Information fusion management method based on Internet of Things

Abstract

The invention discloses an information fusion management method based on the Internet of Things, and relates to the technical field of information management, and the method comprises the following steps: S1, obtaining the historical information of a user from a cloud platform, and constructing a knowledge graph according to the historical information of the user; s2, when the cloud platform generates latest information of the user, generating a plurality of local feature coefficients, and based on the local feature coefficients, fusing the latest information and historical information by using the knowledge graph to obtain a real-time portrait of the user; and S3, encrypting the real-time portrait of the user, and uploading the real-time portrait to the cloud platform. According to the method, information fusion can be enhanced, the fragmentation defect of an existing information fusion technology is overcome, and the user interest portrait is generated in a high-precision and high-dynamic manner.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to an information fusion management method based on the Internet of Things. Background Art

[0002] In the IoT (Internet of Things) context, user browsing information (such as smart device browsing history and platform interaction content) is subject to dynamic, high-frequency updates. However, existing technologies for the integrated management of user browsing information suffer from the following key deficiencies: First, they lack the ability to mine local browsing features. When constructing knowledge graphs of historical browsing information, existing methods focus only on the global topology (such as the overall connectivity of browsing relationships) and ignore the real-time information generated. As a result, when real-time browsing information (such as new browsing content) is associated with historical graphs, it is impossible to accurately capture the dynamic continuity of user interests (such as the evolution of short-term interests into long-term preferences). Second, traditional information management methods struggle to efficiently integrate historical and real-time information, accurately portraying users' real-time status, and fail to fully utilize knowledge graphs, resulting in poor fusion results. Therefore, a complex information management method based on the IoT is urgently needed. Summary of the Invention

[0003] In order to solve the above problems, the present invention proposes an information fusion management method based on the Internet of Things.

[0004] The technical solution of the present invention is: an information fusion management method based on the Internet of Things includes the following steps:

[0005] S1. Obtain the user's historical information from the cloud platform and build a knowledge graph based on the user's historical information;

[0006] S2. When the cloud platform generates the latest information about the user, it generates several local feature coefficients. Based on the local feature coefficients, it uses the knowledge graph to fuse the latest information with historical information to obtain a real-time profile of the user.

[0007] S3. Encrypt the user's real-time portrait and upload it to the cloud platform.

[0008] Furthermore, S2 includes the following sub-steps:

[0009] S21, extract the global Laplacian matrix of the knowledge graph;

[0010] S22. Calculate a number of local feature coefficients for the knowledge graph based on the global Laplace matrix of the knowledge graph;

[0011] S23. When the latest information of the user is generated on the cloud platform, a real-time portrait of the user is obtained based on several local feature coefficients of the knowledge graph.

[0012] The beneficial effects of this further solution are as follows: In this invention, a global Laplacian matrix is ​​extracted to characterize the global connectivity of historical information; local feature coefficients are calculated based on the global matrix, and these are used to associate the knowledge graph with real-time browsing information to generate a portrait. This overcomes the limitation of existing knowledge graphs that rely solely on global topology, explores the integration of historical and real-time information, improves the accuracy of the integration of real-time information and historical graphs, and makes the portrait more tailored to the user's interests.

[0013] Furthermore, S22 includes the following sub-steps:

[0014] S221. Split the global Laplacian matrix into a left singular vector matrix and a right singular vector matrix;

[0015] S222. Extracting a plurality of left singular vectors of the left singular vector matrix and a plurality of right singular vectors of the right singular vector matrix;

[0016] S223. Calculate several local feature coefficients for the knowledge graph based on the left singular vector and the corresponding right singular vector.

[0017] The beneficial effects of this further approach are as follows: In this invention, singular value decomposition is used to split the global Laplacian matrix into left and right singular vector matrices, decomposing the core feature directions of the graph. Singular vectors are extracted and quantified using the vector norm and element extrema. Utilizing the dimensionality reduction and feature extraction capabilities of SVD, the complex graph matrix is ​​converted into vector features, generating local feature coefficients that contribute to the image update.

