Data processing method, system and equipment and storage medium

Abstract

The invention provides a data processing method, system and device and a storage medium, and relates to the technical field of computer application. The data processing method comprises the following steps: collecting initial information of a preset field from a plurality of data sources; preprocessing the initial information to obtain standardized data; analyzing the standardized data to obtain analysis information, wherein the analysis information comprises keywords, themes, entity information and entity associated information; and generating the knowledge graph according to the analysis information. By the adoption of the data processing method, the analysis information is obtained by analyzing the initial information of the data sources, the knowledge graph is generated according to the analysis information, and therefore efficient graph traversal and query functions can be provided based on the knowledge graph.

Description

Technical Field

[0001] The present invention relates to the field of computer application technology, and more specifically, to a data processing method, system, device and storage medium. Background Art

[0002] With the rapid development of digital transformation in the financial industry, the amount of information such as risk control policies, information, rules and regulations has increased dramatically and is updated frequently. However, existing risk control systems generally face problems such as information islands, low data processing efficiency, and delayed early warning responses, making it difficult to meet the needs of the rapidly changing financial environment. Therefore, there is an urgent need for a technical solution that can share risk control information in real time and improve communication efficiency to solve problems such as poor information sharing between upstream and downstream risk control links, inconsistent risk control policy versions, and untimely information updates. Summary of the invention

[0003] In order to solve the problems existing in the above-mentioned prior art or at least part of the problems, the embodiments of the present invention provide a data processing method, system, storage medium, device and computer program product, which obtains parsed information by parsing the initial information of multiple data sources, and generates a knowledge graph based on the parsed information, thereby providing efficient graph traversal and query functions based on the knowledge graph.

[0004] According to the first aspect of the present invention, an embodiment of the present invention provides a data processing method, which includes: collecting initial information of a preset field from multiple data sources; preprocessing the initial information to obtain standardized data; parsing the standardized data to obtain parsed information, the parsed information including: keywords, topics, entity information, entity association information; generating a knowledge graph based on the parsed information.

[0005] According to the above-mentioned embodiment of the present invention, by collecting initial information from multiple data sources and generating a knowledge graph based on the parsed information of the initial information, the knowledge graph can provide efficient graph traversal and query functions, thereby quickly finding the relationships and paths between nodes.

[0006] In some embodiments of the present invention, the data processing method further includes: generating a knowledge list of the initial information based on the parsed information; generating classification labels of the knowledge list based on the parsed information, and generating corresponding classification indexes based on the classification labels.

[0007] According to the above-mentioned embodiment of the present invention, by generating a corresponding knowledge list for the initial information, and generating a classification label and a classification index of the knowledge list according to the parsed information, it is possible to facilitate quick retrieval by the user.

[0008] In some implementations of the present invention, the data processing method further includes: obtaining a user behavior log; and obtaining recommended knowledge items from a knowledge list according to the user behavior log.

[0009] According to the above-mentioned embodiments of the present invention, personalized knowledge recommendations are provided based on user behaviors, thereby improving knowledge utilization efficiency.

[0010] In some embodiments of the present invention, the data processing method further includes: obtaining potential risk information by parsing the knowledge list, and issuing warning information according to the risk information.

[0011] According to the above-mentioned embodiments of the present invention, by analyzing and timely acquiring potential risk information and pushing early warning information, it is possible to help users quickly respond to and handle risk events.

[0012] According to the second aspect of the present invention, an embodiment of the present invention provides a data processing system, which includes: an initial information acquisition module, used to collect initial information of a preset field from multiple data sources; a data preprocessing module, used to preprocess the initial information to obtain standardized data; a data parsing module, used to parse the standardized data to obtain parsed information, and the parsed information includes: keywords, topics, entity information, entity association information; a knowledge graph generation module, used to generate a knowledge graph based on the parsed information.

[0013] According to the above-mentioned embodiment of the present invention, by collecting initial information from multiple data sources and generating a knowledge graph based on the parsed information of the initial information, the knowledge graph can provide efficient graph traversal and query functions, thereby quickly finding the relationships and paths between nodes.

[0014] In some embodiments of the present invention, the data processing system also includes a knowledge list generation module for performing the following operations: generating a knowledge list of the initial information based on the parsed information; generating classification labels for the knowledge list based on the parsed information, and generating corresponding classification indexes based on the classification labels.

[0015] According to the above-mentioned embodiment of the present invention, by generating a corresponding knowledge list for the initial information, and generating a classification label and a classification index of the knowledge list according to the parsed information, it is possible to facilitate quick retrieval by the user.

[0016] In some embodiments of the present invention, the data processing system further includes an information recommendation module for obtaining a user behavior log and obtaining recommended knowledge items from a knowledge list according to the user behavior log.

[0017] According to the above-mentioned embodiments of the present invention, personalized knowledge recommendations are provided based on user behaviors, thereby improving knowledge utilization efficiency.

[0018] In some embodiments of the present invention, the data processing system further includes an early warning module for parsing the knowledge list to obtain potential risk information and issuing early warning information according to the risk information.

[0019] According to the above-mentioned embodiments of the present invention, by analyzing and timely acquiring potential risk information and pushing early warning information, it is possible to help users quickly respond to and handle risk events.

[0020] According to the third aspect of the present invention, an embodiment of the present invention provides a computer-readable storage medium having computer-readable instructions stored thereon. When the computer-readable instructions are executed by a processor, the computer performs the following operations: the operations include the steps included in the data processing method described in any one of the above embodiments.

[0021] According to the fourth aspect of the present invention, an embodiment of the present invention provides a computer device including a memory and a processor, wherein the memory is used to store one or more computer-readable instructions, wherein the one or more computer-readable instructions, when executed by the processor, can implement the data processing method described in any one of the above embodiments.

[0022] According to a fifth aspect of the present invention, an embodiment of the present invention provides a computer program product including a computer program, and when the computer program is executed by a processor, the data processing method described in any one of the above embodiments is implemented.

[0023] From the above, it can be seen that the data processing method, system, storage medium, device and computer program product provided by the embodiments of the present invention collect initial information from multiple data sources and generate a knowledge graph based on the parsed information of the initial information. The knowledge graph can provide efficient graph traversal and query functions, thereby quickly finding the relationships and paths between nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a flow chart of a data processing method according to Embodiment 1 of the present invention;

[0025] Figure 2 is a schematic diagram of the architecture of a risk control knowledge base system for executing the data processing method of embodiment 1 according to embodiment 2 of the present invention;

[0026] Figure 3 Schematic diagram of the architecture of a data processing system according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0027] The various aspects of the present invention are described in detail below in conjunction with the accompanying drawings and specific embodiments. Among them, well-known modules, units and their connections, links, communications or operations are not shown or described in detail. In addition, the described features, architectures or functions can be combined in any way in one or more embodiments. It should be understood by those skilled in the art that the various embodiments described below are only used for illustration and are not intended to limit the scope of protection of the present invention. It can also be easily understood that the modules or units or processing methods in each embodiment described herein and shown in the accompanying drawings can be combined and designed in various different configurations.

[0028] The following is a brief description of the terms used in this article.

[0029] RESTful API: Representational State Transfer API, representational state transfer application programming interface.

[0030] Blockchain technology: a decentralized distributed ledger technology with the characteristics of being tamper-proof, secure and transparent.

[0031] ETL (Extract, Transform, Load): Extract, Transform, Load, a process used to extract data from different data sources into a unified data storage, clean, transform and integrate it, and finally load it into the target database or data warehouse.

[0032] NLP technology: Natural Language Processing, natural language processing technology, is used to understand and analyze the structure and meaning of human language, so as to realize automatic processing of text, such as text classification, sentiment analysis, named entity recognition, relationship extraction, etc.

[0033] Graph database: A database specifically designed to store and query graph-structured data.

[0034] BERT: Bidirectional Encoder Representations from Transformers, a pre-trained language model based on the Transformer architecture.

[0035] GPT: Generative Pretrained Transformer, a pre-trained language model based on the Transformer architecture.

[0036] NLTK: Natural Language Toolkit, a Python library for natural language processing (NLP), which provides a rich corpus and tools to facilitate developers to perform text processing, classification, tagging and other operations.

[0037] [Example 1]

[0038] Figure 1 It is a flowchart of a data processing method according to Embodiment 1 of the present invention.

[0039] like Figure 1 As shown, in Embodiment 1 of the present invention, the data processing method may include: step S11, step S12, step S13 and step S14, and the above steps are described in detail below.

[0040] In step S11, initial information in a preset field is collected from multiple data sources. In some implementations, the initial information is initial information in the field of risk control, that is, text data related to risk control, such as risk policies, case reports, news reports, etc.

[0041] In this embodiment, a RESTful API interface is used to establish a connection with authoritative data sources such as financial regulatory agencies, industry associations, and financial institutions; and web crawler technology is deployed to capture risk control related information from public websites, forums, social media, and other channels. In this way, risk control policies, information, rules and regulations, and other information can be obtained from multiple data sources.

[0042] In an exemplary implementation, the requests library of the Python programming language is used to regularly obtain the latest financial policies, industry reports and other information from authoritative data sources such as financial regulatory agencies and industry associations through the RESTful API interface; web crawler frameworks such as Scrapy are deployed to capture information related to financial risks from public websites, forums, social media and other channels to ensure the comprehensiveness and accuracy of the data; and the collected initial data is stored and verified through blockchain technology to ensure the reliability and immutability of the data.

[0043] In step S12, the initial information is preprocessed to obtain standardized data.

[0044] In some embodiments, the preprocessing operation of the initial information includes: (1) preliminary screening of the original data to remove obviously erroneous or duplicate information; (2) data cleaning, deep cleaning of the collected data, including but not limited to: removing invalid characters, formatting dates, unifying units, etc.; (3) standardization processing, that is, converting the cleaned data into a unified format.

[0045] In an optional embodiment, an ETL process is used to clean, deduplicate, classify and standardize the data to obtain standard data for subsequent processing. Exemplarily, the Pandas library is used for data preprocessing operations, and regular expressions are used for text cleaning.

[0046] In step S13, the standardized data is parsed to obtain parsed information, which includes: keywords, topics, entity information, and entity association information.

[0047] In some embodiments, NLP techniques, such as word segmentation, part-of-speech tagging, named entity recognition, etc., are used to deeply parse the text to extract key information (such as policy name, release date, main content, etc.). Among them, the NLTK library is used for preliminary natural language processing. Further, pre-trained language models such as BERT and GPT are used to perform deep semantic analysis on the pre-processed text to extract keywords, topics, named entities (such as risk type, company name, person, etc.) and the relationship between entities.

[0048] In step S14, a knowledge graph is generated based on the parsed information. Furthermore, the information in the knowledge graph is intelligently analyzed by combining NLP technology, such as risk prediction and association analysis, so as to realize subsequent recorded knowledge query, knowledge recommendation, and risk warning.

[0049] In some embodiments, based on the analysis results, a risk control knowledge graph is constructed using a graph database such as Neo4j to achieve knowledge association and visualization. The extracted entities and relationships are stored in the graph database in the form of a graph structure (knowledge graph), each entity corresponds to a node (for example, risk type, company name, person, etc.), and the relationship represents the connection between entities, and each relationship corresponds to an edge (for example, "a company faces a certain risk", "a certain risk leads to a certain consequence", etc.). A knowledge graph specifically used in the field of risk control can be constructed using NLP and graph database technology, which contains keywords, topics, and relationships between entities related to risk control. The risk control knowledge graph can provide strong support for risk control decisions and help decision makers better understand and respond to risks; the graph database provides efficient graph traversal and query functions, which can quickly find the relationships and paths between nodes.

[0050] In a further embodiment, knowledge retrieval and analysis is performed through a graph database query language, such as Cypher. Using the query function of the graph database, information and relationships related to a specific risk or entity can be quickly found.

[0051] In a further implementation, new data is continuously collected, information is extracted using NLP technology, and the knowledge graph is updated and enriched. For example, the relationships between entities such as risk type, company name, person, "a company faces a certain risk", "a certain risk leads to a certain consequence", etc. are obtained. Optionally, the graph can also include the attributes of the entity (such as the level of risk, time of occurrence, etc.).

[0052] By adopting the above data processing method of Example 1 of the present invention, initial information from multiple data sources is collected, and a knowledge graph is generated based on the parsed information of the initial information. The knowledge graph intuitively displays the knowledge and relationships in the field of risk control in the form of a graph structure, and new entities and relationships can be continuously added to enrich the content of the graph. At the same time, the knowledge graph can provide efficient graph traversal and query functions, so as to quickly find the relationships and paths between nodes.

[0053] In some embodiments, the data processing method further includes: generating a knowledge list of the initial information based on the parsed information; generating a classification label for the knowledge list based on the parsed information, and generating a corresponding classification index based on the classification label. Exemplarily, a structured risk control knowledge list is automatically generated based on the NLP analysis results, and the risk control knowledge list includes policy interpretations, risk cases, prevention and control strategies, etc., and is classified and indexed through a label system to facilitate quick retrieval by users. Furthermore, the parsed risk control information (including but not limited to policies, information, rules and regulations, etc.) is stored in a knowledge base; classified management is performed according to attributes such as the type and importance of the risk control information; and keyword search, category browsing and other functions are implemented based on a user-friendly query interface. Furthermore, the newly added or updated risk control information is published to relevant users through a system interface or an API interface.

[0054] In some embodiments, the data processing method further includes: obtaining a user's query request; obtaining a target knowledge item from a knowledge list according to the query request. In an optional embodiment, a search engine technology such as Elasticsearch is used to construct a variety of query methods such as full-text search, keyword search, fuzzy matching, and semantic search, thereby realizing intelligent search of knowledge. Furthermore, the data processing method further includes: intelligently combining relevant risk control knowledge items according to the user's query requirements, generating customized risk control reports or suggestions, and exporting them in PDF, Excel, and other formats to facilitate further analysis and decision-making by users.

[0055] In some embodiments, the data processing method further includes: obtaining a user behavior log; and obtaining recommended knowledge items from a knowledge list according to the user behavior log. In an optional embodiment, personalized knowledge recommendation is achieved by combining the user behavior log and using collaborative filtering, deep learning and other algorithms. Thus, relevant risk control knowledge items and reports can be intelligently recommended based on user interests and historical query records.

[0056] In some embodiments, the data processing method further includes: obtaining potential risk information by parsing the knowledge list, and issuing early warning information based on the risk information. In an optional embodiment, advanced machine learning algorithms (such as time series analysis, cluster analysis, anomaly detection, etc.) and artificial intelligence large language models (AI-LLM) are used to deeply mine historical data and real-time information to identify potential risk trends and abnormal patterns. For example, by introducing a specially trained artificial intelligence large language model, the text information is deeply understood and analyzed to identify possible hidden risk points, such as policy changes, market trend changes, negative public opinion, etc. As a result, the artificial intelligence large language model can process complex semantics and understand the context, thereby providing a more accurate risk assessment.

[0057] In a further implementation, the data processing method also includes: by setting a scheduled task or monitoring mechanism to detect changes in data sources in real time, ensuring timely updates of risk control information and early warning notifications; using machine learning algorithms such as time series analysis, cluster analysis, and anomaly detection to conduct in-depth mining of historical data and real-time information; obtaining set risk thresholds and early warning rules, triggering early warning mechanisms when abnormal behaviors or risk events are detected, and implementing real-time push of early warning information through message queue technologies such as Kafka and RabbitMQ. Optionally, according to business needs, combined with the output of the artificial intelligence large language model, the risk thresholds and early warning rules are dynamically adjusted to ensure the sensitivity and accuracy of the early warning mechanism.

[0058] In an optional implementation, when abnormal behavior, risk events, or potential risks identified by the artificial intelligence language model are monitored, the early warning mechanism is triggered, and early warning information is sent to relevant personnel through multiple channels such as SMS, email, and APP push. Among them, the early warning information includes but is not limited to at least one or more of the following: detailed risk analysis report, possible risk points, risk level, risk summary, and response suggestions. This can help users quickly respond to and handle risk events.

[0059] [Example 2]

[0060] Figure 2 2 is a schematic diagram of the architecture of a risk control knowledge base system for executing the data processing method of Example 1 according to Example 2 of the present invention.

[0061] like Figure 2 As shown, in embodiment 2 of the present invention, the risk control knowledge base system includes: a business application layer, a data service layer, and an infrastructure layer.

[0062] The business application layer includes basic information, user interface, and system support. Among them, technical information includes unit information and personnel information; the user interface includes search engine, personalized recommendation, early warning notification, and knowledge release function modules. Users can query information and receive early warning information through the Web interface; system support includes knowledge management, classification management, role authority management, data authority management, and page authority management.

[0063] The data service layer includes data collection, data processing, and data storage. Data collection is to obtain initial data from multiple data sources through API interfaces and crawler technology; data processing includes ETL processes, data cleaning and standardization, NLP analysis and other processing steps; data storage includes the storage of structured risk control knowledge items in relational databases and graph databases.

[0064] The infrastructure layer includes server resources and data security support.

[0065] The risk control knowledge base system of Example 2 of the present invention is used to execute the data processing method of Example 1. By integrating multiple advanced technologies such as API interface, crawler technology, NLP, machine learning, blockchain, graph database, etc., it realizes the automatic collection, intelligent analysis, structured storage and real-time warning of risk control information, which significantly improves the intelligence level and practicality of the risk control knowledge base system. More specifically, (1) Real-time sharing: Through an efficient data collection and update mechanism, the real-time and accuracy of risk control information is ensured, and information sharing and collaboration among various risk control links are achieved; (2) Efficient communication: Through a unified knowledge base system and intelligent query function, communication costs are reduced and communication efficiency is improved; (3) Intelligent recommendation: Based on user behavior logs and interest preferences, combined with artificial intelligence algorithms, personalized risk control knowledge recommendations are provided to improve knowledge utilization efficiency; (4) Large language model risk identification and deep understanding: By introducing a specially trained artificial intelligence large language model, deep understanding and analysis of text information is carried out, which can identify potential risk points in complex semantics and contexts, and improve the accuracy and comprehensiveness of risk identification; (5) Dynamic warning: Combined with the output of the artificial intelligence large language model, the system can dynamically adjust the warning rules, timely detect abnormal behaviors, risk events and potential risks, and push warning information to help users quickly respond to and handle risk events; (6) Visual display: Combined with NLP and graph databases, it provides intuitive risk visualization functions to help users better understand risk distribution, trends and impacts, and provide strong support for decision-making.

[0066] [Example 3]

[0067] Figure 3 Schematic diagram of the architecture of a data processing system according to Embodiment 3 of the present invention.

[0068] like Figure 3 As shown, the data processing system includes: an initial information acquisition module 310, a data preprocessing module 320, a data analysis module 330, a knowledge graph generation module 340, a knowledge list generation module 350, an information recommendation module 360, an early warning module 370, and an information query module 380.

[0069] The initial information acquisition module 310 is used to collect initial information in a preset field from multiple data sources. In some implementations, the initial information is initial information in the field of risk control, that is, text data related to risk control, such as risk policies, case reports, news reports, etc.

[0070] In this embodiment, a RESTful API interface is used to establish a connection with authoritative data sources such as financial regulatory agencies, industry associations, and financial institutions; and web crawler technology is deployed to capture risk control related information from public websites, forums, social media, and other channels. In this way, risk control policies, information, rules and regulations, and other information can be obtained from multiple data sources.

[0071] The data preprocessing module 320 is used to preprocess the initial information to obtain standardized data.

[0072] In some embodiments, the preprocessing operation of the initial information includes: (1) preliminary screening of the original data to remove obviously erroneous or duplicate information; (2) data cleaning, deep cleaning of the collected data, including but not limited to: removing invalid characters, formatting dates, unifying units, etc.; (3) standardization processing, that is, converting the cleaned data into a unified format.

[0073] In an optional embodiment, an ETL process is used to clean, deduplicate, classify and standardize the data to obtain standard data for subsequent processing. Exemplarily, the Pandas library is used for data preprocessing operations, and regular expressions are used for text cleaning.

[0074] The data parsing module 330 is used to parse the standardized data to obtain parsed information, where the parsed information includes: keywords, topics, entity information, and entity association information.

[0075] In some embodiments, NLP techniques, such as word segmentation, part-of-speech tagging, named entity recognition, etc., are used to deeply parse the text to extract key information (such as policy name, release date, main content, etc.). Among them, the NLTK library is used for preliminary natural language processing. Further, pre-trained language models such as BERT and GPT are used to perform deep semantic analysis on the pre-processed text to extract keywords, topics, named entities (such as risk type, company name, person, etc.) and the relationship between entities.

[0076] The knowledge graph generation module 340 is used to generate a knowledge graph based on the parsed information.

[0077] In some embodiments, based on the analysis results, a risk control knowledge graph is constructed using a graph database such as Neo4j to achieve knowledge association and visualization. The extracted entities and relationships are stored in the graph database in the form of a graph structure (knowledge graph), each entity corresponds to a node, and the relationship represents the connection between entities, and each relationship corresponds to an edge. A knowledge graph specifically used in the field of risk control is constructed using NLP and graph database technology, which contains keywords, topics, and relationships between entities related to risk control. The risk control knowledge graph can provide strong support for risk control decisions and help decision makers better understand and respond to risks; the graph database provides efficient graph traversal and query functions, which can quickly find the relationships and paths between nodes.

[0078] In a further embodiment, the knowledge graph generation module is also used to perform knowledge retrieval and analysis through a graph database query language, such as Cypher. Using the query function of the graph database, information and relationships related to a specific risk or entity can be quickly found.

[0079] In a further implementation, the knowledge graph generation module is also used to continuously collect new data, extract information using NLP technology, and update and enrich the knowledge graph. For example, the relationships between entities such as risk type, company name, person, etc., "a company faces a certain risk", "a certain risk leads to a certain consequence", etc. Optionally, the graph can also include the attributes of the entity.

[0080] The knowledge list generation module 350 is used to perform the following operations: generate a knowledge list of the initial information according to the parsed information; generate a classification label of the knowledge list according to the parsed information, and generate a corresponding classification index according to the classification label.

[0081] The information recommendation module 360 ​​is used to obtain user behavior logs and obtain recommended knowledge items from the knowledge list according to the user behavior logs.

[0082] The warning module 370 is used to parse the knowledge list to obtain potential risk information and issue warning information based on the risk information.

[0083] The information query module 380 is used to obtain a user's query request and obtain a target knowledge item from the knowledge list according to the query request.

[0084] The above-mentioned data processing system of Example 3 of the present invention is adopted, by collecting initial information from multiple data sources, and generating a knowledge graph based on the parsed information of the initial information. The knowledge graph intuitively displays the knowledge and relationships in the field of risk control in the form of a graph structure, and can continuously add new entities and relationships to enrich the content of the graph. The knowledge graph can provide efficient graph traversal and query functions, so as to quickly find the relationships and paths between nodes; by generating a corresponding knowledge list for the initial information, and generating classification labels and classification indexes of the knowledge list based on the parsed information, it can facilitate users to quickly search; it can provide personalized knowledge recommendations based on user behavior, thereby improving knowledge utilization efficiency; by timely obtaining potential risk information through analysis and pushing early warning information, it can help users quickly respond to and handle risk events.

[0085] Through the description of the above implementation modes, those skilled in the art can clearly understand that the present invention can be implemented by combining software with a hardware platform. Based on such an understanding, all or part of the contribution of the technical solution of the present invention to the background technology can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation modes of the present invention or some parts of the implementation modes.

[0086] Correspondingly, an embodiment of the present invention further provides a computer-readable storage medium on which computer-readable instructions or programs are stored. When the computer-readable instructions or programs are executed by a processor, the computer performs the following operations: the operations include the steps included in the data processing method described in any of the above embodiments, which are not repeated here. The storage medium may include, for example, an optical disk, a hard disk, a floppy disk, a flash memory, a magnetic tape, etc.

[0087] In addition, an embodiment of the present invention further provides a computer device including a memory and a processor, wherein the memory is used to store one or more computer-readable instructions or programs, wherein the one or more computer-readable instructions or programs can implement the data processing method described in any of the above embodiments when executed by the processor. The computer device can be, for example, a server, a desktop computer, a notebook computer, a tablet computer, etc.

[0088] The present invention also provides a computer program product including a computer program, wherein the computer program includes a program code for executing the data processing method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the data processing method provided by the embodiment of the present disclosure.

[0089] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention is described in detail with reference to the above embodiments, a person skilled in the art should understand that the technical solutions described in the above embodiments can still be modified, or some of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention. Therefore, the protection scope of the present invention shall be subject to the claims.

Claims

1. A data processing method, characterized in that: The data processing method comprises: Gather initial information on pre-defined domains from multiple data sources; Preprocessing the initial information to obtain standardized data; Parsing the standardized data to obtain parsed information, the parsed information including: keywords, topics, entity information, and entity association information; Generate a knowledge graph based on the parsed information.

2. The data processing method according to claim 1, characterized in that: The data processing method further includes: Generate a knowledge list of the initial information according to the parsed information; A classification label of the knowledge list is generated according to the parsing information, and a corresponding classification index is generated according to the classification label.

3. The data processing method according to claim 2, characterized in that: The data processing method further includes: Obtain user behavior logs; Acquire recommended knowledge items from the knowledge list according to the user behavior log.

4. The data processing method according to claim 2, characterized in that: The data processing method further includes: Potential risk information is obtained by parsing the knowledge list, and warning information is issued according to the risk information.

5. A data processing system, characterized in that: The data processing system comprises: An initial information acquisition module is used to collect initial information in a preset field from multiple data sources; A data preprocessing module, used for preprocessing the initial information to obtain standardized data; A data parsing module, used to parse the standardized data to obtain parsed information, wherein the parsed information includes: keywords, topics, entity information, and entity association information; A knowledge graph generation module is used to generate a knowledge graph based on the parsed information.

6. The data processing system according to claim 5, characterized in that The data processing system further includes a knowledge list generating module, which is used to perform the following operations: Generate a knowledge list of the initial information according to the parsed information; A classification label of the knowledge list is generated according to the parsing information, and a corresponding classification index is generated according to the classification label.

7. The data processing system according to claim 6, characterized in that The data processing system further comprises: An information recommendation module, used to obtain user behavior logs, and obtain recommended knowledge items from the knowledge list according to the user behavior logs; The early warning module is used to parse the knowledge list to obtain potential risk information and issue early warning information based on the risk information.

8. A computer-readable storage medium storing computer-readable instructions, characterized in that: The computer-readable instructions are executed by a processor to implement the data processing method according to any one of claims 1 to 4.

9. A computer device comprising a memory and a processor, The memory stores computer-readable instructions, characterized in that: The processor executes the computer-readable instructions to implement the data processing method according to any one of claims 1 to 4.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 4 is implemented.

Images