阅读说明：本技术 一种基于大数据技术的工业能力标签方法 (Industrial capacity labeling method based on big data technology ) 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大数据技术的工业能力标签方法,该方法包括：获取标注对象；确定标注对象的业务来源、数据来源和需求来源；根据标注对象的业务来源、数据来源和需求来源,从标签系统的标签库中确定最终标签；根据最终标签确定融合度；根据融合度,生成最终标签的标签图；将标签图作为标注对象的标注标签进行标注。现有通过单一特性标签查找关键信息时因为考虑的不全面造成查找的信息只符合需求中的一个方面而不符合整体需求,而本发明提供的方法,根据标签的融合度生成标签图,并基于标签图进行标注,使得标注体现了数据的融合特性,该标签能够反应工业信息的整体属性,提升了在海量工业信息中快速准确查询关键信息的速度和准确性。(The invention relates to an industrial capacity labeling method based on a big data technology, which comprises the following steps: acquiring a labeling object; determining a service source, a data source and a demand source of the labeled object; determining a final label from a label library of a label system according to a service source, a data source and a demand source of the labeled object; determining the fusion degree according to the final label; generating a label graph of the final label according to the fusion degree; and marking the label graph as a marking label of the marking object. According to the method provided by the invention, the label graph is generated according to the fusion degree of the label, and labeling is carried out based on the label graph, so that the labeling embodies the fusion characteristic of data, the integral attribute of industrial information can be reflected by the label, and the speed and the accuracy for quickly and accurately querying key information in massive industrial information are improved.)

1. An industrial capacity labeling method based on big data technology, which is characterized by comprising the following steps:

s101, acquiring a label object;

s102, determining a service source, a data source and a demand source of the labeled object;

s103, determining a final label from a label library of the label system according to the service source, the data source and the demand source of the labeled object;

s104, determining the fusion degree according to the final label;

s105, generating a label graph of the final label according to the fusion degree;

and S106, marking the label graph as a marking label of the marking object.

2. The method of claim 1, wherein the labeling system comprises: a service source domain, a data source domain, a demand source domain and a label library;

the service source domain is used for representing a service source of the labeling object;

the data source domain is used for representing a data source of the labeling object;

the demand source domain is used for representing the demand source of the labeling object;

the label library comprises specific labels;

any label in the label library corresponds to one or more service sources in the service source domain, one or more data sources in the data source domain and one or more demand sources in the demand source domain;

any label in the label library has a three-dimensional attribute, and the first-dimensional attribute is each service source in a service source domain corresponding to the any label and the corresponding degree I1 of each service source; the second-dimension attribute is that each data source in the data source domain corresponding to any label and the corresponding degree I2 of each data source; the third dimension attribute is that any label corresponds to each demand source in the demand source domain and the corresponding degree I3 of each demand source.

3. The method according to claim 2, wherein the S103 specifically includes:

s103-1, determining similarity between the service source of the labeled object and each service source in the service source domain S1, and acquiring D1 service sources with the highest S1 to form a service source set A1; wherein, D1 is a preset service source acquisition threshold;

s103-2, determining similarity between the data source of the annotation object and each data source in the data source domain S2, and acquiring D2 data sources with the highest S2 to form a data source set A2; wherein D2 is a preset data source acquisition threshold;

s103-3, determining similarity between the demand source of the annotation object and each demand source in the demand source domain S3, and obtaining D3 demand sources with the highest S3 to form a demand source set A3; wherein D3 is a preset demand source acquisition threshold;

s103-4, sequentially selecting one element from A1, A2 and A3 to form a combination; the number of combinations was D1 by D2 by D3;

s103-5, for any combination, determining whether a label corresponding to the any combination exists in a label library, and if so, taking the label as an alternative label;

s103-6, determining a final label according to the three-dimensional attributes of the alternative labels.

4. The method according to claim 3, wherein the S103-6 specifically comprises:

if one alternative label is selected, determining that the alternative label is the final label;

if the number of the alternative labels is multiple, the average value of I1 of each alternative label is determinedI2 mean valueAnd I3 mean valueDetermining all alternative tagsThe mean value of,Mean value ofThe mean value of (a); computing alternative labelsThe average value of (a) of (b),the average value of (a) of (b),the mean value of (a); if the alternative label of which the P1, P2 and P3 are not less than 0.5 exists, taking the alternative label as a final label; if no alternative label with the P1, the P2 and the P3 being not less than 0.5 exists, calculating the P4 of each alternative label as P1+ P2+ P3, sorting the alternative labels from small to small according to the P4, and selecting D4 alternative labels with the top sorting as a final label.

5. The method of claim 4, wherein the step of determining the target position is performed by a computer

Wherein D5 is min { variance of each alternative tag I1, variance of each alternative tag I2, variance of each alternative tag I3 }.

6. The method according to claim 3, wherein the S104 specifically includes:

if the number of the final tags is 1, determining that the fusion degree is max { the maximum value of the similarity between the service source corresponding to the final tag and the service source of the labeled object, the maximum value of the similarity between the data source corresponding to the final tag and the data source of the labeled object, and the maximum value of the similarity between the demand source corresponding to the final tag and the demand source of the labeled object }.

7. The method according to claim 6, wherein the S105 specifically comprises:

acquiring a three-dimensional attribute corresponding to the final label;

taking the final label as a point Z, and marking the fusion degree as the attribute of the Z;

taking each service source in the corresponding three-dimensional attribute as a point Z1, and connecting each Z1 with Z to form an edge; marking the value of the I1-fusion degree of each service source as the attribute of the edge connecting the point corresponding to the service source and the Z point;

taking each data source in the corresponding three-dimensional attribute as a point Z2, and connecting each Z2 with Z to form an edge; marking the value of the I2 fusion degree of each service source as the attribute of the edge connecting the point corresponding to the data source and the Z point;

taking each demand source in the corresponding three-dimensional attributes as a point Z3, and connecting each Z3 with Z to form an edge; marking the value of the I3 fusion degree of each demand source as the attribute of the edge connecting the point corresponding to the demand source and the point Z;

a graph consisting of all points and edges is taken as a label graph.

8. The method according to claim 3, wherein the S104 specifically includes:

if the number of the final labels is multiple, determining that the total fusion degree is max { the maximum value of the similarity between the service sources corresponding to all the final labels and the service sources of the labeled object, the maximum value of the similarity between the data sources corresponding to all the final labels and the data sources of the labeled object, and the maximum value of the similarity between the demand sources corresponding to all the final labels and the demand sources of the labeled object };

determining the fusion degree between any two terminal notes according to the three-dimensional attributes of any two final notes;

and taking the fusion degree and the total fusion degree between any two terminal notes as the fusion degree.

9. The method according to claim 8, wherein the determining the degree of fusion between any two terminal notes according to the three-dimensional attributes of any two final notes specifically comprises:

for any two final notes u, v, the fusion degree between the final label u and the final label v is max { a first value, a second value, a third value };

wherein the content of the first and second substances,

the first value is: the maximum value of the similarity between the service sources of the labeling object and the service sources with the same number of the service sources in the service sources corresponding to the final label u and the final label v;

the second value is: the maximum value of the similarity between the service sources of the labeled object and the data sources with the same data source quantity in the data source corresponding to the final label u and the data source corresponding to the final label v;

the third value is: and the maximum value of the similarity between the demand sources corresponding to the final label u and the demand sources corresponding to the final label v, wherein the same demand sources are the same in number.

10. The method according to claim 8, wherein the S105 specifically includes:

acquiring three-dimensional attributes corresponding to the final labels;

taking each final label as a point Y, connecting all the Y, marking the total fusion degree as the attribute of each Y, and marking the fusion degree between the two final labels as the attribute of the connected edge between the corresponding points of the two final labels;

taking each service source in the three-dimensional attribute corresponding to each final label as a point Y1, and connecting each Y1 with the corresponding final label by one edge; marking the value of the total fusion degree I1 of each service source as the attribute of the edge connected between the point corresponding to the service source and the point corresponding to the corresponding final label;

taking each data source in the three-dimensional attributes corresponding to each final label as a point Y2, and connecting each Y2 with the corresponding final label by an edge; marking the value of the total fusion degree I2 of each data source as the attribute of the edge connected between the point corresponding to the data source and the point corresponding to the corresponding final label;

taking each demand source in the three-dimensional attributes corresponding to each final label as a point Y3, and connecting each Y3 with the corresponding final label to form an edge; marking the value of the total fusion degree I3 of each demand source as the attribute of the edge connected between the point corresponding to the demand source and the point corresponding to the corresponding final label;

a graph consisting of all points and edges is taken as a label graph.

Technical Field

The invention relates to the field of labels, in particular to an industrial capacity labeling method based on a big data technology.

Background

With the development of industrial modernization, the related information of industrial products is explosively increased. How to quickly and accurately find the key information in the massive industrial information becomes a problem which is relatively concerned by related personnel.

At present, one solution is to construct a label system, and implement operation and maintenance of product-related data, such as tracing, by labeling industrial products.

However, with the development of product diversification, products with single attribute gradually become less, more products with multiple attributes fused across multiple fields are provided, and tags in the existing tag system are still in independent relationship, so that tags printed by the existing tag system for diversified products can be very long and very large, the most critical tags can still be difficult to find out from a plurality of tags, and the diversification characteristics of the products can also be difficult to embody, and therefore, a tag system capable of embodying the fusion characteristics is urgently needed.

Disclosure of Invention

Technical problem to be solved

In view of the above disadvantages and shortcomings of the prior art, the present invention provides an industrial capability labeling method based on big data technology.

(II) technical scheme

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

an industrial capacity tagging method based on big data technology, the method comprising:

s101, acquiring a label object;

s102, determining a service source, a data source and a demand source of the labeled object;

s103, determining a final label from a label library of the label system according to the service source, the data source and the demand source of the labeled object;

s104, determining the fusion degree according to the final label;

s105, generating a label graph of the final label according to the fusion degree;

and S106, marking the label graph as a marking label of the marking object.

Optionally, the label system comprises: a service source domain, a data source domain, a demand source domain and a label library;

the service source domain is used for representing a service source of the labeling object;

the data source domain is used for representing a data source of the labeling object;

the demand source domain is used for representing the demand source of the labeling object;

the label library comprises specific labels;

any label in the label library corresponds to one or more service sources in the service source domain, one or more data sources in the data source domain and one or more demand sources in the demand source domain;

any label in the label library has a three-dimensional attribute, and the first-dimensional attribute is each service source in a service source domain corresponding to the any label and the corresponding degree I1 of each service source; the second-dimension attribute is that each data source in the data source domain corresponding to any label and the corresponding degree I2 of each data source; the third dimension attribute is that any label corresponds to each demand source in the demand source domain and the corresponding degree I3 of each demand source.

Optionally, the S103 specifically includes:

s103-1, determining similarity between the service source of the labeled object and each service source in the service source domain S1, and acquiring D1 service sources with the highest S1 to form a service source set A1; wherein, D1 is a preset service source acquisition threshold;

s103-2, determining similarity between the data source of the annotation object and each data source in the data source domain S2, and acquiring D2 data sources with the highest S2 to form a data source set A2; wherein D2 is a preset data source acquisition threshold;

s103-3, determining similarity between the demand source of the annotation object and each demand source in the demand source domain S3, and obtaining D3 demand sources with the highest S3 to form a demand source set A3; wherein D3 is a preset demand source acquisition threshold;

s103-4, sequentially selecting one element from A1, A2 and A3 to form a combination; the number of combinations was D1 by D2 by D3;

s103-5, for any combination, determining whether a label corresponding to the any combination exists in a label library, and if so, taking the label as an alternative label;

s103-6, determining a final label according to the three-dimensional attributes of the alternative labels.

Optionally, the S103-6 specifically includes:

if one alternative label is selected, determining that the alternative label is the final label;

if the number of the alternative labels is multiple, the average value of I1 of each alternative label is determinedI2 mean valueAnd I3 mean valueDetermining all alternative tagsThe mean value of,Mean value ofThe mean value of (a); computing alternative labelsThe average value of (a) of (b),the average value of (a) of (b),the mean value of (a); if P1, P2 and P3 existIf the alternative label is not less than 0.5, taking the alternative label as a final label; if no alternative label with the P1, the P2 and the P3 being not less than 0.5 exists, calculating the P4 of each alternative label as P1+ P2+ P3, sorting the alternative labels from small to small according to the P4, and selecting D4 alternative labels with the top sorting as a final label.

Optionally, the D4 ═ total number of alternative tags D5 ];

wherein D5 is min { variance of each alternative tag I1, variance of each alternative tag I2, variance of each alternative tag I3 }.

Optionally, the S104 specifically includes:

if the number of the final tags is 1, determining that the fusion degree is max { the maximum value of the similarity between the service source corresponding to the final tag and the service source of the labeled object, the maximum value of the similarity between the data source corresponding to the final tag and the data source of the labeled object, and the maximum value of the similarity between the demand source corresponding to the final tag and the demand source of the labeled object }.

Optionally, the S105 specifically includes:

acquiring a three-dimensional attribute corresponding to the final label;

taking the final label as a point Z, and marking the fusion degree as the attribute of the Z;

taking each service source in the corresponding three-dimensional attribute as a point Z1, and connecting each Z1 with Z to form an edge; marking the value of the I1-fusion degree of each service source as the attribute of the edge connecting the point corresponding to the service source and the Z point;

taking each data source in the corresponding three-dimensional attribute as a point Z2, and connecting each Z2 with Z to form an edge; marking the value of the I2 fusion degree of each service source as the attribute of the edge connecting the point corresponding to the data source and the Z point;

taking each demand source in the corresponding three-dimensional attributes as a point Z3, and connecting each Z3 with Z to form an edge; marking the value of the I3 fusion degree of each demand source as the attribute of the edge connecting the point corresponding to the demand source and the point Z;

a graph consisting of all points and edges is taken as a label graph.

Optionally, the S104 specifically includes:

if the number of the final labels is multiple, determining that the total fusion degree is max { the maximum value of the similarity between the service sources corresponding to all the final labels and the service sources of the labeled object, the maximum value of the similarity between the data sources corresponding to all the final labels and the data sources of the labeled object, and the maximum value of the similarity between the demand sources corresponding to all the final labels and the demand sources of the labeled object };

determining the fusion degree between any two terminal notes according to the three-dimensional attributes of any two final notes;

and taking the fusion degree and the total fusion degree between any two terminal notes as the fusion degree.

Optionally, the determining, according to the three-dimensional attributes of any two final notes, the fusion degree between any two terminal notes specifically includes:

for any two final notes u, v, the fusion degree between the final label u and the final label v is max { a first value, a second value, a third value };

wherein the content of the first and second substances,

the first value is: the maximum value of the similarity between the service sources of the labeling object and the service sources with the same number of the service sources in the service sources corresponding to the final label u and the final label v;

the second value is: the maximum value of the similarity between the service sources of the labeled object and the data sources with the same data source quantity in the data source corresponding to the final label u and the data source corresponding to the final label v;

the third value is: and the maximum value of the similarity between the demand sources corresponding to the final label u and the demand sources corresponding to the final label v, wherein the same demand sources are the same in number.

Optionally, the S105 specifically includes:

acquiring three-dimensional attributes corresponding to the final labels;

taking each final label as a point Y, connecting all the Y, marking the total fusion degree as the attribute of each Y, and marking the fusion degree between the two final labels as the attribute of the connected edge between the corresponding points of the two final labels;

taking each service source in the three-dimensional attribute corresponding to each final label as a point Y1, and connecting each Y1 with the corresponding final label by one edge; marking the value of the total fusion degree I1 of each service source as the attribute of the edge connected between the point corresponding to the service source and the point corresponding to the corresponding final label;

taking each data source in the three-dimensional attributes corresponding to each final label as a point Y2, and connecting each Y2 with the corresponding final label by an edge; marking the value of the total fusion degree I2 of each data source as the attribute of the edge connected between the point corresponding to the data source and the point corresponding to the corresponding final label;

taking each demand source in the three-dimensional attributes corresponding to each final label as a point Y3, and connecting each Y3 with the corresponding final label to form an edge; marking the value of the total fusion degree I3 of each demand source as the attribute of the edge connected between the point corresponding to the demand source and the point corresponding to the corresponding final label;

a graph consisting of all points and edges is taken as a label graph.

(III) advantageous effects

The industrial capacity labeling method based on the big data technology acquires a labeled object; determining a service source, a data source and a demand source of the labeled object; determining a final label from a label library of a label system according to a service source, a data source and a demand source of the labeled object; determining the fusion degree according to the final label; generating a label graph of the final label according to the fusion degree; and marking the label graph as a marking label of the marking object. According to the method provided by the invention, the label graph is generated according to the fusion degree of the label, and labeling is carried out based on the label graph, so that the labeling embodies the fusion characteristic of data, the integral attribute of industrial information can be reflected by the label, and the speed and the accuracy for quickly and accurately querying key information in massive industrial information are improved.

Drawings

Fig. 1 is a schematic flow chart of an industrial capability labeling method based on big data technology 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, the related information of industrial products is explosively increased. How to quickly and accurately find the key information in the massive industrial information becomes a problem which is relatively concerned by related personnel.

At present, one solution is to construct a label system, and implement operation and maintenance of product-related data, such as tracing, by labeling industrial products. However, with the development of product diversification, products with single attribute gradually become less, more products with multiple attributes fused across multiple fields are provided, and tags in the existing tag system are still in independent relationship, so that tags printed by the existing tag system for diversified products can be very long and very large, the most critical tags can still be difficult to find out from a plurality of tags, and the diversification characteristics of the products can also be difficult to embody, and therefore, a tag system capable of embodying the fusion characteristics is urgently needed.

Based on the technical scheme, the invention discloses an industrial capacity labeling method based on a big data technology, which comprises the following steps: acquiring a labeling object; determining a service source, a data source and a demand source of the labeled object; determining a final label from a label library of a label system according to a service source, a data source and a demand source of the labeled object; determining the fusion degree according to the final label; generating a label graph of the final label according to the fusion degree; and marking the label graph as a marking label of the marking object. According to the method provided by the invention, the label graph is generated according to the fusion degree of the label, and labeling is carried out based on the label graph, so that the labeling embodies the fusion characteristic of data, the integral attribute of industrial information can be reflected by the label, and the speed and the accuracy for quickly and accurately querying key information in massive industrial information are improved.

Referring to fig. 1, the industrial capability labeling method based on big data technology provided in this embodiment is implemented as follows:

s101, obtaining the labeling object.

The annotation object may be an industrial product to be annotated, each industrial product is determined based on a service and a requirement, and the corresponding data of the industrial product is also stored in a corresponding storage location, so that each representative number of industrial products has a service source (representing the service corresponding to the industrial product), a data source (representing the storage location of the data corresponding to the industrial product), and a requirement source (representing the requirement corresponding to the industrial product).

S102, determining a service source, a data source and a demand source of the labeled object.

S103, determining a final label from a label library of the label system according to the service source, the data source and the demand source of the labeled object.

Wherein, the label system includes: a service source domain, a data source domain, a demand source domain and a label library.

And the service source domain is used for representing the service source of the labeling object.

And the data source field is used for representing the data source of the labeling object.

And the requirement source domain is used for representing the requirement source of the labeling object.

And the label library comprises specific labels.

Any label in the label library corresponds to one or more service sources in the service source domain, one or more data sources in the data source domain and one or more demand sources in the demand source domain.

Any label in the label library has three-dimensional attributes, and the first-dimensional attributes are each service source in the service source domain corresponding to any label and the corresponding degree I1 of each service source. The second dimension attribute is that any label corresponds to each data source in the data source domain and the corresponding degree I2 of each data source. The third dimension attribute is that any label corresponds to each demand source in the demand source domain and the corresponding degree I3 of each demand source.

Based on the label system, the implementation process of the step is as follows:

s103-1, determining similarity between the service source of the annotation object and each service source in the service source domain S1, and obtaining D1 service sources with the highest S1 to form a service source set A1.

Wherein D1 is a preset traffic source acquisition threshold.

In addition, the similarity S1 can be determined according to the description of the service source description and the service source domain, for example, determining the semantics of the two descriptions, and regarding the similarity of the semantics as S1.

S103-2, determining similarity between the data source of the annotation object and each data source in the data source domain S2, and acquiring D2 data sources with the highest S2 to form a data source set A2.

Wherein D2 is a preset data source acquisition threshold.

Additionally, the similarity S2 may be determined based on the relationship of the data source to the data source domain, such as based on whether it originates from the same database, the same data space, and so forth.

S103-3, determining similarity between the demand source of the annotation object and each demand source in the demand source domain S3, and obtaining D3 demand sources with the highest S3 to form a demand source set A3.

Wherein D3 is a preset demand source acquisition threshold.

In addition, the similarity S3 may be determined according to the description of the demand source description and the demand source domain, for example, determining the semantics of the two descriptions, and regarding the similarity of the semantics as S3.

S103-4, and sequentially selecting one element from A1, A2 and A3 to form a combination.

Wherein the number of combinations is D1 by D2 by D3.

S103-5, for any combination, determining whether a label corresponding to any combination exists in the label library, and if so, taking the label as an alternative label.

S103-6, determining a final label according to the three-dimensional attributes of the alternative labels.

In particular, the method comprises the following steps of,

and if one alternative label is selected, determining that the alternative label is the final label.

If there are multiple alternative labels, then

1) Determining the mean value of I1 for each candidate tagI2 mean valueAnd I3 mean value

2) Determining all alternative tagsThe mean value of,Mean value ofIs measured.

3) Computing alternative labelsThe average value of (a) of (b),the average value of (a) of (b),is measured.

4) And if the alternative label of which the P1, P2 and P3 are not less than 0.5 exists, the alternative label is taken as the final label.

If no alternative label with the P1, the P2 and the P3 being not less than 0.5 exists, calculating the P4 of each alternative label as P1+ P2+ P3, sorting the alternative labels from small to small according to the P4, and selecting D4 alternative labels with the top sorting as a final label.

D4 ═ total number of alternative tags D5.

Wherein D5 is min { variance of each alternative tag I1, variance of each alternative tag I2, variance of each alternative tag I3 }.

And S104, determining the fusion degree according to the final label.

In particular, the method comprises the following steps of,

if the final label is 1, then

And determining the fusion degree as max { the maximum value of the similarity between the service source corresponding to the final tag and the service source of the labeled object, the maximum value of the similarity between the data source corresponding to the final tag and the data source of the labeled object, and the maximum value of the similarity between the demand source corresponding to the final tag and the demand source of the labeled object }.

If there are multiple final labels, then

a) And determining the total fusion degree as max { the maximum value of the similarity between the service sources corresponding to all the final tags and the service source of the labeled object, the maximum value of the similarity between the data sources corresponding to all the final tags and the data source of the labeled object, and the maximum value of the similarity between the demand source corresponding to all the final tags and the demand source of the labeled object }.

b) And determining the fusion degree between any two terminal notes according to the three-dimensional attributes of any two final notes.

Specifically, for any two final notes u and v, the fusion degree between the final label u and the final label v is max { a first value, a second value, and a third value }.

Wherein the content of the first and second substances,

the first value is: and the maximum value of the similarity between the service sources with the same number of service sources and the service sources of the labeled object in the service sources corresponding to the final label u and the service sources corresponding to the final label v.

The second value is: and the maximum value of the similarity between the data sources with the same data source number and the service sources of the labeled object in the data sources corresponding to the final label u and the data sources corresponding to the final label v.

The third value is: and the maximum value of the similarity between the demand sources corresponding to the final label u and the demand sources corresponding to the final label v, wherein the same demand sources are the same in number.

c) And taking the fusion degree and the total fusion degree between any two terminal notes as the fusion degree.

And S105, generating a label graph of the final label according to the fusion degree.

If the final label is 1, then

And A.1) acquiring the three-dimensional attribute corresponding to the final label.

And A.2) marking the final label as a point Z and the fusion degree as the attribute of the Z.

A.3) takes each service source in the corresponding three-dimensional attribute as a point Z1, and each Z1 is connected with Z by an edge. And marking the value of the I1 fusion degree of each service source as the attribute of the edge connecting the point corresponding to the service source and the Z point.

A.4) treat each data source in the corresponding three-dimensional attribute as a point Z2, and each Z2 connects an edge to Z. And marking the value of the I2 fusion degree of each service source as the attribute of the edge connecting the point corresponding to the data source and the Z point.

A.5) takes each source of demand in the corresponding three-dimensional attribute as a point Z3, and each Z3 connects Z with an edge. And marking the value of the I3 fusion degree of each demand source as the attribute of the edge connecting the point corresponding to the demand source and the point Z.

A.6) using the graph formed by all points and edges as a label graph.

If there are multiple final labels, then

And B.1) acquiring the three-dimensional attribute corresponding to each final label.

And B.2) taking each final label as a point Y, connecting all the Y, marking the total fusion degree as the attribute of each Y, and marking the fusion degree between the two final labels as the attribute of the connected edge between the corresponding points of the two final labels.

And B.3) taking each service source in the three-dimensional attribute corresponding to each final label as a point Y1, and connecting each Y1 with the corresponding final label by one edge. And marking the value of the total fusion degree I1 of each service source as the attribute of the edge connected between the point corresponding to the service source and the point corresponding to the corresponding final label.

B.4) taking each data source in the three-dimensional attribute corresponding to each final label as a point Y2, and connecting each Y2 with the corresponding final label by an edge. And marking the value of the total fusion degree I2 of each data source as the attribute of the edge connected between the point corresponding to the data source and the point corresponding to the corresponding final label.

B.5) taking each demand source in the three-dimensional attribute corresponding to each final label as a point Y3, and connecting each Y3 with the corresponding final label by an edge. And marking the value of the total fusion degree I3 of each demand source as the attribute of the edge connected between the point corresponding to the demand source and the point corresponding to the corresponding final label.

B.6) using the graph formed by all the points and the edges as a label graph.

And S106, marking the label graph as a marking label of the marking object.

The method determines the fusion degree of the label through the service source, the data source and the demand source, can describe the attributes of the industrial product in multiple aspects through the fusion degree, can ensure that the data inquired through the label is more in line with the demand rather than in line with the demand of a certain aspect through the labeling of the fusion degree of the label, and ensures the accurate retrieval of the data.

The industrial capacity labeling method based on the big data technology provided by the embodiment comprises the following steps: acquiring a labeling object; determining a service source, a data source and a demand source of the labeled object; determining a final label from a label library of a label system according to a service source, a data source and a demand source of the labeled object; determining the fusion degree according to the final label; generating a label graph of the final label according to the fusion degree; and marking the label graph as a marking label of the marking object. According to the method provided by the invention, the label graph is generated according to the fusion degree of the label, and labeling is carried out based on the label graph, so that the labeling embodies the fusion characteristic of data, the integral attribute of industrial information can be reflected by the label, and the speed and the accuracy for quickly and accurately querying key information in massive industrial information are improved.

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.