CN112069323A - Recommendation method based on industrial knowledge graph - Google Patents
Recommendation method based on industrial knowledge graph Download PDFInfo
- Publication number
- CN112069323A CN112069323A CN202010774714.3A CN202010774714A CN112069323A CN 112069323 A CN112069323 A CN 112069323A CN 202010774714 A CN202010774714 A CN 202010774714A CN 112069323 A CN112069323 A CN 112069323A
- Authority
- CN
- China
- Prior art keywords
- point
- industrial
- edge
- determining
- degree
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a recommendation method based on an industrial knowledge graph, which comprises the following steps: acquiring an industrial knowledge graph, wherein the industrial knowledge graph comprises points and edges, each point corresponds to an industrial entity, and if a relationship exists between the two industrial entities, one edge exists between the points corresponding to the two industrial entities; determining a keyword; calculating the point association degree between the key word and each point in the industrial knowledge graph and the edge association degree between the key word and each point in the industrial knowledge graph; and determining the recommended object according to the point association degree and the edge association degree. The method provided by the invention can be recommended based on the relation among industrial data.
Description
Technical Field
The invention relates to the technical field of information recommendation, in particular to a recommendation method based on an industrial knowledge graph.
Background
In the industrial field, a large amount of data is generated during the operation or production of a device. For example, the device is running, timing signals or analog signals generated by different sensors on the device, and parameters of the device itself (e.g., hardware address of the device, address of the memory). How to make recommendations based on relationships between industrial data is a major concern.
Disclosure of Invention
Technical problem to be solved
In order to solve the problems, the invention provides a recommendation method based on an industrial knowledge graph.
(II) technical scheme
In order to achieve the purpose, the invention adopts the main technical scheme that:
a recommendation method based on an industrial knowledge graph, the method comprising:
s101, acquiring an industrial knowledge graph, wherein the industrial knowledge graph comprises points and edges, each point corresponds to an industrial entity, and if a relationship exists between the two industrial entities, one edge exists between the points corresponding to the two industrial entities;
s102, determining keywords;
s103, calculating the point association degree between the key words and each point in the industrial knowledge graph and the edge association degree between the key words and each point in the industrial knowledge graph;
and S104, determining a recommended object according to the point relevance and the edge relevance.
Optionally, the calculating the point association degree between the keyword and each point in the industrial knowledge graph in S103 specifically includes:
s201, obtaining description information of each industrial entity;
s202, determining the point association degree of a point corresponding to the industrial entity where the description information not including the keyword is located as 0;
s203, determining the point association degree of the point corresponding to the industrial entity where the description information including the keyword is located as N1/N;
wherein N1 is the number of words with the same description information as the keyword, and N is the total word number of the keyword.
Optionally, the calculating the point association degree between the keyword and each point in the industrial knowledge graph in S103 specifically includes:
s211, obtaining description information of each industrial entity;
s212, determining the point association degree of a point corresponding to the industrial entity where the description information not including the keyword is located as 0;
s213, determining the point association degree of the points corresponding to the industrial entity containing the description information of the keywords as X D N1/N;
wherein N1 is the number of words with the same description information as the keyword, N is the total number of words of the keyword, X is the industrial entity grade, and D is the degree of the point corresponding to the industrial entity.
Optionally, the calculating the point association degree between the keyword and each point in the industrial knowledge graph in S103 specifically includes:
s221, obtaining description information of each industrial entity;
s222, setting the point association degree of the points corresponding to all the industrial entities to be 0;
s223, determining a point corresponding to the industrial entity where the description information including the keyword is located;
s224, sequentially selecting a point corresponding to the industrial entity where the description information including the keyword is located, and determining the communication rate between each point in the industrial knowledge graph and the selected point through the following formula:
Aij＝Yij*Xi*Di/Dj；
s225, determining the point association degree of the point corresponding to the industrial entity containing the description information of the keyword as the current point association degree + Xi Di 1/N; determining the point association degree of the points corresponding to the industrial entities without the description information of the keywords as the sum of the current point association degree + the connectivity rate of the points corresponding to the industrial entities with the description information of the keywords and/or 1/N | Di-Dj | of the points;
wherein i is the selected industrial entity identifier, j is the identifier of the midpoint of the industrial knowledge graph, Aij is the communication rate between the midpoint j of the industrial knowledge graph and the selected point i, Yi is the number of nodes between the midpoint j of the industrial knowledge graph and the selected point i, Xi is the industrial entity grade of the selected point i, Di is the degree of the selected point i, and Dj is the degree of the midpoint j of the industrial knowledge graph.
