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

By obtaining and processing historical credit card business project information, building a knowledge graph and using predictive models, the problems of unified management and automated processing in the credit card management system are solved, management efficiency and accuracy are improved, and an intelligent approval process is realized.

CN119006144APending Publication Date: 2024-11-22PING AN BANK CO LTD
View PDF 0 Cites 9 Cited by

Patent Information

Application Number
CN202411036386.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The existing credit card management system lacks a unified management platform, which makes it difficult to centrally manage and track input data, and project goal setting and cost management are not included in the system maintenance, resulting in inefficient management and incomplete data, and lack of full-process automated processing.

Method used

By obtaining historical business project information, extracting data related to business scenarios, performing knowledge extraction and semantic annotation, building a business scenario knowledge graph, and using prediction models to match and manage the approval process, realizing intelligent and automated business project management.

Benefits of technology

It improves the efficiency and accuracy of credit card business project management, realizes an intelligent and data-driven approval process, enhances decision-making support capabilities, and ensures data integrity and process automation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006144A_ABST
    Figure CN119006144A_ABST
Patent Text Reader

Abstract

The invention discloses a business project management method and device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: collecting historical business item information, and extracting data related to a business scene to form business scene data; performing knowledge extraction and semantic annotation on the data to obtain business scene entity data; constructing a business scene knowledge graph based on the entity data, and training a business scene prediction model by using the graph; using the prediction model to predict the to-be-approved business item to obtain a business scene prediction result; and matching a corresponding business project approval process according to the prediction result, approving the to-be-approved project based on the process, and outputting an approval result. The invention further relates to the technical field of the block chain, and the business item information is stored on the block chain node. According to the application, through the knowledge graph and the prediction model, intelligent and data-driven business project management is realized, and the approval efficiency, accuracy and decision support capability are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and specifically to a business project management method, device, computer equipment and storage medium. Background Art

[0002] The credit card management system is an integrated platform designed to uniformly manage the credit card application process, track data, maintain project goals and costs, control the approval process, and realize full-process automation. It solves the problems of decentralization and manual operation of the existing system and improves management efficiency and data integrity.

[0003] However, there is currently a lack of unified management for applications for different credit card scenarios, which makes it difficult to centrally manage and effectively track actual application data. There are differences in the application categories, suppliers, and project types between the sub-centers, and there is a lack of a dedicated system for tracking and closed-loop management. In addition, the project's goal setting and cost management have not been included in the dedicated system for maintenance, resulting in a lack of project management. There is no systematic control over project submission, review, project establishment, and the entire approval process, making it difficult to ensure data integrity. The processes of adding new projects, card processing points, and card processing link generation rely on offline document management, and cannot achieve full process automation and online processing.

[0004] The above-mentioned problems lead to inefficient credit card management, incomplete data management, and cumbersome processes. There is an urgent need to establish a unified and systematic management platform through technical means to improve the efficiency and accuracy of credit card business project management. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a business project management method, apparatus, computer equipment and storage medium, aiming to establish a unified and systematic management platform to improve the efficiency and accuracy of credit card business project management.

[0006] In order to solve the above technical problems, the present application embodiment provides a business project management method, which adopts the following technical solution:

[0007] A business project management method, comprising:

[0008] Acquire pre-collected historical business project information, and extract data related to business scenarios from the historical business project information to obtain business scenario data;

[0009] Perform knowledge extraction and semantic annotation on business scenario data to obtain business scenario entity data;

[0010] Build a business scenario knowledge graph based on business scenario entity data, and train a business scenario prediction model based on the business scenario knowledge graph;

[0011] Use the business scenario prediction model to predict the business scenarios of the business items to be approved and obtain the business scenario prediction results;

[0012] Obtain the business project approval process that matches the business scenario prediction results, approve the business projects to be approved based on the business project approval process, and output the business project approval results.

[0013] Furthermore, the previously collected historical business project information is obtained, and data related to the business scenario in the historical business project information is extracted to obtain business scenario data, specifically including:

[0014] Perform data cleaning on historical business project information, including outlier detection and missing value processing;

[0015] Split the historical business project information and perform cluster analysis on the split data;

[0016] The association rule learning method is used to find data related to the business scenario in the clustering results to obtain the business scenario data.

[0017] Furthermore, knowledge extraction and semantic annotation are performed on the business scenario data to obtain business scenario entity data, including:

[0018] Identify text data in business scenario data and segment the text data to obtain text segmentation;

[0019] Use the hidden Markov model to perform part-of-speech tagging on text segmentation to obtain the part-of-speech tagging results of the text segmentation;

[0020] Use the conditional random field algorithm to perform entity recognition on the part-of-speech tagging results to obtain entity data;

[0021] Based on the pre-built semantic rule base and entity data, semantic annotation is performed in the part-of-speech tagging results to obtain entity category data and entity relationship data;

[0022] Entity data, entity category data and entity relationship data are combined to obtain business scenario entity data.

