	US 12,292,913 B2
	Automatic industry classification method and system
Kai Cao, Beijing (CN); Weining Li, Beijing (CN); and Minyue Zhang, Beijing (CN)
Assigned to BEIJING BENYING TECHNOLOGIES CO., LTD., Beijing (CN)
Appl. No. 17/788,303
Filed by BEIJING BENYING TECHNOLOGIES CO., LTD., Beijing (CN)
PCT Filed Jan. 19, 2020, PCT No. PCT/CN2020/073042 § 371(c)(1), (2) Date Jun. 23, 2022, PCT Pub. No. WO2021/128521, PCT Pub. Date Jul. 1, 2021.
Claims priority of application No. 201911358987.3 (CN), filed on Dec. 25, 2019.
Prior Publication US 2022/0374462 A1, Nov. 24, 2022
Int. Cl. G06F 16/353 (2025.01); G06F 18/243 (2023.01)

CPC G06F 16/353 (2019.01) [G06F 18/24323 (2023.01)]

11 Claims

1. An automatic industry classification method, comprising determining a scope of target patents, wherein the automatic industry classification method further comprises following steps:

step 1: defining a target industry tree;

step 2: generating marks on the target industry tree;

step 3: performing a rough classification for the target patents by using the marks; and

step 4: performing a fine classification for the target patents according to a result of the rough classification,

wherein step 1 further comprises:

defining an industry tree I={[i₁, . . . , i_j, . . . , i_n}, wherein i_j∈ I and is a first level industry, j is a serial number of the first level industry, 1≤j≤n, and n is a number of all leaf nodes of I; and

setting i_{jkl . . .}={i_{jkl, . . . ,}i_{jkl . . . t}} as any non-leaf node of I, wherein degree of other nodes except the leaf nodes is greater than or equal to 2, k is a serial number of a second level industry, l is a serial number of a third level industry, and t is a serial number of a penultimate level industry:

wherein the determining of the scope of the target patents is to manually determine the scope of the target patents to be classified,

wherein step 3 comprises determining nodes above the leaf nodes; and wherein step 3 further comprises following sub-steps:

step 31: generating a node set V of a graph:

step 32: arranging the marks;

step 33: generating an edge set E of the graph;

step 34: generating an adjacency matrix; and

step 35: performing node division,

wherein step 35 further comprises following sub-steps:

step 351: generating a degree matrix D=diag (d₁, d₂, . . . ,d_l+u), having a diagonal element d_i=Σ_j=1^l+uW_ij, wherein, u is a number of unmarked nodes, and W_ij, is an adjacent matrix;

step 352: generating a marked matrix, and a nonnegative (l+u)×|γ| marked matrix F= (F₁^T, F₂^T, . . . , F_l+u^T)^T, wherein an element of an i-th row F_i=(F_i1, E_i2, . . . , F_i|γ|) is a marked vector of an International Patent Classification (IPC) in the node set, a classification rule is γ_i=ar gmax_1≤j≤|γ|F_ij, wherein, γ is a set of industries, and T represents a transposition a matrix:

step 353: initializing the nonnegative marked matrix F, for i=1,2, . . . , m and j=1,2, . . . |γ[

step 354: constructing a propagation matrix

wherein,

d represents diagonal elements of th degree matric D;

step 355: generating an iterative calculation formula F(t+1)=α*B*F(t)+ (1−α) Y—wherein, α ∈(0,1) is a parameter,F(t) is a result of a t-th iteration, and Y is an initial matrix;

step 356: iterating the iterative calculation formula to convergence to obtain a state F*=lim/t→∞F(t)=(1−α) (M-αB)⁻¹Y under convergence, wherein, M is a unit matrix; and

step 357: performing a prediction of the unmarked nodes γ_i=argmax_1≤j≤|γ|F_ij*, wherein, l+1≤i≤l+u.