阅读说明：本技术 基于知识图谱的工业能力对接技术方法 (Knowledge graph-based industrial capability docking technical method ) 是由 罗红宇 吴家宏 于 2021-08-12 设计创作，主要内容包括：本发明涉及一种基于知识图谱的工业能力对接技术方法,该方法包括：获取需求,需求包括类别、产量、期限、性能指标、需求流向；需求流向为流入或流出,其中,流入为从目标企业输入,流出为向目标企业输出；从知识图谱中确定满足需求中类别、产量、期限、性能指标的子图；根据需求中的需求流向,从子图中确定目标企业；其中知识图谱中包括一级点和二级点,其中一级点与工业链的位置一一对应,二级点与企业一一对应,两个一级点之间的边表征该两个一级点在工业链中的流动关系；两个二级点之间的边表征该两个一级点对应企业的业务关系；各二级点的属性为其对应企业的属性,各二级点之间的边的权重与二级点对应企业的属性确定。(The invention relates to an industrial capacity docking technical method based on a knowledge graph, which comprises the following steps: acquiring requirements, wherein the requirements comprise categories, yield, time limit, performance indexes and requirement flow direction; the flow direction of the demand is inflow or outflow, wherein the inflow is input from the target enterprise, and the outflow is output to the target enterprise; determining subgraphs which meet the category, yield, period and performance indexes in the demand from the knowledge graph; determining a target enterprise from the subgraph according to the flow direction of the demands in the demands; the knowledge graph comprises primary points and secondary points, wherein the primary points correspond to the positions of the industrial chain one by one, the secondary points correspond to the enterprises one by one, and the edge between the two primary points represents the flowing relation of the two primary points in the industrial chain; the edge between the two secondary points represents the business relationship of the two primary points corresponding to the enterprise; the attribute of each secondary point is the attribute of the corresponding enterprise, and the weight of the edge between the secondary points is determined according to the attribute of the enterprise corresponding to the secondary points.)

1. A knowledge graph-based industrial capability docking technical method is characterized by comprising the following steps:

s101, acquiring requirements, wherein the requirements comprise categories, yields, deadlines, performance indexes and requirement flow directions; the demand flow direction is inflow or outflow, wherein the inflow is input from a target enterprise, and the outflow is output to the target enterprise;

s102, determining sub-graphs meeting the category, yield, time limit and performance indexes in the demand from the knowledge graph;

s103, determining a target enterprise from the subgraph according to the demand flow direction in the demand;

the knowledge graph comprises primary points and secondary points, wherein the primary points correspond to the positions of the industrial chain one by one, the secondary points correspond to the enterprises one by one, and the edge between the two primary points represents the flowing relation of the two primary points in the industrial chain; the edge between the two secondary points represents the business relationship of the two primary points corresponding to the enterprise; the attribute of each secondary point is the attribute of the corresponding enterprise, and the weight of the edge between the secondary points is determined according to the attribute of the enterprise corresponding to the secondary points.

2. The method according to claim 1, wherein before S102, further comprising:

s201, acquiring attributes of each enterprise; the attributes include: enterprise attributes, industrial attributes, service attributes; the enterprise attributes include: enterprise identification, position of an enterprise in an industrial chain, enterprise category and enterprise basic information; the industrial attributes include: product type, number of product lines, and production capacity of each product line; the service attributes include: production period and product performance indexes;

s202, classifying the enterprises according to the positions of the enterprises in the industrial chain, wherein each class corresponds to a primary point in the knowledge graph, determining the flow relationship between the primary points according to the industrial chain, and connecting an edge pointing from an outflow primary point to an inflow primary point between two primary points with the flow relationship;

s203, enabling each enterprise to correspond to a secondary point in the knowledge graph, connecting an edge pointing to the secondary point from the primary point between each secondary point and the primary point corresponding to the enterprise classification to which the secondary point belongs, and taking the attribute of each enterprise as the attribute of the corresponding secondary point;

s204, acquiring business relations among the enterprises, forming an edge between the two corresponding secondary points of the enterprises according to the business relations, wherein the direction of the edge is the same as the business direction, and determining the weight of the edge according to the industrial attributes and the service attributes of the two secondary points connected with the edge.