[0023] Furthermore, semantic annotation is performed on the part-of-speech tagging results based on the pre-built semantic rule base and entity data to obtain entity category data and entity relationship data, specifically including:

[0024] Constructing a semantic rule base, wherein the semantic rule base includes entity category semantic rules and entity relationship semantic rules;

[0025] Perform entity category-related semantic annotation in the part-of-speech tagging results based on entity category semantic rules;

[0026] Perform entity relationship-related semantic annotation in the part-of-speech tagging results based on entity relationship semantic rules;

[0027] After completing the entity category semantic labeling and entity relationship semantic labeling, the conditional random field algorithm is used to identify the category and relationship of the entity data based on the semantic labeling results to obtain entity category data and entity relationship data.

[0028] Furthermore, a business scenario knowledge graph is constructed based on the business scenario entity data, and a business scenario prediction model is trained based on the business scenario knowledge graph, specifically including:

[0029] The business scenario entity data is converted into a knowledge graph using graph embedding technology to obtain a business scenario knowledge graph;

[0030] Use the business scenario knowledge graph as a training dataset;

[0031] The preset initial prediction model is iteratively trained using the training data set until the model is fitted to obtain a business scenario prediction model.

[0032] Furthermore, the preset initial prediction model is iteratively trained using the training data set until the model is fitted to obtain a business scenario prediction model, which specifically includes:

[0033] Iteratively train the preset initial prediction model using the training data set to obtain the initial scene prediction results;

[0034] Based on the initial scenario prediction results, the initial prediction model is iteratively updated using a cross-validation algorithm to obtain an intermediate prediction model;

[0035] Use the preset decision tree algorithm to screen the initial scenario prediction results to obtain the prediction screening results;

[0036] Determine the training data features corresponding to the predicted screening results;

[0037] The intermediate prediction model is iteratively updated using the training data features corresponding to the prediction screening results until the model is fitted to obtain a business scenario prediction model.

[0038] Furthermore, a business project approval process matching the business scenario prediction result is obtained, and the business project to be approved is approved based on the business project approval process, and the business project approval result is output, which specifically includes:

[0039] A decision tree algorithm is used to classify the business scenario prediction results to obtain business scenario classification results;

[0040] Use a clustering algorithm to cluster the business scenario classification results to obtain several business project groups;

[0041] Get the approval process template corresponding to each business project group;

[0042] Based on the sequence pattern analysis method, the approval process templates corresponding to each business project group are integrated to obtain the business project approval process;

[0043] Use the business project approval process to approve the business projects to be approved and output the business project approval results.

[0044] In order to solve the above technical problems, the embodiment of the present application further provides a business project management device, which adopts the following technical solution:

[0045] A business project management device, comprising:

[0046] A data extraction module is used to obtain the pre-collected historical business project information and extract the data related to the business scenario in the historical business project information to obtain the business scenario data;

[0047] The entity recognition module is used to extract knowledge and semantically annotate business scenario data to obtain business scenario entity data;

[0048] The model training module is used to build a business scenario knowledge graph based on business scenario entity data and train a business scenario prediction model based on the business scenario knowledge graph;

[0049] A scenario prediction module is used to use a business scenario prediction model to predict the business scenario of the business project to be approved and obtain a business scenario prediction result;

[0050] The project approval module is used to obtain the business project approval process that matches the business scenario prediction results, approve the business projects to be approved based on the business project approval process, and output the business project approval results.

[0051] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0052] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of any one of the above-mentioned business project management methods when executing the computer-readable instructions.

[0053] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0054] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of any one of the business project management methods described above.

[0055] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0056] The present application discloses a business project management method, device, computer equipment and storage medium, and relates to the field of artificial intelligence technology. The present application collects historical business project information and extracts data related to business scenarios to form business scenario data; performs knowledge extraction and semantic annotation on these data to obtain business scenario entity data; constructs a business scenario knowledge graph based on these entity data, and uses the graph to train a business scenario prediction model; uses the prediction model to predict the pending business projects to obtain business scenario prediction results; matches the corresponding business project approval process according to the prediction results, and approves the pending approval projects based on this process, and outputs the approval results. The present application realizes the intelligence and automation of business project management by collecting and processing historical business data, constructing a knowledge graph, and using a prediction model for intelligent analysis, realizing intelligent and data-driven business project management, and improving approval efficiency, accuracy and decision-making support capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0058] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0059] Figure 2 A flowchart showing an embodiment of a business project management method according to the present application is shown;

[0060] Figure 3 A schematic diagram showing the structure of an embodiment of a business project management device according to the present application is shown;

[0061] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0063] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0064] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0065] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0066] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0067] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0068] Server 105 can be a server that provides various services, such as a background server that provides support for pages displayed on terminal devices 101, 102, and 103. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDNs), and big data and artificial intelligence platforms.

[0069] It should be noted that the business project management method provided in the embodiment of the present application is generally executed by a server, and accordingly, the business project management device is generally set in the server.

[0070] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0071] Continue to refer Figure 2 , showing a flow chart of an embodiment of the business project management method according to the present application. The embodiment of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0072] The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning. The business project management method includes the following steps:

[0073] S201, obtaining pre-collected historical business project information, and extracting data related to business scenarios in the historical business project information to obtain business scenario data.

[0074] First, you need to obtain a large amount of historical business project information, which can come from various channels such as internal enterprise databases, documents, email records, customer feedback, etc. The types of data include structured data (such as database tables), semi-structured data (such as XML, JSON), and unstructured data (such as text, pictures). After the data is collected, it needs to be preprocessed, including data cleaning, deduplication, denoising, and format standardization to ensure the accuracy and consistency of the data. Next, it is necessary to extract information related to the business scenario from these historical data through data splitting, cluster analysis, and association rule learning, such as project name, customer type, project budget, project progress, risk assessment and other key fields.

[0075] The purpose of this step is to transform disorganized raw data into meaningful business scenario data, laying the foundation for subsequent knowledge extraction and semantic annotation. After the data extraction is completed, the relevant data will be stored in a centralized database for subsequent processing and access.

[0076] S202, extract knowledge and semantically annotate the business scenario data to obtain business scenario entity data.

[0077] In this step, the extracted business scenario data needs to be further processed in order to mine valuable knowledge from it. It is mainly based on knowledge extraction and semantic annotation. Knowledge extraction is to extract key entities and relationships from business scenario data using natural language processing (NLP) technology; entity recognition is to identify important entities in the data, such as projects, customers, suppliers, resources, etc.; relationship extraction is to identify the relationship between entities, such as cooperative relationships, dependency relationships, etc. Semantic annotation is to semantically annotate these extracted entities and relationships to ensure that the definition of each entity and relationship is clear and consistent, which involves using predefined ontologies or dictionaries to standardize terms to ensure data consistency and comprehensibility.

[0078] For example, there is a business scenario dataset for a bank card management project, which contains information in multiple dimensions, such as customer information, transaction records, credit scores, risk assessments, product types, etc. The specific data examples are as follows:

[0079] Customer information: customer name, age, occupation, income level, address, etc.

[0080] Transaction records: transaction date, transaction amount, transaction location, transaction type.

[0081] Product Type: Credit card type, card issue date, card status, etc.

[0082] By performing knowledge extraction and semantic annotation on business scenario data, the business scenario entity data obtained is as follows:

[0083] Entity Recognition:

[0084] Identify the "Customer" entity from the customer information and extract its attributes such as name, age, occupation, income level, address, etc.

[0085] Identify the "transaction" entity from the transaction record and extract attributes such as transaction date, amount, location, type, etc.

[0086] Identify the "Credit Card" entity from the product type information and extract attributes such as card type, issue date, and card status.

[0087] Entity Relationships:

[0088] Identify the relationship between "customer" and "transaction" and define the "customer conducts transaction" relationship.

[0089] Identify the relationship between "Customer" and "Credit Card" and define the "Customer Holds Credit Card" relationship.

[0090] The data that has been processed through knowledge extraction and semantic annotation is called business scenario entity data. These data are more structured and contain richer semantic information, providing a basis for the subsequent construction of knowledge graphs.

[0091] S203, constructing a business scenario knowledge graph based on the business scenario entity data, and training a business scenario prediction model based on the business scenario knowledge graph.

[0092] First, it is necessary to use the business scenario entity data to build a business scenario knowledge graph. The knowledge graph is a data structure that represents entities and their relationships in the form of a graph, which can organically link scattered information. Graph construction requires defining the nodes and edges of entities and relationships, and integrating all data into a unified knowledge graph. After the graph is built, it is necessary to optimize and verify the graph to ensure its accuracy and consistency. Next, based on the constructed knowledge graph, extract features and perform feature engineering to prepare for training the business scenario prediction model. Select appropriate machine learning or deep learning algorithms, such as random forests, support vector machines, neural networks, etc., and use business scenario data for model training. During the model training process, it is necessary to optimize the model parameters to improve the prediction accuracy of the model and obtain a trained business scenario prediction model.

[0093] By building a business scenario knowledge graph to train a business scenario prediction model, the trained prediction model can perform intelligent analysis and prediction on business scenarios, providing a scientific basis for the approval of business projects.

[0094] S204, using the business scenario prediction model to predict the business scenario of the business item to be approved, and obtaining a business scenario prediction result.

[0095] Apply the trained business scenario prediction model to the business projects to be approved. First, it is necessary to collect the basic information and relevant data of the business projects to be approved, and pre-process the data, including cleaning, standardization and format conversion, to ensure the quality and consistency of the data. Then input the processed data into the business scenario prediction model, which will perform intelligent analysis and prediction based on the input data and output the business scenario prediction results, which include various types of information such as project success rate, risk score, resource requirements, etc.

[0096] Through this step, scientific prediction results can be provided for each business project to be approved, helping decision makers make more accurate and efficient approval decisions.

[0097] S205, obtaining a business project approval process that matches the business scenario prediction result, approving the business project to be approved based on the business project approval process, and outputting the business project approval result.

[0098] First, according to the prediction results, such as project success rate, risk score, etc., determine the appropriate approval process and rules. The approval process may include multi-level approval, different approval conditions and steps, etc. Then, based on the matching approval process, the actual approval operation is performed on the approval business project. During the approval process, it is necessary to verify the approval conditions, record the approval opinions, and update the process status. In order to improve the efficiency and accuracy of approval, the approval process can be automated, and the approval operation can be performed through automated tools, and the approval process and results can be recorded in real time. Finally, the approval results are recorded in the system, a detailed approval report is generated, and the results are notified to the relevant personnel and departments. At the same time, the execution of the approval process and user feedback are collected, and the approval process and prediction model are continuously optimized to improve the efficiency and accuracy of overall business project management.