Optionally, the calculating the edge association degree between the keyword and each point in the industrial knowledge graph in S103 specifically includes:
s301, determining the point association degree of two points connected by the edge;
s302, determining the average value of the point association degrees of the two points as the edge association degree of the edge.
Optionally, the calculating the edge association degree between the keyword and each point in the industrial knowledge graph in S103 specifically includes:
s311, determining the point association degree of two points connected by the edge;
s312, the association degree of the edge is the point association degree/Du + the point association degree/Dv of a point u connected to the edge;
where Du is the degree of point u and Dv is the degree of point v.
Optionally, the calculating the edge association degree between the keyword and each point in the industrial knowledge graph in S103 specifically includes:
s321, determining the point association degree of two points connected by the edge;
s322, determining the maximum value max (u), the minimum value min (u) and the average value avg (u) in the point association degrees of all the points connected by the point u connected by the edge;
s323, determining the maximum value max (v), the minimum value min (v) and the average value avg (v) in the point association degrees of all the points connected by the point v connected by the edge;
s324, the degree of association of the side ═ max (u) -avg (u)). the degree of association of points/Du × (u) + (max (v) -avg (v)). the degree of association of points/Dv × (v) of a point (v) to which the side is connected;
where Du is the degree of point u and Dv is the degree of point v.
Optionally, the S104 specifically includes:
s104-1, determining a median value of the point association degree;
s104-2, taking the points with the point association degree larger than the median as candidate points;
s104-3, determining a maximum connected graph in a sub-graph formed by the candidate points;
and S104-4, determining a recommended object based on the maximum connected graph.
9. The method according to claim 8, wherein the S104-4 specifically comprises:
s104-4-11, determining the edge association degree of each edge in the maximum connected graph;
s104-4-12, determining the recommended value of each side as the relevance degree a Da of the side; wherein a is the highest grade of the industrial entity corresponding to the two nodes connected by the edge, and Da is the sum of the degrees of the two nodes connected by the edge;
and S104-4-13, determining a graph formed by edges with recommendation values larger than a preset threshold value and connected candidate nodes as a recommendation object.
Optionally, the S104-4 specifically includes:
s104-4-21, determining the edge association degree of each edge in the maximum connected graph;
s104-4-22, determining the recommended value of each edge as the relevance degree of the edge a Da as the minimum value of the relevance degree of the midpoint of the two nodes connected by the edge/the maximum value of the relevance degree of the midpoint of the two nodes connected by the edge; wherein a is the highest grade of the industrial entity corresponding to the two nodes connected by the edge, and Da is the sum of the degrees of the two nodes connected by the edge;
and S104-4-23, determining a graph formed by edges with recommendation values larger than a preset threshold value and connected candidate nodes as a recommendation object.
(III) advantageous effects
The invention has the beneficial effects that: acquiring an industrial knowledge graph, wherein the industrial knowledge graph comprises points and edges, each point corresponds to an industrial entity, and if a relationship exists between the two industrial entities, one edge exists between the points corresponding to the two industrial entities; determining a keyword; calculating the point association degree between the key word and each point in the industrial knowledge graph and the edge association degree between the key word and each point in the industrial knowledge graph; and determining a recommendation object according to the point association degree and the edge association degree, and further realizing recommendation based on the relationship among the industrial data.
Drawings
FIG. 1 is a schematic flow chart of a recommendation method based on an industrial knowledge graph according to an embodiment of the present application;
fig. 2 is a schematic structural diagram based on an industrial knowledge graph according to an embodiment of the present application.
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.
In the industrial field, a large amount of data is generated during the operation or production of a device. For example, the device is running, timing signals or analog signals generated by different sensors on the device, and parameters of the device itself (e.g., hardware address of the device, address of the memory). How to make recommendations based on relationships between industrial data is a major concern.
Based on the above, the invention provides a recommendation method based on an industrial knowledge graph, which comprises points and edges, wherein each point corresponds to an industrial entity, and if a relationship exists between the two industrial entities, an edge exists between the points corresponding to the two industrial entities; determining a keyword; calculating the point association degree between the key word and each point in the industrial knowledge graph and the edge association degree between the key word and each point in the industrial knowledge graph; and determining a recommendation object according to the point association degree and the edge association degree, and further realizing recommendation based on the relationship among the industrial data.