3. The method of claim 2, wherein for an edge L connecting the secondary point a and the secondary point B, and the edge L points from the secondary point a to the secondary point B, the weight of the edge L is DataA/DataB;

the data A is the sum of first values corresponding to all product categories of the enterprise corresponding to the second-level point A and the maximum value of the number of corresponding product lines in all the product categories;

the data B is the sum of second values corresponding to all product categories of the enterprise corresponding to the second-level point B and the maximum value of the number of corresponding product lines in all the product categories;

the first value corresponding to any product category of the enterprise corresponding to the second-level point A is the sum of the production capacities of all product lines corresponding to any product category of the enterprise corresponding to the second-level point A/the production period of any product category of the enterprise corresponding to the second-level point A;

and (3) the first value corresponding to any product type of the enterprise corresponding to the secondary point B is the sum of the production capacities of all product lines corresponding to any product type of the enterprise corresponding to the secondary point B/the production cycle of any product type of the enterprise corresponding to the secondary point B.

4. The method according to claim 3, wherein the S102 specifically comprises:

s102-1, determining a target primary point according to the category in the demand;

s102-2, determining a first secondary point in all secondary points connected with the target primary point according to performance indexes in requirements;

s102-3, determining a second secondary point according to the yield and the time limit in the demand in the first secondary point;

and S102-4, forming a subgraph meeting the requirement according to the second-level point.

5. The method according to claim 4, wherein the S102-1 specifically comprises:

determining the position of the enterprise corresponding to the category in the industrial chain according to the category in the requirement;

and determining the primary point corresponding to the position of the enterprise corresponding to the category in the industrial chain as a target primary point.

6. The method according to claim 4, wherein the S102-3 specifically comprises:

determining the number of product lines corresponding to the category in the demand, the production capacity of the corresponding product line and the corresponding production period in each first secondary point;

selecting a first secondary point corresponding to a production cycle less than or equal to a demand medium term;

calculating a third value of the selected first secondary point, which is the sum of the production capacities of all the corresponding product lines of the selected first secondary point, and a stable value of the selected first secondary point;

taking the selected first secondary point with the third value greater than or equal to the yield in demand as a second secondary point;

wherein the content of the first and second substances,

the stable value of the selected first secondary point is equal to the number of product lines/a fourth value + a fifth value corresponding to the selected first secondary point;

the fourth value is (the maximum production capacity of the product line corresponding to the selected first secondary point + the minimum production capacity of the product line corresponding to the selected first secondary point +4 ×) the average production capacity of the product line corresponding to the selected first secondary point)/6;

the fifth value is the in-demand deadline-the production cycle/in-demand deadline corresponding to the selected first secondary point.

7. The method according to claim 4, wherein the S102-4 specifically comprises:

taking all the second-level points as points in the subgraph, and taking edges between all the second-level points as edges between all the points in the subgraph to form the subgraph;

the attribute of each point in the subgraph is the same as the attribute of the point in the knowledge graph, and the weight of each edge in the subgraph is the same as the weight of the edge in the knowledge graph;

and taking the in-degree and out-degree of each second-level point in the knowledge graph as the specific in-degree attribute and the specific out-degree attribute of each point in the subgraph.

8. The method according to claim 7, wherein the S103 specifically includes:

s103-1, determining the out-degree out and the in-degree in of each second-level point;

s103-2, determining the specific in-degree attribute and the specific out-degree attribute of each second-level point;

s103-3, determining the target enterprise according to the demand flow direction, the specific in-degree attribute and the specific out-degree attribute of each second-level point, out and in the demand.

9. The method according to claim 7, wherein the S103-3 specifically comprises:

calculating a sixth value out + in of each second secondary point;

taking the enterprise corresponding to the second level point with the preset threshold value with the maximum sixth value as a target enterprise;

the out-degree weight and the in-degree weight are determined according to the requirement flow direction, the specific in-degree attribute and the specific out-degree attribute in the requirement.

10. The method of claim 9,

if the flow direction of the demand in the demand is input, the out-degree weight of any second secondary point is the difference between the specific out-degree attribute of any second secondary point and the out of any second secondary point/the specific out-degree attribute of any second secondary point, and the in-degree weight is 0.2 x the out-degree weight;

and if the flow direction of the demand in the demand is output, the out-degree weight is 0.2 x out-degree weight, and the in-degree weight of any second level point is the difference between the specific in-degree attribute of any second level point and the in of any second level point/the specific in-degree attribute of any second level point.

