CN110197280B - Knowledge graph construction method, device and system - Google Patents
Knowledge graph construction method, device and system Download PDFInfo
- Publication number
- CN110197280B CN110197280B CN201910418358.9A CN201910418358A CN110197280B CN 110197280 B CN110197280 B CN 110197280B CN 201910418358 A CN201910418358 A CN 201910418358A CN 110197280 B CN110197280 B CN 110197280B
- Authority
- CN
- China
- Prior art keywords
- data
- enterprise
- target
- knowledge
- relationship
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- 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
Abstract
The embodiment of the specification discloses a knowledge graph construction method, a knowledge graph construction device and a knowledge graph construction system, wherein the method comprises the steps of obtaining unstructured data, semi-structured data and structured data of a target theme according to an industrial chain relation; performing natural language processing on the unstructured data, and processing the unstructured data and the semi-structured data after the natural language processing by utilizing a machine learning algorithm; performing data conversion on the structured data, the unstructured data and the semi-structured data processed by utilizing a machine learning algorithm to obtain data to be processed; and extracting knowledge and fusing the knowledge of the data to be processed to obtain a knowledge graph corresponding to the target theme. By utilizing the embodiments of the specification, the accuracy and the efficiency of knowledge graph construction can be greatly improved.
Description
Technical Field
The invention relates to the technical field of computer data processing, in particular to a knowledge graph construction method, a knowledge graph construction device and a knowledge graph construction system.
Background
The knowledge graph concept and the knowledge graph technology provide important directions for financial institutions to improve data utilization efficiency and break through current production and operation dilemma, and the knowledge graph-based reasoning provides efficient and accurate decision support for the financial institutions to develop services. The construction of the knowledge map in the financial field can guide a financial structure to carry out efficient risk prevention and control, accurately market and obtain customers, accurately predict the future trend of the existing customers, promote the development of multi-party services and realize multi-party win-win. However, the traditional knowledge graph construction method has the disadvantages that the referenced and acquired calculation data source is single, and the preprocessing process is too complex, so that the accuracy and the efficiency of knowledge graph construction are seriously influenced.
Disclosure of Invention
The embodiment of the specification aims to provide a method, a device and a system for constructing a knowledge graph, which can improve the accuracy and efficiency of construction of the knowledge graph.
The specification provides a method, a device and a system for establishing a knowledge graph, which are realized by the following modes:
a knowledge graph construction method comprises the following steps:
acquiring unstructured data, semi-structured data and structured data of a target theme according to the industrial chain relation;
performing natural language processing on the unstructured data, and processing the unstructured data and the semi-structured data after the natural language processing by utilizing a machine learning algorithm;
performing data conversion on the structured data, the unstructured data and the semi-structured data processed by utilizing a machine learning algorithm to obtain data to be processed;
and extracting knowledge and fusing the knowledge of the data to be processed to obtain a knowledge graph corresponding to the target theme.
In another embodiment of the method provided in this specification, the processing unstructured data and semi-structured data processed by natural language by using a machine learning algorithm includes:
and performing clustering processing based on association rules on the unstructured data and the semi-structured data after natural language processing.
In another embodiment of the method provided by the present specification, the structured data includes transaction data between enterprises, enterprise fund flow information, and financial product transaction data, the unstructured data includes performance behavior data of the enterprises, and the unstructured data includes public information data of the enterprises.
In another embodiment of the method provided in this specification, the acquiring service data to be processed includes:
the method comprises the steps of obtaining unstructured data, semi-structured data and structured data of a target theme based on preset business rules and an industrial chain relation, wherein the business rules comprise business processing rules which are configured in advance according to a business application scene corresponding to the target theme.
In another embodiment of the method provided in this specification, the extracting knowledge of the data to be processed includes:
and extracting the knowledge of the data to be processed based on a classification algorithm and an expert knowledge base.
In another embodiment of the method provided in this specification, the method further comprises:
acquiring attribute data of a target enterprise according to the knowledge graph, and determining a first risk prediction result of the target enterprise according to the attribute data of the target enterprise;
determining the relationship type and the relationship degree between the target enterprise and other enterprises according to the knowledge graph, and determining a second risk prediction result of the target enterprise according to the attribute data of other enterprises and the relationship type and the relationship degree between other enterprises and the target enterprise;
and determining the risk prediction result of the target enterprise according to the first risk prediction result and the second risk prediction result.
In another aspect, the present specification further provides a knowledge graph constructing apparatus, including:
the data acquisition module is used for acquiring unstructured data, semi-structured data and structured data of the target theme according to the industrial chain relation;
the first data processing module is used for carrying out natural language processing on the unstructured data and processing the unstructured data and the semi-structured data which are processed by the natural language by utilizing a machine learning algorithm;
the second data processing module is used for carrying out data conversion on the structured data, the unstructured data and the semi-structured data which are processed by utilizing a machine learning algorithm to obtain data to be processed;
and the knowledge map construction module is used for extracting knowledge and fusing knowledge of the data to be processed to obtain a knowledge map corresponding to the target theme.
In another embodiment of the apparatus provided in this specification, the first data processing module includes:
and the first data processing unit is used for carrying out clustering processing based on association rules on the unstructured data and the semi-structured data after natural language processing.
In another embodiment of the apparatus provided in this specification, the apparatus further comprises:
the business rule configuration module is used for configuring the business rule corresponding to the target theme according to the business application scene corresponding to the target theme;
correspondingly, the data acquisition module is further configured to acquire unstructured data, semi-structured data, and structured data of a target topic based on the business rule and the industry chain relationship.
In another embodiment of the apparatus provided in the present specification, the knowledge-graph constructing module includes:
and the knowledge extraction unit is used for extracting the knowledge of the data to be processed based on a classification algorithm and an expert knowledge base.
In another embodiment of the apparatus provided herein, the apparatus further comprises a risk prediction module, wherein the risk prediction module comprises:
the first risk prediction unit is used for acquiring attribute data of a target enterprise according to the knowledge graph and determining a first risk prediction result of the target enterprise according to the attribute data of the target enterprise;
the second risk prediction unit is used for determining the relationship type and the relationship degree between the target enterprise and other enterprises according to the knowledge graph, and determining a second risk prediction result of the target enterprise according to the attribute data of other enterprises and the relationship type and the relationship degree between other enterprises and the target enterprise;
and the third risk prediction unit is used for determining the risk prediction result of the target enterprise according to the first risk prediction result and the second risk prediction result.
In another aspect, embodiments of the present specification further provide a knowledge graph constructing apparatus, including a processor and a memory for storing processor-executable instructions, where the instructions, when executed by the processor, implement steps including:
acquiring unstructured data, semi-structured data and structured data of a target theme according to the industrial chain relation;
performing natural language processing on the unstructured data, and processing the unstructured data and the semi-structured data after the natural language processing by utilizing a machine learning algorithm;
performing data conversion on the structured data, the unstructured data and the semi-structured data processed by utilizing a machine learning algorithm to obtain data to be processed;
and extracting knowledge and fusing the knowledge of the data to be processed to obtain a knowledge graph corresponding to the target theme.
In another aspect, the present specification further provides a knowledge graph building system, where the data processing system includes at least one processor and a memory storing computer-executable instructions, and the processor executes the instructions to implement the steps of the method according to any one of the above embodiments.
The knowledge graph construction method, the knowledge graph construction device and the knowledge graph construction system provided by one or more embodiments of the specification can obtain the truest and comprehensive data of an enterprise from the most basic first-line production operation data based on the complete industrial chain relation developed by financial services, and ensure the accuracy and the coverage of the original data of the knowledge graph. And aiming at different types of data sources, a differential and distributed data processing mode is provided, so that the accuracy and the efficiency of data processing can be further improved. By utilizing the embodiments of the specification, the accuracy and the efficiency of knowledge graph construction can be greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort. In the drawings:
FIG. 1 is a schematic flow chart diagram of an embodiment of a method for constructing a knowledge graph provided herein;
FIG. 2 is a schematic diagram of a knowledge graph building process in one embodiment provided herein;
FIG. 3 is a schematic view of a risk prediction process in another embodiment provided herein;
FIG. 4 is a block diagram of an embodiment of a knowledge graph building system provided in the present specification;
FIG. 5 is a block diagram of another embodiment of a knowledge graph building system provided herein;
fig. 6 is a schematic block diagram of a server according to an exemplary embodiment of the present description.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in one or more embodiments of the present specification will be clearly and completely described below with reference to the drawings in one or more embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the specification, and not all embodiments. All other embodiments obtained by a person skilled in the art based on one or more embodiments of the present specification without making any creative effort shall fall within the protection scope of the embodiments of the present specification.
The knowledge graph concept and the knowledge graph technology provide important directions for financial institutions to improve data utilization efficiency and break through current production and operation dilemma, and the knowledge graph-based reasoning provides efficient and accurate decision support for the financial institutions to develop services. The construction of the knowledge map in the financial field can guide a financial structure to carry out efficient risk prevention and control, accurately market and obtain customers, accurately predict the future trend of the existing customers, promote the development of multi-party services and realize multi-party win-win. However, the traditional knowledge graph construction method has the disadvantages that the referenced and acquired calculation data source is single, and the preprocessing process is too complex, so that the accuracy and the efficiency of knowledge graph construction are seriously influenced.
Correspondingly, the embodiment of the specification provides a knowledge graph construction method, which can be used for acquiring the truest and comprehensive data of an enterprise from the most basic first-line production operation data based on the complete industrial chain relation developed by financial services, and ensuring the accuracy and the coverage of the original data of the knowledge graph. And aiming at different types of data sources, a differential and distributed data processing mode is provided, so that the accuracy and the efficiency of data processing can be further improved. By utilizing the embodiments of the specification, the accuracy and the efficiency of knowledge graph construction can be greatly improved.
FIG. 1 is a schematic flow chart of an embodiment of a method for constructing a knowledge graph provided in the present specification. Although the present specification provides the method steps or apparatus structures as shown in the following examples or figures, more or less steps or modules may be included in the method or apparatus structures based on conventional or non-inventive efforts. In the case of steps or structures which do not logically have the necessary cause and effect relationship, the execution order of the steps or the block structure of the apparatus is not limited to the execution order or the block structure shown in the embodiments or the drawings of the present specification. When the described method or module structure is applied to a device, a server or an end product in practice, the method or module structure according to the embodiment or the figures may be executed sequentially or in parallel (for example, in a parallel processor or multi-thread processing environment, or even in an implementation environment including distributed processing and server clustering).
In a specific embodiment, as shown in fig. 1, in an embodiment of the method for constructing a knowledge graph provided in the present specification, the method may include:
s102: and acquiring unstructured data, semi-structured data and structured data of the target theme according to the industrial chain relation.
The target theme may include an application field and an application scene corresponding to the knowledge graph, such as target enterprise risk prevention and control, target enterprise behavior prediction, and the like. The industry chain relationship may be an industry chain relationship between enterprises determined based on industry chain financial services developed by existing financial institutions.
The financial institution and the core enterprise in the industrial chain keep close cooperative relationship, and the financial institution can conveniently acquire financial data of other enterprises cooperating with the core enterprise by taking the core enterprise of the financial industrial chain as a center, so that information such as information flow, fund flow and logistics of small and medium enterprises can be accurately controlled, and the accuracy of acquiring basic data corresponding to the construction of the knowledge graph can be greatly improved.
And extracting multi-source heterogeneous data corresponding to the target subject based on the determined industrial chain relation for constructing a knowledge graph. In some implementations, the multi-source heterogeneous data can include unstructured data, semi-structured data, and structured data.
In some embodiments of the present description, the structured data may include transaction data between businesses, business fund flow information, and financial product transaction data; the unstructured data may include fulfillment behavior data for an enterprise; the unstructured data may include public information data for an enterprise.
Structured data such as transaction data, enterprise fund flow information, financial product transaction data and the like among enterprises can be acquired according to the business chain data. Such as the data of the fund flow information, such as contract, order, sales list, purchase order, receivable, accounts payable, invoice, product logistics, enterprise bank bill acceptance and subsidence, business bill acceptance and subsidence, liquidity loan, fund turnover details and the like, can be obtained. Meanwhile, semi-structured data such as the performance data of the enterprise, such as tax information, public service payment information, enterprise registered financial reports, research and the like of the enterprise can be obtained based on the current cooperative government part and public service units. Furthermore, unstructured data such as public information data of enterprises and the like can be obtained, such as internet public sentiment, internal reports, supervision files and the like.
According to the scheme of the embodiment of the specification, basic production data such as transaction data, enterprise fund flow information and financial product transaction data of an enterprise are accurately extracted based on an industrial chain, then the scale of the enterprise, fund flow of the enterprise, investment direction of the enterprise and the like can be analyzed by using the basic production data, and therefore accurate control over overall evaluation of the enterprise can be improved. Meanwhile, the relationship between the enterprises is analyzed by utilizing the transaction information between the enterprises, so that the accurate determination of the relationship degree between the enterprises can be improved.
Furthermore, by acquiring multi-source data such as basic production data, fulfillment behavior data and public information data in an industrial chain, the comprehensiveness of data acquisition can be further improved. And the performance behavior data and the public information data of the enterprises are combined to assist in the overall evaluation of the enterprises and the determination of the relationship degree between the enterprises, so that the accuracy of analyzing the enterprises by using the established knowledge map can be further improved.
S104: and performing natural language processing on the unstructured data, and processing the unstructured data and the semi-structured data subjected to the natural language processing by utilizing a machine learning algorithm.
For the unstructured data, information contained in audio, video, and pictures in the unstructured data may be converted into text information by a character conversion device, and then Natural Language Processing (NLP) such as word segmentation and introduction of stop words may be performed on the text information. Then, the NLP processed information is subjected to feature processing, such as vectorization and Hash lock processing. And then, inputting the processed data into a machine learning algorithm, and extracting the data by using a machine learning model.
For the semi-structured data, a pre-constructed machine learning model can be directly utilized to extract data, so that core information data contained in the semi-structured data is determined, and meanwhile, the unification of data format and mode is realized.
By the mode, the core information data contained in the unstructured data and the semi-structured data can be extracted quickly and effectively to serve as basic data constructed by the subsequent knowledge graph. Meanwhile, the unification of data formats and modes can be realized, and the subsequent data processing is facilitated.
In one embodiment of the present description, the machine learning algorithm may be a clustering algorithm based on association rules. An association rule can be preset according to actual requirements, then cluster analysis processing is carried out on the unstructured data and the semi-structured data after NLP processing according to the set association rule, and core information in the unstructured data and the semi-structured data is extracted. By setting the association rule in advance according to actual needs and then performing cluster analysis on the data based on the set association rule, core data related to the knowledge graph to be constructed in the mass data can be extracted more accurately and efficiently, and the accuracy of data used in subsequent processing is further improved.
S106: and performing data conversion on the structured data, the unstructured data and the semi-structured data processed by utilizing a machine learning algorithm to obtain data to be processed.
The structured data, the semi-structured data processed in the above manner, and the unstructured data may be subjected to data conversion. In one or more embodiments of the present description, the data transformation may include two steps, data cleansing and data transformation. The cleaning of the data may include filling in missing values, smoothing noise data, identifying or deleting outliers, and solving inconsistency. The cleaned data may then be subjected to data transformation, which may include smooth aggregation, data generalization, normalization, and the like, to convert the data into a form suitable for data mining.
Finally, the converted unstructured data, semi-structured data and structured data can be loaded into corresponding databases to be used as basic data for construction of the knowledge graph.
By means of the method, the three types of data are integrated and processed based on different processes, and scattered, disordered and standard source data related to enterprises can be integrated together more efficiently and accurately to obtain data to be processed. And the whole processing flow can be effectively configured into a distributed data processing form, so that the data processing efficiency can be greatly improved.
In another embodiment of the present specification, unstructured data, semi-structured data, and structured data of a target topic may also be obtained based on a preset business rule and an industry chain relationship, where the business rule may include a business processing rule configured in advance according to a business application scenario corresponding to the target topic.
The service rules can be pre-configured according to the actual service application scenario, and the service rules can be preset and stored in the database, or can be self-set according to the service scenario. Then, the business rules can be used for data acquisition and data integration processing so as to further improve the pertinence of the constructed knowledge graph and the accuracy of subsequent data analysis.
For example, if the application scenario is risk prevention and control, the corresponding business rule may be determined according to the risk prevention and control. The corresponding business rules may include, for example, the enterprise to be analyzed, the type of the enterprise, requirements for the acquired data, requirements for processing the acquired multi-source heterogeneous data (e.g., requirements for association rules), and the like. Then, multi-source heterogeneous data can be obtained based on the business rule, and the multi-source heterogeneous data is integrated to obtain to-be-processed data constructed by the knowledge graph for risk prevention and control.
S108: and extracting knowledge and fusing the knowledge of the data to be processed to obtain a knowledge graph corresponding to the target theme.
The extracting knowledge of the data to be processed may include extracting a target object, an attribute of the target object, and a relationship between the target objects to obtain an entity and entity relationship data for constructing a knowledge graph. The knowledge fusion can include fusion processing of knowledge maps of two or more different sources of the same target object, so as to obtain information of the target object more comprehensively and accurately. The target object may be an analysis object corresponding to a target topic, for example, if the target topic is enterprise wind control analysis, the analysis object may have various enterprises, units, individuals related to the enterprises, and other entities.
For example, in some embodiments of the present description, after the cleansing translation load is completed, knowledge extraction may be performed on the data in the data warehouse. For example, the attributes of enterprises, the scale of the enterprises, the credit of the enterprises and the like, and the relationship among the enterprises can be extracted: for example, enterprise a is a subordinate sub-enterprise of enterprise B, enterprise C is a client of enterprise a, and so on.
After the extraction of the entities and entity relationships is completed, knowledge fusion may be performed to fuse the descriptive information about the same entity from multiple data sources. The specific steps of knowledge fusion may include syntax normalization and data normalization of data, attribute similarity calculation and entity similarity calculation, blocking, load balancing, and the like. If the knowledge fusion can be carried out in an ontology matching mode, the information of the same entity is fused, the multi-solution is eliminated, and the knowledge graph corresponding to the target theme is accurately constructed and obtained.
In one embodiment of the present specification, the data to be processed may be subjected to knowledge extraction based on a classification algorithm and an expert knowledge base. The financial application scenes are complex and changeable, and comprehensiveness and accuracy of entity and entity relation extraction can be further improved by combining a method utilizing an expert knowledge base and a method based on machine learning.
The expert knowledge base can be used for constructing a knowledge system based on expert suggestion and experience analysis, and entities and entity relations in the data to be processed can be more accurately mined by utilizing the expert knowledge base. Related entities and entity relations can be automatically mined from the data to be processed through a pre-established classification algorithm. The classification algorithms may include decision tree classification, naive bayes classification, support vector machine-based classification, and the like.
In one or more embodiments of the present disclosure, the expert knowledge base and the proportion of the final result based on the machine learning algorithm may be controlled by pre-configuring the weight, so as to ensure the accuracy and comprehensiveness of the finally extracted knowledge. By combining the two modes and increasing the weight, the method not only can be separated from the human factors of the traditional expert knowledge base, but also can eliminate the uncontrollable characteristic of the pure machine learning algorithm agent in a suspicious manner, thereby improving the accuracy and the applicability of the result obtained by analyzing by utilizing the constructed knowledge graph finally.
In the solutions provided by the above embodiments of the present specification, the most real data of an enterprise is obtained from the most basic first-line production operation data through a complete industrial chain relationship based on financial business development, and the accurate production operation data of the enterprise ensures the original accuracy of the knowledge graph. And semi-structured data such as tax data, public service payment data, financial and newspaper research data and the like of enterprises and non-mechanization data such as Internet public opinions, supervision documents and the like are synchronously collected so as to assist in construction of the knowledge map. Therefore, the coverage and accuracy of data sources for constructing the knowledge graph and the accuracy of application analysis by using the constructed knowledge graph can be further improved.
And aiming at different types of data sources, a differential and distributed data processing mode is provided, and the accuracy and the efficiency of data processing are further improved. And the corresponding service rule can be further configured according to the service scene, and the data is acquired and processed based on the configured service rule, so that the finally obtained knowledge graph has better pertinence, and the accuracy of specific application analysis by using the constructed knowledge graph can be further improved.
FIG. 2 shows a flowchart of knowledge graph construction in an application scenario provided by the present specification. The construction of the knowledge graph in the embodiment of the present specification is described by taking a risk prevention and control application scenario as an example. As shown in fig. 2, the business rules may be determined according to the application scenario of risk prevention and control. Then, structured data, semi-structured data and unstructured data are obtained according to the financial industry chain relation and a predetermined business rule.
The structured data, the semi-structured data, and the unstructured data may then be preprocessed separately based on a distributed manner. The NLP processing can be carried out on the unstructured data machine firstly; then, an association rule can be determined according to the determined service rule, and clustering processing based on the association rule is carried out on the non-structured data and the semi-structured data after NLP processing; the structured data can be directly extracted without processing.
The structured data, clustered unstructured data, and semi-structured data may then be data transformed to make the data more suitable for data mining. And finally, loading the converted multi-source heterogeneous data into a database to serve as basic data constructed by the knowledge graph.
Then, the entity-relation extraction can be carried out on the basic data in a mode of combining an expert database with a classification algorithm, and the extracted entity and entity relation data are subjected to knowledge fusion to construct and obtain a knowledge graph.
The constructed knowledge graph can then be used to make risk prediction for the enterprise. And acquiring performance behavior data, fund circulation and other attribute data of the target enterprise according to the knowledge graph. And performing risk prediction on the target enterprise by using the attribute data of the target enterprise to obtain a first risk prediction result of the target enterprise. Meanwhile, the relationship between the target enterprise and the enterprise can be analyzed, and a second risk prediction result of the target enterprise is determined by using the attribute data of other enterprises and the relationship between other enterprises and the target enterprise. And determining the risk prediction result of the target enterprise by combining the first risk prediction result and the second risk prediction result.
In some embodiments, when determining the influence degree of other enterprises on the target enterprise, the relationship type between the two enterprises may be determined according to the knowledge graph, and if the enterprises are in a transaction relationship, the relationship degree between the two enterprises may be calculated according to transaction information such as transaction amount, transaction category, and the like between the two enterprises. If the relationship between two enterprises is an affiliation, that is, one enterprise is a subsidiary of another enterprise, the relationship between the two enterprises can be determined according to the data of the asset amount, the dividend ratio and the like between the two enterprises.
For example, enterprise a is in a transaction relationship with enterprise B, enterprise B is in an affiliation relationship with enterprise C, and enterprise B is a subsidiary of enterprise C. A first degree of relationship between a and B may be determined based on transaction information between a and B and a second degree of relationship between B and C may be determined based on asset amount, dividend ratio, etc. between B and C. Then, a third degree of relationship between a and C may be determined based on the first degree of relationship and the second degree of relationship. Furthermore, according to the relationship type, the first relationship degree and the second relationship degree are multiplied by a certain weight respectively to determine a third relationship degree between A and C.
Therefore, the relationship and the association tightness among enterprises in an industrial chain can be effectively established by utilizing the pre-constructed knowledge graph so as to determine the influence of other enterprises on the target enterprise. The second risk prediction outcome for the target business may then be determined using the credit data for the other business and the relationship of the other business to the target business.
Correspondingly, based on the solution provided by the foregoing scenario embodiment, as shown in fig. 3, in an embodiment of this specification, the method may further include:
s110: determining attribute data of the target enterprise according to the knowledge graph, and performing risk prediction on the target enterprise according to the attribute data of the target enterprise to obtain a first risk prediction result of the target enterprise;
s112: determining the relationship type and the relationship degree between the target enterprise and other enterprises according to the knowledge graph, and determining a second risk prediction result of the target enterprise according to the attribute data of other enterprises and the relationship type and the relationship degree between other enterprises and the target enterprise;
s114: and determining the risk prediction result of the target enterprise according to the first risk prediction result and the second risk prediction result.
Of course, if the predetermined application scenario is accurate customer acquisition or customer behavior prediction, the construction of the knowledge graph may also be guided by configuring the corresponding business rule based on the corresponding application scenario. The corresponding service rule is configured in advance according to the service scene, so that the constructed and obtained knowledge graph has higher pertinence, and the accuracy of the service inference application analysis result is improved.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. For details, reference may be made to the description of the related embodiments of the related processing, and details are not repeated herein.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The knowledge graph construction method provided by one or more embodiments of the specification can be used for acquiring the most real and comprehensive data of an enterprise from the most basic first-line production operation data based on the complete industrial chain relation developed by financial services, and ensuring the accuracy and the coverage of the original data of the knowledge graph. And aiming at different types of data sources, a differential and distributed data processing mode is provided, so that the accuracy and the efficiency of data processing can be further improved. By utilizing the embodiments of the specification, the accuracy and the efficiency of knowledge graph construction can be greatly improved.
Based on the above knowledge graph construction method, one or more embodiments of the present specification further provide a knowledge graph construction apparatus. The apparatus may include systems, software (applications), modules, components, servers, etc. that utilize the methods described in the embodiments of the present specification in conjunction with hardware implementations as necessary. Based on the same innovative conception, embodiments of the present specification provide an apparatus as described in the following embodiments. Since the implementation scheme of the apparatus for solving the problem is similar to that of the method, the specific implementation of the apparatus in the embodiment of the present specification may refer to the implementation of the foregoing method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Specifically, fig. 4 is a schematic block diagram of an embodiment of a knowledge graph constructing apparatus provided in the specification, and as shown in fig. 4, the apparatus may include:
the data obtaining module 202 may be configured to obtain unstructured data, semi-structured data, and structured data of a target topic according to an industry chain relationship;
the first data processing module 204 may be configured to perform natural language processing on the unstructured data, and process the unstructured data and the semi-structured data after the natural language processing by using a machine learning algorithm;
the second data processing module 206 may be configured to perform data conversion on the structured data and the unstructured data and the semi-structured data processed by using the machine learning algorithm to obtain to-be-processed data;
the knowledge graph constructing module 208 may be configured to extract knowledge and fuse knowledge of the data to be processed, so as to obtain a knowledge graph corresponding to the target topic.
In another embodiment of the present specification, the first data processing module 204 may include:
the first data processing unit may be configured to perform clustering processing based on association rules on the unstructured data and the semi-structured data after natural language processing.
Fig. 5 is a schematic block diagram of an embodiment of a knowledge graph building apparatus provided in the specification, and as shown in fig. 5, in another embodiment of the specification, the apparatus may further include:
a service rule configuration module 201, configured to configure a service rule corresponding to the target theme according to a service application scenario corresponding to the target theme;
correspondingly, the data obtaining module 202 may be further configured to obtain unstructured data, semi-structured data, and structured data of a target topic based on the business rules and the industry chain relationship.
In another embodiment of the present description, the knowledge-graph building module 208 may include:
and the knowledge extraction unit can be used for extracting the knowledge of the data to be processed based on a classification algorithm and an expert knowledge base.
As shown in fig. 5, in another embodiment of the present specification, the apparatus may further include a risk prediction module 210, wherein the risk prediction module 201 may include:
the first risk prediction unit may be configured to obtain attribute data of a target enterprise according to the knowledge graph, and determine a first risk prediction result of the target enterprise according to the attribute data of the target enterprise;
the second risk prediction unit may be configured to determine a relationship type and a relationship degree between the target enterprise and another enterprise according to the knowledge graph, and determine a second risk prediction result of the target enterprise according to attribute data of the another enterprise and the relationship type and the relationship degree between the another enterprise and the target enterprise;
and the third risk prediction unit can be used for determining the risk prediction result of the target enterprise according to the first risk prediction result and the second risk prediction result.
It should be noted that the above-described apparatus may also include other embodiments according to the description of the method embodiment. The specific implementation manner may refer to the description of the related method embodiment, and is not described in detail herein.
The knowledge graph construction device provided by one or more embodiments of the specification can obtain the truest and comprehensive data of an enterprise from the most basic first-line production operation data based on the complete industrial chain relation developed by financial services, and ensure the accuracy and coverage of the original data of the knowledge graph. And aiming at different types of data sources, a differential and distributed data processing mode is provided, so that the accuracy and the efficiency of data processing can be further improved. By utilizing the embodiments of the specification, the accuracy and the efficiency of knowledge graph construction can be greatly improved.
The method or apparatus provided by the present specification and described in the foregoing embodiments may implement service logic through a computer program and record the service logic on a storage medium, where the storage medium may be read and executed by a computer, so as to implement the effect of the solution described in the embodiments of the present specification. Accordingly, the present specification also provides a knowledge-graph building apparatus comprising a processor and a memory storing processor-executable instructions which, when executed by the processor, implement steps comprising:
acquiring unstructured data, semi-structured data and structured data of a target theme according to the industrial chain relation;
performing natural language processing on the unstructured data, and processing the unstructured data and the semi-structured data after the natural language processing by utilizing a machine learning algorithm;
performing data conversion on the structured data, the unstructured data and the semi-structured data processed by utilizing a machine learning algorithm to obtain data to be processed;
and extracting knowledge and fusing the knowledge of the data to be processed to obtain a knowledge graph corresponding to the target theme.
The storage medium may include a physical device for storing information, and typically, the information is digitized and then stored using an electrical, magnetic, or optical media. The storage medium may include: devices that store information using electrical energy, such as various types of memory, e.g., RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, and usb disks; devices that store information optically, such as CDs or DVDs. Of course, there are other ways of storing media that can be read, such as quantum memory, graphene memory, and so forth.
It should be noted that the above description of the apparatus according to the method embodiment may also include other embodiments. The specific implementation manner may refer to the description of the related method embodiment, and is not described in detail herein.
The method embodiments provided by the embodiments of the present specification can be executed in a mobile terminal, a computer terminal, a server or a similar computing device. Taking the example of the application on a server, fig. 6 is a block diagram of a hardware structure of a server constructed by applying the knowledge graph of the embodiment of the present specification. As shown in fig. 6, the server 10 may include one or more (only one shown) processors 20 (the processors 20 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 30 for storing data, and a transmission module 40 for communication functions. It will be understood by those skilled in the art that the structure shown in fig. 6 is merely illustrative and is not intended to limit the structure of the electronic device. For example, the server 10 may also include more or fewer components than shown in FIG. 6, and may also include other processing hardware, such as a database or multi-level cache, a GPU, or have a different configuration than shown in FIG. 6, for example.
The memory 30 may be used to store software programs and modules of application software, such as program instructions/modules corresponding to the search method in the embodiment of the present invention, and the processor 20 executes various functional applications and data processing by executing the software programs and modules stored in the memory 30. The memory 30 may include high speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 30 may further include memory located remotely from the processor 20, which may be connected to a computer terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission module 40 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission module 40 includes a Network adapter (NIC) that can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission module 40 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The knowledge graph construction equipment provided by the embodiment can be used for acquiring the truest and comprehensive data of an enterprise from the most basic first-line production operation data based on the complete industrial chain relation developed by financial services, and the accuracy and the coverage of the original data of the knowledge graph are ensured. And aiming at different types of data sources, a differential and distributed data processing mode is provided, so that the accuracy and the efficiency of data processing can be further improved. By utilizing the embodiments of the specification, the accuracy and the efficiency of knowledge graph construction can be greatly improved.
The present specification also provides a knowledge graph construction system that may be a stand-alone knowledge graph construction system or may be implemented in a variety of computer data processing systems. The system may be a single server, or may include a server cluster, a system (including a distributed system), software (applications), an actual operating device, a logic gate device, a quantum computer, etc. using one or more of the methods or one or more of the example devices of the present specification, in combination with a terminal device implementing hardware as necessary. The knowledge-graph building system may comprise at least one processor and a memory storing computer-executable instructions that, when executed, perform the steps of the method described in any one or more of the embodiments above.
It should be noted that the above-mentioned system may also include other implementation manners according to the description of the method or apparatus embodiment, and specific implementation manners may refer to the description of the related method embodiment, which is not described in detail herein.
The knowledge graph construction system of the embodiment can obtain the truest and comprehensive data of an enterprise from the most basic first-line production operation data based on the complete industrial chain relation developed by financial services, and ensures the accuracy and coverage of the original data of the knowledge graph. And aiming at different types of data sources, a differential and distributed data processing mode is provided, so that the accuracy and the efficiency of data processing can be further improved. By utilizing the embodiments of the specification, the accuracy and the efficiency of knowledge graph construction can be greatly improved.
It should be noted that, the above-mentioned apparatus or system in this specification may also include other implementation manners according to the description of the related method embodiment, and a specific implementation manner may refer to the description of the method embodiment, which is not described herein in detail. The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class, storage medium + program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, refer to the partial description of the method embodiment.
Although the data transformation, loading, etc. operations and data descriptions are referred to in the context of the embodiments of the present specification, the embodiments of the present specification are not limited to necessarily conform to a standard data model/template or to the case described by the embodiments of the present specification. Certain industry standards, or implementations modified slightly from those described using custom modes or examples, may also achieve the same, equivalent, or similar, or other, contemplated implementations of the above-described examples. The embodiments using these modified or transformed data acquisition, storage, judgment, processing, etc. may still fall within the scope of the alternative embodiments of the present description.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a vehicle-mounted human-computer interaction device, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, when implementing one or more of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, etc. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may therefore be considered as a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method or apparatus that comprises the element.
As will be appreciated by one skilled in the art, one or more embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, one or more embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
One or more embodiments of the present description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. One or more embodiments of the present specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description of the specification, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.
Claims (10)
1. A knowledge graph construction method is characterized by comprising the following steps:
acquiring unstructured data, semi-structured data and structured data of a target theme according to the industrial chain relation;
performing natural language processing on the unstructured data, and processing the unstructured data and the semi-structured data after the natural language processing by utilizing a machine learning algorithm;
performing data conversion on the structured data, the unstructured data and the semi-structured data processed by utilizing a machine learning algorithm to obtain data to be processed;
extracting knowledge and fusing the knowledge of the data to be processed to obtain a knowledge graph corresponding to the target theme;
acquiring attribute data of a target enterprise A according to the knowledge graph, and determining a first risk prediction result of the target enterprise A according to the attribute data of the target enterprise A;
determining the relationship type between the target enterprise A and the enterprise B according to the knowledge graph, acquiring data between the target enterprise A and the enterprise B based on the corresponding relationship type, and determining a first relationship degree between the target enterprise A and the enterprise B according to the acquired data between the target enterprise A and the enterprise B; determining a second degree of relationship between the enterprise B and the enterprise C in the same manner; configuring a first weight corresponding to a first degree of relationship between a target enterprise A and an enterprise B by using the type of relationship between the target enterprise A and the enterprise B; configuring a second weight corresponding to a second degree of relationship between the enterprise B and the enterprise C in the same manner;
calculating a third relation degree between the target enterprise A and the enterprise C based on the first relation degree and the second relation degree and a first weight and a second weight which respectively correspond to the first relation degree and the second relation degree;
determining a second risk prediction result of the target enterprise A by using the third degree of relationship between the target enterprise A and the enterprise C and the attribute data of the enterprise C;
and determining the risk prediction result of the target enterprise A according to the first risk prediction result and the second risk prediction result.
2. The method of claim 1, wherein the processing the unstructured data and the semi-structured data processed by the natural language using a machine learning algorithm comprises:
and performing clustering processing based on association rules on the unstructured data and the semi-structured data after natural language processing.
3. The method of claim 1, wherein the structured data includes transaction data between businesses, business fund flow information, and financial product transaction data, wherein the semi-structured data includes performance data for businesses, and wherein the unstructured data includes public information data for businesses.
4. The method of any of claims 1-3, wherein obtaining unstructured data, semi-structured data, and structured data of a target topic comprises:
the method comprises the steps of obtaining unstructured data, semi-structured data and structured data of a target theme based on preset business rules and an industrial chain relation, wherein the business rules comprise business processing rules which are configured in advance according to a business application scene corresponding to the target theme.
5. The method of claim 1, wherein the extracting knowledge of the data to be processed comprises:
and extracting the knowledge of the data to be processed based on a classification algorithm and an expert knowledge base.
6. An apparatus for knowledge-graph construction, the apparatus comprising:
the data acquisition module is used for acquiring unstructured data, semi-structured data and structured data of the target theme according to the industrial chain relation;
the first data processing module is used for carrying out natural language processing on the unstructured data and processing the unstructured data and the semi-structured data which are processed by the natural language by utilizing a machine learning algorithm;
the second data processing module is used for carrying out data conversion on the structured data, the unstructured data and the semi-structured data which are processed by utilizing a machine learning algorithm to obtain data to be processed;
the knowledge map construction module is used for extracting knowledge and fusing knowledge of the data to be processed to obtain a knowledge map corresponding to the target theme;
the apparatus further comprises a risk prediction module, wherein the risk prediction module comprises:
the first risk prediction unit is used for acquiring the attribute data of the target enterprise A according to the knowledge graph and determining a first risk prediction result of the target enterprise A according to the attribute data of the target enterprise A;
the second risk prediction unit is used for determining the relationship type between the target enterprise A and the enterprise B according to the knowledge graph, acquiring data between the corresponding target enterprise A and the enterprise B based on the corresponding relationship type, and determining a first relationship degree between the target enterprise A and the enterprise B according to the acquired data between the target enterprise A and the enterprise B; determining a second degree of relationship between the enterprise B and the enterprise C in the same manner; configuring a first weight corresponding to a first degree of relationship between the target enterprise A and the enterprise B by using the type of relationship between the target enterprise A and the enterprise B; configuring a second weight corresponding to a second degree of relationship between the enterprise B and the enterprise C in the same manner; calculating a third relation degree between the target enterprise A and the enterprise C based on the first relation degree and the second relation degree and a first weight and a second weight which respectively correspond to the first relation degree and the second relation degree; determining a second risk prediction result of the target enterprise A by using the third degree of relationship between the target enterprise A and the enterprise C and the attribute data of the enterprise C;
and the third risk prediction unit is used for determining the risk prediction result of the target enterprise A according to the first risk prediction result and the second risk prediction result.
7. The apparatus of claim 6, wherein the first data processing module comprises:
and the first data processing unit is used for carrying out clustering processing based on association rules on the unstructured data and the semi-structured data after natural language processing.
8. The apparatus of claim 6 or 7, further comprising:
the business rule configuration module is used for configuring the business rule corresponding to the target theme according to the business application scene corresponding to the target theme;
correspondingly, the data acquisition module is further configured to acquire unstructured data, semi-structured data, and structured data of a target topic based on the business rule and the industry chain relationship.
9. The apparatus of claim 6, wherein the knowledge-graph building module comprises:
and the knowledge extraction unit is used for extracting the knowledge of the data to be processed based on a classification algorithm and an expert knowledge base.
10. A knowledge graph construction system comprising at least one processor and a memory storing computer-executable instructions which, when executed by the processor, implement the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910418358.9A CN110197280B (en) | 2019-05-20 | 2019-05-20 | Knowledge graph construction method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910418358.9A CN110197280B (en) | 2019-05-20 | 2019-05-20 | Knowledge graph construction method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110197280A CN110197280A (en) | 2019-09-03 |
| CN110197280B true CN110197280B (en) | 2021-08-06 |
Family
ID=67752873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910418358.9A Active CN110197280B (en) | 2019-05-20 | 2019-05-20 | Knowledge graph construction method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110197280B (en) |
Families Citing this family (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110750588A (en) * | 2019-10-29 | 2020-02-04 | 珠海格力电器股份有限公司 | Multi-source heterogeneous data fusion method, system, device and storage medium |
| CN111223004A (en) * | 2019-11-14 | 2020-06-02 | 国网湖北省电力有限公司电力科学研究院 | Relay protection knowledge modeling method and platform for business application |
| CN110971674A (en) * | 2019-11-15 | 2020-04-07 | 北京明略软件系统有限公司 | Method, device, computer storage medium and terminal for realizing information processing |
| CN111027832A (en) * | 2019-11-28 | 2020-04-17 | 卓尔智联(武汉)研究院有限公司 | Tax risk determination method, apparatus and storage medium |
| CN111143448B (en) * | 2019-12-03 | 2023-05-12 | 北京博瑞彤芸科技股份有限公司 | Knowledge base construction method |
| CN111241213A (en) * | 2020-01-23 | 2020-06-05 | 北京明略软件系统有限公司 | Method and device for constructing knowledge graph, computer storage medium and terminal |
| CN111242774A (en) * | 2020-01-23 | 2020-06-05 | 中国建设银行股份有限公司 | Bank customer asset map construction method and device |
| CN111428090A (en) * | 2020-03-10 | 2020-07-17 | 北京明略软件系统有限公司 | Method and device for realizing data processing, computer storage medium and terminal |
| CN111428053B (en) * | 2020-03-30 | 2023-10-20 | 西安交通大学 | Construction method of tax field-oriented knowledge graph |
| CN111488741A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Tax knowledge data semantic annotation method and related device |
| CN111488465A (en) * | 2020-04-14 | 2020-08-04 | 税友软件集团股份有限公司 | Knowledge graph construction method and related device |
| CN111552820A (en) * | 2020-04-30 | 2020-08-18 | 江河瑞通（北京）技术有限公司 | Water engineering scheduling data processing method and device |
| CN111951079B (en) * | 2020-08-14 | 2024-04-02 | 国网数字科技控股有限公司 | Credit rating method and device based on knowledge graph and electronic 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 |
| CN112579782A (en) * | 2020-12-28 | 2021-03-30 | 上海明略人工智能(集团)有限公司 | Data processing method, knowledge management system, electronic device, and readable storage medium |
| CN112685572B (en) * | 2020-12-31 | 2021-12-17 | 天云融创数据科技（北京）有限公司 | Heterogeneous data fusion method and device |
| CN112784057B (en) * | 2021-01-11 | 2022-05-13 | 武汉大学 | Three-network industrial map construction method based on regional industrial enterprises |
| CN112818131B (en) * | 2021-02-01 | 2023-10-03 | 亚信科技（成都）有限公司 | Map construction method, system and storage medium for threat information |
| CN113297395B (en) * | 2021-07-08 | 2021-09-24 | 中国人民解放军国防科技大学 | Spatio-temporal multi-modal mixed data processing method, correlation method and indexing method |
| CN113590835A (en) * | 2021-07-28 | 2021-11-02 | 上海致景信息科技有限公司 | Method and device for establishing knowledge graph of textile industry data and processor |
| CN113392229A (en) * | 2021-08-13 | 2021-09-14 | 四川新龟科技有限公司 | Supply chain relation construction and prediction method, device, equipment and storage medium |
| CN114417012A (en) * | 2022-01-20 | 2022-04-29 | 上海弘玑信息技术有限公司 | Method for generating knowledge graph and electronic equipment |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182454A (en) * | 2014-07-04 | 2014-12-03 | 重庆科技学院 | Multi-source heterogeneous data semantic integration model constructed based on domain ontology and method |
| CN106815307A (en) * | 2016-12-16 | 2017-06-09 | 中国科学院自动化研究所 | Public Culture knowledge mapping platform and its use method |
| CN108073673A (en) * | 2017-05-15 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of legal knowledge map construction method, apparatus, system and medium based on machine learning |
| CN108182245A (en) * | 2017-12-28 | 2018-06-19 | 北京锐安科技有限公司 | The construction method and device of people's object properties classificating knowledge collection of illustrative plates |
| CN108345647A (en) * | 2018-01-18 | 2018-07-31 | 北京邮电大学 | Domain knowledge map construction system and method based on Web |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN108875051A (en) * | 2018-06-28 | 2018-11-23 | 中译语通科技股份有限公司 | Knowledge mapping method for auto constructing and system towards magnanimity non-structured text |
| CN108874878A (en) * | 2018-05-03 | 2018-11-23 | 众安信息技术服务有限公司 | A kind of building system and method for knowledge mapping |
| CN108932340A (en) * | 2018-07-13 | 2018-12-04 | 华融融通（北京）科技有限公司 | The construction method of financial knowledge mapping under a kind of non-performing asset operation field |
| CN109189943A (en) * | 2018-09-19 | 2019-01-11 | 中国电子科技集团公司信息科学研究院 | A kind of capability knowledge extracts and the method for capability knowledge map construction |
| 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 |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109446387A (en) * | 2018-10-09 | 2019-03-08 | 众蚁(上海)信息技术有限公司 | A kind of Owners Committee's intelligent Answer System based on artificial intelligence |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107945024B (en) * | 2017-12-12 | 2020-08-21 | 厦门市美亚柏科信息股份有限公司 | Method for identifying internet financial loan enterprise operation abnormity, terminal equipment and storage medium |
| CN109064313A (en) * | 2018-07-20 | 2018-12-21 | 重庆富民银行股份有限公司 | Warning monitoring system after the loan of knowledge based graphical spectrum technology |
| CN109064318A (en) * | 2018-08-24 | 2018-12-21 | 苏宁消费金融有限公司 | A kind of internet financial risks monitoring system of knowledge based map |
-
2019
- 2019-05-20 CN CN201910418358.9A patent/CN110197280B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182454A (en) * | 2014-07-04 | 2014-12-03 | 重庆科技学院 | Multi-source heterogeneous data semantic integration model constructed based on domain ontology and method |
| CN106815307A (en) * | 2016-12-16 | 2017-06-09 | 中国科学院自动化研究所 | Public Culture knowledge mapping platform and its use method |
| CN108073673A (en) * | 2017-05-15 | 2018-05-25 | 北京华宇元典信息服务有限公司 | A kind of legal knowledge map construction method, apparatus, system and medium based on machine learning |
| CN108182245A (en) * | 2017-12-28 | 2018-06-19 | 北京锐安科技有限公司 | The construction method and device of people's object properties classificating knowledge collection of illustrative plates |
| CN108345647A (en) * | 2018-01-18 | 2018-07-31 | 北京邮电大学 | Domain knowledge map construction system and method based on Web |
| CN108596439A (en) * | 2018-03-29 | 2018-09-28 | 北京中兴通网络科技股份有限公司 | A kind of the business risk prediction technique and system of knowledge based collection of illustrative plates |
| CN108874878A (en) * | 2018-05-03 | 2018-11-23 | 众安信息技术服务有限公司 | A kind of building system and method for knowledge mapping |
| CN108875051A (en) * | 2018-06-28 | 2018-11-23 | 中译语通科技股份有限公司 | Knowledge mapping method for auto constructing and system towards magnanimity non-structured text |
| CN108932340A (en) * | 2018-07-13 | 2018-12-04 | 华融融通（北京）科技有限公司 | The construction method of financial knowledge mapping under a kind of non-performing asset operation field |
| 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 |
| CN109189943A (en) * | 2018-09-19 | 2019-01-11 | 中国电子科技集团公司信息科学研究院 | A kind of capability knowledge extracts and the method for capability knowledge map construction |
| CN109446387A (en) * | 2018-10-09 | 2019-03-08 | 众蚁(上海)信息技术有限公司 | A kind of Owners Committee's intelligent Answer System based on artificial intelligence |
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110197280A (en) | 2019-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110197280B (en) | Knowledge graph construction method, device and system | |
| CN112785397B (en) | Product recommendation method, device and storage medium | |
| CN110363449B (en) | Risk identification method, device and system | |
| US11682093B2 (en) | Document term recognition and analytics | |
| US20220020026A1 (en) | Anti-money laundering methods and systems for predicting suspicious transactions using artifical intelligence | |
| Li et al. | Telecom customer churn prediction method based on cluster stratified sampling logistic regression | |
| AU2021355322B2 (en) | Heterogeneous graph embedding | |
| CN111949643A (en) | Data processing method and system based on business modeling | |
| CN112529584A (en) | Transaction dispute data processing method, device, equipment and storage medium | |
| CN110197426B (en) | Credit scoring model building method, device and readable storage medium | |
| Jiang | Credit scoring model based on the decision tree and the simulated annealing algorithm | |
| Su et al. | A ensemble machine learning based system for merchant credit risk detection in merchant MCC misuse | |
| CN111259975B (en) | Method and device for generating classifier and method and device for classifying text | |
| CN111177653A (en) | Credit assessment method and device | |
| CN117057866A (en) | Service recommendation method and device, electronic equipment and storage medium | |
| Chauhan et al. | Big data analytics for ICT monitoring and development | |
| CN113988878B (en) | Graph database technology-based anti-fraud method and system | |
| CN115983982A (en) | Credit risk identification method, credit risk identification device, credit risk identification equipment and computer readable storage medium | |
| CN110163482B (en) | Method for determining safety scheme data of activity scheme, terminal equipment and server | |
| Kaufman | Deep Learning: a Brazilian case | |
| Baruah et al. | Risk Prediction in Life Insurance Industry Using Machine Learning Techniques—A Review | |
| CN112559897B (en) | Matching relation identification method, device and equipment | |
| WO2024093960A1 (en) | Verification method and verification apparatus for abnormal transaction coping strategy | |
| Holubová et al. | Advanced Behavioral Analyses Using Inferred Social Networks: A Vision | |
| Harbaugh | Predicting Retail Bank Customer Churn Using Push, Mooring, and Temporal Inputs with Machine Learning |
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 |