Referring to fig. 1, the implementation process of the recommendation method based on the industrial knowledge graph is as follows:
and S101, acquiring an industrial knowledge graph.
The industrial knowledge graph comprises points and edges, each point corresponds to one industrial entity, and if a relationship exists between the two industrial entities, one edge exists between the points corresponding to the two industrial entities.
Such as the industry knowledge graph shown in fig. 2.
S102, determining keywords.
The keywords may be input by the user or obtained through user behavior.
S103, calculating the point association degree between the key words and each point in the industrial knowledge graph and the edge association degree between the key words and each point in the industrial knowledge graph.
1) There are many schemes for calculating the point association between the keywords and each point in the industrial knowledge graph, and only a few implementations are provided below.
The first implementation scheme is as follows:
s201, obtaining description information of each industrial entity.
The industrial entities herein each describe information including, but not limited to, profiles of the industrial entities.
S202, determining the point association degree of the point corresponding to the industrial entity where the description information without the keyword is located as 0.
S203, determining the point association degree of the point corresponding to the industrial entity where the description information including the keyword is located as N1/N.
Where N1 is the number of words with the same description information as the keyword, and N is the total number of words of the keyword.
The second implementation scheme is as follows:
and S211, acquiring the description information of each industrial entity.
S212, the point association degree of the point corresponding to the industrial entity where the description information without the keyword is located is determined to be 0.
And S213, determining the point association degree of the points corresponding to the industrial entities containing the description information of the keywords as X D N1/N.
Wherein N1 is the number of words with the same description information and the keyword, N is the total number of words of the keyword, X is the industrial entity level, and D is the degree of the point corresponding to the industrial entity.
The industrial entity level here is a predetermined level for describing the importance of the industrial entity, such as a level 1 of the industrial entity related to confidential information, or a level 10 of the industrial entity related to confidential products, and the like. The setting is specifically performed according to the situation in the practical application, and is not limited here.
The third implementation scheme is as follows:
s221, obtaining the description information of each industrial entity.
S222, setting the point association degree of the points corresponding to all the industrial entities to be 0.
S223, determining the point corresponding to the industrial entity where the description information including the keyword is located.
S224, sequentially selecting a point corresponding to the industrial entity where the description information including the keyword is located, and determining the communication rate between each point in the industrial knowledge graph and the selected point through the following formula:
Aij＝Yij*Xi*Di/Dj。
wherein i is the selected industrial entity identifier, j is the identifier of the midpoint of the industrial knowledge graph, Aij is the communication rate between the midpoint j of the industrial knowledge graph and the selected point i, Yi is the number of nodes between the midpoint j of the industrial knowledge graph and the selected point i, Xi is the industrial entity grade of the selected point i, Di is the degree of the selected point i, and Dj is the degree of the midpoint j of the industrial knowledge graph.
And S225, determining the point association degree of the point corresponding to the industrial entity containing the description information of the keyword as the current point association degree + Xi Di 1/N.
Determining the point association degree of the points corresponding to the industrial entity where the description information not including the keyword is located as follows: and the current point association degree + the sum of the connectivity rate N1/N | Di-Dj | of the points corresponding to the industrial entities each containing the description information of the keyword.
Since the point relevance degrees of the points corresponding to all the industrial entities are all set to 0 in S222, the point relevance degree of the industrial entity has a value which can be the latest calculated real point relevance degree or 0.
If the point corresponding to the industrial entity where the description information not including the keyword is located is the point a, the point association degree of the point a is equal to the point association degree + of the current point a (the connectivity rate N1/N | Di-Dj | + of the point a and the first point corresponding to the industrial entity where the description information including the keyword is located is equal to the connectivity rate N1/N | Di-Dj | + … … + of the point a and the last point corresponding to the industrial entity where the description information including the keyword is located).
2) There may be many schemes for calculating the degree of edge association between the keywords and each point in the industrial knowledge graph, and only a few implementation schemes are provided below.
The first implementation scheme is as follows:
s301, determining the point association degree of two points connected by the edge.
S302, determining the average value of the point association degrees of the two points as the edge association degree of the edge.
The second implementation scheme is as follows:
s311, determine the point association degree of two points connected by the edge.