Technical Field

The invention relates to the technical field of data processing, in particular to an industrial capacity docking technical method based on a knowledge graph.

Background

With the development of industrial modernization and the improvement of market, the number of productive industrial enterprises is increased rapidly, and the updating rate is faster. This makes it more difficult to dock to a target enterprise that meets demand among many industrial enterprises.

Disclosure of Invention

Technical problem to be solved

In view of the above-mentioned shortcomings and drawbacks of the prior art, the present invention provides a knowledge-graph based industrial capability docking technology method.

(II) technical scheme

In order to achieve the purpose, the invention adopts the main technical scheme that:

a knowledge-graph-based industrial capability docking technology method, the method comprising:

s101, acquiring requirements, wherein the requirements comprise categories, yields, deadlines, performance indexes and requirement flow directions; the demand flow direction is inflow or outflow, wherein the inflow is input from a target enterprise, and the outflow is output to the target enterprise;

s102, determining sub-graphs meeting the category, yield, time limit and performance indexes in the demand from the knowledge graph;

s103, determining a target enterprise from the subgraph according to the demand flow direction in the demand;

the knowledge graph comprises primary points and secondary points, wherein the primary points correspond to the positions of the industrial chain one by one, the secondary points correspond to the enterprises one by one, and the edge between the two primary points represents the flowing relation of the two primary points in the industrial chain; the edge between the two secondary points represents the business relationship of the two primary points corresponding to the enterprise; the attribute of each secondary point is the attribute of the corresponding enterprise, and the weight of the edge between the secondary points is determined according to the attribute of the enterprise corresponding to the secondary points.

Optionally, before S102, the method further includes:

s201, acquiring attributes of each enterprise; the attributes include: enterprise attributes, industrial attributes, service attributes; the enterprise attributes include: enterprise identification, position of an enterprise in an industrial chain, enterprise category and enterprise basic information; the industrial attributes include: product type, number of product lines, and production capacity of each product line; the service attributes include: production period and product performance indexes;

s202, classifying the enterprises according to the positions of the enterprises in the industrial chain, wherein each class corresponds to a primary point in the knowledge graph, determining the flow relationship between the primary points according to the industrial chain, and connecting an edge pointing from an outflow primary point to an inflow primary point between two primary points with the flow relationship;

s203, enabling each enterprise to correspond to a secondary point in the knowledge graph, connecting an edge pointing to the secondary point from the primary point between each secondary point and the primary point corresponding to the enterprise classification to which the secondary point belongs, and taking the attribute of each enterprise as the attribute of the corresponding secondary point;

s204, acquiring business relations among the enterprises, forming an edge between the two corresponding secondary points of the enterprises according to the business relations, wherein the direction of the edge is the same as the business direction, and determining the weight of the edge according to the industrial attributes and the service attributes of the two secondary points connected with the edge.

Optionally, for an edge L connecting the secondary point a and the secondary point B, and the edge L points from the secondary point a to the secondary point B, the weight of the edge L is DataA/DataB;

the data A is the sum of first values corresponding to all product categories of the enterprise corresponding to the second-level point A and the maximum value of the number of corresponding product lines in all the product categories;

the data B is the sum of second values corresponding to all product categories of the enterprise corresponding to the second-level point B and the maximum value of the number of corresponding product lines in all the product categories;

the first value corresponding to any product category of the enterprise corresponding to the second-level point A is the sum of the production capacities of all product lines corresponding to any product category of the enterprise corresponding to the second-level point A/the production period of any product category of the enterprise corresponding to the second-level point A;

and (3) the first value corresponding to any product type of the enterprise corresponding to the secondary point B is the sum of the production capacities of all product lines corresponding to any product type of the enterprise corresponding to the secondary point B/the production cycle of any product type of the enterprise corresponding to the secondary point B.