[0018] Furthermore, in S223, the local feature coefficient of the knowledge graph The expression is:

[0019] ;

[0020] Where, represents the L2 norm of the left singular vector, represents the L2 norm of the corresponding right singular vector, represents the maximum value of all elements in the left singular vector, represents the average of all elements of the left singular vector and the corresponding right singular vector, Represents the maximum of all elements of the left singular vector and the corresponding right singular vector.

[0021] Furthermore, S23 includes the following sub-steps:

[0022] S231. When the cloud platform generates the latest information of the user, extract keywords from the latest information as entities to be inserted;

[0023] S232. Obtain several entity pairs connected by relationship edges in the knowledge graph;

[0024] S233. Construct a knowledge graph update rule, and use the knowledge graph update rule and several entity pairs to determine the best relationship edge corresponding to the entity to be inserted;

[0025] S234. Calculate the fusion weight of the latest information based on the optimal relationship edges corresponding to each entity to be inserted and several local feature coefficients of the knowledge graph;

[0026] S235. Obtain a real-time portrait of the user based on the fusion weight of the latest information.

[0027] The beneficial effect of this further solution is that, in this invention, keywords (entities to be inserted) from real-time browsing information are extracted, associated with existing entity pairs in the knowledge graph, knowledge graph update rules are constructed, the optimal relationship edges for the entities to be inserted are screened, and the fusion weight of the real-time information (balancing the contribution of historical interests and real-time behavior) is calculated by combining local feature coefficients. This operation determines the association logic between real-time browsing information and the knowledge graph. By screening for optimal relationship edges (relationship types that align with browsing behavior) and calculating weights, the problem of accurately integrating new browsing information into the historical interest graph is solved, thereby improving the real-time and reasonableness of the portrait.

[0028] Furthermore, in S233, the knowledge graph update rule The expression is:

[0029] ;

[0030] Where, Indicates the entity to be inserted. Indicates the entity to be inserted Insert one of the entities of the relationship edge, Indicates the entity to be inserted Insert another entity on the relationship edge, Indicates the entity to be inserted The weight of the relationship edge after inserting the relationship edge, Represents the weight of the entity in the knowledge graph, Indicates taking the maximum value.

[0031] Furthermore, in S234, the expression of the fusion weight of the latest information is:

[0032]

[0033] Where, Indicates the first local characteristic coefficients, Represents the number of all local characteristic coefficients, Indicates that the entity to be inserted is inserted into the Relationship Edge The weight of the relationship edge after Indicates the number of relationship edges inserted into the entity.

[0034] The beneficial effect of the above further scheme is: in the present invention, the mean value of the relationship edge weight of the updated knowledge graph is further corrected by using the mean value of the local feature coefficient of the initial knowledge graph to determine the fusion weight of the latest information, taking into account the local regularity of the initial graph and the intensity characteristics of the real-time behavior.

[0035] Furthermore, in S235, the difference between 1 and the fusion weight of the latest information is used as the fusion weight of the historical information, and based on the fusion weight of the historical information and the fusion weight of the latest information, the user's historical information and the latest information are fused using the Bayesian network to obtain a real-time portrait of the user.

[0036] The beneficial effects of the present invention are: the present invention constructs a global topology of historical browsing relationships through a knowledge graph, and then calculates local feature coefficients with the help of singular value decomposition to accurately determine the fusion ratio of user historical information and the latest information; integrates local feature coefficients (historical interest structure) and real-time relationship edge weights (current behavior intensity) to balance the contributions of historical browsing and real-time browsing, breaking through the limitations of single-dimensional weighting; the present invention can strengthen information fusion, solve the fragmentation defects of existing information fusion technology, and generate user interest portraits with high accuracy and high dynamics. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of the information fusion management method based on the Internet of Things. DETAILED DESCRIPTION

[0038] The embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0039] like Figure 1 As shown, the present invention provides an information fusion management method based on the Internet of Things, comprising the following steps:

[0040] S1. Obtain the user's historical information from the cloud platform and build a knowledge graph based on the user's historical information;

[0041] S2. When the cloud platform generates the latest information about the user, it generates several local feature coefficients. Based on the local feature coefficients, it uses the knowledge graph to fuse the latest information with historical information to obtain a real-time profile of the user.

[0042] S3. Encrypt the user's real-time portrait and upload it to the cloud platform.