S312, the association degree of the edge is the point association degree/Du + the point association degree/Dv of a point u connected to the edge.
Where Du is the degree of point u and Dv is the degree of point v.
The third implementation scheme is as follows:
s321, determining a point association degree of two points connected by the edge.
S322, determine the maximum value max (u), the minimum value min (u) and the average value avg (u) of the point association degrees of all the points to which the one point u connected to the edge is connected.
S323, determine the maximum value max (v), the minimum value min (v), and the average value avg (v) of the point association degrees of all the points to which the one point v connected to the edge is connected.
S324, the degree of association of the side ═ max (u) -avg (u)). the degree of association of the point u to which the side is connected/Du × min (u) + (max (v) -avg (v)). the degree of association of the point v to which the side is connected/Dv × min (v).
Where Du is the degree of point u and Dv is the degree of point v.
And S104, determining a recommended object according to the point association degree and the edge association degree.
In particular, the method comprises the following steps of,
s104-1, determining the median value of the point relevance.
And S104-2, taking the points with the point association degree larger than the median as candidate points.
And S104-3, determining the maximum connected graph in the subgraph formed by the candidate points.
And S104-4, determining a recommended object based on the maximum connected graph.
One implementation of S104-4 is for example,
and S104-4-11, determining the edge association degree of each edge in the maximum connected graph.
And S104-4-12, determining the recommended value of each side as the relevance degree a Da of the side.
Wherein a is the highest grade of the industrial entity corresponding to the two nodes connected by the edge, and Da is the sum of the degrees of the two nodes connected by the edge.
And S104-4-13, determining a graph formed by edges with recommendation values larger than a preset threshold value and connected candidate nodes as a recommendation object.
Another implementation of S104-4 is for example,
and S104-4-21, determining the edge association degree of each edge in the maximum connected graph.
And S104-4-22, determining the recommended value of each edge as the relevance degree of the edge a Da and the minimum value of the relevance degree of the middle points of the two nodes connected by the edge/the maximum value of the relevance degree of the middle points of the two nodes connected by the edge.
Wherein a is the highest grade of the industrial entity corresponding to the two nodes connected by the edge, and Da is the sum of the degrees of the two nodes connected by the edge.
And S104-4-23, determining a graph formed by edges with recommendation values larger than a preset threshold value and connected candidate nodes as a recommendation object.
Has the advantages that: acquiring an industrial knowledge graph, wherein the industrial knowledge graph comprises points and edges, each point corresponds to an industrial entity, and if a relationship exists between the two industrial entities, one edge exists between the points corresponding to the two industrial entities; determining a keyword; calculating the point association degree between the key word and each point in the industrial knowledge graph and the edge association degree between the key word and each point in the industrial knowledge graph; and determining a recommendation object according to the point association degree and the edge association degree, and further realizing recommendation based on the relationship among the industrial data.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Finally, it should be noted that: the above-mentioned embodiments are only used for illustrating the technical solution of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An industrial knowledge graph-based recommendation method, characterized in that the method comprises:
s101, acquiring an industrial knowledge graph, wherein the industrial knowledge graph comprises points and edges, each point corresponds to an industrial entity, and if a relationship exists between the two industrial entities, one edge exists between the points corresponding to the two industrial entities;
s102, determining keywords;
s103, calculating the point association degree between the key words and each point in the industrial knowledge graph and the edge association degree between the key words and each point in the industrial knowledge graph;
and S104, determining a recommended object according to the point relevance and the edge relevance.
2. The method according to claim 1, wherein the step of calculating the point association degree between the keyword and each point in the industrial knowledge graph in the step S103 specifically comprises:
s201, obtaining description information of each industrial entity;
s202, determining the point association degree of a point corresponding to the industrial entity where the description information not including the keyword is located as 0;
s203, determining the point association degree of the point corresponding to the industrial entity where the description information including the keyword is located as N1/N;
wherein N1 is the number of words with the same description information as the keyword, and N is the total word number of the keyword.
3. The method according to claim 1, wherein the step of calculating the point association degree between the keyword and each point in the industrial knowledge graph in the step S103 specifically comprises:
s211, obtaining description information of each industrial entity;
s212, determining the point association degree of a point corresponding to the industrial entity where the description information not including the keyword is located as 0;
s213, determining the point association degree of the points corresponding to the industrial entity containing the description information of the keywords as X D N1/N;
wherein N1 is the number of words with the same description information as the keyword, N is the total number of words of the keyword, X is the industrial entity grade, and D is the degree of the point corresponding to the industrial entity.