Optionally, the S102 specifically includes:

s102-1, determining a target primary point according to the category in the demand;

s102-2, determining a first secondary point in all secondary points connected with the target primary point according to performance indexes in requirements;

s102-3, determining a second secondary point according to the yield and the time limit in the demand in the first secondary point;

and S102-4, forming a subgraph meeting the requirement according to the second-level point.

Optionally, the S102-1 specifically includes:

determining the position of the enterprise corresponding to the category in the industrial chain according to the category in the requirement;

and determining the primary point corresponding to the position of the enterprise corresponding to the category in the industrial chain as a target primary point.

Optionally, the S102-3 specifically includes:

determining the number of product lines corresponding to the category in the demand, the production capacity of the corresponding product line and the corresponding production period in each first secondary point;

selecting a first secondary point corresponding to a production cycle less than or equal to a demand medium term;

calculating a third value of the selected first secondary point, which is the sum of the production capacities of all the corresponding product lines of the selected first secondary point, and a stable value of the selected first secondary point;

taking the selected first secondary point with the third value greater than or equal to the yield in demand as a second secondary point;

wherein the content of the first and second substances,

the stable value of the selected first secondary point is equal to the number of product lines/a fourth value + a fifth value corresponding to the selected first secondary point;

the fourth value is (the maximum production capacity of the product line corresponding to the selected first secondary point + the minimum production capacity of the product line corresponding to the selected first secondary point +4 ×) the average production capacity of the product line corresponding to the selected first secondary point)/6;

the fifth value is the in-demand deadline-the production cycle/in-demand deadline corresponding to the selected first secondary point.

Optionally, the S102-4 specifically includes:

taking all the second-level points as points in the subgraph, and taking edges between all the second-level points as edges between all the points in the subgraph to form the subgraph;

the attribute of each point in the subgraph is the same as the attribute of the point in the knowledge graph, and the weight of each edge in the subgraph is the same as the weight of the edge in the knowledge graph;

and taking the in-degree and out-degree of each second-level point in the knowledge graph as the specific in-degree attribute and the specific out-degree attribute of each point in the subgraph.

Optionally, the S103 specifically includes:

s103-1, determining the out-degree out and the in-degree in of each second-level point;

s103-2, determining the specific in-degree attribute and the specific out-degree attribute of each second-level point;

s103-3, determining the target enterprise according to the demand flow direction, the specific in-degree attribute and the specific out-degree attribute of each second-level point, out and in the demand.

Optionally, the S103-3 specifically includes:

calculating a sixth value out + in of each second secondary point;

taking the enterprise corresponding to the second level point with the preset threshold value with the maximum sixth value as a target enterprise;

the out-degree weight and the in-degree weight are determined according to the requirement flow direction, the specific in-degree attribute and the specific out-degree attribute in the requirement.

Alternatively,

if the flow direction of the demand in the demand is input, the out-degree weight of any second secondary point is the difference between the specific out-degree attribute of any second secondary point and the out of any second secondary point/the specific out-degree attribute of any second secondary point, and the in-degree weight is 0.2 x the out-degree weight;

and if the flow direction of the demand in the demand is output, the out-degree weight is 0.2 x out-degree weight, and the in-degree weight of any second level point is the difference between the specific in-degree attribute of any second level point and the in of any second level point/the specific in-degree attribute of any second level point.

(III) advantageous effects

The knowledge graph-based industrial capacity docking technical method acquires requirements, wherein the requirements comprise categories, output, time limit, performance indexes and requirement flow direction; the flow direction of the demand is inflow or outflow, wherein the inflow is input from the target enterprise, and the outflow is output to the target enterprise; determining subgraphs which meet the category, yield, period and performance indexes in the demand from the knowledge graph; determining a target enterprise from the subgraph according to the flow direction of the demands in the demands; the knowledge graph comprises primary points and secondary points, wherein the primary points correspond to the positions of the industrial chain one by one, the secondary points correspond to the enterprises one by one, and the edge between the two primary points represents the flowing relation of the two primary points in the industrial chain; the edge between the two secondary points represents the business relationship of the two primary points corresponding to the enterprise; the attribute of each secondary point is the attribute of the corresponding enterprise, the weight of the edge between the secondary points is determined according to the attribute of the enterprise corresponding to the secondary points, and the accurate butt joint of the current enterprise based on the requirement is realized.

