A (en) | Item recommendation method and related device, electronic equipment and storage medium | |
| US11068236B2 (en) | Identification of users across multiple platforms |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |