CN117422137A - Intelligent association method and system for business process nodes and knowledge graph - Google Patents
Intelligent association method and system for business process nodes and knowledge graph Download PDFInfo
- Publication number
- CN117422137A CN117422137A CN202311491248.8A CN202311491248A CN117422137A CN 117422137 A CN117422137 A CN 117422137A CN 202311491248 A CN202311491248 A CN 202311491248A CN 117422137 A CN117422137 A CN 117422137A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- node
- business process
- nodes
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 201
- 230000008569 process Effects 0.000 title claims abstract description 165
- 238000013507 mapping Methods 0.000 claims abstract description 100
- 238000004364 calculation method Methods 0.000 claims abstract description 32
- 230000007246 mechanism Effects 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 6
- 230000003068 static effect Effects 0.000 abstract description 6
- 238000010276 construction Methods 0.000 abstract description 4
- 230000003993 interaction Effects 0.000 description 10
- 238000007726 management method Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 9
- 239000013598 vector Substances 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 239000000969 carrier Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of knowledge graphs, and provides a business process node and knowledge graph intelligent association method, wherein a first attribute value of a knowledge node is obtained through the knowledge graph, a second attribute value of the business process node is obtained from a newly-built business process network, similarity calculation is carried out on summary information and knowledge demand information to obtain a similarity value, and a first mapping relation is established; acquiring knowledge nodes with association degree exceeding a second preset value through a knowledge graph, and establishing a second mapping relation; establishing a knowledge association sequence through the first mapping relation and the second mapping relation; the invention also discloses a system, which can quickly and dynamically establish the matching of the business process nodes and the knowledge nodes from the knowledge graph after the business process nodes are changed, effectively correlate modularized and static knowledge nodes with the business process nodes, and respond to the requirements of new construction, change and the like of the business process.
Description
Technical Field
The invention relates to the technical field of knowledge graphs, in particular to a business process node and knowledge graph intelligent association method and system.
Background
Knowledge Graph (KG) is a Knowledge domain visualization or Knowledge domain mapping map, which is a series of different graphs for displaying Knowledge development process and structural relationship, knowledge resources and carriers thereof are described by using a visualization technology, knowledge and the interrelation between the Knowledge resources and carriers are mined, analyzed, constructed, drawn and displayed, the complex Knowledge domain is displayed by data mining, information processing, knowledge metering and Graph drawing, and the Knowledge domain has wide application prospect in the high-dimensional Knowledge management field along with the development of artificial intelligence technology.
CN114417018B discloses a full-flow visual configuration system and method of a knowledge graph, comprising a data source management module, a data source connection module and a knowledge graph management module, wherein the data source management module is used for acquiring data sources to be connected and establishing connection with all the data sources to be connected; the data mapping management module is used for acquiring the mapping relation between the structured data in the data source to be connected and the map; the data synchronization module is used for extracting data in the connected data sources to the graph database and constructing a knowledge graph based on the mapping relation; the element style configuration module is used for acquiring element styles of the atlas and displaying the knowledge atlas; the data acquisition module is used for reading the relational database and selecting the table as a data set; supporting the execution of custom sql on a page, and saving the query result as a view type result set; supporting the execution of java codes on pages, and storing the results of program execution as a result set; the interaction configuration module is used for acquiring interaction configuration information, generating and storing the relationship between the interaction instruction and the event and the relationship between the operation and the feedback content; the interaction configuration module comprises a trigger event rule configuration module and an interaction content configuration module; the trigger event rule configuration module is used for defining interaction events, acquiring events corresponding to interaction instructions configured by a user, and obtaining the relation between the interaction instructions and the events, so that when the system acquires the interaction instructions of the user, the map is updated according to the corresponding events; the interaction instruction comprises clicking, long pressing, mouse and suspending; the interactive content configuration module is used for defining interactive feedback, acquiring feedback content of different operations configured by a user, and acquiring a relation between the operations and the feedback content, so that when the system acquires the operations of the user, the map is displayed according to the corresponding feedback content; the operation comprises unfolding, hiding, popup and downloading; the map information reading module is used for selecting a configured Neo4j data source and loading data, and the system can reversely generate an ontology schema according to the entity and the relationship data in the map database to intuitively display the concept and the relationship structure of knowledge; the API release management module is used for acquiring a query algorithm selected by a user, querying the knowledge graph based on the query algorithm, and releasing a query result set into a data interface which can be called by a third party, and comprises a graph algorithm configuration module and an interface release module; the graph algorithm configuration module is used for storing and managing a graph database algorithm built in the system and acquiring and storing a user-defined query algorithm; acquiring a query algorithm selected by a user; the interface issuing module is used for issuing a query result set into a data interface which can be called by a third party based on a query algorithm, and a user selects the algorithm and the input parameters according to service requirements and issues the query result into an http interface for the third party to call; the calling party can read and use the graph calculation result set of the system only by filling parameters according to the format specified by the interface; and the permission configuration module is used for acquiring roles, function permissions and data permissions of the user and limiting the operation and viewing range of the knowledge graph by the user.
CN112632197a discloses a business relation processing method and device based on a knowledge graph, which are applied to a server, and the method comprises the following steps: acquiring service data to be processed, wherein the service data comprises service attribute data of each first service object, first relation service data between other associated first service objects and second relation service data between the other associated first service objects; carrying out data processing on the service data to be processed to obtain first service objects in the same service relationship circle network, and constructing a target knowledge graph between the first service objects and the second service objects, wherein the service relationship circle network is used for representing the association relationship between each first service object under the same service relationship circle; calculating an initial business index attribute value of a first business object in each business relationship circle network according to a preset business index attribute value rule, calculating a relationship attribute conduction weight corresponding to each relationship type between each first business object and a second business object according to a preset relationship weight rule, and/or calculating a relationship attribute conduction weight corresponding to each relationship type between each first business object and other first business objects; and calculating to obtain a relation attribute conduction parameter of the first business object in each business relation circle network according to the initial business index attribute value of the first business object in each business relation circle network, the relation attribute conduction weight corresponding to each relation type and the target knowledge graph, and pushing business information according to the relation attribute conduction parameter.
CN116090466A discloses a method and a system for constructing a semantic unit of a technical information document, wherein the method for constructing the semantic unit of the technical information document comprises the following steps of S1, acquiring a word set in the technical document by adopting a word bag model, carrying out similarity matching calculation on a vocabulary in the vocabulary set and a term set in an enterprise knowledge base, and acquiring a corresponding noun set and predicate set; step S2, mapping noun sets to a high-dimensional real vector space, wherein A (x) is the noun set of x elements, and w is one dimension in a Gao Weishi vector space; nm step S3, extracting standard nouns from the Gao Weishi vector space, and combining the standard nouns with the predicate set to form an xml format text with labels; and S4, reconstructing the technical information semantic unit from the standard xml format text.
In the prior art, an enterprise knowledge base is generally constructed in a static mode, and is difficult to dynamically map with specific business processes in an information system, for example, the knowledge base of an enterprise is difficult to correlate with the change of business processes according to different product design of the enterprise, so that the knowledge base is in the utilization stage of passive retrieval, inquiry and the like, and the high-efficiency application of the knowledge map in the industry is hindered.
Disclosure of Invention
Through long-term practice, knowledge modules in the traditional knowledge management process usually adopt a structured and systematic management mode, and particularly when the business process in an information system is changed or node adjustment is performed, on one hand, the whole enterprise knowledge base is difficult to quickly and dynamically adapt to the updating requirement of the business process; on the other hand, knowledge modules of the enterprise knowledge base are continuously updated, and the business process nodes are manually or manually associated, so that the efficiency is low, and the dynamic business node changing requirement is difficult to adapt.
In view of the above, the present invention is directed to a method for intelligently associating a business process node with a knowledge graph, where the method for intelligently associating a business process node with a knowledge graph includes,
step S1, acquiring a first attribute value of a knowledge node through a knowledge graph, wherein the first attribute value at least comprises a node number and abstract information; the node numbers are used for determining the network positions of the knowledge nodes in the knowledge graph; the abstract information comprises a plurality of keywords and phrases of the content in the knowledge node;
step S2, a business process network is established, and a second attribute value of a business process node is obtained from the business process network, wherein the second attribute value at least comprises a business process node number and knowledge demand information; the business process node number is used for determining the node position of the process node in the business process and comprises a front node set and a rear node set; the knowledge demand information comprises knowledge content information required by business content in the flow node;
step S3, similarity calculation is carried out on the abstract information and the knowledge demand information to obtain a similarity value, and a first mapping relation is established between a knowledge node corresponding to the similarity value exceeding a first preset value and the business process node; the similarity calculation is carried out by adopting a multi-head self-attention mechanism; a Multi-head Self-Attention mechanism (Multi-head-Self-Attention) is the use of a Self-Attention mechanism (Self-Attention) for each word in a sentence to calculate its context representation. This process maps the original representation of each word into a number of subspaces, calculates the attention weight in each subspace, and finally sums the attention weights of the subspaces weighted to get the context representation of each word.
Step S4, according to the association degree with the knowledge nodes in the step S3, obtaining knowledge nodes with the association degree exceeding a second preset value through a knowledge graph, and establishing a second mapping relation with the business process nodes;
s5, establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and correcting the first mapping relation and the second mapping relation through the evaluation value of the knowledge node in the business process node.
Preferably, the summary information and the knowledge demand information are calculated through text similarity, and the obtained maximum similarity value is compared with the first preset value.
Preferably, in step S3, an association relationship between the knowledge node and the business process node is established according to the first mapping relationship, where the first mapping relationship includes a weight, and the weight is used to determine the strength of the association relationship.
Preferably, the recommendation sequence pushed to the business process node is determined according to the weight.
Preferably, the first attribute value further includes a frequency of use, where the frequency of use is a number of times that the knowledge node and the business process node establish a mapping;
and calculating the value degree of the knowledge nodes in the knowledge graph according to the use frequency.
The invention also discloses a system for executing the intelligent association method of the business process node and the knowledge graph, which comprises,
the knowledge node extraction unit is used for obtaining a first attribute value of a knowledge node through a knowledge graph, wherein the first attribute value at least comprises a node number and abstract information; the node numbers are used for determining the network positions of the knowledge nodes in the knowledge graph; the abstract information comprises a plurality of keywords and phrases of the content in the knowledge node;
the business process node extraction unit is used for establishing a business process network, and acquiring a second attribute value of a business process node from the business process network, wherein the second attribute value at least comprises a business process node number and knowledge demand information; the business process node number is used for determining the node position of the process node in the business process and comprises a front node set and a rear node set; the knowledge demand information comprises knowledge content information required by business content in the flow node;
the first mapping unit is used for carrying out similarity calculation on the abstract information and the knowledge demand information to obtain a similarity value, and establishing a first mapping relation between a knowledge node corresponding to the similarity value exceeding a first preset value and the business process node; the similarity calculation is carried out by adopting a multi-head self-attention mechanism;
the second mapping unit is used for acquiring knowledge nodes with the association degree exceeding a second preset value through a knowledge graph according to the association degree with the knowledge nodes in the step S3, and establishing a second mapping relation with the business process nodes;
the optimizing unit is used for establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and correcting the first mapping relation and the second mapping relation through the evaluation value of the knowledge node in the business process node.
Preferably, the first mapping unit further includes a similarity calculation module, where the similarity calculation module is configured to calculate, through text similarity, the summary information and the knowledge requirement information, and obtain a maximum similarity value and compare the maximum similarity value with the first preset value.
Preferably, the second mapping unit further includes a weight calculating module, where the weight calculating module is configured to establish an association relationship between a knowledge node and the business process node according to the first mapping relationship, the first mapping relationship includes a weight, and the weight is used to determine a strength of the association relationship; determining a recommendation sequence pushed to the business process node according to the weight;
the optimization unit further comprises a value degree module, wherein the value degree module is used for calculating the value degree of the knowledge nodes in the knowledge graph according to the use frequency.
The invention discloses an electronic device, which comprises a memory and a processor: the memory is used for storing a computer program; the processor is used for realizing the intelligent association method of the business process node and the knowledge graph when executing the computer program.
The present invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the method provided by the present invention.
Compared with the prior art, the business process node and knowledge graph intelligent association method provided by the invention has the advantages that the first attribute value of the knowledge node is obtained through the knowledge graph by steps S1-S5, and the first attribute value at least comprises node numbers and abstract information; obtaining a second attribute value of the business process node from the newly-built business process network, wherein the second attribute value at least comprises the business process node number and knowledge demand information; performing similarity calculation on the summary information and the knowledge demand information to obtain a similarity value, and establishing a first mapping relation; acquiring knowledge nodes with association degree exceeding a second preset value through a knowledge graph, and establishing a second mapping relation; establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and adjusting the first mapping relation and the second mapping relation according to the evaluation value of the knowledge node in the business process node. The invention also discloses a system for executing the intelligent association method of the business process nodes and the knowledge graph, which can quickly and dynamically establish the mapping relation between the business process nodes and the knowledge nodes from the knowledge graph after the business process nodes are changed, associate modularized and static knowledge nodes with the business process nodes, and respond to the requirements of new construction, change and the like of the business process.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention, illustrate and explain the invention and are not to be construed as limiting the invention. In the drawings:
FIG. 1 is a flow diagram of a business process node and knowledge graph intelligent association method of the present invention;
FIG. 2 is a business process node and knowledge node similarity calculation model of the present invention.
Detailed Description
The following describes specific embodiments of the present invention in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and claims of the present invention and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In order to solve the problem that the knowledge module in the traditional knowledge management process pointed out in the background art part usually adopts a structured and systematic management mode, especially when the business process in the information system is changed or node adjustment is carried out, on one hand, the whole enterprise knowledge base is difficult to quickly and dynamically adapt to the updating requirement of the business process; on the other hand, knowledge modules of the enterprise knowledge base are continuously updated, and the business process nodes are manually or manually associated, so that the efficiency is low, and the problems that dynamic business node changing needs are difficult to adapt and the like are solved. The invention provides a business process node and knowledge graph intelligent association method, as shown in figure 1, which comprises the following steps of,
step S1, acquiring a first attribute value of a knowledge node through a knowledge graph, wherein the first attribute value at least comprises a node number and abstract information; the node numbers are used for determining the network positions of the knowledge nodes in the knowledge graph; the abstract information comprises a plurality of keywords and phrases of the content in the knowledge node;
step S2, a business process network is established, and a second attribute value of a business process node is obtained from the business process network, wherein the second attribute value at least comprises a business process node number and knowledge demand information; the business process node number is used for determining the node position of the process node in the business process and comprises a front node set and a rear node set; the knowledge demand information comprises knowledge content information required by business content in the flow node;
step S3, similarity calculation is carried out on the abstract information and the knowledge demand information to obtain a similarity value, and a first mapping relation is established between a knowledge node corresponding to the similarity value exceeding a first preset value and the business process node; the similarity calculation is carried out by adopting a multi-head self-attention mechanism; for example, as shown in FIG. 2, the computation is performed using a framework of transformers, using the self-attention mechanisms of multiple encoders and decoders. The multi-head self-attention mechanism can process sentence information at different positions in parallel, so that semantic association on the whole world is better captured, and the gradient transfer problem in a long sequence is avoided.
Step S4, according to the association degree with the knowledge nodes in the step S3, obtaining knowledge nodes with the association degree exceeding a second preset value through a knowledge graph, and establishing a second mapping relation with the business process nodes;
s5, establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and correcting the first mapping relation and the second mapping relation through the evaluation value of the knowledge node in the business process node.
The business process node and knowledge graph intelligent association method provided by the invention comprises the steps of S1-S5, obtaining a first attribute value of a knowledge node through a knowledge graph, wherein the first attribute value at least comprises a node number and abstract information; obtaining a second attribute value of the business process node from the newly-built business process network, wherein the second attribute value at least comprises the business process node number and knowledge demand information; performing similarity calculation on the summary information and the knowledge demand information to obtain a similarity value, and establishing a first mapping relation; acquiring knowledge nodes with association degree exceeding a second preset value through a knowledge graph, and establishing a second mapping relation; establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and adjusting the first mapping relation and the second mapping relation according to the evaluation value of the knowledge node in the business process node. The method can quickly and dynamically establish the mapping relation between the business process nodes and the knowledge nodes from the knowledge graph after the business process nodes are changed, can correlate modularized and static knowledge nodes with the business process nodes, and effectively match knowledge content information required by the business process nodes with the knowledge nodes in the knowledge graph in response to the needs of new construction, change and the like of the business process, thereby realizing the quick correlation of knowledge.
The knowledge graph can be represented by G (V, E), where V is a set of knowledge nodes and E is an edge, i.e., the knowledge has a weight association relationship with the knowledge. The unit (entity, relation, entity) with the minimum knowledge graph. The first attribute value of each knowledge node further comprises content, rules, links, version information, wherein the content is data describing specific knowledge in the knowledge node, typically a structured knowledge representation. Rules are the presence of decision logic and order information in the knowledge nodes, e.g., when the temperature is greater than a certain value, then a certain operation or content can be selected. Links are linking relationships established in content within the knowledge nodes, e.g., proprietary term nouns point to conceptual text or other data types of a node, video or picture. The version information is version control information established after the knowledge node is updated for a plurality of times. In the knowledge graph, knowledge nodes are used as entities, and association is realized through edges (relations).
For example, in step S4, the degree of association between the other knowledge nodes and the knowledge node in step S3 is determined to exceed a second preset value. And if the association degree between the knowledge nodes and the knowledge nodes is greater than the preset value 10, associating the knowledge node set greater than the preset value 10 with the business process nodes according to the association relation.
Because the static text matching is large in calculation amount and low in efficiency, and semantic association on the whole world cannot be captured well, the similarity matching accuracy is relatively low. In order to calculate the knowledge demand information of the knowledge nodes and the business process nodes more accurately and faster, a multi-head attention mechanism capable of capturing semantic association on the whole and simultaneously carrying out calculation processing at different positions is adopted. And simultaneously carrying out similarity calculation on all nodes of the newly-built or changed business process network, and more comprehensively knowing the knowledge requirement condition of the whole business process network so as to more accurately establish a first mapping relation. In order to improve the utilization efficiency and quality of knowledge, in the preferred case of the invention, the summary information and the knowledge demand information are calculated through text similarity, and the maximum similarity value is obtained and compared with the first preset value. Under a more preferable condition, similarity calculation can be simultaneously carried out on all nodes of the newly-built or changed business process network, and the establishment of the first mapping relation of the whole business process network is completed.
In order to better measure the importance degree of the association relationship between different knowledge nodes and the business process node, in the preferred case of the present invention, in step S3, the association relationship between the knowledge nodes and the business process node is established according to the first mapping relationship, where the first mapping relationship is the first mapping relationshipThe mapping relation comprises a weight, and the weight is used for determining the strength of the association relation. For example, the business process node W, the knowledge node P, the first attribute value is an element of a W vector, the second attribute value is an element of a P vector, and then the first mapping relationship w=f (P), where W, P are vectors of the same dimension, the mapping relationship includes a nonlinear mapping, and f (P) further includes a model of a neural network. The intensity of the association can be determined by the European norm ||f (P) | 2 And calculating, and forming the weight after normalization processing.
In order to obtain the data of the knowledge nodes in the business process nodes more orderly, in the preferred case of the invention, the recommendation sequence pushed to the business process nodes is determined according to the weight. Because the knowledge nodes associated with the business process nodes are more, the recommendation and the association with the same strength can not be carried out at one time, and the recommendation and the association can be carried out by pushing the knowledge nodes from large to small to the corresponding business process nodes according to the weight.
In order to further optimize the importance ranking of the knowledge nodes in the knowledge graph formed by the knowledge nodes and better digitize the importance of the knowledge, in the preferred case of the present invention, the first attribute value further includes a frequency of use, the frequency of use being the number of times the knowledge nodes and the business process nodes are mapped; and calculating the value degree of the knowledge nodes in the knowledge graph according to the use frequency. Wherein the value degree can be used for ordering the knowledge nodes, and the larger the value degree is, the larger the node is in the process of displaying the knowledge nodes. In the network of the knowledge graph, the network structure can be continuously optimized according to the value degree, so that the mapping with the business process nodes can be better carried out.
The invention also provides a system for executing the intelligent association method of the business process node and the knowledge graph, which comprises,
the knowledge node extraction unit is used for obtaining a first attribute value of a knowledge node through a knowledge graph, wherein the first attribute value at least comprises a node number and abstract information; the node numbers are used for determining the network positions of the knowledge nodes in the knowledge graph; the abstract information comprises a plurality of keywords and phrases of the content in the knowledge node;
the business process node extraction unit is used for establishing a business process network, and acquiring a second attribute value of a business process node from the business process network, wherein the second attribute value at least comprises a business process node number and knowledge demand information; the business process node number is used for determining the node position of the process node in the business process and comprises a front node set and a rear node set; the knowledge demand information comprises knowledge content information required by business content in the flow node;
the first mapping unit is used for carrying out similarity calculation on the abstract information and the knowledge demand information to obtain a similarity value, and establishing a first mapping relation between a knowledge node corresponding to the similarity value exceeding a first preset value and the business process node;
the second mapping unit is used for acquiring knowledge nodes with the association degree exceeding a second preset value through a knowledge graph according to the association degree with the knowledge nodes in the step S3, and establishing a second mapping relation with the business process nodes;
the optimizing unit is used for establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and correcting the first mapping relation and the second mapping relation through the evaluation value of the knowledge node in the business process node.
The system for executing the intelligent association method of the business process node and the knowledge graph, provided by the invention, acquires a first attribute value of the knowledge node through the knowledge graph, wherein the first attribute value at least comprises a node number and abstract information; obtaining a second attribute value of the business process node from the newly-built business process network, wherein the second attribute value at least comprises the business process node number and knowledge demand information; performing similarity calculation on the summary information and the knowledge demand information to obtain a similarity value, and establishing a first mapping relation; acquiring knowledge nodes with association degree exceeding a second preset value through a knowledge graph, and establishing a second mapping relation; establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and adjusting the first mapping relation and the second mapping relation according to the evaluation value of the knowledge node in the business process node. The system can quickly and dynamically establish the mapping relation between the business process nodes and the knowledge nodes from the knowledge graph after the business process nodes are changed, and can associate modularized and static knowledge nodes with the business process nodes to respond to the needs of new construction, change and the like of the business process.
In order to better and more quickly establish the first mapping relation between the business process node and the knowledge node, in a more preferable case of the invention, the first mapping unit further comprises a similarity calculation module, wherein the similarity calculation module is used for calculating the abstract information and the knowledge demand information through text similarity to obtain a maximum similarity value and comparing the maximum similarity value with the first preset value.
In order to obtain the data of the knowledge nodes in the business process nodes more orderly and enable the network formed by the knowledge nodes in the knowledge graph to be more optimized, under the more preferable condition of the invention, the second mapping unit further comprises a weight calculation module, wherein the weight calculation module is used for establishing the association relation between the knowledge nodes and the business process nodes according to the first mapping relation, the first mapping relation comprises a weight, and the weight is used for determining the strength of the association relation; and determining the recommendation sequence pushed to the business process node according to the weight, so that more accurate and intelligent knowledge recommendation can be realized.
In order to better reflect the importance and the use value of the knowledge, the accuracy and the effectiveness of knowledge recommendation are further improved. Personalized recommendation can be performed according to actual requirements and data conditions of the service flow node change, and the utilization efficiency and quality of knowledge are improved. The optimization unit further comprises a value degree module, wherein the value degree module is used for calculating the value degree of the knowledge nodes in the knowledge graph according to the use frequency.
The invention also discloses an electronic device, which comprises a memory and a processor: the memory is used for storing a computer program; the processor is used for realizing the intelligent association method of the business process node and the knowledge graph when executing the computer program.
Further, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method provided by the present invention.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present invention is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present invention. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present invention.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present invention, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution contributing to the prior art or in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a mobile terminal, a server or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A business process node and knowledge graph intelligent association method is characterized in that the business process node and knowledge graph intelligent association method comprises,
step S1, acquiring a first attribute value of a knowledge node through a knowledge graph, wherein the first attribute value at least comprises a node number and abstract information; the node numbers are used for determining the network positions of the knowledge nodes in the knowledge graph; the abstract information comprises a plurality of keywords and phrases of the content in the knowledge node;
step S2, a business process network is established, and a second attribute value of a business process node is obtained from the business process network, wherein the second attribute value at least comprises a business process node number and knowledge demand information; the business process node number is used for determining the node position of the process node in the business process and comprises a front node set and a rear node set; the knowledge demand information comprises knowledge content information required by business content in the flow node;
step S3, similarity calculation is carried out on the abstract information and the knowledge demand information to obtain a similarity value, and a first mapping relation is established between a knowledge node corresponding to the similarity value exceeding a first preset value and the business process node, wherein the similarity calculation is carried out by adopting a multi-head self-attention mechanism;
step S4, according to the association degree with the knowledge nodes in the step S3, obtaining knowledge nodes with the association degree exceeding a second preset value through a knowledge graph, and establishing a second mapping relation with the business process nodes;
s5, establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and correcting the first mapping relation and the second mapping relation through the evaluation value of the knowledge node in the business process node.
2. The intelligent association method of business process nodes and knowledge graph according to claim 1, wherein the summary information and the knowledge demand information are calculated through text similarity, and the maximum similarity value is compared with the first preset value.
3. The intelligent association method of business process nodes and knowledge graph according to claim 1, wherein in step S3, an association relationship between a knowledge node and the business process nodes is established according to the first mapping relationship, wherein the first mapping relationship includes a weight, and the weight is used for determining the strength of the association relationship.
4. The intelligent association method of business process nodes and knowledge graph according to claim 3, wherein the recommendation sequence pushed to the business process nodes is determined according to the weight.
5. The intelligent association method of a business process node and a knowledge graph according to any one of claims 1-4, wherein the first attribute value further includes a frequency of use, the frequency of use being a number of times the knowledge node and the business process node establish a mapping;
and calculating the value degree of the knowledge nodes in the knowledge graph according to the use frequency.
6. A system for performing the intelligent association method of business process nodes and knowledge-graph according to any one of claims 1-5, characterized in that the system comprises,
the knowledge node extraction unit is used for obtaining a first attribute value of a knowledge node through a knowledge graph, wherein the first attribute value at least comprises a node number and abstract information; the node numbers are used for determining the network positions of the knowledge nodes in the knowledge graph; the abstract information comprises a plurality of keywords and phrases of the content in the knowledge node;
the business process node extraction unit is used for establishing a business process network, and acquiring a second attribute value of a business process node from the business process network, wherein the second attribute value at least comprises a business process node number and knowledge demand information; the business process node number is used for determining the node position of the process node in the business process and comprises a front node set and a rear node set; the knowledge demand information comprises knowledge content information required by business content in the flow node;
the first mapping unit is used for carrying out similarity calculation on the summary information and the knowledge demand information to obtain a similarity value, and establishing a first mapping relation between a knowledge node corresponding to the similarity value exceeding a first preset value and the business process node, wherein the similarity calculation is carried out by adopting a multi-head self-attention mechanism;
the second mapping unit is used for acquiring knowledge nodes with the association degree exceeding a second preset value through a knowledge graph according to the association degree with the knowledge nodes in the step S3, and establishing a second mapping relation with the business process nodes;
the optimizing unit is used for establishing a knowledge association sequence through the first mapping relation and the second mapping relation; and correcting the first mapping relation and the second mapping relation through the evaluation value of the knowledge node in the business process node.
7. The system of claim 6, wherein the first mapping unit further includes a similarity calculation module, and the similarity calculation module is configured to calculate the summary information and the knowledge requirement information through text similarity, so as to obtain a maximum similarity value and compare the maximum similarity value with the first preset value.
8. The system according to any one of claims 6-7, wherein the second mapping unit further includes a weight calculation module, the weight calculation module is configured to establish an association between a knowledge node and the business process node according to the first mapping relationship, the first mapping relationship includes a weight, and the weight is used to determine a strength of the association; determining a recommendation sequence pushed to the business process node according to the weight;
the optimization unit further comprises a value degree module, wherein the value degree module is used for calculating the value degree of the knowledge nodes in the knowledge graph according to the use frequency.
9. An electronic device comprising a memory and a processor: the memory is used for storing a computer program; the processor is configured to implement the business process node and knowledge graph intelligent association method according to any one of claims 1-5 when executing the computer program.
10. A machine-readable storage medium having stored thereon instructions for causing a machine to perform the business process node and knowledge-graph intelligent correlation method of any of claims 1-5 of the present application.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311491248.8A CN117422137A (en) | 2023-11-09 | 2023-11-09 | Intelligent association method and system for business process nodes and knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311491248.8A CN117422137A (en) | 2023-11-09 | 2023-11-09 | Intelligent association method and system for business process nodes and knowledge graph |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117422137A true CN117422137A (en) | 2024-01-19 |
Family
ID=89524747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311491248.8A Pending CN117422137A (en) | 2023-11-09 | 2023-11-09 | Intelligent association method and system for business process nodes and knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117422137A (en) |
-
2023
- 2023-11-09 CN CN202311491248.8A patent/CN117422137A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106796578B (en) | Autoknowledge system and method and memory | |
| Zhang et al. | UniBench: a benchmark for multi-model database management systems | |
| US8316012B2 (en) | Apparatus and method for facilitating continuous querying of multi-dimensional data streams | |
| WO2019063449A1 (en) | Semantic search engine and visualization platform | |
| US10339038B1 (en) | Method and system for generating production data pattern driven test data | |
| Lanti et al. | The NPD Benchmark: Reality Check for OBDA Systems. | |
| US7593957B2 (en) | Hybrid data provider | |
| KR102330547B1 (en) | Building reports | |
| US8515897B2 (en) | Automatically generating reports matching user interests represented in a dynamically adjusted user interest analytic model | |
| US20110137917A1 (en) | Retrieving a data item annotation in a view | |
| CN111444256A (en) | Method and device for realizing data visualization | |
| US7702609B2 (en) | Adapting to inexact user input | |
| US9547646B2 (en) | User-created members positioning for OLAP databases | |
| WO2012129149A2 (en) | Aggregating search results based on associating data instances with knowledge base entities | |
| US9110970B2 (en) | Destructuring and restructuring relational data | |
| US20160092554A1 (en) | Method and system for visualizing relational data as rdf graphs with interactive response time | |
| US9779135B2 (en) | Semantic related objects | |
| Rahnama | Distributed real-time sentiment analysis for big data social streams | |
| US8260772B2 (en) | Apparatus and method for displaying documents relevant to the content of a website | |
| US8615733B2 (en) | Building a component to display documents relevant to the content of a website | |
| US9792355B2 (en) | Searches for similar documents | |
| US10521455B2 (en) | System and method for a neural metadata framework | |
| US20160085758A1 (en) | Interest-based search optimization | |
| US10614091B1 (en) | Warehouse based reporting and operational reporting integration | |
| US10311049B2 (en) | Pattern-based query result enhancement |
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 |