4. The method according to claim 1, wherein the step of calculating the point association degree between the keyword and each point in the industrial knowledge graph in the step S103 specifically comprises:
s221, obtaining description information of each industrial entity;
s222, setting the point association degree of the points corresponding to all the industrial entities to be 0;
s223, determining a point corresponding to the industrial entity where the description information including the keyword is located;
s224, sequentially selecting a point corresponding to the industrial entity where the description information including the keyword is located, and determining the communication rate between each point in the industrial knowledge graph and the selected point through the following formula:
Aij＝Yij*Xi*Di/Dj；
s225, determining the point association degree of the point corresponding to the industrial entity containing the description information of the keyword as the current point association degree + Xi Di 1/N; determining the point association degree of the points corresponding to the industrial entities without the description information of the keywords as the sum of the current point association degree + the connectivity rate of the points corresponding to the industrial entities with the description information of the keywords and/or 1/N | Di-Dj | of the points;
wherein i is the selected industrial entity identifier, j is the identifier of the midpoint of the industrial knowledge graph, Aij is the communication rate between the midpoint j of the industrial knowledge graph and the selected point i, Yi is the number of nodes between the midpoint j of the industrial knowledge graph and the selected point i, Xi is the industrial entity grade of the selected point i, Di is the degree of the selected point i, and Dj is the degree of the midpoint j of the industrial knowledge graph.
5. The method according to claim 1, wherein the step of calculating the edge association between the keyword and each point in the industrial knowledge graph in the step S103 specifically comprises:
s301, determining the point association degree of two points connected by the edge;
s302, determining the average value of the point association degrees of the two points as the edge association degree of the edge.
6. The method according to claim 1, wherein the step of calculating the edge association between the keyword and each point in the industrial knowledge graph in the step S103 specifically comprises:
s311, determining the point association degree of two points connected by the edge;
s312, the association degree of the edge is the point association degree/Du + the point association degree/Dv of a point u connected to the edge;
where Du is the degree of point u and Dv is the degree of point v.
7. The method according to claim 1, wherein the step of calculating the edge association between the keyword and each point in the industrial knowledge graph in the step S103 specifically comprises:
s321, determining the point association degree of two points connected by the edge;
s322, determining the maximum value max (u), the minimum value min (u) and the average value avg (u) in the point association degrees of all the points connected by the point u connected by the edge;
s323, determining the maximum value max (v), the minimum value min (v) and the average value avg (v) in the point association degrees of all the points connected by the point v connected by the edge;
s324, the degree of association of the side ═ max (u) -avg (u)). the degree of association of points/Du × (u) + (max (v) -avg (v)). the degree of association of points/Dv × (v) of a point (v) to which the side is connected;
where Du is the degree of point u and Dv is the degree of point v.
8. The method according to claim 1, wherein the S104 specifically includes:
s104-1, determining a median value of the point association degree;
s104-2, taking the points with the point association degree larger than the median as candidate points;
s104-3, determining a maximum connected graph in a sub-graph formed by the candidate points;
and S104-4, determining a recommended object based on the maximum connected graph.
9. The method according to claim 8, wherein the S104-4 specifically comprises:
s104-4-11, determining the edge association degree of each edge in the maximum connected graph;
s104-4-12, determining the recommended value of each side as the relevance degree a Da of the side; wherein a is the highest grade of the industrial entity corresponding to the two nodes connected by the edge, and Da is the sum of the degrees of the two nodes connected by the edge;
and S104-4-13, determining a graph formed by edges with recommendation values larger than a preset threshold value and connected candidate nodes as a recommendation object.
