Business terminology management method, device, computer equipment and storage medium

Abstract

The present disclosure proposes a method, apparatus, computer equipment and storage medium for managing business terms, the method comprising: obtaining business-related texts of a target enterprise; performing information extraction processing on the business-related texts to determine a first business term; performing entity recognition on the business-related texts based on a pre-trained deep learning model to determine a second business term, wherein the first business term and the second business term have different description granularity; identifying entity relationships between different target business terms, wherein the target business term is the first business term or the second business term; and constructing a target knowledge graph based on the entity relationships. By implementing the method of the present disclosure, it is possible to combine information extraction technology and deep learning models to achieve accurate recognition of terms in enterprise business-related texts, clearly and accurately display the association relationship between terms based on the knowledge graph, and effectively improve the management effect of massive terms.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method, apparatus, computer equipment and storage medium for managing business terms. Background Art

[0002] In the process of enterprise knowledge management, business terms usually need to be sorted and classified. However, as the scale of enterprise data expands, traditional manual sorting and classification methods can no longer meet the increasingly complex information needs.

[0003] In the related technologies, the management effect of massive terminology in enterprise business-related texts is poor, and the complex relationship between terms cannot be accurately displayed. Summary of the invention

[0004] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the purpose of the present invention is to propose a business terminology management method, device, computer equipment and storage medium, which can combine information extraction technology and deep learning models to accurately identify terms in enterprise business-related texts, clearly and accurately display the relationship between terms based on knowledge graphs, and effectively improve the management effect of massive terms.

[0006] To achieve the above-mentioned purpose, a method for managing business terms proposed in an embodiment of the first aspect of the present disclosure includes:

[0007] Obtain business-related texts of target enterprises;

[0008] Performing information extraction processing on the business-related text to determine a first business term;

[0009] Performing entity recognition on the business-related text based on a pre-trained deep learning model to determine a second business term, wherein the first business term and the second business term have different description granularities;

[0010] identifying entity relationships between different target business terms, wherein the target business term is the first business term or the second business term;

[0011] Construct a target knowledge graph based on the entity relationships.

[0012] To achieve the above-mentioned purpose, a business term management device proposed in a second aspect of the present disclosure includes:

[0013] An acquisition module is used to acquire business-related texts of target enterprises;

[0014] A determination module, configured to perform information extraction processing on the business-related text to determine a first business term;

[0015] a first recognition module, configured to perform entity recognition on the business-related text based on a pre-trained deep learning model to determine a second business term, wherein the first business term and the second business term have different description granularities;

[0016] a second identification module, configured to identify entity relationships between different target business terms, wherein the target business term is the first business term or the second business term;

[0017] A construction module is used to construct a target knowledge graph based on the entity relationship.

[0018] The computer device proposed in the third aspect of the present disclosure includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the business terminology management method proposed in the first aspect of the present disclosure is implemented.

[0019] The fourth aspect of the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the business terminology management method as provided in the first aspect of the present disclosure.

[0020] The fifth aspect of the present disclosure provides a computer program product. When instructions in the computer program product are executed by a processor, the method for managing business terms as provided in the first aspect of the present disclosure is performed.

[0021] The business term management method, apparatus, computer equipment and storage medium provided by the present disclosure obtain business-related texts of the target enterprise; perform information extraction processing on the business-related texts to determine the first business term; perform entity recognition on the business-related texts based on a pre-trained deep learning model to determine the second business term, wherein the first business term and the second business term have different description granularity; identify the entity relationship between different target business terms, wherein the target business term is the first business term or the second business term; and construct a target knowledge graph based on the entity relationship. Thus, it is possible to combine information extraction technology and deep learning models to achieve accurate recognition of terms in enterprise business-related texts, clearly and accurately display the association relationship between terms based on the knowledge graph, and effectively improve the management effect of massive terms.

[0022] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 It is a flowchart of a method for managing business terms proposed in an embodiment of the present disclosure;

[0025] Figure 2 is a flowchart of a business term management method proposed in another embodiment of the present disclosure;

[0026] Figure 3 It is a flowchart of an innovative method for automatic classification and management of knowledge terms for enterprise business optimization proposed in the present disclosure;

[0027] Figure 4 It is a structural diagram of a business term management device proposed in an embodiment of the present disclosure;

[0028] Figure 5 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0029] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present disclosure, and are not to be construed as limitations of the present disclosure. On the contrary, the embodiments of the present disclosure include all changes, modifications, and equivalents that fall within the spirit and connotation of the appended claims.

[0030] Figure 1 It is a flowchart of a method for managing business terms proposed in an embodiment of the present disclosure.

[0031] It should be noted that the executor of the business terminology management method of this embodiment is a business terminology management device, which can be implemented by software and / or hardware. The device can be configured in a computer device, and the computer device can include but is not limited to a terminal, a server, etc. For example, the terminal can be a mobile phone, a handheld computer, etc.

[0032] like Figure 1 As shown, the management method of the business term includes:

[0033] S101: Obtain business-related text of the target enterprise.

[0034] The target enterprise may refer to an enterprise to be managed with business terms in the embodiment of the present disclosure. The type and number of enterprises are not limited in the embodiment of the present disclosure.

[0035] The business-related texts may refer to the relevant texts generated by the target enterprise during the business processing, for example, internal documents, emails, reports, databases, etc. of the enterprise, without limitation.

[0036] In the embodiment of the present disclosure, when business-related texts of a target enterprise are acquired, reliable data support can be provided for subsequent identification and determination of business terms.

[0037] S102: performing information extraction processing on the business-related text to determine a first business term.

[0038] The first business term may refer to a business term determined based on the information extraction technology in the embodiment of the present disclosure. For example, the first business term may be used to indicate a term related to a major category of business processes.

[0039] That is, in the embodiment of the present disclosure, after obtaining the business-related text of the target enterprise, information extraction processing can be performed on the business-related text to determine the first business term, thereby achieving preliminary recognition of the term.

[0040] S103: Perform entity recognition on the business-related text based on the pre-trained deep learning model to determine a second business term, wherein the first business term and the second business term have different description granularities.

[0041] The deep learning model may be, for example, BERT or other pre-trained models, without limitation.

[0042] The second business term may refer to a business term identified based on a deep learning model in the embodiment of the present disclosure. The second business term may be used to indicate a term related to a subclass of a business process relative to the first business term.

[0043] The description granularity can be used to indicate the description level of the business term for the business-related entity. For example, when the first business term is "sales performance", the corresponding second business term can be "monthly sales", "annual sales", etc., without limitation.

[0044] In the embodiment of the present disclosure, when entity recognition is performed on business-related text based on a pre-trained deep learning model to determine the second business term, accurate recognition of the term can be achieved in combination with text context understanding.

[0045] S104: Identify entity relationships between different target business terms, where the target business term is a first business term or a second business term.

[0046] The entity relationship may be used to indicate the relationship between terms, for example, it may refer to "belong to", "associated with", etc., without limitation.

[0047] In the disclosed embodiment, when identifying entity relationships between different target business terms, reliable reference information can be provided for the subsequent construction of a target indication graph.

[0048] S105: Build the target knowledge graph based on entity relationships.

[0049] The target knowledge graph may refer to a knowledge graph constructed based on entity relationships and used to indicate association information between different terms. The type of the target knowledge graph is not limited in the embodiments of the present disclosure.

[0050] Optionally, in some embodiments, new business-related texts may be obtained, and the target knowledge graph may be updated based on the new business-related texts, thereby achieving dynamic updating of the target knowledge graph to ensure the applicability of the obtained target knowledge graph.

[0051] It is understandable that in the process of enterprise development, new business-related texts may appear, and new terminology information may exist in the new business-related texts. Therefore, new business-related texts can be obtained in the embodiments of the present disclosure; the target knowledge graph is updated based on the new business-related texts to ensure that the obtained target knowledge graph can be applicable to changing business scenarios.

[0052] In this embodiment, the business-related text of the target enterprise is obtained; information extraction is performed on the business-related text to determine the first business term; entity recognition is performed on the business-related text based on a pre-trained deep learning model to determine the second business term, wherein the description granularity of the first business term and the second business term is different; the entity relationship between different target business terms is identified, wherein the target business term is the first business term or the second business term; and a target knowledge graph is constructed based on the entity relationship. In this way, the accurate recognition of terms in the business-related text of the enterprise can be achieved by combining information extraction technology and deep learning models, and the association relationship between terms can be clearly and accurately displayed based on the knowledge graph, effectively improving the management effect of massive terms.

[0053] Figure 2 It is a flowchart of a method for managing business terms proposed in another embodiment of the present disclosure.

[0054] like Figure 2 As shown, the management method of the business term includes:

[0055] S201: Obtain business-related text of the target enterprise.

[0056] S202: performing information extraction processing on the business-related text to determine a first business term.

[0057] S203: Perform entity recognition on the business-related text based on the pre-trained deep learning model to determine a second business term, wherein the first business term and the second business term have different description granularities.

[0058] The description of S201 - S203 can be specifically referred to the above embodiment, which will not be repeated here.

[0059] S204: pre-processing the target business term, wherein the target business term is the first business term or the second business term.

[0060] It is understandable that due to technical problems, the target business terms identified in the embodiments of the present disclosure may contain errors. Therefore, in order to avoid affecting the subsequent terminology management process, they can be preprocessed to ensure the practicability of the obtained target business terms in the subsequent management process.

[0061] For example, in the embodiments of the present disclosure, when preprocessing the target business terms, it may include but is not limited to: removing noise, unifying upper and lower cases, unifying language types, processing missing values, etc., and there is no limitation to this.

[0062] Optionally, in some embodiments, when preprocessing the target business terms, the following steps may be performed: determining the semantic information corresponding to each target business term; determining the semantic similarity between different semantic information; and normalizing different target business terms when the semantic similarity is greater than or equal to a first preset threshold. In this way, business terms with the same meaning can be effectively avoided from appearing simultaneously in the knowledge graph, thereby effectively improving the standardization of term management.

[0063] The semantic information may refer to the definition or explanation text corresponding to the target business term.

[0064] Among them, semantic similarity can be used to indicate the similarity between different semantics.

[0065] The first preset threshold refers to the threshold configured for determining whether different target business terms are synonyms in the embodiment of the present disclosure. For example, the first preset threshold can be set to 90%, or can be flexibly configured to other values ​​according to the application scenario, without limitation.

[0066] It is understandable that different terms may be used to describe the same entity in different scenarios. If they are used directly to construct a knowledge graph, it may result in more redundant information in the knowledge graph, and may increase the difficulty of user retrieval and mislead the user's understanding of the terms. Therefore, in the embodiment of the present disclosure, the semantic information corresponding to each target business term can be determined; the semantic similarity between different semantic information can be determined; when the semantic similarity is greater than or equal to a first preset threshold, the different target business terms are normalized.

[0067] Optionally, in some embodiments, when the semantic similarity is less than a first preset threshold and greater than a second preset threshold, different target business terms are associated, wherein the second preset threshold is less than the first preset threshold. Thus, accurate identification of related terms and associated processing can be achieved based on the second preset threshold.

[0068] The second preset threshold refers to a threshold pre-configured in the embodiment of the present disclosure for determining whether different business terms are related. The specific value of the second preset threshold can be flexibly adjusted according to the application scenario, and there is no limitation on this.

[0069] Optionally, in some embodiments, the target business terms and semantic information may be associated in the target knowledge graph, thereby effectively improving the clarity of the target knowledge graph in indicating the term information.

[0070] That is, in the embodiment of the present disclosure, after the target business term is obtained, the target business term may be preprocessed to effectively improve the reliability of the obtained target business term.

[0071] S205: Determine classification results of the preprocessed multiple target business terms based on the pre-trained term classification model.

[0072] The term classification model refers to a model pre-trained in the embodiments of the present disclosure for classifying terms.

[0073] The classification result may be used to indicate category information corresponding to the target business term.

[0074] In the embodiment of the present disclosure, when determining the classification results of multiple target business terms after preprocessing based on the pre-trained term classification model, the terms can be classified using a clustering algorithm (K-means, DBSCAN) or supervised learning (SVM, random forest).

[0075] Optionally, in some embodiments, the classification results may be verified to obtain verification results, and the term classification model may be optimized and adjusted according to the verification results. Thus, iterative optimization of the term classification model may be achieved to ensure that the term classification model is suitable for personalized application scenarios.

[0076] The verification result can be used to indicate whether there is an error in the classification result.

[0077] That is, in the embodiment of the present disclosure, the classification results of multiple target business terms after preprocessing can be determined based on the pre-trained term classification model to effectively improve the efficiency of the classification processing, and the obtained classification results can accurately indicate the hierarchical information of the multiple target business terms.

[0078] S206: Identify entity relationships between different target business terms based on the classification results.

[0079] That is, in the embodiment of the present disclosure, after the target business terms are identified, the target business terms can be preprocessed; the classification results of the preprocessed target business terms can be determined based on the pretrained term classification model; and the entity relationships between different target business terms can be identified in combination with the classification results. Thus, the clarity and accuracy of the indication of the obtained entity relationships can be guaranteed in combination with the classification results.

[0080] S207: Build a target knowledge graph based on entity relationships.

[0081] The description of S207 can be specifically referred to the above embodiment, which will not be repeated here.

[0082] In this embodiment, the target business terms are preprocessed; the classification results of the preprocessed target business terms are determined based on the pretrained term classification model; and the entity relationships between different target business terms are identified in combination with the classification results. Thus, the clarity and accuracy of the indication of the obtained entity relationships can be guaranteed in combination with the classification results.

[0083] For example, in combination with the above embodiments, Figure 3 As shown, Figure 3 The following is a flow chart of an innovative method for automatic classification and management of knowledge terms for enterprise business optimization proposed in the present disclosure, which includes:

[0084] ①Data collection and preprocessing:

[0085] Identify data sources, including internal corporate documents, emails, reports, databases, etc.

[0086] Information Extraction: Use information extraction techniques to extract key terms from text, including named entity recognition (NER).

[0087] Data cleaning: remove noise, standardize terminology (such as capitalization, synonyms), and handle missing values;

[0088] ②Term identification and definition

[0089] Deep learning models: Apply BERT or other pre-trained models for term recognition and use contextual understanding to improve accuracy.

[0090] Terminology definition acquisition: capture the definition and explanation of corresponding terms from authoritative sources or internal corporate materials;

[0091] ③Automatic classification and clustering:

[0092] Model training: Classify terms using clustering algorithms (K-means, DBSCAN) or supervised learning (SVM, Random Forest).

[0093] Feedback loop: allows humans to review and adjust classification results to iteratively optimize the model;

[0094] ④Knowledge graph construction

[0095] Entity and relationship extraction: Identify the relationships between terms, such as "belongs to", "associated with", etc., and build a term relationship network.

[0096] Graph database storage: Use graph databases such as Neo4j or JanusGraph to store knowledge graphs for easy query and reasoning;

[0097] ⑤Search and recommendation system

[0098] Intelligent query engine: Develop a search engine that supports fuzzy queries and synonym queries.

[0099] Personalized recommendation: Recommend relevant terms and knowledge resources based on user behavior and contextual information;

[0100] ⑥System integration and interface design

[0101] API interface: Provide API interface for integration with other enterprise systems (such as CRM, ERP).

[0102] User interface: Design a friendly and intuitive interface to facilitate users to browse, search and edit terminology information.

[0103] ⑦Continuous learning and optimization

[0104] Model updating: Implement online learning mechanisms to continuously track new data and automatically or semi-automatically update the model.

[0105] Performance monitoring: Set performance indicators, regularly evaluate system performance, and make adjustments based on feedback.

[0106] In summary, the core technical points of the technical solution disclosed in this disclosure include:

[0107] 1. Intelligent recognition and extraction: Using deep learning models, we can perform high-precision recognition and extraction of professional terms in various corporate documents and reports, overcoming the limitations of traditional methods in complex text environments.

[0108] 2. Automatic classification algorithm: Combining word vector representation and clustering algorithm, it automatically classifies terms according to their semantic similarity and business context to form a hierarchical terminology system, enhancing the convenience of term search and understanding.

[0109] 3. Knowledge graph construction: Use graph neural network technology to associate classified terms into a knowledge graph to visualize and reason about the relationships between terms, and support complex queries and knowledge discovery.

[0110] 4. Continuous learning and optimization: Introducing online learning mechanisms enables the system to continuously optimize classification models and knowledge graphs based on new data feedback to ensure the timeliness and accuracy of the term base.

[0111] Innovations include:

[0112] 1. Realize the automatic conversion from text to structured knowledge, greatly improving the efficiency and quality of terminology management.

[0113] 2. Accurately adapt to the business language environment of a specific enterprise through customized training of deep learning models.

[0114] 3. Build a dynamically updated knowledge graph to provide enterprises with intelligent decision-making assistance and knowledge services.

[0115] 4. Support multi-dimensional query and intelligent recommendation to promote internal knowledge sharing and innovation within the enterprise.

[0116] Figure 4 It is a structural diagram of a business term management device proposed in an embodiment of the present disclosure.

[0117] like Figure 4 As shown, the business term management device 40 includes:

[0118] An acquisition module 401 is used to acquire business-related texts of a target enterprise;

[0119] A determination module 402 is used to perform information extraction processing on the business-related text to determine a first business term;

[0120] A first recognition module 403 is used to perform entity recognition on the business-related text based on a pre-trained deep learning model to determine a second business term, wherein the first business term and the second business term have different description granularities;

[0121] A second identification module 404, configured to identify entity relationships between different target business terms, wherein the target business term is a first business term or a second business term;

[0122] Construction module 405 is used to construct a target knowledge graph based on entity relationships.

[0123] It should be noted that the above explanation of the business term management method is also applicable to the business term management device of this embodiment, and will not be repeated here.

[0124] In this embodiment, the business-related text of the target enterprise is obtained; information extraction is performed on the business-related text to determine the first business term; entity recognition is performed on the business-related text based on a pre-trained deep learning model to determine the second business term, wherein the description granularity of the first business term and the second business term is different; the entity relationship between different target business terms is identified, wherein the target business term is the first business term or the second business term; and a target knowledge graph is constructed based on the entity relationship. In this way, the accurate recognition of terms in the business-related text of the enterprise can be achieved by combining information extraction technology and deep learning models, and the association relationship between terms can be clearly and accurately displayed based on the knowledge graph, effectively improving the management effect of massive terms.

[0125] Figure 5 A block diagram of an exemplary computer device suitable for implementing embodiments of the present disclosure is shown. Figure 5 The computer device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0126] like Figure 5 As shown, the computer device 12 is in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0127] The bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.

[0128] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0129] The memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 Not shown, often called a "hard drive").

[0130] although Figure 5 Not shown, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a compact disc read only memory (Compact Disc Read Only Memory; hereinafter referred to as: CD-ROM), a digital versatile disc read only memory (Digital Video Disc Read Only Memory; hereinafter referred to as: DVD-ROM) or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.

[0131] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in the memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described in the present disclosure.

[0132] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a human body to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via an input / output (I / O) interface 22. In addition, the computer device 12 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0133] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the business term management method mentioned in the above embodiment.

[0134] In order to implement the above embodiments, the present disclosure further proposes a non-transitory computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the business term management method proposed in the above embodiments of the present disclosure is implemented.

[0135] In order to implement the above embodiments, the present disclosure further proposes a computer program product. When an instruction processor in the computer program product is executed, the business term management method proposed in the above embodiments of the present disclosure is executed.

[0136] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0137] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

[0138] It should be noted that, in the description of the present disclosure, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present disclosure, unless otherwise specified, the meaning of "plurality" is two or more.

[0139] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present disclosure includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present disclosure belong.

[0140] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0141] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0142] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0143] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0144] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0145] Although the embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present disclosure. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present disclosure.

Claims

1. A method for managing business terms, characterized in that: include: Obtain business-related texts of target enterprises; Performing information extraction processing on the business-related text to determine a first business term; Performing entity recognition on the business-related text based on a pre-trained deep learning model to determine a second business term, wherein the first business term and the second business term have different description granularities; identifying entity relationships between different target business terms, wherein the target business term is the first business term or the second business term; Construct a target knowledge graph based on the entity relationships.

2. The method according to claim 1, characterized in that The identifying entity relationships between different target business terms includes: Preprocessing the target business term; Determining classification results of the plurality of target business terms after preprocessing based on a pretrained term classification model; The entity relationships between different target business terms are identified in combination with the classification results.

3. The method according to claim 2, characterized in that The preprocessing of the target business term includes: Determining semantic information corresponding to each of the target business terms; Determining semantic similarities between different semantic information; When the semantic similarity is greater than or equal to a first preset threshold, the different target business terms are normalized.

4. The method according to claim 3, characterized in that The method further comprises: When the semantic similarity is less than the first preset threshold and greater than a second preset threshold, association processing is performed on the different target business terms, wherein the second preset threshold is less than the first preset threshold.

5. The method according to claim 3, characterized in that The method further comprises: The target business term and the semantic information are associated in the target knowledge graph.

6. The method according to claim 2, characterized in that The method further comprises: Performing verification processing on the classification result to obtain a verification result; The term classification model is optimized and adjusted according to the verification result.

7. The method according to claim 1, characterized in that The method further comprises: Get new business-related texts; The target knowledge graph is updated based on the new business-related text.

8. A business term management device, characterized in that: include: An acquisition module is used to acquire business-related texts of target enterprises; A determination module, configured to perform information extraction processing on the business-related text to determine a first business term; a first recognition module, configured to perform entity recognition on the business-related text based on a pre-trained deep learning model to determine a second business term, wherein the first business term and the second business term have different description granularities; a second identification module, configured to identify entity relationships between different target business terms, wherein the target business term is the first business term or the second business term; A construction module is used to construct a target knowledge graph based on the entity relationship.

9. A computer device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: in, The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

Images