Drawings

FIG. 1 is a schematic flow chart of a knowledge-graph-based industrial capability docking technique method according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a knowledge graph according to an embodiment of the present invention.

Detailed Description

For the purpose of better explaining the present invention and to facilitate understanding, the present invention will be described in detail by way of specific embodiments with reference to the accompanying drawings.

With the development of industrial modernization and the improvement of market, the number of productive industrial enterprises is increased rapidly, and the updating rate is faster. This makes it more difficult to dock to a target enterprise that meets demand among many industrial enterprises.

Based on the technical scheme, the invention provides an industrial capacity docking technical method based on a knowledge graph, which comprises the following steps: acquiring requirements, wherein the requirements comprise categories, yield, time limit, performance indexes and requirement flow direction; the flow direction of the demand is inflow or outflow, wherein the inflow is input from the target enterprise, and the outflow is output to the target enterprise; determining subgraphs which meet the category, yield, period and performance indexes in the demand from the knowledge graph; determining a target enterprise from the subgraph according to the flow direction of the demands in the demands; the knowledge graph comprises primary points and secondary points, wherein the primary points correspond to the positions of the industrial chain one by one, the secondary points correspond to the enterprises one by one, and the edge between the two primary points represents the flowing relation of the two primary points in the industrial chain; the edge between the two secondary points represents the business relationship of the two primary points corresponding to the enterprise; the attribute of each secondary point is the attribute of the corresponding enterprise, the weight of the edge between the secondary points is determined according to the attribute of the enterprise corresponding to the secondary points, and the accurate butt joint of the current enterprise based on the requirement is realized.

Referring to fig. 1, the implementation flow of the knowledge graph-based industrial capability docking technical method according to the embodiment is as follows:

and S101, acquiring a demand.

Wherein, the demand comprises category, yield, period, performance index and demand flow direction.

Demand flows are either inflows, where inflows are inputs from the target enterprise (e.g., purchasing products from the target enterprise), and outflows are outputs to the target enterprise (e.g., selling products to the target enterprise).

And S102, determining sub-graphs meeting the category, yield, period and performance indexes in the demand from the knowledge graph.

The knowledge graph comprises primary points and secondary points, wherein the primary points correspond to positions of the industrial chain one by one, the secondary points correspond to enterprises one by one, and edges between the two primary points represent the flowing relation of the two primary points in the industrial chain. And the edge between the two secondary points represents the business relationship of the two primary points corresponding to the enterprise. The attribute of each secondary point is the attribute of the corresponding enterprise, and the weight of the edge between the secondary points is determined according to the attribute of the enterprise corresponding to the secondary points.

That is, before executing S102, a knowledge graph is constructed, and the construction process of the knowledge graph is as follows:

s201, acquiring the attributes of each enterprise.

Wherein the attributes include: enterprise attributes, industrial attributes, service attributes.

The enterprise attributes include: enterprise identification, location of the enterprise in the industrial chain (e.g., upstream, midstream, downstream), enterprise category (e.g., industrial, transportation, service, etc.), enterprise base information.

The industrial attributes include: product type (e.g., bolts, nuts, etc.), number of product lines, and throughput per product line.

The service attributes include: production period and product performance index.

S202, classifying the enterprises according to the positions of the enterprises in the industrial chain, wherein each class corresponds to a primary point in the knowledge graph, determining the flow relationship between the primary points according to the industrial chain, and connecting an edge pointing from an outflow primary point to an inflow primary point between two primary points with the flow relationship.

As shown in FIG. 2, the enterprises are classified into upstream, midstream and downstream, the upstream corresponds to a primary point P1 in FIG. 2, the midstream corresponds to a primary point P2 in FIG. 2, and the downstream corresponds to a primary point P3 in FIG. 2. According to the upstream-to-midstream-to-downstream Liudong relationship, an edge pointing from P1 to P2 is formed between P1 and P2, and an edge pointing from P2 to P3 is formed between P2 and P3.

S203, each enterprise corresponds to a secondary point in the knowledge graph, an edge pointing to the secondary point from the primary point is connected between each secondary point and the primary point corresponding to the enterprise classification to which the secondary point belongs, and the attribute of each enterprise is used as the attribute of the corresponding secondary point.

For example, the white circles in fig. 2 are secondary points, each of which corresponds to a business. The enterprises corresponding to p11, p12 and p13 are upstream enterprises, the enterprise corresponding to p21 is a midstream enterprise, and the enterprises corresponding to p31 and p32 are downstream enterprises. Then an edge pointing from P1 to P11, P12, P13 is formed between P1 and P11, P12, P13, respectively. An edge pointing from P1 to P21 is formed between P2 and P21. An edge pointing from P1 to P31 and P32 is formed between P3 and P31 and P32 respectively.

S204, acquiring business relations among the enterprises, forming an edge between the two corresponding secondary points of the enterprises according to the business relations, wherein the direction of the edge is the same as the business direction, and determining the weight of the edge according to the industrial attributes and the service attributes of the two secondary points connected with the edge.

If the business corresponding to p13 sells its products to the business corresponding to p21, an edge is formed between p13 and p21, which is pointed to p21 from p13, as shown in fig. 2.

The weight of the edge connecting any two secondary points (e.g., the weight of the edge L connecting the secondary point a and the secondary point B), and if the edge L points from the secondary point a to the secondary point B, the weight of the edge L is DataA/DataB.

And the DataA is the sum of first values corresponding to all product categories of the enterprise corresponding to the secondary point A and the maximum value of the number of corresponding product lines in all the product categories.

And the DataB is the sum of second values corresponding to all product categories of the enterprise corresponding to the second-level point B and the maximum value of the number of corresponding product lines in all the product categories.

The first value corresponding to any product category of the enterprise corresponding to the second-level point A is the sum of the production capacities of all product lines corresponding to any product category of the enterprise corresponding to the second-level point A/the production cycle of any product category of the enterprise corresponding to the second-level point A.

And (3) the first value corresponding to any product type of the enterprise corresponding to the secondary point B is the sum of the production capacities of all product lines corresponding to any product type of the enterprise corresponding to the secondary point B/the production cycle of any product type of the enterprise corresponding to the secondary point B.

Based on the knowledge graph, the implementation process of the step is as follows:

s102-1, determining a target primary point according to the category in the demand.

For example: and determining the position of the corresponding enterprise of the category in the industrial chain according to the category in the demand. And determining the primary point corresponding to the position of the enterprise corresponding to the category in the industrial chain as a target primary point.

Taking fig. 2 as an example, if the category is the service industry, the service industry corresponds to and the position of the enterprise in the industrial chain is downstream, then P3 is determined as the target first-class point.

S102-2, determining a first secondary point in all secondary points connected with the target primary point according to the performance index in the demand.

For example, it is determined that the corresponding attribute of p31 (specifically, the product performance index in the service attribute) meets the performance index in the demand, and at the same time, it is determined that the corresponding attribute of p32 (specifically, the product performance index in the service attribute) meets the performance index in the demand.

If both p31 and p32 meet the performance criteria in demand, then both p31 and p32 are the first secondary points.

If only p31 meets the performance criteria in demand, then only p31 is the first secondary point.

If only p33 meets the performance criteria in demand, then only p33 is the first secondary point.

If neither p31 nor p32 meets the performance criteria in demand, then there is no first secondary point, in which case the docking fails. Namely, the process is not executed any more, and the information related to the docking failure is fed back to the user.

S102-3, in the first secondary point, determining a second secondary point according to the yield and the time limit in the demand.

Specifically, the number of product lines corresponding to the category in the demand, the production capacity of the corresponding product line, and the corresponding production period in each first-level point are determined.

A first secondary point is selected corresponding to a production cycle less than or equal to the medium term of demand.

And calculating a third value of the selected first secondary point, which is the sum of the production capacities of all the corresponding product lines of the selected first secondary point, and the stable value of the selected first secondary point.

The second level point is selected as the first level point having the third value greater than or equal to the yield in demand.

Wherein the content of the first and second substances,

and the stable value of the selected first secondary point is equal to the number of the product lines/the fourth value + the fifth value corresponding to the selected first secondary point.

The fourth value (maximum throughput of the product line corresponding to the selected first secondary point + minimum throughput of the product line corresponding to the selected first secondary point +4 ×) average throughput of the product line corresponding to the selected first secondary point)/6.

The fifth value is the in-demand deadline-the production cycle/in-demand deadline corresponding to the selected first secondary point.

In this step, if the second level point does not exist, the docking fails in this case. Namely, the process is not executed any more, and the information related to the docking failure is fed back to the user.

And S102-4, forming a subgraph meeting the requirement according to the second level point.

Namely, all the second-level points are used as points in the subgraph, and edges among all the second-level points are used as edges among all the points in the subgraph to form the subgraph.

The attribute of each point in the subgraph is the same as that of the point in the knowledge graph, and the weight of each edge in the subgraph is the same as that of the edge in the knowledge graph.

And taking the in-degree and out-degree of each second-level point in the knowledge graph as the specific in-degree attribute and the specific out-degree attribute of each point in the subgraph.

That is, a subgraph is one subgraph in the knowledge-graph.

S103, determining the target enterprise from the subgraph according to the flow direction of the requirements.

The implementation process of the step is as follows:

s103-1, determining the out-degree out and the in-degree in of each second-level point.

S103-2, determining the specific in-degree attribute and the specific out-degree attribute of each second-level point.

S103-3, determining the target enterprise according to the demand flow direction, the specific in-degree attribute and the specific out-degree attribute of each second-level point, out and in the demand.

For example:

and calculating a sixth value out + in of each second secondary point.

And taking the enterprise corresponding to the second level point with the preset threshold value with the maximum sixth value as a target enterprise.

The out-degree weight and the in-degree weight are determined according to the requirement flow direction, the specific in-degree attribute and the specific out-degree attribute in the requirement.

If the flow direction of the demand in the demand is input, the out-degree weight of any second secondary point is the difference between the specific out-degree attribute of any second secondary point and the out of any second secondary point/the specific out-degree attribute of any second secondary point, and the in-degree weight is 0.2 x out-degree weight.

And if the flow direction of the demand in the demand is output, the out-degree weight is 0.2 x out-degree weight, and the in-degree weight of any second level point is the difference between the specific in-degree attribute of any second level point and the in of any second level point/the specific in-degree attribute of any second level point.

According to the industrial capability docking technical method based on the knowledge graph, the attributes of the enterprises are described through the knowledge graph, the target enterprise is determined based on the relation between the knowledge graph and the requirements, and the accurate docking of the current enterprise based on the requirements can be achieved.

Wherein the attributes include: enterprise attributes, industrial attributes, service attributes; the enterprise attributes include: enterprise identification, position of an enterprise in an industrial chain, enterprise category and enterprise basic information; the industrial attributes include: product type, number of product lines, and production capacity of each product line; the service attributes include: production period and product performance index.

The embodiment provides an industrial capacity docking technical method based on a knowledge graph, which comprises the following steps: acquiring requirements, wherein the requirements comprise categories, yield, time limit, performance indexes and requirement flow direction; the flow direction of the demand is inflow or outflow, wherein the inflow is input from the target enterprise, and the outflow is output to the target enterprise; determining subgraphs which meet the category, yield, period and performance indexes in the demand from the knowledge graph; determining a target enterprise from the subgraph according to the flow direction of the demands in the demands; the knowledge graph comprises primary points and secondary points, wherein the primary points correspond to the positions of the industrial chain one by one, the secondary points correspond to the enterprises one by one, and the edge between the two primary points represents the flowing relation of the two primary points in the industrial chain; the edge between the two secondary points represents the business relationship of the two primary points corresponding to the enterprise; the attribute of each secondary point is the attribute of the corresponding enterprise, the weight of the edge between the secondary points is determined according to the attribute of the enterprise corresponding to the secondary points, and the accurate butt joint of the current enterprise based on the requirement is realized.

In order to better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention 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 present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. 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.

It should be noted that in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the terms first, second, third and the like are for convenience only and do not denote any order. These words are to be understood as part of the name of the component.

Furthermore, it should be noted that in the description of the present specification, the description of the term "one embodiment", "some embodiments", "examples", "specific examples" or "some examples", etc., means that a specific feature, structure, material or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the claims should be construed to include preferred embodiments and all changes and modifications that fall within the scope of the invention.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include such modifications and variations.