10. The method according to claim 8, wherein the S104-4 specifically comprises:
s104-4-21, determining the edge association degree of each edge in the maximum connected graph;
s104-4-22, determining the recommended value of each edge as the relevance degree of the edge a Da as the minimum value of the relevance degree of the midpoint of the two nodes connected by the edge/the maximum value of the relevance degree of the midpoint of the two nodes connected by the edge; wherein a is the highest grade of the industrial entity corresponding to the two nodes connected by the edge, and Da is the sum of the degrees of the two nodes connected by the edge;
and S104-4-23, determining a graph formed by edges with recommendation values larger than a preset threshold value and connected candidate nodes as a recommendation object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010774714.3A CN112069323B (en) | 2020-08-04 | 2020-08-04 | Recommendation method based on industrial knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010774714.3A CN112069323B (en) | 2020-08-04 | 2020-08-04 | Recommendation method based on industrial knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112069323A true CN112069323A (en) | 2020-12-11 |
| CN112069323B CN112069323B (en) | 2024-04-26 |
Family
ID=73657424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010774714.3A Active CN112069323B (en) | 2020-08-04 | 2020-08-04 | Recommendation method based on industrial knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112069323B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699251A (en) * | 2021-03-23 | 2021-04-23 | 中国信息通信研究院 | Data aggregation method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016008261A1 (en) * | 2014-07-16 | 2016-01-21 | 百度在线网络技术（北京）有限公司 | Method and device for showing recommendation result |
| CN108153901A (en) * | 2018-01-16 | 2018-06-12 | 北京百度网讯科技有限公司 | The information-pushing method and device of knowledge based collection of illustrative plates |
| CN108536702A (en) * | 2017-03-02 | 2018-09-14 | 腾讯科技（深圳）有限公司 | A kind of related entities determine method, apparatus and computing device |
-
2020
- 2020-08-04 CN CN202010774714.3A patent/CN112069323B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016008261A1 (en) * | 2014-07-16 | 2016-01-21 | 百度在线网络技术（北京）有限公司 | Method and device for showing recommendation result |
| CN108536702A (en) * | 2017-03-02 | 2018-09-14 | 腾讯科技（深圳）有限公司 | A kind of related entities determine method, apparatus and computing device |
| CN108153901A (en) * | 2018-01-16 | 2018-06-12 | 北京百度网讯科技有限公司 | The information-pushing method and device of knowledge based collection of illustrative plates |
Non-Patent Citations (2)
| Title |
|---|
| CHAN LIU 等: "A Survey of Recommendation Algorithms Based on Knowledge Graph Embedding", 2019 IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND EDUCATIONAL INFORMATIZATION (CSEI), pages 168 - 171 * |
| 孙雨生 等: "国内基于知识图谱的信息推荐研究进展", 情报理论与实践, vol. 42, no. 12, pages 163 - 149 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699251A (en) * | 2021-03-23 | 2021-04-23 | 中国信息通信研究院 | Data aggregation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112069323B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu et al. | Design and analysis of discrete-time robust Kalman filters | |
| CN110276442A (en) | A kind of searching method and device of neural network framework | |
| CN112528995B (en) | Method for training target detection model, target detection method and device | |
| CN113032117A (en) | Deep learning framework training method and device and storage medium | |
| EP3428838A2 (en) | Skin condition detection method and electronic device | |
| CN114816393B (en) | Information generation method, device, equipment and storage medium | |
| WO2021169478A1 (en) | Fusion training method and apparatus for neural network model | |
| CN112069323A (en) | Recommendation method based on industrial knowledge graph | |
| CN110601978A (en) | Flow distribution control method and device | |
| CN110740193A (en) | platform activity prediction method and device, storage medium and electronic equipment | |
| CN109978172B (en) | Resource pool utilization rate prediction method and device based on extreme learning machine | |
| CN113326449A (en) | Method, apparatus, electronic device, and medium for predicting traffic flow | |
| CN110442754B (en) | Label updating method and device and distributed storage system | |
| CN115186738B (en) | Model training method, device and storage medium | |
| CN113301673B (en) | Distributed filtering method, device, equipment and storage medium for wireless sensor network | |
| CN115908036A (en) | Method and device for identifying key nodes of social network based on local topological information | |
| CN115293329A (en) | Parameter updating method, device, equipment and storage medium | |
| CN115082742A (en) | Training method and device for image classification model, electronic equipment and storage medium | |
| CN114662777A (en) | Photovoltaic module serial line arrangement determining method and device, electronic equipment and storage medium | |
| CN109635281B (en) | Method and device for updating nodes in traffic guide graph | |
| CN114139605A (en) | Distributed model training method, system, device and storage medium | |
| CN115292339B (en) | Database updating method, device, electronic equipment and storage medium | |
| CN113361719A (en) | Incremental learning method based on image processing model and image processing method | |
| CN114491416B (en) | Processing method and device of characteristic information, electronic equipment and storage medium | |
| CN113315656B (en) | Node importance evaluation method and system based on graph propagation and readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |