CN114417020B - Industrial chain map construction system and method - Google Patents
Industrial chain map construction system and method Download PDFInfo
- Publication number
- CN114417020B CN114417020B CN202210315027.4A CN202210315027A CN114417020B CN 114417020 B CN114417020 B CN 114417020B CN 202210315027 A CN202210315027 A CN 202210315027A CN 114417020 B CN114417020 B CN 114417020B
- Authority
- CN
- China
- Prior art keywords
- node
- acquiring
- display
- industry
- value
- 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.)
- Active
Links
- 238000010276 construction Methods 0.000 title claims abstract description 140
- 238000000034 method Methods 0.000 title claims abstract description 137
- 238000012549 training Methods 0.000 claims abstract description 36
- 230000008569 process Effects 0.000 claims description 107
- 238000007689 inspection Methods 0.000 claims description 35
- 238000011156 evaluation Methods 0.000 claims description 33
- 230000006978 adaptation Effects 0.000 claims description 30
- 238000001228 spectrum Methods 0.000 claims description 28
- 238000012163 sequencing technique Methods 0.000 claims description 25
- 238000004519 manufacturing process Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000005516 engineering process Methods 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 239000013589 supplement Substances 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 230000000295 complement effect Effects 0.000 claims 1
- 230000006399 behavior Effects 0.000 description 14
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000011144 upstream manufacturing Methods 0.000 description 9
- 238000012795 verification Methods 0.000 description 8
- 238000010801 machine learning Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000007704 transition Effects 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an industrial chain map construction system and method, wherein the system comprises: the acquisition module is used for acquiring a target industry input by a user and acquiring industry big data corresponding to the target industry; the training module is used for training the industrial chain chart building model; and the construction module is used for constructing a model based on the industry chain map, and constructing the industry chain map corresponding to the target industry according to the industry big data. According to the system and the method for constructing the industrial chain map, when a user needs to construct the industrial chain map, the user only needs to input a target industry needing to be analyzed, industrial big data corresponding to the target industry is obtained, a model is constructed based on the trained industrial chain map, and corresponding industrial chain map construction is carried out according to the industrial big data, so that convenience is improved, and the problem that incomplete construction may occur when an industrial chain map is constructed by manually looking up industrial data is solved.
Description
Technical Field
The invention relates to the technical field of big data, in particular to an industrial chain map construction system and method.
Background
At present, when a certain industry is analyzed, an industry chain map of the industry needs to be constructed; generally, when an industrial chain map is constructed, a large amount of industrial data needs to be consulted manually, which is complicated, and in addition, problems of incomplete construction and the like can also occur when the industrial chain map is constructed by consulting the industrial data manually;
therefore, a solution is needed.
Disclosure of Invention
The invention provides an industrial chain map building system and method, when a user needs to build an industrial chain map, the user only needs to input a target industry needing to be analyzed to obtain large industrial data corresponding to the target industry, a model is built based on the trained industrial chain map, and corresponding industrial chain map building is carried out according to the large industrial data, so that the convenience is improved, and the problem that the construction of the industrial chain map is incomplete when the industrial chain map is built by manually looking up industrial data is also solved.
The invention provides an industrial chain chart spectrum construction system, which comprises:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a target industry input by a user and acquiring industry big data corresponding to the target industry;
the training module is used for training the industrial chain chart building model;
and the construction module is used for constructing a model based on the industry chain map spectrum and constructing an industry chain map corresponding to the target industry according to the industry big data.
Preferably, the obtaining module performs the following operations:
acquiring a preset industry big data node set, wherein the industry big data node set comprises: a plurality of first nodes;
acquiring a reliability index corresponding to the first node, and if the reliability index is greater than or equal to a preset reliability index threshold value, taking the corresponding first node as a second node;
acquiring target data corresponding to the target industry through the second node;
and integrating the acquired target data to acquire industrial big data, and finishing acquisition.
Preferably, the obtaining of the reliability index corresponding to the first node includes:
establishing an industry big data node association library, determining at least one other first node associated with the first node based on the industry big data node association library, and taking the first node as a second node;
acquiring a plurality of credit records corresponding to the first node and the second node;
based on a preset credit scoring model, according to the credit record, performing credit scoring on the first node to obtain a credit score, giving a preset first weight to the credit score, and obtaining a first target value;
acquiring at least one guarantor corresponding to the first node, acquiring a guarantee value for the guarantor to guarantee the first node, giving a preset second weight to the guarantee value, and acquiring a second target value;
summing the first target value and the second target value to obtain a reliability index corresponding to the first node, and finishing obtaining;
wherein the first weight is greater than the second weight.
Preferably, the building of the industry big data node association library comprises the following steps:
randomly selecting two first nodes as a third node and a fourth node respectively;
attempting to acquire at least one historically generated correlation event between the third node and the fourth node;
if the acquisition is successful, acquiring an association type corresponding to the association event, wherein the association type comprises: relationship association and behavior association;
when the association type corresponding to the association event is relationship association, extracting at least one association relationship generated between the third node and the fourth node from the association event, and meanwhile, acquiring a first association value corresponding to the association relationship;
when the association type corresponding to the association event is behavior association, extracting at least one association behavior generated between the third node and the fourth node from the association event, and meanwhile, acquiring a second association value corresponding to the association behavior;
accumulating and calculating the first correlation value and the second correlation value to obtain a correlation value sum;
if the correlation value sum is greater than or equal to a preset correlation value and a preset threshold value, performing node correlation pairing on the corresponding third node and fourth node to obtain a paired group;
acquiring a preset blank database, and storing the pairing group into the blank database;
and when all the pairing groups needing to be stored in the blank database are stored, taking the blank database as a production industry big data node association database to finish construction.
Preferably, the training module performs the following operations:
acquiring a plurality of first construction processes for manually constructing an industrial chain chart;
acquiring the capacity index of a constructor corresponding to the first construction process, and if the capacity index is greater than or equal to a preset capacity index threshold, taking the corresponding first construction process as a second construction process;
otherwise, taking the corresponding first construction process as a third construction process;
splitting the third construction flow into a plurality of first sub-flows, and sequencing the first sub-flows based on a preset sequencing rule to obtain a flow sequence;
acquiring a first flow type corresponding to the first sub-flow, and acquiring a trigger value corresponding to the first flow type;
if the trigger value is greater than or equal to a preset trigger threshold value, taking the corresponding first sub-process as a second sub-process;
acquiring the first flow type corresponding to the second sub-flow and taking the first flow type as a second flow type;
acquiring at least one check item corresponding to the second flow type, wherein the check item comprises: the inspection direction, the inspection range and the inspection flow type;
determining that the first flow type corresponding to the inspection flow type in the inspection range in the inspection direction of the second flow in the flow sequence is the first flow corresponding to the inspection flow type, and using the first flow as a third flow;
integrating the second sub-process and the third sub-process to obtain a part of process to be inspected;
acquiring a process rationality inspection model corresponding to the second process type, performing rationality inspection on the part of the process to be inspected, acquiring a rational value, and associating the rational value with the corresponding third construction process;
accumulating and calculating the reasonable values associated with the third construction process to obtain a reasonable value sum;
acquiring a reasonable value and a threshold value corresponding to the capability index of the builder corresponding to the third building process;
if the reasonable value sum is larger than or equal to the reasonable value sum and the threshold value, taking the corresponding third construction process as a fourth construction process;
and taking the second construction process and the fourth construction process as training samples, and performing model training on the training samples based on a preset model training algorithm to obtain an industrial chain diagram spectrum construction model.
Preferably, the obtaining of the capability index of the builder corresponding to the first building process includes:
acquiring a construction initial time point corresponding to the first construction process;
acquiring an empirical value of a constructor corresponding to the first construction process, corresponding to the construction initial time point, and acquiring a construction weight of the constructor corresponding to the first construction process;
giving the empirical value corresponding to the construction weight to obtain a capability value;
and summing the capability values to obtain the capability index of the builder, and finishing the obtaining.
Preferably, the industry chain map building system further includes:
and the supplement construction module is used for carrying out adaptive supplement construction on the industrial chain map when a user views the industrial chain map.
Preferably, the supplementary building block performs the following operations:
analyzing whether a user watches any first industrial chain node in the industrial chain map when looking at the industrial chain map based on attention analysis technology;
if so, taking the first industrial chain node watched by the user as a second industrial chain node;
acquiring a plurality of first alternative enterprises corresponding to the second industry link point;
acquiring a first evaluation index corresponding to the first candidate enterprise;
if the first evaluation index is larger than or equal to a preset first evaluation index threshold value, taking the corresponding first candidate enterprise as a first display target;
sorting the first display target from large to small according to the first evaluation index corresponding to the first display target to obtain a first display block;
acquiring a first introduction item corresponding to the first display target, and marking the first introduction item on the first display target corresponding to the first display block;
associating the first display block with the corresponding second industrial chain node, acquiring a first display position corresponding to the second industrial chain node, and arranging the first display block at the first display position for display;
in the display process, whether a user watches other at least one first industry chain node within a preset time period is analyzed based on attention analysis technology;
if the other first industrial chain nodes watched by the user in the time period are used as third industrial chain nodes;
acquiring a plurality of second alternative enterprises corresponding to the third production chain link points;
acquiring a second evaluation index corresponding to the second candidate enterprise;
if the second evaluation index is larger than or equal to a preset second evaluation index threshold value, taking the corresponding second candidate enterprise as a second display target;
sorting the second display targets from large to small according to the second evaluation indexes corresponding to the second display targets to obtain second display blocks;
acquiring a second introduction item corresponding to the second display target, and marking the second introduction item on the second display target corresponding to the second display block;
associating the second display block with the corresponding third production chain node, acquiring a second display position corresponding to the third production chain node, and arranging the second display block at the second display position for display;
taking the first display block and the second display block as a third display block, and meanwhile, obtaining the second industrial chain node or the third industrial chain node associated with the third display block and taking the second industrial chain node or the third industrial chain node as a fourth industrial chain node;
acquiring node weights corresponding to the fourth industrial chain link points;
randomly selecting a third display target from the corresponding third display blocks according to the node weights from large to small, and sequencing the selected third display targets according to the selection sequence to obtain a display target sequence;
sequentially traversing the third display targets in the display target sequence, acquiring adaptation values between other third display targets after the third display target traversed each time in the display target sequence and the traversed third display targets, and marking the adaptation values on the traversed third display targets;
after traversing the third display target, accumulating and calculating the marked adaptation value of the third display target to obtain an adaptation value sum, giving the adaptation value sum a preset third weight to obtain a first sequencing value, and associating the first sequencing value with the corresponding third display target;
obtaining ranking scores of the third display targets in the ranking corresponding to the third display blocks, giving a preset fourth weight to the ranking scores to obtain a second ranking value, and associating the second ranking value with the third display targets;
acquiring a sequence position of the third display target in the display target sequence, and acquiring a position weight corresponding to the sequence position;
accumulating and calculating the first ranking value and the second ranking value associated with the third display target to obtain a ranking value sum, endowing the ranking value sum with the corresponding position weight to obtain a ranking index, and associating the ranking index with the corresponding display target sequence;
accumulating the ranking indexes associated with the display target sequence to obtain a ranking index sum;
acquiring a third display position corresponding to each fourth industrial chain node, and meanwhile, arranging the maximum sorting index and the corresponding display target sequence at the third display position for display;
wherein the third weight is greater than the fourth weight.
The invention provides an industrial chain chart construction method, which comprises the following steps:
step 1: acquiring a target industry input by a user, and acquiring industry big data corresponding to the target industry;
step 2: training an industrial chain graph spectrum building model;
and step 3: and constructing an industry chain map corresponding to the target industry according to the industry big data based on the industry chain map construction model.
Preferably, in step 1, the obtaining of industry big data corresponding to the target industry includes:
acquiring a preset industry big data node set, wherein the industry big data node set comprises: a plurality of first nodes;
acquiring a reliability index corresponding to the first node, and if the reliability index is greater than or equal to a preset reliability index threshold, taking the corresponding first node as a second node;
acquiring target data corresponding to the target industry through the second node;
and integrating the acquired target data to acquire industrial big data, and finishing acquisition.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of an industrial chain chart diagram constructing system according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for constructing an industry chain map spectrum according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides an industrial chain chart spectrum construction system, as shown in fig. 1, comprising:
the system comprises an acquisition module 1, a display module and a display module, wherein the acquisition module 1 is used for acquiring a target industry input by a user and acquiring industry big data corresponding to the target industry;
the training module 2 is used for training an industrial chain chart spectrum building model;
and the building module 3 is used for building a model based on the industry chain map spectrum and building an industry chain map corresponding to the target industry according to the industry big data.
The working principle and the beneficial effects of the technical scheme are as follows:
inputting a target industry (such as an automobile part industry) needing to construct an industry chain map by a user, and acquiring industry big data (such as a large amount of industry data related to the automobile part industry) corresponding to a target production area; training an industry chain map building model (a machine learning model which can learn to manually build an industry chain map according to industry data), building an industry chain map corresponding to a target industry according to industry big data based on the industry chain map building model (for example, classifying industry upstream, industry midstream and industry downstream according to the industry data);
according to the embodiment of the invention, when a user needs to construct the industry chain map, only the target industry needing to be analyzed needs to be input, the industry big data corresponding to the target industry is obtained, the model is constructed based on the trained industry chain map, and the corresponding industry chain map is constructed according to the industry big data, so that the convenience is improved, and the problem that the construction of the industry chain map by manually looking up the industry data is incomplete is solved.
The invention provides an industrial chain map construction system, wherein an acquisition module 1 executes the following operations:
acquiring a preset industry big data node set, wherein the industry big data node set comprises: a plurality of first nodes;
acquiring a reliability index corresponding to the first node, and if the reliability index is greater than or equal to a preset reliability index threshold, taking the corresponding first node as a second node;
acquiring target data corresponding to the target industry through the second node;
and integrating the acquired target data to acquire industrial big data, and finishing acquisition.
The working principle and the beneficial effects of the technical scheme are as follows:
when industrial big data is obtained, a plurality of industrial big data nodes, namely first nodes, are set, and the first nodes correspond to a collection party (such as a big data service mechanism) for collecting the industrial data; however, in order to ensure the acquisition quality of industrial big data acquisition and ensure the accuracy of subsequent industrial chain chart construction, reliability verification needs to be performed on the first node, that is, a reliability index corresponding to the first node is acquired, the larger the reliability index is, the more reliable the first node is, and if the reliability index is greater than or equal to a preset reliability index threshold, the corresponding first node is taken as a second node; and acquiring target data corresponding to the target industry through the second node, and integrating the target data to obtain industry big data.
The invention provides an industrial chain chart construction system, which is used for acquiring a reliability index corresponding to a first node and comprises the following steps:
establishing an industry big data node association library, determining at least one other first node associated with the first node based on the industry big data node association library, and taking the first node as a second node;
acquiring a plurality of credit records corresponding to the first node and the second node;
based on a preset credit scoring model, according to the credit record, performing credit scoring on the first node to obtain a credit score, giving a preset first weight to the credit score, and obtaining a first target value;
acquiring at least one guarantor corresponding to the first node, acquiring a guarantee value for the guarantor to guarantee the first node, giving a preset second weight to the guarantee value, and acquiring a second target value;
summing the first target value and the second target value to obtain a reliability index corresponding to the first node, and finishing obtaining;
wherein the first weight is greater than the second weight.
The working principle and the beneficial effects of the technical scheme are as follows:
when the reliability of the first node is judged, the reliability can be judged according to the historical credit condition (the overall authenticity of the industry data provided historically and the like) and the guaranteed condition of the first node;
according to the historical credit condition, a second node related to the first node is determined based on the established industry big data node association library, and comprehensive credit judgment is carried out based on credit records (such as authenticity, quality condition and the like of industry data provided historically) corresponding to the first node and the second node, so that when the first node generates poor credit, the credit condition of the second node is influenced, and when the second node generates poor credit, the credit condition of the first node is also influenced, the cost of generating the poor credit by the industry big data node is increased, and the quality of the industry data provided by the industry big data node is indirectly improved; based on a preset credit scoring model (a pre-trained model for scoring credit according to credit records), scoring the credit of the first node according to the credit records to obtain a credit score;
according to the guaranteed condition, a guarantor (such as a guaranty organization and other big data service organizations) corresponding to the first node is obtained, and a guaranty value for the guarantor to guarantee the first node is obtained (the greater the guaranty value is, the greater the guaranty degree is);
in addition, when the reliability of the first node is judged, the historical credit condition of the first node is looked at, so that the first weight is set to be larger than the second weight, the credit score is given with the first weight (multiplication of the two), meanwhile, the guarantee value is given with the second weight (multiplication of the two), and after the first weight and the second weight are respectively given, the summation technology is carried out, so that the reliability index is obtained, the acquisition is completed, and the reliability of the first node is judged more reasonably.
The invention provides an industrial chain graph spectrum construction system, which is used for constructing an industrial big data node association database and comprises the following steps:
randomly selecting two first nodes as a third node and a fourth node respectively;
attempting to acquire at least one historically generated correlation event between the third node and the fourth node;
if the attempt to acquire is successful, acquiring an association type corresponding to the association event, wherein the association type comprises: relationship association and behavior association;
when the association type corresponding to the association event is relationship association, extracting at least one association relationship generated between the third node and the fourth node from the association event, and meanwhile, acquiring a first association value corresponding to the association relationship;
when the association type corresponding to the association event is behavior association, extracting at least one association behavior generated between the third node and the fourth node from the association event, and meanwhile, acquiring a second association value corresponding to the association behavior;
accumulating and calculating the first correlation value and the second correlation value to obtain a correlation value sum;
if the correlation value sum is larger than or equal to a preset correlation value and a preset threshold value, performing node correlation pairing on the corresponding third node and fourth node to obtain a pairing group;
acquiring a preset blank database, and storing the pairing group into the blank database;
and when all the pairing groups needing to be stored in the blank database are stored, taking the blank database as a production big data node association library to finish construction.
The working principle and the beneficial effects of the technical scheme are as follows:
when a production big data node association library is constructed, a third node and a fourth node are randomly selected from a first node, association events which are generated historically between the third node and the fourth node are obtained, association types of the association events are divided into relationship association (for example, the third node guarantees the fourth node, and a guarantee relationship is generated between the third node and the fourth node) and behavior association (for example, data sharing is performed between the third node and the fourth node, and a sharing association behavior is generated), when the association type of the association events is the relationship association, association relationship (for example, the guarantee relationship) is extracted from the association events, and a first association value corresponding to the association relationship is obtained; when the association type of the association event is behavior association, extracting the association behavior (for example, sharing the association behavior) from the association event, and acquiring a second association value corresponding to the association behavior; accumulating and calculating a first correlation value and a second correlation value to obtain a correlation value sum; and when the correlation value sum is greater than or equal to the preset correlation value and threshold value, performing correlation pairing on the corresponding fourth node and the fourth node to obtain a pairing group, and storing the pairing group in a blank database to complete construction of the industry big data node correlation database.
The invention provides an industrial chain chart construction system, wherein a training module 2 executes the following operations:
acquiring a plurality of first construction processes for manually constructing an industrial chain chart;
acquiring the capacity index of a constructor corresponding to the first construction process, and if the capacity index is greater than or equal to a preset capacity index threshold, taking the corresponding first construction process as a second construction process;
otherwise, taking the corresponding first construction process as a third construction process;
splitting the third construction flow into a plurality of first sub-flows, and sequencing the first sub-flows based on a preset sequencing rule to obtain a flow sequence;
acquiring a first flow type corresponding to the first sub-flow, and acquiring a trigger value corresponding to the first flow type;
if the trigger value is greater than or equal to a preset trigger threshold value, taking the corresponding first sub-process as a second sub-process;
acquiring the first flow type corresponding to the second sub-flow, and using the first flow type as a second flow type;
acquiring at least one check item corresponding to the second flow type, wherein the check item comprises: the inspection direction, the inspection range and the inspection flow type;
determining that the first flow type corresponding to the inspection flow type in the inspection range in the inspection direction of the second flow in the flow sequence is the first flow corresponding to the inspection flow type, and using the first flow as a third flow;
integrating the second sub-process and the third sub-process to obtain a part of process to be detected;
acquiring a process rationality inspection model corresponding to the second process type, performing rationality inspection on the part of the process to be inspected, acquiring a rational value, and associating the rational value with the corresponding third construction process;
accumulating and calculating the reasonable values associated with the third construction process to obtain a reasonable value sum;
acquiring a reasonable value and a threshold value corresponding to the capability index of the builder corresponding to the third building process;
if the reasonable value sum is larger than or equal to the reasonable value sum and the threshold value, taking the corresponding third construction process as a fourth construction process;
and taking the second construction process and the fourth construction process as training samples, and performing model training on the training samples based on a preset model training algorithm to obtain an industrial chain chart spectrum construction model.
The working principle and the beneficial effects of the technical scheme are as follows:
when the industrial chain chart is trained to construct the model, learning how to manually construct the industrial chain chart can be carried out on the basis of a machine learning technology, and constructing the model; therefore, a plurality of first construction processes for manually constructing the industrial chain spectrum are obtained, but in order to ensure the training quality of the industrial chain spectrum construction model, so that the accuracy of the subsequent industrial chain spectrum construction based on the trained industrial chain spectrum construction model needs to be verified;
when the quality of the first construction process is verified, the capability index of a construction party (an artificial party for constructing the industrial chain map) corresponding to the first construction process is firstly obtained, if the capability index is greater than or equal to a preset capability index threshold value, the capability of the corresponding construction party is enough, verification is not needed, verification resources are reduced, and the verification efficiency is improved; otherwise (the capability index is smaller than the capability index threshold), performing quality verification on the corresponding third construction process;
when the quality of the third construction process is verified, splitting the third construction process into a plurality of first sub-processes, and sequencing the first sub-processes based on a preset sequencing rule (sequencing according to the sequence of the processes) to obtain a process sequence; firstly, acquiring a trigger value corresponding to a first flow type corresponding to a first flow (for example, analyzing an association relation between an industry upstream and an industry midstream, and performing association transition between the industry upstream and the industry midstream), and when the trigger value is greater than or equal to a preset trigger threshold value, indicating that a second flow corresponding to the second flow type needs to be verified, and not needing to verify each first flow, further reducing verification resources and improving verification efficiency; acquiring at least one check item corresponding to the second flow type, wherein the check item comprises a check direction (for example, when whether the association relationship between the upstream industry and the industry midstream is reasonable is verified and analyzed, which categories exist in the upstream industry acquired before and which categories exist in the midstream industry acquired after the collection need to be acquired, so that the check direction is front and back), a check range (for example, within 3 flows) and a check flow type (for example, the upstream industry comprises category collection and the midstream industry comprises category collection); based on the check item, the required third flow division is quickly determined, and the verification efficiency is further improved; integrating the second sub-process and the third sub-process (performing sequential sequencing integration of the processes) to obtain a part of the process to be inspected; acquiring a process rationality inspection model (a model which is trained in advance and used for inspecting the rationality of the second process type, and during inspection, for example, verifying and analyzing the association relationship between the industry upstream and the industry midstream) corresponding to the second process type, and performing rationality inspection on a part of the process to be inspected to obtain a rational value; accumulating and calculating reasonable values to obtain a reasonable value sum; acquiring a reasonable value and a threshold value corresponding to the capability index of the construction party corresponding to the third construction flow (the smaller the capability index is, the higher the quality requirement on the construction flow is, and the higher the requirement on the reasonable value and the threshold value are, the larger the reasonable value and the threshold value are); if the reasonable value sum is larger than or equal to the reasonable value sum and the threshold value, taking the corresponding third construction process as a fourth construction process; performing model training on the second construction process and the fourth construction process based on a preset model training algorithm (for example, a machine learning algorithm) (the model training performed by using the machine learning algorithm belongs to the field of the prior art and is not repeated), and obtaining an industrial chain graph spectrum construction model;
obtaining a reasonable value and a threshold value corresponding to the capability index of the builder corresponding to the third building process through the following formula:
wherein the content of the first and second substances,
a reasonable value and a threshold value corresponding to the capability index of the builder corresponding to the third building process,
the capability index of the constructor corresponding to the third construction flow,
the relation coefficient is preset and can be set by the staff.
The invention provides an industrial chain chart spectrum construction system, which is used for acquiring the capability index of a construction party corresponding to a first construction process and comprises the following steps:
acquiring a construction initial time point corresponding to the first construction process;
acquiring an empirical value of a constructor corresponding to the first construction process, corresponding to the construction initial time point, and acquiring a construction weight of the constructor corresponding to the first construction process;
giving the empirical value corresponding to the construction weight to obtain a capability value;
and summing the capability values to obtain the capability index of the builder, and finishing the obtaining.
The working principle and the beneficial effects of the technical scheme are as follows:
when the capability index corresponding to the builder is obtained, an experience value can be obtained from the experience degree of the builder for building the industrial chain chart, but the experience value of the builder is continuously increased, so that a building initial time point (a time point when building starts) corresponding to a first building process needs to be obtained, the experience value of the builder corresponding to the building initial time is obtained, and the accuracy of obtaining the capability index is improved; in addition, the process of constructing the industrial chain map is complex, and the participation degree, the contribution degree and the like of different construction parties are different due to the fact that multiple persons participate, namely multiple construction parties, so that the accuracy of obtaining the capacity index is further improved, the construction weight corresponding to the first construction process of the construction party is obtained, the size of the construction weight represents the participation degree, the contribution degree and the like of the construction party, the experience value is endowed to correspond to the construction weight (the two are multiplied), the capacity value is obtained, and the capacity value is summed and calculated to obtain the capacity index.
The invention provides an industrial chain chart spectrum construction system, which further comprises:
and the supplement construction module is used for carrying out adaptive supplement construction on the industrial chain map when a user views the industrial chain map.
The working principle and the beneficial effects of the technical scheme are as follows:
when a user views the industry chain map, the industry chain map can be subjected to adaptive supplementary construction (for example, enterprise ranking scores upstream of the industry are shown to the user).
The invention provides an industrial chain graph spectrum construction system, wherein a supplementary construction module executes the following operations:
analyzing whether a user watches any first industrial chain node in the industrial chain map when looking at the industrial chain map based on attention analysis technology;
if so, taking the first industrial chain node watched by the user as a second industrial chain node;
acquiring a plurality of first alternative enterprises corresponding to the second industry link points;
acquiring a first evaluation index corresponding to the first candidate enterprise;
if the first evaluation index is larger than or equal to a preset first evaluation index threshold value, taking the corresponding first candidate enterprise as a first display target;
sorting the first display target from large to small according to the first evaluation index corresponding to the first display target to obtain a first display block;
acquiring a first introduction item corresponding to the first display target, and marking the first introduction item on the first display target corresponding to the first display block;
associating the first display block with the corresponding second industrial chain node, acquiring a first display position corresponding to the second industrial chain node, and arranging the first display block at the first display position for display;
in the display process, whether a user watches other at least one first industry chain node within a preset time period is analyzed based on attention analysis technology;
if the other first industrial chain nodes watched by the user in the time period are used as third industrial chain nodes;
acquiring a plurality of second alternative enterprises corresponding to the third production link points;
acquiring a second evaluation index corresponding to the second candidate enterprise;
if the second evaluation index is larger than or equal to a preset second evaluation index threshold value, taking the corresponding second candidate enterprise as a second display target;
sorting the second display targets from large to small according to the second evaluation indexes corresponding to the second display targets to obtain second display blocks;
acquiring a second introduction item corresponding to the second display target, and marking the second introduction item on the second display target corresponding to the second display block;
associating the second display block with the corresponding third production chain node, acquiring a second display position corresponding to the third production chain node, and arranging the second display block at the second display position for display;
taking the first display block and the second display block as a third display block, and meanwhile, acquiring a second industrial chain node or a third industrial chain node associated with the third display block and taking the second industrial chain node or the third industrial chain node as a fourth industrial chain node;
acquiring node weights corresponding to the fourth industrial chain link points;
randomly selecting a third display target from the corresponding third display blocks according to the node weights from large to small, and sequencing the selected third display targets according to the selection sequence to obtain a display target sequence;
sequentially traversing the third display targets in the display target sequence, acquiring adaptation values between other third display targets after the third display target traversed each time in the display target sequence and the traversed third display targets, and marking the adaptation values on the traversed third display targets;
after traversing the third display target, accumulating and calculating the marked adaptation value of the third display target to obtain an adaptation value sum, giving the adaptation value sum a preset third weight to obtain a first sequencing value, and associating the first sequencing value with the corresponding third display target;
obtaining ranking scores of the third display targets in the ranking corresponding to the third display blocks, giving a preset fourth weight to the ranking scores to obtain a second ranking value, and associating the second ranking value with the corresponding third display targets;
acquiring a sequence position of the third display target in the display target sequence, and acquiring a position weight corresponding to the sequence position;
accumulating and calculating the first ranking value and the second ranking value associated with the third display target to obtain a ranking value sum, endowing the ranking value sum with the corresponding position weight to obtain a ranking index, and associating the ranking index with the corresponding display target sequence;
accumulating the ranking indexes associated with the display target sequence to obtain a ranking index sum;
acquiring a third display position corresponding to each fourth industrial chain node, and meanwhile, arranging the maximum sorting index and the corresponding display target sequence at the third display position for display;
wherein the third weight is greater than the fourth weight.
The working principle and the beneficial effects of the technical scheme are as follows:
when a user views an industrial chain map (for example, a 5G base station industrial chain map), related enterprises of some industrial chain nodes (for example, base station design, base station planning, station address planning and the like at the upstream of an industry) often need to be viewed, at the moment, the user needs to query data (for example, hundred-degree search) by himself according to the industrial chain nodes, and the data is complex, and in addition, the user needs to query evaluation and the like of different related enterprises by himself to perform reasonable sequencing, so that the complexity is further improved, and the user experience is poor; meanwhile, if a user wants to invest in the industry or collaborate together, the adaptability between the corresponding related enterprises of different industry link points needs to be considered, and an investment plan is planned based on the adaptation condition, but when the adaptation condition is researched, the corresponding enterprise data (such as scale, supply speed, historical collaboration record and the like) needs to be searched automatically, so that the complexity is further improved, and the humanization is not enough; therefore, a solution is urgently needed;
when a user views an industrial chain map, whether the user watches any first industrial chain node (for example, base station design) in the industrial chain map is analyzed based on an attention analysis technology (the attention analysis technology belongs to the field of the prior art and is not described any more, for example, attention analysis is performed based on eye movement and the like), if so, a plurality of first candidate enterprises (for example, related enterprises of the base station design) corresponding to a second industrial chain node watched by the user are obtained, a first evaluation index corresponding to the first candidate enterprises is obtained (the larger the first evaluation index is, the better the corresponding first candidate enterprises is, during the obtaining, comprehensive analysis and obtaining can be performed based on credit evaluation of the first candidate enterprises, evaluation of enterprise scale and historical partner, and the like), and if the first evaluation index is greater than or equal to a preset first evaluation index threshold, the first candidate enterprise is better corresponding to and can be used as a first display target, to be displayed to the user; in order to enable a user to know ranking scores, ranking the first display targets based on the corresponding first evaluation indexes to obtain first display blocks; in order to enable a user to know the enterprise information, acquiring a first introduction item (such as enterprise scale, experience business range and the like) corresponding to a first display target, and marking the first introduction item on the first display target; a first display position corresponding to a second industrial chain link point is reserved on the industrial chain map, and a first display block is displayed at the first display position; when a user needs to check related enterprise information, enterprise ranking scores and the like corresponding to a certain industrial chain node, the user only needs to simply watch the related better enterprise information and corresponding enterprise information of a second industrial chain node, the user does not need to search resources by himself or herself and perform ranking score by combining evaluation, and convenience is improved to a great extent;
when the user watches other third production chain nodes in a preset time period (for example, 7 seconds), generating a second display block corresponding to the third production chain node in the same way, and displaying the second display block at a corresponding second display position; at this time, adaptation analysis needs to be performed on the related enterprises corresponding to the second industrial chain node and the third industrial chain node; taking the first display block and the second display block as a third display block, and acquiring a second industrial chain node or a third industrial chain node corresponding to the third display block as a fourth industrial chain node; acquiring node weights corresponding to the fourth industrial chain nodes, wherein the greater the node weights, the greater the importance of the corresponding fourth industrial chain nodes in the industrial chain (for example, the maximum importance of network engineering maintenance in the 5G base station industrial chain); randomly selecting a third display target from the corresponding third display blocks in turn from a large guide according to the node weight, and sequencing the selected third display targets according to the selection sequence, so that the more important third display target is ranked to the front; during adaptation analysis, the third display target with high importance needs to be preferentially ensured not to change, and the adaptation situation between the third display target with low importance and the third display target with high importance is analyzed, so that the third display targets are sequentially traversed, the adaptation values between the traversed third display target and the third display targets behind the third display target are obtained (the adaptation situations can be analyzed based on whether the scale adaptation and the supply speed between enterprises meet the production speed and whether the enterprises cooperate or not), the adaptation values are obtained, the tagged adaptation values of the third display target are accumulated and calculated, and the sum of the adaptation values is obtained;
then, the optimal display target sequence needs to be screened out, displayed to a user, and subjected to investment or co-operation suggestion; when the display target sequence is screened, the enterprise ranking scores in the corresponding industrial chain nodes can be selected according to the adaptation values and the third display targets, but the adaptation condition, namely the adaptation value sum, is considered to be more important, so that the third weight is set to be greater than the fourth weight; endowing the adaptive value and a third weight (multiplying the adaptive value and the third weight) to obtain a first sequencing value; obtaining ranking scores of the third display targets in the third display block (the ranking is higher and higher), giving a preset fourth weight to the ranking scores, and obtaining a second ranking value; accumulating and calculating a first sorting value and a second sorting value to obtain a sum of the sorting values; in addition, acquiring a position weight corresponding to the sequence position of the third display target in the display target sequence (the more the sequence position is forward, the greater the importance is, and the greater the position weight is), giving a ranking value and a corresponding position weight, and acquiring a ranking index; accumulating all the ranking indexes to obtain a ranking index sum; the maximum sequencing index and the corresponding display target sequence are displayed on the corresponding third display position for the user to check, the user does not need to search for resource research adaptation conditions and the like by himself, and only needs to continuously look at a plurality of industrial chain nodes in a short time, so that convenience is further improved, user experience is further improved, and meanwhile, the display method is more intelligent.
The invention provides an industrial chain map construction method, as shown in fig. 2, comprising the following steps:
step 1: acquiring a target industry input by a user, and acquiring industry big data corresponding to the target industry;
step 2: training an industrial chain graph spectrum building model;
and step 3: and constructing a model based on the industry chain map, and constructing an industry chain map corresponding to the target industry according to the industry big data.
The working principle and the beneficial effects of the technical scheme are already explained in the system and are not described in detail.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and 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 is also intended to include such modifications and variations.
Claims (9)
1. An industry chain graph building system, comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a target industry input by a user and acquiring industry big data corresponding to the target industry;
the training module is used for training the industrial chain chart building model;
the construction module is used for constructing a model based on the industry chain map spectrum and constructing an industry chain map corresponding to the target industry according to the industry big data;
the training module performs the following operations:
acquiring a plurality of first construction processes for manually constructing an industrial chain chart;
acquiring the capacity index of a builder corresponding to the first building process, and if the capacity index is greater than or equal to a preset capacity index threshold, taking the corresponding first building process as a second building process;
otherwise, taking the corresponding first construction process as a third construction process;
splitting the third construction flow into a plurality of first sub-flows, and sequencing the first sub-flows based on a preset sequencing rule to obtain a flow sequence;
acquiring a first flow type corresponding to the first sub-flow, and acquiring a trigger value corresponding to the first flow type;
if the trigger value is greater than or equal to a preset trigger threshold value, taking the corresponding first sub-process as a second sub-process;
acquiring the first flow type corresponding to the second sub-flow and taking the first flow type as a second flow type;
acquiring at least one check item corresponding to the second flow type, wherein the check item comprises: checking direction, checking range and checking process type;
determining that the first flow type corresponding to the inspection flow type in the inspection range in the inspection direction of the second flow in the flow sequence is the first flow corresponding to the inspection flow type, and using the first flow as a third flow;
integrating the second sub-process and the third sub-process to obtain a part of process to be detected;
acquiring a process rationality inspection model corresponding to the second process type, performing rationality inspection on the part of the process to be inspected, acquiring a rational value, and associating the rational value with the corresponding third construction process;
accumulating and calculating the reasonable values associated with the third construction process to obtain a reasonable value sum;
acquiring a reasonable value and a threshold value corresponding to the capability index of the builder corresponding to the third building process;
if the reasonable value sum is larger than or equal to the reasonable value sum and the threshold value, taking the corresponding third construction process as a fourth construction process;
and taking the second construction process and the fourth construction process as training samples, and performing model training on the training samples based on a preset model training algorithm to obtain an industrial chain diagram spectrum construction model.
2. The system of claim 1, wherein the acquisition module performs the following operations:
acquiring a preset industry big data node set, wherein the industry big data node set comprises: a plurality of first nodes;
acquiring a reliability index corresponding to the first node, and if the reliability index is greater than or equal to a preset reliability index threshold, taking the corresponding first node as a second node;
acquiring target data corresponding to the target industry through the second node;
and integrating the acquired target data to acquire industrial big data, and finishing acquisition.
3. The system for building an industry chain graph spectrum according to claim 2, wherein obtaining the reliability index corresponding to the first node comprises:
establishing an industry big data node association library, determining at least one other first node associated with the first node based on the industry big data node association library, and taking the first node as a second node;
acquiring a plurality of credit records corresponding to the first node and the second node;
based on a preset credit scoring model, according to the credit record, performing credit scoring on the first node to obtain a credit score, giving a preset first weight to the credit score, and obtaining a first target value;
acquiring at least one guarantor corresponding to the first node, acquiring a guarantee value for the guarantor to guarantee the first node, giving a preset second weight to the guarantee value, and acquiring a second target value;
summing the first target value and the second target value to obtain a reliability index corresponding to the first node, and finishing the obtaining;
wherein the first weight is greater than the second weight.
4. The industry chain graph spectrum building system of claim 3, wherein building a large production data node association library comprises:
randomly selecting two first nodes as a third node and a fourth node respectively;
attempting to acquire at least one historically generated correlation event between the third node and the fourth node;
if the attempt to acquire is successful, acquiring an association type corresponding to the association event, wherein the association type comprises: relationship association and behavior association;
when the association type corresponding to the association event is a relationship association, extracting at least one association relationship generated between the third node and the fourth node from the association event, and meanwhile, acquiring a first association value corresponding to the association relationship;
when the association type corresponding to the association event is behavior association, extracting at least one association behavior generated between the third node and the fourth node from the association event, and meanwhile, acquiring a second association value corresponding to the association behavior;
accumulating and calculating the first correlation value and the second correlation value to obtain a correlation value sum;
if the correlation value sum is larger than or equal to a preset correlation value and a preset threshold value, performing node correlation pairing on the corresponding third node and fourth node to obtain a pairing group;
acquiring a preset blank database, and storing the pairing group into the blank database;
and when all the pairing groups needing to be stored in the blank database are stored, taking the blank database as a production big data node association library to finish construction.
5. The system for building an industry chain graph spectrum according to claim 1, wherein the obtaining of the capability index of the builder corresponding to the first building process comprises:
acquiring a construction initial time point corresponding to the first construction process;
acquiring an empirical value of a constructor corresponding to the first construction process, corresponding to the construction initial time point, and acquiring a construction weight of the constructor corresponding to the first construction process;
giving the empirical value corresponding to the construction weight to obtain a capability value;
and summing the capability values to obtain the capability index of the builder, and finishing the obtaining.
6. The system for building an industry chain spectrum as recited in claim 1, further comprising:
and the supplement construction module is used for carrying out adaptive supplement construction on the industrial chain map when a user views the industrial chain map.
7. The industrial chain graph spectrum building system of claim 6, wherein the complementary building module performs the following operations:
analyzing whether a user watches any first industrial chain node in the industrial chain map when looking at the industrial chain map based on attention analysis technology;
if so, taking the first industrial chain node watched by the user as a second industrial chain node;
acquiring a plurality of first alternative enterprises corresponding to the second industry link point;
acquiring a first evaluation index corresponding to the first candidate enterprise;
if the first evaluation index is larger than or equal to a preset first evaluation index threshold value, taking the corresponding first candidate enterprise as a first display target;
sorting the first display target from large to small according to the first evaluation index corresponding to the first display target to obtain a first display block;
acquiring a first introduction item corresponding to the first display target, and marking the first introduction item on the first display target corresponding to the first display block;
associating the first display block with the corresponding second industrial chain node, acquiring a first display position corresponding to the second industrial chain node, and arranging the first display block at the first display position for display;
in the display process, whether a user watches other at least one first industry chain node within a preset time period is analyzed based on attention analysis technology;
if the other first industrial chain nodes watched by the user in the time period are used as third industrial chain nodes;
acquiring a plurality of second alternative enterprises corresponding to the third production link points;
acquiring a second evaluation index corresponding to the second candidate enterprise;
if the second evaluation index is larger than or equal to a preset second evaluation index threshold value, taking the corresponding second candidate enterprise as a second display target;
sorting the second display targets from large to small according to the second evaluation indexes corresponding to the second display targets to obtain second display blocks;
acquiring a second introduction item corresponding to the second display target, and marking the second introduction item on the second display target corresponding to the second display block;
associating the second display block with the corresponding third production chain node, acquiring a second display position corresponding to the third production chain node, and arranging the second display block at the second display position for display;
taking the first display block and the second display block as a third display block, and meanwhile, acquiring a second industrial chain node or a third industrial chain node associated with the third display block and taking the second industrial chain node or the third industrial chain node as a fourth industrial chain node;
acquiring node weights corresponding to the fourth industrial chain link points;
randomly selecting a third display target from the corresponding third display blocks according to the node weights from large to small, and sequencing the selected third display targets according to the selection sequence to obtain a display target sequence;
sequentially traversing the third display targets in the display target sequence, acquiring adaptation values between other third display targets after the third display target traversed each time in the display target sequence and the traversed third display targets, and marking the adaptation values on the traversed third display targets;
after traversing the third display target, accumulating and calculating the marked adaptation value of the third display target to obtain an adaptation value sum, endowing the adaptation value sum with a preset third weight to obtain a first sequencing value, and associating the first sequencing value with the corresponding third display target;
obtaining ranking scores of the third display targets in the ranking corresponding to the third display blocks, giving a preset fourth weight to the ranking scores to obtain a second ranking value, and associating the second ranking value with the corresponding third display targets;
acquiring a sequence position of the third display target in the display target sequence, and acquiring a position weight corresponding to the sequence position;
accumulating and calculating the first ranking value and the second ranking value associated with the third display target to obtain a ranking value sum, endowing the ranking value sum with the corresponding position weight to obtain a ranking index, and associating the ranking index with the corresponding display target sequence;
accumulating the ranking indexes associated with the display target sequence to obtain a ranking index sum;
acquiring a third display position corresponding to each fourth industrial chain node, and meanwhile, arranging the maximum sorting index and the corresponding display target sequence at the third display position for display;
wherein the third weight is greater than the fourth weight.
8. An industrial chain map construction method is characterized by comprising the following steps:
step 1: acquiring a target industry input by a user, and acquiring industry big data corresponding to the target industry;
step 2: training an industrial chain chart building model;
and step 3: constructing an industry chain map corresponding to the target industry according to the industry big data based on the industry chain map construction model;
the method for training the industrial chain diagram construction model comprises the following steps: acquiring a plurality of first construction processes for manually constructing an industrial chain chart;
acquiring the capacity index of a builder corresponding to the first building process, and if the capacity index is greater than or equal to a preset capacity index threshold, taking the corresponding first building process as a second building process;
otherwise, taking the corresponding first construction process as a third construction process;
splitting the third construction flow into a plurality of first sub-flows, and sequencing the first sub-flows based on a preset sequencing rule to obtain a flow sequence;
acquiring a first flow type corresponding to the first branch flow, and acquiring a trigger value corresponding to the first flow type;
if the trigger value is greater than or equal to a preset trigger threshold value, taking the corresponding first sub-process as a second sub-process;
acquiring the first flow type corresponding to the second sub-flow and taking the first flow type as a second flow type;
acquiring at least one check item corresponding to the second flow type, wherein the check item comprises: the inspection direction, the inspection range and the inspection flow type;
determining that the first flow type corresponding to the inspection flow type in the inspection range in the inspection direction of the second flow in the flow sequence is the first flow, and taking the first flow as a third flow;
integrating the second sub-process and the third sub-process to obtain a part of process to be detected;
acquiring a process rationality inspection model corresponding to the second process type, performing rationality inspection on the part of the process to be inspected, acquiring a rational value, and associating the rational value with the corresponding third construction process;
accumulating and calculating the reasonable values associated with the third construction process to obtain a reasonable value sum;
acquiring a reasonable value and a threshold value corresponding to the capability index of the builder corresponding to the third building process;
if the reasonable value sum is larger than or equal to the reasonable value sum and the threshold value, taking the corresponding third construction process as a fourth construction process;
and taking the second construction process and the fourth construction process as training samples, and performing model training on the training samples based on a preset model training algorithm to obtain an industrial chain chart spectrum construction model.
9. The method for constructing an industry chain graph spectrum according to claim 8, wherein in the step 1, acquiring industry big data corresponding to the target industry comprises:
acquiring a preset industry big data node set, wherein the industry big data node set comprises: a plurality of first nodes;
acquiring a reliability index corresponding to the first node, and if the reliability index is greater than or equal to a preset reliability index threshold value, taking the corresponding first node as a second node;
acquiring target data corresponding to the target industry through the second node;
and integrating the acquired target data to acquire industrial big data, and finishing acquisition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210315027.4A CN114417020B (en) | 2022-03-29 | 2022-03-29 | Industrial chain map construction system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210315027.4A CN114417020B (en) | 2022-03-29 | 2022-03-29 | Industrial chain map construction system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114417020A CN114417020A (en) | 2022-04-29 |
| CN114417020B true CN114417020B (en) | 2022-09-09 |
Family
ID=81263047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210315027.4A Active CN114417020B (en) | 2022-03-29 | 2022-03-29 | Industrial chain map construction system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114417020B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115544336A (en) * | 2022-12-01 | 2022-12-30 | 南方电网数字电网研究院有限公司 | Industrial chain generation method and device, computer equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018208945A1 (en) * | 2017-05-12 | 2018-11-15 | Honeywell International Inc. | Apparatus and method for assimilation of supply chain and production management (scpm) for industrial process control and automation system |
| CN109255034A (en) * | 2018-08-08 | 2019-01-22 | 数据地平线（广州）科技有限公司 | A kind of domain knowledge map construction method based on industrial chain |
| CN111784151A (en) * | 2020-06-29 | 2020-10-16 | 中电工业互联网有限公司 | System and method for generating industrial chain panoramic image |
| CN112328803A (en) * | 2020-10-14 | 2021-02-05 | 上海华鑫股份有限公司 | Construction method of company knowledge graph based on industrial chain data |
| CN112650898A (en) * | 2020-12-28 | 2021-04-13 | 武汉烽火信息集成技术有限公司 | Industrial chain visual analysis method, device and equipment |
| CN113051365A (en) * | 2020-12-10 | 2021-06-29 | 深圳证券信息有限公司 | Industrial chain map construction method and related equipment |
| CN113449046A (en) * | 2021-06-29 | 2021-09-28 | 平安资产管理有限责任公司 | Model training method, system and related device based on enterprise knowledge graph |
| CN113505242A (en) * | 2021-07-16 | 2021-10-15 | 珍岛信息技术（上海）股份有限公司 | Method and system for automatically embedding knowledge graph |
| CN113656590A (en) * | 2021-07-16 | 2021-11-16 | 北京百度网讯科技有限公司 | Industry map construction method and device, electronic equipment and storage medium |
| CN113837527A (en) * | 2021-08-02 | 2021-12-24 | 深圳前海微众银行股份有限公司 | Enterprise rating method, device, equipment and storage medium |
| CN113869768A (en) * | 2021-10-11 | 2021-12-31 | 爱信诺征信有限公司 | Method, device, equipment and readable medium for evaluating strength of industrial chain |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170293835A1 (en) * | 2016-04-06 | 2017-10-12 | Saudi Arabian Oil Company | Data-driven simulation method of multiphase choke performance |
| WO2021107449A1 (en) * | 2019-11-25 | 2021-06-03 | 주식회사 데이터마케팅코리아 | Method for providing knowledge graph-based marketing information analysis service using conversion of transliterated neologisms and apparatus therefor |
| CN111428053B (en) * | 2020-03-30 | 2023-10-20 | 西安交通大学 | Construction method of tax field-oriented knowledge graph |
| CN112347752B (en) * | 2020-11-16 | 2021-09-14 | 中国信息通信研究院 | Autonomous drawing management method and device for industrial chain |
-
2022
- 2022-03-29 CN CN202210315027.4A patent/CN114417020B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018208945A1 (en) * | 2017-05-12 | 2018-11-15 | Honeywell International Inc. | Apparatus and method for assimilation of supply chain and production management (scpm) for industrial process control and automation system |
| CN109255034A (en) * | 2018-08-08 | 2019-01-22 | 数据地平线（广州）科技有限公司 | A kind of domain knowledge map construction method based on industrial chain |
| CN111784151A (en) * | 2020-06-29 | 2020-10-16 | 中电工业互联网有限公司 | System and method for generating industrial chain panoramic image |
| CN112328803A (en) * | 2020-10-14 | 2021-02-05 | 上海华鑫股份有限公司 | Construction method of company knowledge graph based on industrial chain data |
| CN113051365A (en) * | 2020-12-10 | 2021-06-29 | 深圳证券信息有限公司 | Industrial chain map construction method and related equipment |
| CN112650898A (en) * | 2020-12-28 | 2021-04-13 | 武汉烽火信息集成技术有限公司 | Industrial chain visual analysis method, device and equipment |
| CN113449046A (en) * | 2021-06-29 | 2021-09-28 | 平安资产管理有限责任公司 | Model training method, system and related device based on enterprise knowledge graph |
| CN113505242A (en) * | 2021-07-16 | 2021-10-15 | 珍岛信息技术（上海）股份有限公司 | Method and system for automatically embedding knowledge graph |
| CN113656590A (en) * | 2021-07-16 | 2021-11-16 | 北京百度网讯科技有限公司 | Industry map construction method and device, electronic equipment and storage medium |
| CN113837527A (en) * | 2021-08-02 | 2021-12-24 | 深圳前海微众银行股份有限公司 | Enterprise rating method, device, equipment and storage medium |
| CN113869768A (en) * | 2021-10-11 | 2021-12-31 | 爱信诺征信有限公司 | Method, device, equipment and readable medium for evaluating strength of industrial chain |
Non-Patent Citations (1)
| Title |
|---|
| 大都市边缘区旅游产业链动态演化研究――以西安临潼区为例;董皓;《经济地理》;20130930;第188-192页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114417020A (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110223168B (en) | Label propagation anti-fraud detection method and system based on enterprise relationship map | |
| CN111882446B (en) | Abnormal account detection method based on graph convolution network | |
| CN114066242A (en) | Enterprise risk early warning method and device | |
| CN106600423A (en) | Machine learning-based car insurance data processing method and device and car insurance fraud identification method and device | |
| CN110298601A (en) | A kind of real time business air control system of rule-based engine | |
| CN114417020B (en) | Industrial chain map construction system and method | |
| CN111340457A (en) | Building fire-fighting examination and acceptance platform system based on artificial intelligence and method thereof | |
| CN110163532A (en) | Methods of risk assessment, risk management method, device, equipment and storage medium | |
| CN110033191B (en) | Business artificial intelligence analysis method and system | |
| CN115456695A (en) | Method, device, system and medium for analyzing shop address selection | |
| CN113642922A (en) | Small and medium-sized micro enterprise credit evaluation method and device | |
| CN114912510A (en) | On-line investigation sample quality evaluation system | |
| CN105740434A (en) | Network information scoring method and device | |
| CN115577172A (en) | Article recommendation method, device, equipment and medium | |
| CN113988616A (en) | Enterprise risk assessment system and method based on industry data | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN116596395B (en) | Operation quality control platform for engineering project evaluation unit guidance and detection | |
| CN112767126A (en) | Collateral grading method and device based on big data | |
| CN112580992B (en) | Illegal fund collecting risk monitoring system for financial-like enterprises | |
| CN115660645A (en) | Method, device, equipment and storage medium for evaluating skills of maintenance personnel | |
| Umamaheswari et al. | Building accurate legal case outcome prediction models | |
| CN114328668A (en) | Method and device for generating deposit risk control strategy, terminal and storage medium | |
| CN115577897A (en) | Talent selection method and device based on smart cloud platform | |
| CN111325390B (en) | Student cooperative relationship prediction method based on interest evolution | |
| Ahmad et al. | Ensemble machine learning model for higher learning scholarship award decisions |
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 |