[0043] In this embodiment of the present invention, S2 includes the following sub-steps:

[0044] S21, extract the global Laplacian matrix of the knowledge graph;

[0045] S22. Calculate a number of local feature coefficients for the knowledge graph based on the global Laplace matrix of the knowledge graph;

[0046] S23. When the latest information of the user is generated on the cloud platform, a real-time portrait of the user is obtained based on several local feature coefficients of the knowledge graph.

[0047] In this paper, a global Laplacian matrix is ​​extracted to characterize the global connectivity of historical information. Local feature coefficients are calculated based on this global matrix, and these coefficients are used to link the knowledge graph with real-time browsing information to generate a portrait. This overcomes the limitation of existing knowledge graphs that rely solely on global topology, explores the integration of historical and real-time information, improves the accuracy of the fusion of real-time information and historical graphs, and makes the portrait more tailored to the user's interests.

[0048] In this embodiment of the present invention, S22 includes the following sub-steps:

[0049] S221. Split the global Laplacian matrix into a left singular vector matrix and a right singular vector matrix;

[0050] S222. Extracting a plurality of left singular vectors of the left singular vector matrix and a plurality of right singular vectors of the right singular vector matrix;

[0051] S223. Calculate several local feature coefficients for the knowledge graph based on the left singular vector and the corresponding right singular vector.

[0052] In this paper, singular value decomposition (SVD) is used to split the global Laplacian matrix into left and right singular vector matrices, decomposing the core feature directions of the graph. Singular vectors are then extracted and quantified using the vector norm and element extrema. Utilizing the dimensionality reduction and feature extraction capabilities of SVD, the complex graph matrix is ​​converted into vector features, generating local feature coefficients that contribute to the image update.

[0053] In the embodiment of the present invention, in S223, the local feature coefficient of the knowledge graph The expression is:

[0054] ;

[0055] Where, represents the L2 norm of the left singular vector, represents the L2 norm of the corresponding right singular vector, represents the maximum value of all elements in the left singular vector, represents the average of all elements of the left singular vector and the corresponding right singular vector, Represents the maximum of all elements of the left singular vector and the corresponding right singular vector.

[0056] In this embodiment of the present invention, S23 includes the following sub-steps:

[0057] S231. When the cloud platform generates the latest information of the user, extract keywords from the latest information as entities to be inserted;

[0058] S232. Obtain several entity pairs connected by relationship edges in the knowledge graph;

[0059] S233. Construct a knowledge graph update rule, and use the knowledge graph update rule and several entity pairs to determine the best relationship edge corresponding to the entity to be inserted;

[0060] S234. Calculate the fusion weight of the latest information based on the optimal relationship edges corresponding to each entity to be inserted and several local feature coefficients of the knowledge graph;

[0061] S235. Obtain a real-time portrait of the user based on the fusion weight of the latest information.

[0062] In this method, keywords (entities to be inserted) from real-time browsing information are extracted, associated with existing entity pairs in the knowledge graph, knowledge graph update rules are constructed, the optimal relationship edges for the entities to be inserted are screened, and the fusion weight of the real-time information (balancing the contribution of historical interests and real-time behavior) is calculated by combining local feature coefficients. This operation determines the association logic between real-time browsing information and the knowledge graph. By selecting the optimal relationship edges (relationship types that match browsing behavior) and calculating weights, the problem of accurately integrating new browsing information into the historical interest graph is solved, improving the real-time and reasonableness of the portrait.

[0063] In the embodiment of the present invention, in S233, the knowledge graph update rule The expression is:

[0064] ;

[0065] Where, Indicates the entity to be inserted. Indicates the entity to be inserted Insert one of the entities of the relationship edge, Indicates the entity to be inserted Insert another entity on the relationship edge, Indicates the entity to be inserted The weight of the relationship edge after inserting the relationship edge, Represents the weight of the entity in the knowledge graph, Indicates taking the maximum value.

[0066] In this embodiment of the present invention, in S234, the expression of the fusion weight of the latest information is:

[0067]

[0068] Where, Indicates the first local characteristic coefficients, Represents the number of all local characteristic coefficients, Indicates that the entity to be inserted is inserted into the Relationship Edge The weight of the relationship edge after Indicates the number of relationship edges inserted into the entity.

[0069] In the present invention, the mean value of the local feature coefficient of the initial knowledge graph is used to correct the mean value of the relationship edge weight of the updated knowledge graph again to determine the fusion weight of the latest information, taking into account the local regularity of the initial graph and the intensity characteristics of the real-time behavior.

[0070] In an embodiment of the present invention, in S235, the difference between 1 and the fusion weight of the latest information is used as the fusion weight of the historical information, and based on the fusion weight of the historical information and the fusion weight of the latest information, the user's historical information and the latest information are fused using a Bayesian network to obtain a real-time portrait of the user.

[0071] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the present invention.

Claims

1. An information fusion management method based on the Internet of Things, characterized in that: The following steps are involved: S1. Obtain the user's historical information from the cloud platform and build a knowledge graph based on the user's historical information; S2. When the cloud platform generates the latest information about the user, it generates several local feature coefficients. Based on the local feature coefficients, it uses the knowledge graph to fuse the latest information with historical information to obtain a real-time profile of the user. S3. Encrypt the user's real-time portrait and upload it to the cloud platform.

2. The information fusion management method based on the Internet of Things according to claim 1 is characterized in that: The S2 includes the following sub-steps: S21, extract the global Laplacian matrix of the knowledge graph; S22. Calculate a number of local feature coefficients for the knowledge graph based on the global Laplace matrix of the knowledge graph; S23. When the latest information of the user is generated on the cloud platform, a real-time portrait of the user is obtained based on several local feature coefficients of the knowledge graph.

3. The information fusion management method based on the Internet of Things according to claim 2 is characterized in that: The S22 includes the following sub-steps: S221. Split the global Laplacian matrix into a left singular vector matrix and a right singular vector matrix; S222. Extracting a plurality of left singular vectors of the left singular vector matrix and a plurality of right singular vectors of the right singular vector matrix; S223. Calculate several local feature coefficients for the knowledge graph based on the left singular vector and the corresponding right singular vector.

4. The information fusion management method based on the Internet of Things according to claim 3 is characterized in that: In S223, the local feature coefficient of the knowledge graph The expression is: ； Where, represents the L2 norm of the left singular vector, represents the L2 norm of the corresponding right singular vector, represents the maximum value of all elements in the left singular vector, represents the average of all elements of the left singular vector and the corresponding right singular vector, Represents the maximum of all elements of the left singular vector and the corresponding right singular vector.

5. The information fusion management method based on the Internet of Things according to claim 2 is characterized in that: The S23 includes the following sub-steps: S231. When the cloud platform generates the latest information of the user, extract keywords from the latest information as entities to be inserted; S232. Obtain several entity pairs connected by relationship edges in the knowledge graph; S233. Construct a knowledge graph update rule, and use the knowledge graph update rule and several entity pairs to determine the best relationship edge corresponding to the entity to be inserted; S234. Calculate the fusion weight of the latest information based on the optimal relationship edges corresponding to each entity to be inserted and several local feature coefficients of the knowledge graph; S235. Obtain a real-time portrait of the user based on the fusion weight of the latest information.

6. The information fusion management method based on the Internet of Things according to claim 5 is characterized in that: In S233, the knowledge graph update rule The expression is: ； Where, Indicates the entity to be inserted. Indicates the entity to be inserted Insert one of the entities of the relationship edge, Indicates the entity to be inserted Insert another entity on the relationship edge, Indicates the entity to be inserted The weight of the relationship edge after inserting the relationship edge, Represents the weight of the entity in the knowledge graph, Indicates taking the maximum value.

7. The information fusion management method based on the Internet of Things according to claim 5 is characterized in that: In S234, the expression of the fusion weight of the latest information is: ; Where, Indicates the first local characteristic coefficients, Represents the number of all local characteristic coefficients, Indicates that the entity to be inserted is inserted into the Relationship Edge The weight of the relationship edge after Indicates the number of relationship edges inserted into the entity.

8. The information fusion management method based on the Internet of Things according to claim 5 is characterized in that: In S235, the difference between 1 and the fusion weight of the latest information is used as the fusion weight of the historical information, and based on the fusion weight of the historical information and the fusion weight of the latest information, the user's historical information and the latest information are fused using the Bayesian network to obtain a real-time portrait of the user.

Images