Method, device and storage medium for generating RF2 file

Abstract

The embodiment of the present specification provides a method, device and equipment for generating an RF2 file and a storage medium. The method comprises: receiving a web ontology language expression for defining a target concept; wherein the web ontology language expression comprises a main ontology item representing the target concept and a sub-ontology item for defining the target concept; the sub-ontology item is used to represent an associated concept having an association relationship with the target concept; using a specified reasoning rule to perform reasoning processing on the web ontology language expression to obtain a target web ontology language expression; and generating the RF2 file according to the target web ontology language expression. By using the specified reasoning rule to perform reasoning on the web ontology language expression to obtain the target web ontology language expression, and further generating the RF2 file through the target web ontology language expression, the convenience of generating the RF2 file can be improved to a certain extent.

Description

TECHNICAL FIELD

[0001] Embodiments of the present specification relate to the field of data processing, and in particular, to a method, apparatus, device and storage medium for generating an RF2 file. BACKGROUND

[0002] RF2 (SNOMED CT Release Format 2) is a general release format of the SCT (Systematized Nomenclature of Medicine Clinical Terms) terminology set.

[0003] An RF2 file is a file constructed based on the RF2 format. However, according to the requirements of the application field, the complexity of the RF2 format is high. For example, medical terms in the medical field have relatively strict requirements. Therefore, the complexity of the RF2 format for medical terms is high.

[0004] Therefore, there is a technical problem in the prior art that the convenience of generating an RF2 file is low. SUMMARY

[0005] Therefore, the embodiments of the present specification are committed to providing a method, apparatus, device and storage medium for generating an RF2 file, to improve the convenience of generating an RF2 file to a certain extent.

[0006] The embodiments of the present specification provide a method for generating an RF2 file, comprising: receiving a web ontology language expression for defining a target concept; wherein the web ontology language expression comprises a main ontology item representing the target concept and a sub-ontology item for defining the target concept; the sub-ontology item is used to represent an associated concept having an association relationship with the target concept; using a specified reasoning rule, the web ontology language expression is processed by reasoning to obtain a target web ontology language expression; and generating the RF2 file according to the target web ontology language expression.

[0007] One embodiment of the present specification provides a device for generating an RF2 file, comprising: a receiving module configured to receive a web ontology language expression for defining a target concept; wherein the web ontology language expression comprises a main ontology item representing the target concept and a sub-ontology item for defining the target concept; the sub-ontology item is used to represent an associated concept having an association relationship with the target concept; a reasoning module configured to use a specified reasoning rule to process the web ontology language expression by reasoning to obtain a target web ontology language expression; and a generating module configured to generate the RF2 file according to the target web ontology language expression.

[0008] The embodiment of the present specification provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the method of the above embodiment when executing the computer program.

[0009] The embodiment of the present specification provides a computer readable storage medium, which stores computer program instructions, and the program is executed by a processor to implement the method of the above embodiment.

[0010] The plurality of embodiments provided by the present specification can improve the convenience of generating RF2 files to a certain extent by using specified inference rules to infer the received network ontology language expression defining the target concept to obtain the target network ontology language expression, and further generating the RF2 file through the target network ontology language expression. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 The schematic diagram of the method for generating the RF2 file provided by one embodiment of the present specification.

[0012] Figure 2a The schematic diagram of the network ontology language expression provided by one embodiment of the present specification.

[0013] Figure 2b The schematic diagram of the target network ontology language expression provided by one embodiment of the present specification.

[0014] Figure 3 The flowchart of the method for generating the RF2 file provided by one embodiment of the present specification.

[0015] Figure 4a The schematic diagram of the network ontology language expression provided by one embodiment of the present specification.

[0016] Figure 4b The schematic diagram of the first network ontology language expression provided by one embodiment of the present specification.

[0017] Figure 5a The schematic diagram of the network ontology language expression provided by one embodiment of the present specification.

[0018] Figure 5b The schematic diagram of the first network ontology language expression provided by one embodiment of the present specification.

[0019] Figure 5c The schematic diagram of the first network ontology language expression provided by one embodiment of the present specification.

[0020] Figure 6A schematic diagram of a second network ontology language expression provided for an embodiment of the present specification.

[0021] Figure 7 A schematic diagram of a generation apparatus of an RF2 file provided for an embodiment of the present specification.

[0022] Figure 8 A schematic diagram of a computer device provided for an embodiment of the present specification. DETAILED DESCRIPTION

[0023] In the related art, RF2 (SNOMED CT Release Format 2) is a general release format of the SCT (Systematized Nomenclature of Medicine Clinical Terms) term set. Therefore, in order to adapt to the needs of some fields, for example, in order to adapt to the needs of the medical field to build a medical term set, the RF2 format has a high degree of complexity to adapt to the characteristics of medical terms. Specifically, the RF2 format has a strong restriction on the type or value of the data of a specified category in the file. Therefore, it can be cumbersome to generate an RF2 file. In the related art, the RF2 file describing the medical terms is constructed through the relationship between the medical concepts, which needs to be audited by experts, has a low efficiency, and the quality of the constructed medical terms is poor.

[0024] In the related art, the network ontology language expression can include a main ontology item representing a target concept and a subordinate ontology item representing an associated concept, wherein the target concept and the associated concept have an association relationship. The association relationship can be represented by a relationship item. For example, in the medical field, a network ontology language expression defining a target concept in the medical field can be constructed by using the network ontology language. The network ontology language expression defining the target concept and the RF2 file have a certain degree of similarity, and therefore, the network ontology language expression is suitable for generating the RF2 file, and the process of generating the RF2 file by using the network ontology language expression is relatively convenient.

[0025] Therefore, it is necessary to provide an RF2 file generation method, apparatus and device, and storage medium, which can use a specified reasoning rule to perform reasoning processing on the received network ontology language expression defining a target concept to obtain a target network ontology language expression, and further generate an RF2 file by using the target network ontology language expression, so as to improve the convenience of generating the RF2 file to a certain extent.

[0026] Please refer to Figure 1In the specification, an example of an application scenario of an RF2 file generation system is provided. The RF2 file generation system can include a client and a server. A user of the RF2 file generation system can be a staff in the medical field, who wants to convert a web ontology language expression for defining a target concept constructed by a web ontology language (OWL) into an RF2 file through the RF2 file generation system.

[0027] The client can receive configuration information of a user for specifying a reasoning rule, and send the configuration information to the server. The server can request a web ontology language expression for defining a target concept in the medical field from a database. The database can send the web ontology language expression to the server. The web ontology language expression received by the server can be for defining a concept of “lymphocytosis (disease)”. Specifically, the web ontology language expression received by the server can refer to Figure 2a . The “lymphocytosis (disease)” can be a main ontology item representing the target concept. The “lymphocyte disease (disease)” can be a sub ontology item representing an associated concept. Specifically, the “lymphocyte disease (disease)” can have a hierarchical relationship with the target concept represented by the main ontology item. The “above reference range (limit value)” and the “lymphocyte count (operation)” can be sub ontology items representing associated concepts. The “has explanation (property)” and the “explanation (property)” can be relationship items representing the associated relationship. Specifically, the “has explanation (property)” can represent the associated relationship between the “lymphocyte disease (disease)” and the “above reference range (limit value)”. The “explanation (property)” can represent the associated relationship between the “lymphocyte disease (disease)” and the “lymphocyte count (operation)”.

[0028] Then, the server can first infer the web ontology language expression by a semantic inference machine specified by the specified reasoning rule to obtain a first sub ontology item, and a target hierarchical relationship between an associated concept represented by the first sub ontology item and an associated concept represented by the main ontology item. By adding the first sub ontology item and a relationship item representing the target hierarchical relationship to the web ontology language expression, a first target web ontology language expression can be formed. The semantic inference machine can be a target inference machine. Further, the server can deduce the first target web ontology language expression by a necessary paradigm rule specified by the user to obtain a second sub ontology item, and a target attribute relationship between an associated concept represented by the second sub ontology item and an associated concept represented by the main ontology item. By adding the second sub ontology item and a relationship item representing the target attribute relationship to the first target web ontology language expression, a second target web ontology language expression can be obtained. The server can construct a target web ontology language expression according to the second target web ontology language expression.

[0029] Please refer toFigure 2b In the target network ontology language expression, compared with the network ontology language expression, two sub-ontology items representing the association relationship of "leukocytosis (disease)" and "lymphocyte count abnormality (finding)" can be added. At the same time, the target hierarchical relationship can indicate that "lymphocyte disease (disease)" is subordinate to "leukocytosis (disease)", and "lymphocyte count abnormality (finding)" is subordinate to "lymphocyte disease (disease)".

[0030] At the same time, in the target network ontology language expression, compared with the network ontology language expression, the second sub-ontology item representing "abnormal immune process (limited value)" and the relationship item representing "pathological process (attribute)" can be added. Among them, the relationship item can represent the association relationship between the association concept represented by the second sub-ontology item and the target concept represented by the main ontology item.

[0031] Further, after generating the target network ontology language expression, the server can generate a second sub-file of the RF2 file based on the target network ontology language expression, and a first sub-file based on the network ontology language expression generated by the database.

[0032] Through the first sub-file and the second sub-file, the server can generate the RF2 file.

[0033] After generating the RF2 file, the server can send the RF2 file to the client, and the client can display the content of the RF2 file to the user.

[0034] In some embodiments, the RF2 file generation system can maintain a relational database. The relational database can store data constructed according to a specified data type and used to describe knowledge. For example, the relational database can be set to store data of the data type of a string. Correspondingly, the relational database can store medical concepts in medical terms and data representing the relationship between medical concepts through strings.

[0035] Further, in the process of reasoning for the data in the relational database, the RF2 file generation system can convert the data type of the data in the relational database into a target data type suitable for reasoning, and further execute the reasoning process based on the data of the target data type. Among them, the target data type can be a data type suitable for a target reasoning machine, such as OWL or RF2 format, etc. Of course, the RF2 file generation system can also convert the data type of the data in the relational database into a data type suitable for the corresponding use scenario requirement according to different use scenario requirements.

[0036] The RF2 file generation system can be integrated with a file conversion module, which can be used to convert different files into RF2 files, or convert RF2 files into non-RF2 files. In some embodiments, the data conversion module can also implement conversion between data files in multiple different formats. For example, the file formats supported by the data conversion module can include, but are not limited to, RF2 files, OWL files, Xmind files, Excel files, and the like.

[0037] Of course, in the process of storing the data after reasoning into the relational database, the file conversion module can also convert the data type of the data after reasoning into the data type of the data stored in the relational database, and then store it into the relational database. To some extent, the consistency of the data in the relational database can be improved, and the overhead of the database management of different data types of data can be reduced.

[0038] In some embodiments, the RF2 file generation system can also receive data describing knowledge input by staff. Further, the RF2 file generation system can update the data into the relational database. In some embodiments, the data input by the staff can be medical terms and the like. The data input by the staff can be files in XMind, Excel and the like. Correspondingly, the RF2 file generation system can convert the XMind, Excel and the like format files into the data type of the data in the relational database, and then store them into the relational database. To some extent, the consistency of the data in the relational database can be improved, and the overhead of the database management of data can be reduced.

[0039] In some embodiments, the conversion process for the data type stored in the relational database can be implemented by a parser and a generator. Specifically, the parser can be used to convert the data input by the staff into the data type of the relational database, and the generator can be used to convert the data of the relational database into a data type suitable for the requirements of the corresponding use scenario. Through the parser and the generator, the coupling relationship in the data type conversion process can be reduced, and the scalability of the RF2 file generation system can be improved to some extent.

[0040] The embodiment of the present specification provides a system for generating an RF2 file. The system for generating the RF2 file can include a client and a server. The client can be an electronic device with network access capability. Specifically, for example, the client can be a desktop computer, a tablet computer, a notebook computer, a smart phone, a digital assistant, a smart wearable device, a shopping guide terminal, a television, a smart speaker, a microphone, etc. Among them, the smart wearable device includes but is not limited to a smart bracelet, a smart watch, smart glasses, a smart helmet, a smart necklace, etc. Alternatively, the client can also be software that can run in the electronic device. The server can be an electronic device with certain computing processing capability. It can have a network communication module, a processor and a memory, etc. Of course, the server can also refer to software running in the electronic device. The server can also be a distributed server, which can be a system with multiple processors, memories, network communication modules, etc. working together. Alternatively, the server can also be a server cluster formed by several servers. Alternatively, with the development of science and technology, the server can also be a new technical means capable of realizing the corresponding functions of the embodiment of the present specification. For example, it can be a new form of "server" based on quantum computing.

[0041] Please refer to Figure 3 The embodiment of the present specification provides a method for generating an RF2 file. The method for generating the RF2 file can be applied to a server. The method for generating the RF2 file can include the following steps.

[0042] Step S110: receiving a web ontology language expression for defining a target concept; wherein the web ontology language expression includes a main ontology item representing the target concept and a from ontology item for defining the target concept; the from ontology item is used to represent an associated concept having an association relationship with the target concept.

[0043] In some cases, through the web ontology language expression, the data conforming to the definition of the RF2 format can be generated more conveniently. Therefore, the server can receive the web ontology language expression for generating the RF2 file.

[0044] In the embodiment, the RF2 file can represent a file constructed based on the RF2 (SNOMED CT Release Format 2) format. The content of the RF2 file can be used to describe knowledge. Specifically, for example, the content of the RF2 file can represent medical terms in the medical field. Of course, the content of the RF2 file can also be data describing knowledge in other fields constructed based on the format requirements of RF2. Through the web ontology language expression for defining the target concept, the RF2 file capable of describing the knowledge can be generated more conveniently.

[0045] In the present embodiment, the network ontology language expression can represent an expression defining a target concept constructed by the network ontology language. In some embodiments, the network ontology language expression can represent a class of the network ontology language and corresponding class axioms.

[0046] In the present embodiment, the network ontology language expression can include a main ontology item representing the target concept, and a sub ontology item for defining the target concept. The sub ontology item can represent an associated concept having an association relationship with the target concept. Of course, the network ontology language expression can also include a relationship item indicating the association relationship. Specifically, for example, the network ontology language expression can be used to define Xiaoming's family relationship. Accordingly, the network ontology language expression includes a main ontology item representing Xiaoming, and sub ontology items representing Xiaoming's wife Xiaohong and Xiaoming's son Xiaohai, respectively. Moreover, the network ontology language expression includes multiple relationship items, which can respectively indicate that the association relationship between Xiaoming and Xiaohong is husband and wife, the relationship between Xiaoming and Xiaohai is father and son, etc. Of course, the network ontology language expression can also define a medical concept in the medical field. For example, the target concept represented by the main ontology item can be the medical concept of "drug-induced diabetes (disease)". The associated concept represented by the sub ontology item can be the medical concept of "endocrine system structure (body structure)". Accordingly, the association relationship between "drug-induced diabetes (disease)" and "endocrine system structure (body structure)" can be "disease location (attribute)".

[0047] In some embodiments, the association relationship represented by the relationship item of the network ontology language expression can be divided into attribute relationship and hierarchical relationship. Specifically, for example, for the relationship item representing the attribute relationship, "drug-induced diabetes (disease)" can represent the main ontology item. "Disease location (attribute)" can be used as a relationship item to represent the attribute of "drug-induced diabetes (disease)". "Endocrine system structure (body structure)" can be used as a sub ontology item to represent the attribute value of "drug-induced diabetes (disease)" for "disease location (attribute)". For the relationship item representing the hierarchical relationship. For example, "drug-induced diabetes (disease)" can be used as the main ontology item, and "secondary diabetes (disease)" can be used as the sub ontology item. The association relationship between "drug-induced diabetes (disease)" and "secondary diabetes (disease)" can be a hierarchical relationship. Specifically, the hierarchical relationship can be represented as "drug-induced diabetes (disease)" belongs to "secondary diabetes (disease)". In some embodiments, please refer to Figure 4b , figure 401 can represent the hierarchical relationship.

[0048] In the embodiment, after the method for receiving the web ontology language expression for defining the target concept is requested by the database, the web ontology language expression fed back by the database is received. Of course, the method for receiving the web ontology language expression for defining the target concept can also receive the web ontology language expression provided by the client.

[0049] Step S120: using the specified inference rule, the web ontology language expression is processed by inference to obtain a target web ontology language expression.

[0050] In some cases, the RF2 file has strict format requirements. It is difficult to construct the RF2 file directly according to the data stored in the relational database. The web ontology language expression can be more conveniently processed by inference through the corresponding inference rule such as the inference machine. Therefore, through the web ontology language expression, the RF2 file can be more conveniently constructed. Specifically, the web ontology language expression can be processed by inference using the specified inference rule to obtain a target web ontology language expression. Further, the RF2 file can be more conveniently generated through the target web ontology language expression.

[0051] In the embodiment, the specified inference rule can represent the inference logic for inferring the web ontology language expression. Specifically, for example, the specified inference rule can process the inference according to the association relationship between the ontology items in the web ontology language expression. The ontology items can include main ontology items and / or subordinate ontology items. In some embodiments, the concept represented by the ontology item in the web ontology language expression can be a concept in the preset concept set, and the concept set indicates the relationship between the concepts in the concept set. Accordingly, the specified inference rule can also be based on the relationship indicated by the concept set to infer. Of course, the specified inference rule can also indicate that the inference is performed by the specified target inference machine. The target inference machine can be a semantic inference machine. For example, the target inference machine can be an ELK Reasoner inference machine. In some embodiments, the specified inference rule can also include the necessary normal form rule constructed based on the specified necessary normal form (NNF, necessary normal form), and the inference processing of the web ontology language expression can be performed through the necessary normal form rule. The necessary normal form can define the necessary components in the RF2 file representation term.

[0052] In the embodiment, the target network ontology language expression can represent an expression built based on the network ontology language according to the specified inference rule. The target network ontology language expression can be used to generate the RF2 file. Specifically, for example, the target network ontology language expression can add the relationship item, the first slave ontology item and the second slave ontology item obtained through the inference processing to the network ontology language expression. Alternatively, the target network ontology language expression can delete the redundant information from the network ontology language expression.

[0053] In the embodiment, the method for using the specified inference rule to perform the inference processing on the network ontology language expression of the same knowledge to obtain the target network ontology language expression can be to perform the inference processing on the network ontology language expression based on the inference logic of the specified inference rule. Specifically, for example, the method for using the specified inference rule to perform the inference processing on the network ontology language expression to obtain the target network ontology language expression can first perform the processing on the network ontology language expression by using the target inference machine, and then perform the further processing on the network ontology language expression after the inference by the target inference machine by using the specified necessary normal form rule to obtain the target network ontology language expression.

[0054] Step S130: generating the RF2 file according to the target network ontology language expression.

[0055] In some cases, the RF2 file can be more conveniently generated through the target network ontology language expression. The target network ontology language expression can include the main ontology item and the slave ontology item conforming to the provisions of the RF2 format, and the relationship item representing the association relationship between the target concept corresponding to the main ontology item and the associated concept corresponding to the slave ontology item. The target ontology language expression obtained through the inference processing can more accurately define the target concept. Therefore, the accuracy of the knowledge description through the target network ontology language expression to generate the RF2 file is also higher.

[0056] In the embodiment, the method for generating the RF2 file according to the target network ontology language expression can map the main ontology item and / or the slave ontology item and the relationship item in the target network ontology language expression to the data item in the RF2 file through the preset mapping rule. The mapping process can further include the data type conversion process. Specifically, for example, the axiom corresponding to the target network ontology language expression can be converted into a TXT file as a sub-file in the RF2 file to generate the RF2 file. In some embodiments, the network ontology language expression can also generate another sub-file in the RF2 file. Then, the RF2 file can be formed by merging the multiple sub-files.

[0057] In some embodiments, the association relationship comprises a hierarchical relationship; the specified reasoning rule specifies a target reasoning machine; and the step of reasoning the network ontology language expression using the specified reasoning rule to obtain a target network ontology language expression comprises: using the target reasoning machine to infer the network ontology language expression to obtain a first slave ontology item and a target hierarchical relationship between a target concept represented by the master ontology item and an association concept represented by the first slave ontology item, forming a first target network ontology language expression; and generating the target network ontology language expression based on the first target network ontology language expression.

[0058] In some cases, the RF2 file can be divided into multiple sub-files. There is also a certain difference between the target concept defined by the network ontology language expression and the terms describing the target concept in the part of the sub-files in the RF2 file. However, the network ontology language expression can have strong logical reasoning capability. Therefore, by reasoning the network ontology language expression, the data closer to the requirements of the RF2 file, i.e., the target network ontology language expression, can be more conveniently generated. At the same time, the network ontology language expression can also be implemented by various reasoning machines to realize more general inference processing, which can further simplify the process of generating the RF2 file.

[0059] In the embodiment, the hierarchical relationship can represent the subordinate relationship between the master ontology item and the slave ontology item. Specifically, for example, the concept of "diabetes (disease) caused by drugs" represented by the master ontology item can be a subclass of the concept of "secondary diabetes (disease)" represented by the slave ontology item. In some embodiments, the association relationship represented by the relationship item can also include multiple hierarchical relationships. Specifically, for example, the association relationship represented by the relationship item "is a disease" can be a subclass of "is a".

[0060] In the embodiment, the target reasoning machine can represent a tool for performing reasoning processing on the network ontology language expression. Specifically, the target reasoning machine can be a semantic reasoning machine. For example, the target reasoning machine can be an ELK Reasoner reasoning machine. The efficiency can be improved by using the ELK Reasoner reasoning machine. In some embodiments, the target reasoning machine can infer the target hierarchical relationship between the first slave ontology item and the association concept represented by the first slave ontology item and the target concept represented by the master ontology item.

[0061] In the embodiment, the first target network ontology language expression can be generated according to the corresponding network ontology language expression. The first slave ontology item can be an inferred ontology item having a target hierarchical relationship with a master ontology item in the corresponding network ontology language expression. The target hierarchical relationship can represent a hierarchical relationship between a concept represented by the inferred first slave ontology item and a target concept represented by the master ontology item. Specifically, for example, the target hierarchical relationship can represent that the master ontology item in the network ontology language expression is a subclass of the first slave ontology item.

[0062] In the embodiment, the first target network ontology language expression can represent an expression inferred by the target reasoning machine and constructed based on the network ontology language. In some embodiments, the first target network ontology language expression can be formed by the corresponding network ontology language expression, the inferred first slave ontology item, and the target hierarchical relationship. Specifically, the first target network ontology language expression can be generated according to the corresponding network ontology language expression, in combination with the target hierarchical relationship between the master ontology item and the first slave ontology item in the network ontology language expression. For example, please refer to Figure 4a , Figure 4a may represent the network ontology language expression before the inference by the target reasoning machine. Accordingly, please refer to Figure 4b may represent the first target network ontology language expression inferred by the target reasoning machine based on the network ontology language expression. Compared with the network ontology language expression before the inference, the first target network ontology language expression can have the newly added first slave ontology item and the hierarchical relationship between the master ontology item and the slave ontology item in the network ontology language expression, which is the target hierarchical relationship. In the embodiment, the first target network ontology language expression can be generated according to the corresponding network ontology language expression, in combination with the target hierarchical relationship between the master ontology item and the first slave ontology item in the network ontology language expression. Figure 4b In the embodiment, the first slave ontology item can represent a “drug-related disease (disease)”. Accordingly, the target hierarchical relationship can represent that the “secondary diabetes (disease)” can be subordinate to the “drug-related disease (disease)”.

[0063] In this embodiment, the target reasoning machine is used to perform inference processing on the network ontology language expression to obtain a first slave ontology item and a target hierarchical relationship between the target concept represented by the master ontology item and the associated concept represented by the first slave ontology item, and form a first target network ontology language expression. The method can be to use a specified semantic reasoning machine to perform inference according to the hierarchical relationship between ontology items to obtain a first slave ontology item having a target hierarchical relationship with the master ontology item in the corresponding network ontology language expression. The hierarchical relationship between ontology items can be pre-set, learned by the reasoning machine, or obtained from the hierarchical relationship existing in other received network ontology language expressions. Further, based on the target hierarchical relationship and the first slave ontology item, the first target network ontology language expression can be generated in combination with the corresponding network ontology language expression. Compared with the corresponding network ontology language expression, the first target network ontology language expression can have more accurate and detailed hierarchical relationships, so that the target concept can be more accurately defined.

[0064] In some embodiments, please refer to Figure 5a 、 Figure 5b and Figure 5c . Based on the target reasoning machine, the first target network ontology language expression represented by Figure 5a and Figure 5b can be generated according to the network ontology language expression represented by Figure 5c .

[0065] In some embodiments, the specified reasoning rule includes a necessary normal form rule; the associated relationship includes an attribute relationship; and the step of using the specified reasoning rule to perform inference processing on the network ontology language expression to obtain the target network ontology language expression includes: performing deduction on the network ontology language expression according to the specified necessary normal form rule to obtain a second slave ontology item and a target attribute relationship between the target concept represented by the master ontology item and the associated concept represented by the second slave ontology item; and generating the target network ontology language expression according to the network ontology language expression, the second slave ontology item, and the target attribute relationship.

[0066] In some cases, the RF2 file can have high requirements for the relationship between data items representing different concepts and the degree of redundancy of data items. Therefore, the necessary normal form rule can be used to perform deduction on the network ontology language expression to obtain a target attribute relationship between the master ontology item in the network ontology language expression and a second slave ontology item. Further, the target network ontology language expression can be generated according to the corresponding network ontology language expression, the second slave ontology item, and the target attribute relationship. According to the target network ontology language expression, the RF2 file conforming to the RF2 format specification can be conveniently and accurately generated.

[0067] In the embodiment, the property relation can be a characterization of a relation between a concept represented by a main ontology item and a related concept represented by a second ontology item. For example, the target concept represented by the main ontology item can be "lymphocytosis (disease)", and the related concept represented by the second ontology item can be "abnormal immune process (qualifier)". Accordingly, the property relation between the target concept represented by the main ontology item and the related concept represented by the second ontology item can be "pathological process (property)". Accordingly, the network ontology language expression can include a relation item representing the "pathological process (property)". The property relation can also be represented as an object property.

[0068] In the embodiment, the necessary normal form rule can be a rule formulated according to a necessary normal form. The necessary normal form can be used to indicate necessary definitions of concepts. Of course, the necessary normal form can also be used to indicate redundant relations that need to be deleted, etc. In some embodiments, the necessary normal form rule can represent a rule proposed for the specification of the RF2 format. In some embodiments, the necessary normal form rule can deduce a target property relation and a second ontology item for a network ontology language expression. In some embodiments, the necessary normal form rule can also indicate a rule for normalizing redundant ontology items in multiple network ontology language expressions. In some embodiments, the necessary normal form rule can collect the relation items representing the property relations after reasoning, and delete redundant, less specific property relations according to a certain strategy.

[0069] In the embodiment, the second ontology item can be an ontology item representing a related concept deduced according to the necessary normal form rule. Specifically, the second ontology item can have a target property relation with the main ontology item in the corresponding network ontology language expression.

[0070] In the embodiment, according to the specified necessary normal form rule, the network ontology language expression is reasoned to obtain the second ontology item and the target property relation between the target concept represented by the main ontology item and the related concept represented by the second ontology item. The target property relation can be obtained by reasoning the network ontology language expression according to the necessary normal form rule.

[0071] In this embodiment, the target network ontology language expression can be further generated according to the deduction result of deducing the network ontology language expression according to the necessary normal form rule. Specifically, the method for generating the target network ontology language expression according to the network ontology language expression, the second sub-ontology item and the target attribute relationship can combine the corresponding network ontology language expression, the second sub-ontology item and the target attribute relationship to obtain the target network ontology language expression. In the target network ontology language expression, the second sub-ontology item and the relationship item can be newly added on the basis of the corresponding network ontology language expression. Of course, the target network ontology language expression can also be formed after further processing on the basis of the newly added second sub-ontology item and the relationship item.

[0072] In some embodiments, the step of generating the target network ontology language expression according to the network ontology language expression, the second sub-ontology item and the target attribute relationship includes: combining the network ontology language expression and the second sub-ontology item according to the target attribute relationship to form a second target network ontology language expression; performing redundancy removal processing on the second target network ontology language expression by using the necessary normal form rule; and constructing the target network ontology language expression based on the second target network ontology language expression after the redundancy removal processing.

[0073] In some cases, there can be redundant ontology items in the second network ontology language expression. Therefore, the second target network ontology language expression can be subjected to redundancy removal processing, and the target network ontology language expression for generating the RF2 file can be constructed based on the second target network ontology language expression after the redundancy removal processing, which can improve the convenience of generating the RF2 file to a certain extent.

[0074] In this embodiment, the method for combining the network ontology language expression and the second sub-ontology item according to the target attribute relationship to form a second target network ontology language expression can add the second sub-ontology item and the relationship item representing the target attribute relationship into the corresponding network ontology language expression. For example, please refer to Figure 2a and Figure 6 . Among them, Figure 2a may represent the network ontology language expression before the specified necessary normal form rule processing. Figure 6 may represent the second network ontology language expression after the specified necessary normal form rule processing. Among them, Figure 6 in which the “abnormal immune process (limit value)” can be the deduced second sub-ontology item. The “case process (attribute)” can be the deduced relationship item representing the target attribute relationship.

[0075] In this embodiment, the method for performing the redundancy removal processing on the second target network ontology language expression according to the necessary normal form rule can normalize the multiple ontology items with hierarchical relationship according to the association relationship in the second target network ontology language expression. Of course, in some embodiments, the attribute relationship can also have multiple levels. Accordingly, the method for performing the redundancy removal processing on the second target network ontology language expression according to the necessary normal form rule can also normalize the multiple relationship items with hierarchical relationship. Specifically, for the multiple relationship items with hierarchical relationship, the relationship item at the lowest level can be selected to replace the rest of the relationship items. For the multiple ontology items with hierarchical relationship, the ontology item at the lowest level can also be selected to replace the rest of the ontology items. For example, please refer to the network ontology language expressions represented in Figure 5a , Figure 5b and Figure 5c . Among them, "fracture (morphological abnormality)" can be a subclass of "injury (morphological abnormality)". Therefore, after the redundancy removal processing, the ontology item representing "injury (morphological abnormality)" can be replaced by the ontology item representing "fracture (morphological abnormality)".

[0076] In some embodiments, in the case that there is no hierarchical relationship between the ontology items, the method for performing the redundancy removal processing on the second target network ontology language expression according to the necessary normal form rule can perform the redundancy removal processing according to the transitive relationship between the ontology items. Among them, the ontology items with transitive relationship have a specified attribute relationship. Specifically, for example, ontology item 1 is "amoxicillin-containing parenteral administration dosage form product (drug dosage form)", the attribute relationship between ontology item 1 and ontology item 2 is "has active ingredient (attribute)", and ontology item 2 is "amoxicillin (substance)". Ontology item 3 is "common release powder injection product (clinical drug) containing exactly 1g of amoxicillin (sodium amoxicillin) per vial", the attribute relationship between ontology item 3 and ontology item 4 is "has exactly active ingredient (attribute)", and ontology item 4 is "sodium amoxicillin (substance)". Among them, "amoxicillin (substance)" and "sodium amoxicillin (substance)" have no hierarchical relationship. However, "amoxicillin (substance)" and "sodium amoxicillin (substance)" can have a transitive relationship. That is, "sodium amoxicillin (substance)" can be formed by performing some operations on "amoxicillin (substance)". The specified attribute relationship of "amoxicillin (substance)" and "sodium amoxicillin (substance)" can be "is modification (attribute)". Therefore, after associating "amoxicillin (substance)" and "sodium amoxicillin (substance)" through "is modification (attribute)", the ontology item in one of the network ontology language expressions can be deleted.

[0077] In this embodiment, the method for constructing the target network ontology language expression based on the second target network ontology language expression after the redundancy removal processing can be that the second target network ontology language expression after the redundancy removal processing is taken as the target network ontology language expression. Of course, the second target network ontology language expression after the redundancy removal processing can also be inferred by the target inference machine to form the target network ontology language expression.

[0078] In some embodiments, the number of network ontology language expressions is multiple; the main ontology items and the slave ontology items of the multiple network ontology language expressions form an ontology item set; the method further comprises: specifying a reference ontology item in the ontology item set; taking the reference ontology item as a starting traversal node and taking the association relationship between the ontology items as a traversal path to traverse the ontology item set; and only when all the ontology items in the ontology item set are traversed and there is no ontology item that is repeatedly traversed, the step of generating the RF2 file according to the target network ontology language expression is performed.

[0079] In some cases, in some application fields, the hierarchical relationship between multiple concepts may indicate that the association relationship between the multiple concepts may be incorrect when a loop is formed. For example, according to the characteristics of the concepts in the medical terminology in the medical field, the association relationship between the ontology items representing different concepts cannot form a loop, otherwise the medical knowledge described by the network ontology language expression may be inaccurate. Therefore, for the network ontology language expression, the step of generating the RF2 file according to the target network ontology language expression is performed only when all the ontology items are traversed and there is no ontology item that is repeatedly traversed, which can improve the accuracy of the generated RF2 file to a certain extent.

[0080] In this embodiment, the ontology item set can have multiple ontology items. The ontology item set can be formed by the main ontology items and the slave ontology items of a network ontology language expression.

[0081] In this embodiment, the reference ontology item can represent a specified ontology item as a traversal starting point. Accordingly, the method for specifying the reference ontology item in the ontology item set can be that an ontology item is randomly selected as the reference ontology item. Alternatively, the method for specifying the reference ontology item in the ontology item set can also be that according to the hierarchical relationship between the ontology items, the ontology item at the highest level is determined as the reference ontology item.

[0082] In the embodiment, the method for traversing the ontology item set can be based on any traversal method, such as pre-order traversal, in-order traversal, or post-order traversal. In some embodiments, the traversed ontology items can be marked to determine whether to traverse repeatedly. The traversal path can be used to indicate the traversal order. For example, the traversal path can be according to the association between the ontology items, i.e., traversing the parent class first and then the child class. Of course, the traversal path can also be traversing the ontology item at the lowest level first and then traversing the parent class of the ontology item.

[0083] In the embodiment, the step of generating the RF2 file according to the target network ontology language expression is performed only when all the ontology items in the ontology item set are traversed and there is no ontology item that is traversed repeatedly, which can improve the accuracy of the RF2 file to some extent and reduce the problem of efficiency reduction caused by calibration of incorrect data to some extent.

[0084] In some embodiments, the traversal object can also include any one of the target network ontology language expression, the first network ontology language expression, and the second network ontology language expression.

[0085] In some embodiments, the RF2 file includes a first sub-file and a second sub-file, and the step of generating the RF2 file according to the target network ontology language expression includes: creating the first sub-file of the RF2 file through the network ontology language expression; constructing the second sub-file of the RF2 file based on the target network ontology language expression; and generating the RF2 file according to the first sub-file and the second sub-file.

[0086] In some cases, the RF2 file can include multiple sub-files. Specifically, the RF2 file can include a first sub-file and a second sub-file. The first sub-file can be generated through the network ontology language expression. The second sub-file can be generated through the target network ontology language expression. The first sub-file can correspond to the statement view of the RF2. The second sub-file can correspond to the inference view of the RF2. Therefore, by generating the first sub-file and the second sub-file of the RF2 file respectively and then combining the first sub-file and the second sub-file, the RF2 file can be generated more conveniently. In some embodiments, the first sub-file can be a file formed by converting the axioms of the network ontology language expression into TXT format, and the second sub-file can be a file formed by converting the axioms of the target network ontology language expression into TXT format.

[0087] In some embodiments, the method for generating the RF2 file can further include: generating an extended network ontology language expression according to the RF2 file; performing inference processing on the extended network ontology language expression using the specified inference rule to obtain an inference result for the extended network ontology language expression; and adjusting the RF2 file based on the inference result.

[0088] In some cases, after the RF2 file is generated based on the first sub-file and the second sub-file, an extended network ontology language expression can be further generated based on the RF2 file. That is, the RF2 file is converted into an expression described in the network ontology language. Further, the extended network ontology language expression is subjected to inference processing using the specified inference rule to obtain an inference result for the extended network ontology language expression. Based on the inference result of the extended network ontology language expression, the RF2 file can be adjusted to improve the accuracy of the knowledge described in the RF2 description to a certain extent. By performing the specified inference rule multiple times to perform inference processing on the network ontology language expression or the extended network ontology language expression, the accuracy of the knowledge or terms described in the RF2 file is relatively high, and the RF2 file conforms to the specification of the RF2 format. The process of adjusting the RF2 file in the present embodiment can be performed multiple times.

[0089] Referring to Figure 7 One embodiment of the present specification also provides a device for generating an RF2 file. The device for generating an RF2 file can include a receiving module, an inference module, and a generating module.

[0090] The receiving module is configured to receive a network ontology language expression for defining a target concept. The network ontology language expression includes a main ontology item representing the target concept and a sub-ontology item for defining the target concept. The sub-ontology item is used to represent an associated concept having an association relationship with the target concept.

[0091] The inference module is configured to perform inference processing on the network ontology language expression using a specified inference rule to obtain a target network ontology language expression.

[0092] The generating module is configured to generate the RF2 file based on the target network ontology language expression.

[0093] The specific functions and effects of the device for generating an RF2 file can be explained with reference to other embodiments of the present specification, and will not be described here. Each module in the device for generating an RF2 file can be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form to be called and executed by the processor.

[0094] Reference is made to Figure 8 The embodiments of the present specification also provide a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the method for generating an RF2 file according to any one of the embodiments of the present specification when executing the computer program.

[0095] The embodiments of the present specification also provide a computer readable storage medium, which stores a computer program, and wherein the computer program causes a computer to execute the method for generating an RF2 file according to any one of the embodiments of the present specification when being executed by the computer.

[0096] The embodiments of the present specification also provide a computer program product comprising instructions which, when executed by a computer, cause the computer to carry out the method for generating an RF2 file according to any one of the embodiments of the present specification.

[0097] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the present specification are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws and regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0098] It can be understood that the specific examples herein are only to help those skilled in the art better understand the embodiments of the present specification, and not to limit the scope of the present application.

[0099] It can be understood that in various embodiments of the present specification, the size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present specification.

[0100] It can be understood that the various embodiments described in the present specification can be implemented alone or in combination, and the embodiments of the present specification do not limit this.

[0101] Unless otherwise specified, all technical and scientific terms used in the embodiments of the present specification have the same meanings as those commonly understood by those skilled in the art of the present specification. The terms used in the present specification are only for the purpose of describing the specific embodiments and are not intended to limit the scope of the present specification. The term "and / or" used in the present specification includes any and all combinations of one or more related listed terms. The singular forms "a", "an" and "the" used in the embodiments of the present specification and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0102] It can be understood that the processor of the embodiments of the present specification can be an integrated circuit chip with processing capability of signals. In the implementation process, each step of the method embodiments described above can be completed by integrated logic circuits in hardware or instructions in software form in the processor. The processor described above can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. Each method, step and logic block disclosed in the embodiments of the present specification can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor or the like. The steps of the method disclosed in combination with the embodiments of the present specification can be directly embodied as a hardware coding processor for execution, or a combination of hardware and software modules in the coding processor for execution. The software module can be located in a random access memory, a flash memory, a read only memory, a programmable read only memory or an electrically erasable programmable memory, a register or other mature storage medium in the art. The storage medium is located in the storage, and the processor reads the information in the storage, and combines the hardware to complete the steps of the above method.

[0103] It can be understood that the memory in the embodiments of the present specification can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (EPROM), an electrically erasable programmable read only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM). It should be noted that the memory of the system and method described herein is intended to include but not limited to these and any other suitable type of memory.

[0104] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present specification.

[0105] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0106] In several embodiments provided in the specification, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, and the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0107] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0108] In addition, each functional unit in each embodiment of the specification can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0109] If the functions are realized in the form of software functional units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the specification or the essential part or part of the prior art which contributes to the technical solutions can be embodied in the form of a software product, and the computer software product stored in a storage medium includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the specification. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0110] The above is only a specific embodiment of the specification, but the protection scope of the application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the specification, which should be covered within the protection scope of the specification. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A method of generating an RF2 file, characterized by, The method comprises the following steps: receiving a network ontology language expression for defining a target concept; wherein the network ontology language expression comprises a main ontology item representing the target concept, a sub-ontology item for defining an associated concept having an associated relationship with the target concept, and a relationship item for representing the associated relationship; using a specified reasoning rule to perform reasoning processing on the network ontology language expression to obtain a target network ontology language expression; mapping the main ontology item, the sub-ontology item and the relationship item in the target network ontology language expression to data items in an RF2 file by using a preset mapping rule to generate the RF2 file.

2. The method of claim 1, wherein, The associated relationship comprises a hierarchical relationship; and the specified reasoning rule specifies a target reasoning machine. The step of using a specified reasoning rule to perform reasoning processing on the network ontology language expression to obtain a target network ontology language expression comprises the following steps: using the target reasoning machine to perform inference processing on the network ontology language expression to obtain a first sub-ontology item and a target hierarchical relationship between the target concept represented by the main ontology item and the associated concept represented by the first sub-ontology item, thereby forming a first target network ontology language expression; generating the target network ontology language expression based on the first target network ontology language expression.

3. The method of claim 1, wherein, The specified reasoning rule comprises a necessary paradigm rule; the associated relationship comprises an attribute relationship; and the step of using a specified reasoning rule to perform reasoning processing on the network ontology language expression to obtain a target network ontology language expression comprises the following steps: performing reasoning on the network ontology language expression according to the specified necessary paradigm rule to obtain a second sub-ontology item and a target attribute relationship between the target concept represented by the main ontology item and the associated concept represented by the second sub-ontology item; generating the target network ontology language expression according to the network ontology language expression, the second sub-ontology item and the target attribute relationship.

4. The method of claim 3, wherein, The step of generating the target network ontology language expression according to the network ontology language expression, the second sub-ontology item and the target attribute relationship comprises the following steps: merging the network ontology language expression and the second sub-ontology item according to the target attribute relationship to form a second target network ontology language expression; performing redundancy removal processing on the second target network ontology language expression by using the necessary paradigm rule; constructing the target network ontology language expression based on the second target network ontology language expression after the redundancy removal processing.

5. The method of claim 1, wherein, There are multiple network ontology language expressions; the main ontology items and the sub-ontology items of the multiple network ontology language expressions form an ontology item set; and the method further comprises the following steps: specifying a reference ontology item in the ontology item set; traversing the ontology item set by taking the reference ontology item as a starting traversal node and taking the associated relationships between the ontology items as traversal paths; and The step of generating the RF2 file according to the target network ontology language expression is performed only when all the ontology items in the ontology item set are traversed and there is no ontology item that is repeatedly traversed.

6. The method of claim 1, wherein, The RF2 file includes a first sub-file and a second sub-file; the first sub-file of the RF2 file is created by the network ontology language expression; and the second sub-file of the RF2 file is built based on the target network ontology language expression.

7. The method of claim 6, wherein, The method further includes: generating an extended network ontology language expression according to the RF2 file; performing inference processing on the extended network ontology language expression using the specified inference rule to obtain an inference result for the extended network ontology language expression; and adjusting the RF2 file through the inference result.

8. An apparatus for generating an RF2 file, characterized by comprising: The method further includes: receiving a network ontology language expression for defining a target concept; wherein the network ontology language expression includes a main ontology item representing the target concept, a subordinate ontology item for defining the target concept, and a relationship item; the subordinate ontology item is used to represent an associated concept having an associated relationship with the target concept; and the relationship item is used to represent the associated relationship; performing inference processing on the network ontology language expression using a specified inference rule to obtain a target network ontology language expression; mapping the main ontology item, the subordinate ontology item, and the relationship item in the target network ontology language expression to data items in an RF2 file through a preset mapping rule to generate the RF2 file. 9.A computer device, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the method in any one of claims 1 to 7 when executing the computer program. 10.A computer readable storage medium, storing a computer program, and the computer program implementing the method in any one of claims 1 to 7 when executed by a processor.

Images