[0099] Through the closed-loop management process of business project approval, intelligent and data-driven business project approval can be achieved.

[0100] In the above embodiments, this application realizes the intelligence and automation of business project management by collecting and processing historical business data, constructing a knowledge graph, and using a predictive model for intelligent analysis, thereby realizing intelligent and data-driven business project management and improving approval efficiency, accuracy, and decision-making support capabilities.

[0101] Furthermore, the previously collected historical business project information is obtained, and data related to the business scenario in the historical business project information is extracted to obtain business scenario data, specifically including:

[0102] Perform data cleaning on historical business project information, including outlier detection and missing value processing;

[0103] Split the historical business project information and perform cluster analysis on the split data;

[0104] The association rule learning method is used to find data related to the business scenario in the clustering results to obtain the business scenario data.

[0105] In this embodiment, the historical business project information is first cleaned, and the quality and integrity of the data are ensured through outlier detection and missing value processing. The cleaned data is split into smaller subsets for subsequent processing. The split data is grouped through cluster analysis, and data with similar characteristics are clustered together to form different clusters. The association rule learning method is used to deeply mine the clustering results, find key data related to the business scenario, and extract the business scenario data.

[0106] Using association rule learning methods to conduct in-depth mining of clustering results, the clustering results need to be encoded first, and the characteristic items of each cluster are converted into frequent item sets. Then, association rule algorithms (such as April or FP-Growth) are applied to find rules with high support and confidence in frequent item sets, from which key data related to business scenarios are identified. These rules can reveal implicit relationships and patterns between data items, help discover important business scenario features, and then extract key data that is highly relevant to business scenarios, improving the accuracy and practicality of analysis.

[0107] In the above embodiment, multi-step data processing and analysis are used to ensure that the extracted business scenario data is of high quality and high relevance, thereby improving the accuracy and efficiency of data processing.

[0108] Furthermore, knowledge extraction and semantic annotation are performed on the business scenario data to obtain business scenario entity data, including:

[0109] Identify text data in business scenario data and segment the text data to obtain text segmentation;

[0110] Use the hidden Markov model to perform part-of-speech tagging on text segmentation to obtain the part-of-speech tagging results of the text segmentation;

[0111] Use the conditional random field algorithm to perform entity recognition on the part-of-speech tagging results to obtain entity data;

[0112] Based on the pre-built semantic rule base and entity data, semantic annotation is performed in the part-of-speech tagging results to obtain entity category data and entity relationship data;

[0113] Entity data, entity category data and entity relationship data are combined to obtain business scenario entity data.

[0114] In this embodiment, the text data in the business scenario data is first identified, and word segmentation processing is performed to generate text segmentation results. Next, the hidden Markov model (HMM) is used to perform part-of-speech tagging on these word segments to obtain the part-of-speech tagging results of each word segment. Then, the conditional random field (CRF) algorithm is applied to perform entity recognition on the part-of-speech tagging results to extract the entity data in the text. On this basis, the identified entity data is semantically annotated using a pre-built semantic rule library to determine the category of the entity and the relationship between the entity, and to generate entity category data and entity relationship data. Finally, the entity data, entity category data, and entity relationship data are integrated and combined to obtain complete business scenario entity data.

[0115] Hidden Markov Model (HMM) is a statistical model used to describe sequence data with hidden states, where there is a Markov chain transition relationship between hidden states and the hidden states generate observable outputs. In the above solution, HMM is used to perform part-of-speech tagging on business scenario data to help identify the grammatical role of each word after text segmentation, thereby providing key grammatical information for subsequent entity recognition and semantic tagging.

[0116] Conditional Random Field (CRF) is a probabilistic graphical model used to label and segment sequence data, which can make accurate predictions using contextual information. In the above solution, CRF is used to perform entity recognition on the part-of-speech tagging results, which can accurately identify named entities in the text (such as names of people, places, and organizations), and label the categories of these entities, providing basic data for subsequent semantic annotation and business scenario analysis.

[0117] In the above embodiment, multi-level natural language processing and machine learning technologies are used to ensure that the extracted business scenario entity data has high accuracy and rich semantic information. The entire process systematically processes text data, from word segmentation, part-of-speech tagging to entity recognition and semantic tagging, forming a complete data processing and tagging process.

[0118] Furthermore, semantic annotation is performed on the part-of-speech tagging results based on the pre-built semantic rule base and entity data to obtain entity category data and entity relationship data, specifically including:

[0119] Constructing a semantic rule base, wherein the semantic rule base includes entity category semantic rules and entity relationship semantic rules;

[0120] Perform entity category-related semantic annotation in the part-of-speech tagging results based on entity category semantic rules;

[0121] Perform entity relationship-related semantic annotation in the part-of-speech tagging results based on entity relationship semantic rules;

[0122] After completing the entity category semantic labeling and entity relationship semantic labeling, the conditional random field algorithm is used to identify the category and relationship of the entity data based on the semantic labeling results to obtain entity category data and entity relationship data.

[0123] In this embodiment, a semantic rule base is constructed, and semantic annotation is performed in the part-of-speech tagging results to obtain entity category data and entity relationship data. First, a semantic rule base is constructed, including entity category semantic rules and entity relationship semantic rules, which define different types of entities and their relationships in detail. Based on the part-of-speech tagging results, the entity category semantic rules are applied to perform category semantic annotation to identify and annotate the categories of each entity; the entity relationship semantic rules are applied to perform relationship semantic annotation to identify and annotate the relationships between entities. After completing the semantic annotation of categories and relationships, the conditional random field (CRF) algorithm is used to further process the semantic annotation results to accurately identify the categories and relationships of the entity data. Through the context analysis capability of the CRF algorithm, the subtle differences between entities and relationships can be better captured to ensure the accuracy of the annotation. Finally, entity data containing detailed category and relationship information is obtained.

[0124] For example, in a scenario-based bank card management project, the semantic rule base can be used to identify and annotate information related to customers and transactions. First, a semantic rule base is constructed, including entity category rules (such as customers, transactions, credit scores, etc.) and entity relationship rules (such as customer-transaction, customer-credit score, etc.). Based on these rules, semantic annotation is performed in the part-of-speech tagging results. For example, in the identification of "Zhang San made an online payment of 100 US dollars on May 1, 2023", "Zhang San" is annotated as a customer entity, indicating that the entity category is an individual user, "May 1, 2023" is annotated as the transaction date, "100 US dollars" is annotated as the transaction amount, and "online payment" is annotated as the transaction type. At the same time, the relationship between "Zhang San" and "transaction" is annotated through entity relationship semantic rules. After completing the preliminary annotation, the conditional random field (CRF) algorithm is used to further process these annotation results to ensure the accuracy of the annotation. For example, CRF will confirm the relationship between "Zhang San" as a customer entity and multiple transaction records to ensure the consistency and accuracy of the annotation. Finally, we obtain detailed entity category data and entity relationship data, such as customer entity data including name, occupation, income, etc., transaction entity data including amount, date, type, etc., as well as relationship data between customers and transactions.

[0125] In the above embodiment, the rule base and machine learning are combined to ensure the accuracy and comprehensiveness of semantic annotation.

[0126] Furthermore, a business scenario knowledge graph is constructed based on the business scenario entity data, and a business scenario prediction model is trained based on the business scenario knowledge graph, specifically including:

[0127] The business scenario entity data is converted into a knowledge graph using graph embedding technology to obtain a business scenario knowledge graph;

[0128] Use the business scenario knowledge graph as a training dataset;

[0129] The preset initial prediction model is iteratively trained using the training data set until the model is fitted to obtain a business scenario prediction model.

[0130] In this embodiment, the accuracy and intelligence of business prediction are improved by constructing a business scenario knowledge graph and training a business scenario prediction model. First, the business scenario entity data is converted into a knowledge graph using graph embedding technology. By representing entities and relationships as vectors, complex relationship networks can be represented and calculated in a low-dimensional space. The obtained business scenario knowledge graph contains all business scenario-related entities and their relationships, providing comprehensive and structured business information. Next, this knowledge graph is used as a training data set and input into a preset initial prediction model. Through iterative training, the model parameters are continuously adjusted so that the model gradually learns and adapts to the complex relationships and patterns in the knowledge graph. During the training process, the model uses the structural and semantic information in the knowledge graph to continuously improve its understanding and prediction capabilities of business scenarios. Finally, after multiple iterative trainings, the model achieves a good fitting effect and forms an accurate business scenario prediction model.

[0131] In the above embodiments, the prediction model can be applied in actual business to provide accurate business scenario prediction and decision support, improve the intelligence level and efficiency of business management, and combine graph embedding technology and machine learning model training to achieve a closed-loop process from data construction, relationship modeling to intelligent prediction.

[0132] Furthermore, the preset initial prediction model is iteratively trained using the training data set until the model is fitted to obtain a business scenario prediction model, which specifically includes:

[0133] Iteratively train the preset initial prediction model using the training data set to obtain the initial scene prediction results;

[0134] Based on the initial scenario prediction results, the initial prediction model is iteratively updated using a cross-validation algorithm to obtain an intermediate prediction model;

[0135] Use the preset decision tree algorithm to screen the initial scenario prediction results to obtain the prediction screening results;

[0136] Determine the training data features corresponding to the predicted screening results;

[0137] The intermediate prediction model is iteratively updated using the training data features corresponding to the prediction screening results until the model is fitted to obtain a business scenario prediction model.

[0138] In this embodiment, first, the preset initial prediction model is iteratively trained using the training data set to obtain preliminary scenario prediction results. Then, based on the preliminary prediction results, the cross-validation algorithm is applied to iteratively update the initial prediction model to form an intermediate prediction model. Through repeated verification and adjustment, the stability and generalization ability of the model on different data sets are ensured. Then, the preliminary prediction results are screened using the preset decision tree algorithm to extract valuable prediction screening results. The role of the decision tree algorithm in this process is to segment the data through rules, find out the key prediction features and patterns, and determine the training data features corresponding to these prediction screening results. These features are then used again to iteratively update the intermediate prediction model until the model fully fits the data, and finally an accurate business scenario prediction model is formed.

[0139] In the above embodiment, through a multi-stage training and optimization process, through cross-validation and decision tree screening, the prediction accuracy and robustness of the model are continuously improved to ensure that the final prediction model can accurately reflect the actual situation of the business scenario and provide reliable support for business decisions. Combined with various techniques and methods of machine learning, an efficient and accurate prediction model training process is formed.

[0140] Furthermore, a business project approval process matching the business scenario prediction result is obtained, and the business project to be approved is approved based on the business project approval process, and the business project approval result is output, which specifically includes:

[0141] A decision tree algorithm is used to classify the business scenario prediction results to obtain business scenario classification results;

[0142] Use a clustering algorithm to cluster the business scenario classification results to obtain several business project groups;

[0143] Get the approval process template corresponding to each business project group;

[0144] Based on the sequence pattern analysis method, the approval process templates corresponding to each business project group are integrated to obtain the business project approval process;

[0145] Use the business project approval process to approve the business projects to be approved and output the business project approval results.

[0146] In this embodiment, first, a decision tree algorithm is used to classify the business scenario prediction results to obtain clear business scenario classification results. Then, a clustering algorithm is used to cluster these classification results to form several business project groups, each of which contains similar business projects. Then, a corresponding approval process template is obtained for each business project group to ensure that the approval process matches the characteristics of the business scenario. For example, in a scenario-based bank card management project, a decision tree algorithm is first used to classify the business scenario prediction results, such as classifying the customer's transaction behavior prediction results into "high-risk transactions", "medium-risk transactions" and "low-risk transactions". Then, a clustering algorithm is used to cluster these classification results, and similar business projects are grouped, such as clustering different types of "high-risk transactions" (such as large transfers, frequent overseas transactions) together to form several business project groups.

[0147] Then, based on the sequence pattern analysis method, the approval process templates of each business project group are integrated and optimized to form a unified business project approval process. This step ensures the efficiency and consistency of the approval process by analyzing and adjusting the order and structure of the approval process. Finally, the generated business project approval process is used to approve the business projects to be approved and the approval results are output.

[0148] The sequential pattern analysis method is a data mining technology used to identify frequent patterns and regularities in data sequences. In the above solution, the sequential pattern analysis method is used to integrate and optimize the approval process templates of each business project group, identify and adjust the key steps and sequence in the approval process to ensure the efficiency and consistency of the approval process, thereby generating an approval process suitable for different business scenarios.

[0149] In the above embodiments, the approval process is effectively organized and optimized through classification, clustering and sequence pattern analysis, making the approval process more automated and intelligent, which not only improves the efficiency and accuracy of the approval, but also ensures the flexibility and adaptability of the approval process, and can be dynamically adjusted according to different business scenarios.

[0150] In this embodiment, the electronic device (eg, Figure 1 The server shown in the figure) can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0151] It should be emphasized that in order to further ensure the privacy and security of the above business project information, the above business project information can also be stored in a node of a blockchain.

[0152] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0153] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0154] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0155] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a business project management device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0156] like Figure 3 As shown, the business project management device 300 described in this embodiment includes:

[0157] The data extraction module 301 is used to obtain the pre-collected historical business project information and extract the data related to the business scenario in the historical business project information to obtain the business scenario data;

[0158] The entity recognition module 302 is used to extract knowledge and semantically annotate the business scenario data to obtain business scenario entity data;

[0159] A model training module 303 is used to construct a business scenario knowledge graph based on business scenario entity data, and train a business scenario prediction model according to the business scenario knowledge graph;

[0160] A scenario prediction module 304 is used to predict the business scenario of the business project to be approved using the business scenario prediction model to obtain a business scenario prediction result;

[0161] The project approval module 305 is used to obtain a business project approval process that matches the business scenario prediction result, approve the business project to be approved based on the business project approval process, and output the business project approval result.

[0162] Furthermore, the data extraction module 301 specifically includes:

[0163] A data cleaning unit, used to clean the historical business project information, wherein data cleaning includes outlier detection and missing value processing;

[0164] A splitting and clustering unit is used to split the historical business project information and perform cluster analysis on the split data;

[0165] The association rule learning unit is used to use the association rule learning method to find data related to the business scenario in the clustering results to obtain the business scenario data.

[0166] Furthermore, the entity identification module 302 specifically includes:

[0167] A text segmentation unit is used to identify text data in business scenario data and segment the text data to obtain text segmentation;

[0168] A part-of-speech tagging unit is used to perform part-of-speech tagging on text segmentation words using a hidden Markov model to obtain a part-of-speech tagging result of the text segmentation words;

[0169] An entity recognition unit is used to perform entity recognition on the part-of-speech tagging results using a conditional random field algorithm to obtain entity data;

[0170] A semantic tagging unit, used to perform semantic tagging in the part-of-speech tagging results based on a pre-built semantic rule library and entity data, to obtain entity category data and entity relationship data;

[0171] The data combination unit is used to combine entity data, entity category data and entity relationship data to obtain business scenario entity data.

[0172] Furthermore, the semantic annotation unit specifically includes:

[0173] A rule base construction subunit is used to construct a semantic rule base, wherein the semantic rule base includes entity category semantic rules and entity relationship semantic rules;

[0174] A category semantic annotation subunit is used to perform entity category-related semantic annotation in the part-of-speech tagging results based on entity category semantic rules;

[0175] The relational semantic annotation subunit is used to perform semantic annotation related to entity relations in the part-of-speech tagging results based on entity relation semantic rules;

[0176] The category and relationship identification subunit is used to identify the categories and relationships of entity data using a conditional random field algorithm based on the semantic annotation results after completing the entity category semantic annotation and entity relationship semantic annotation, so as to obtain entity category data and entity relationship data.

[0177] Furthermore, the model training module 303 specifically includes:

[0178] A knowledge graph construction unit, used to convert the business scenario entity data into a knowledge graph by using graph embedding technology to obtain a business scenario knowledge graph;

[0179] A data set construction unit, used to use the business scenario knowledge graph as a training data set;

[0180] The iterative training unit is used to iteratively train the preset initial prediction model using the training data set until the model is fitted to obtain a business scenario prediction model.

[0181] Furthermore, the iterative training unit specifically includes:

[0182] An iterative training subunit, used to iteratively train a preset initial prediction model using a training data set to obtain an initial scene prediction result;

[0183] A first iterative updating subunit is used to iteratively update the initial prediction model using a cross-validation algorithm based on the initial scene prediction result to obtain an intermediate prediction model;

[0184] A decision screening subunit is used to screen the initial scenario prediction results using a preset decision tree algorithm to obtain a prediction screening result;

[0185] A data feature matching subunit, used to determine the training data features corresponding to the predicted screening results;

[0186] The second iterative updating subunit is used to iteratively update the intermediate prediction model using the training data features corresponding to the prediction screening results until the model is fitted to obtain a business scenario prediction model.

[0187] Furthermore, the project approval module 305 specifically includes:

[0188] A prediction result classification unit is used to classify the business scenario prediction results using a decision tree algorithm to obtain a business scenario classification result;

[0189] A business scenario clustering unit, used to cluster the business scenario classification results using a clustering algorithm to obtain a number of business project groups;

[0190] An approval template acquisition unit is used to acquire the approval process template corresponding to each business project group;

[0191] An approval template integration unit is used to integrate the approval process templates corresponding to each business project group based on a sequence pattern analysis method to obtain a business project approval process;

[0192] The business project approval unit is used to approve the business projects to be approved using the business project approval process and output the business project approval results.

[0193] In the above embodiment, the present application discloses a business project management device, which relates to the field of artificial intelligence technology. The present application collects historical business project information and extracts data related to business scenarios to form business scenario data; performs knowledge extraction and semantic annotation on these data to obtain business scenario entity data; constructs a business scenario knowledge graph based on these entity data, and uses the graph to train a business scenario prediction model; uses the prediction model to predict the business projects to be approved and obtain business scenario prediction results; matches the corresponding business project approval process according to the prediction results, and approves the approval projects based on this process, and outputs the approval results. The present application realizes the intelligence and automation of business project management by collecting and processing historical business data, constructing a knowledge graph, and using a prediction model for intelligent analysis, realizing intelligent and data-driven business project management, and improving approval efficiency, accuracy, and decision-making support capabilities.

[0194] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0195] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0196] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0197] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the business project management method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0198] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the business project management method.

[0199] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0200] In the above embodiment, the present application discloses a computer device, which relates to the field of artificial intelligence technology. The present application collects historical business project information and extracts data related to business scenarios to form business scenario data; performs knowledge extraction and semantic annotation on these data to obtain business scenario entity data; constructs a business scenario knowledge graph based on these entity data, and uses the graph to train a business scenario prediction model; uses the prediction model to predict the business projects to be approved and obtain business scenario prediction results; matches the corresponding business project approval process according to the prediction results, and approves the approval projects based on this process, and outputs the approval results. The present application realizes the intelligence and automation of business project management by collecting and processing historical business data, constructing a knowledge graph, and using a prediction model for intelligent analysis, realizing intelligent and data-driven business project management, and improving approval efficiency, accuracy, and decision-making support capabilities.

[0201] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the business project management method as described above.

[0202] In the above embodiments, the present application discloses a computer-readable storage medium, which relates to the field of artificial intelligence technology. The present application collects historical business project information and extracts data related to business scenarios to form business scenario data; performs knowledge extraction and semantic annotation on these data to obtain business scenario entity data; constructs a business scenario knowledge graph based on these entity data, and uses the graph to train a business scenario prediction model; uses the prediction model to predict the business projects to be approved and obtain business scenario prediction results; matches the corresponding business project approval process according to the prediction results, and approves the approval projects based on this process, and outputs the approval results. The present application realizes the intelligence and automation of business project management by collecting and processing historical business data, constructing a knowledge graph, and using a prediction model for intelligent analysis, realizing intelligent and data-driven business project management, and improving approval efficiency, accuracy, and decision-making support capabilities.

[0203] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0204] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0205] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A business project management method, characterized in that: include: Acquire pre-collected historical business project information, and extract data related to business scenarios from the historical business project information to obtain business scenario data; Performing knowledge extraction and semantic annotation on the business scenario data to obtain business scenario entity data; Constructing a business scenario knowledge graph based on the business scenario entity data, and training a business scenario prediction model according to the business scenario knowledge graph; Using the business scenario prediction model to predict the business scenario of the business project to be approved, and obtaining a business scenario prediction result; Acquire a business project approval process that matches the business scenario prediction result, approve the business project to be approved based on the business project approval process, and output the business project approval result.

2. The business project management method according to claim 1, characterized in that: Acquire pre-collected historical business project information, and extract data related to business scenarios from the historical business project information to obtain business scenario data, specifically including: Performing data cleaning on the historical business project information, wherein the data cleaning includes outlier detection and missing value processing; Performing data segmentation on the historical business project information, and performing cluster analysis on the segmented data; An association rule learning method is used to search for data related to the business scenario in the clustering results to obtain the business scenario data.

3. The business project management method according to claim 1, characterized in that: The business scenario data is subjected to knowledge extraction and semantic annotation to obtain business scenario entity data, specifically including: Identifying text data in the business scenario data, and performing word segmentation on the text data to obtain text word segmentation; Performing part-of-speech tagging on the text segmentation using a hidden Markov model to obtain a part-of-speech tagging result of the text segmentation; Using a conditional random field algorithm to perform entity recognition on the part-of-speech tagging results to obtain entity data; Based on the pre-built semantic rule library and the entity data, semantic annotation is performed in the part-of-speech tagging result to obtain entity category data and entity relationship data; The entity data, the entity category data and the entity relationship data are combined to obtain the business scenario entity data.

4. The business project management method according to claim 3, characterized in that: Based on the pre-built semantic rule library and the entity data, semantic annotation is performed in the part-of-speech tagging result to obtain entity category data and entity relationship data, specifically including: Constructing the semantic rule base, wherein the semantic rule base includes entity category semantic rules and entity relationship semantic rules; Performing entity category-related semantic annotation in the part-of-speech tagging result based on the entity category semantic rule; Performing entity relationship-related semantic annotation in the part-of-speech tagging result based on the entity relationship semantic rule; After completing entity category semantic labeling and entity relationship semantic labeling, the conditional random field algorithm is used to identify the category and relationship of the entity data based on the semantic labeling results to obtain the entity category data and the entity relationship data.

5. The business project management method according to claim 1, characterized in that: Constructing a business scenario knowledge graph based on the business scenario entity data, and training a business scenario prediction model according to the business scenario knowledge graph, specifically including: Using graph embedding technology to convert the business scenario entity data into a knowledge graph to obtain the business scenario knowledge graph; Using the business scenario knowledge graph as a training data set; The preset initial prediction model is iteratively trained using the training data set until the model is fitted to obtain the business scenario prediction model.

6. The business project management method according to claim 5, characterized in that: The preset initial prediction model is iteratively trained using the training data set until the model is fitted to obtain the business scenario prediction model, specifically including: Iteratively training a preset initial prediction model using the training data set to obtain an initial scene prediction result; Iteratively updating the initial prediction model using a cross-validation algorithm based on the initial scenario prediction result to obtain an intermediate prediction model; Use the preset decision tree algorithm to screen the initial scenario prediction results to obtain the prediction screening results; Determining training data features corresponding to the predicted screening results; The intermediate prediction model is iteratively updated using the training data features corresponding to the prediction screening results until the model is fitted to obtain the business scenario prediction model.

7. The business project management method according to claim 1, characterized in that: Acquiring a business project approval process that matches the business scenario prediction result, approving the business project to be approved based on the business project approval process, and outputting the business project approval result, specifically including: Using a decision tree algorithm to classify the business scenario prediction results to obtain business scenario classification results; Clustering the business scenario classification results using a clustering algorithm to obtain several business project groups; Get the approval process template corresponding to each business project group; Based on the sequence pattern analysis method, the approval process templates corresponding to the various business project groups are integrated to obtain the business project approval process; The business project approval process is used to approve the business project to be approved, and the business project approval result is output.

8. A business project management device, characterized in that: include: A data extraction module is used to obtain pre-collected historical business project information and extract data related to business scenarios from the historical business project information to obtain business scenario data; An entity recognition module is used to extract knowledge and semantically annotate the business scenario data to obtain business scenario entity data; A model training module, used to construct a business scenario knowledge graph based on the business scenario entity data, and train a business scenario prediction model according to the business scenario knowledge graph; A scenario prediction module, used to use the business scenario prediction model to predict the business scenario of the business project to be approved, and obtain a business scenario prediction result; The project approval module is used to obtain a business project approval process that matches the business scenario prediction result, approve the business project to be approved based on the business project approval process, and output the business project approval result.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the business project management method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the business project management method according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Semantic-based AI data governance method, system and equipment and storage medium

    CN119396827A

  • Banking business scheduling method and system for online payment front end

    CN119417478A

  • Intelligent question generation method for knowledge point analysis

    CN119886320A

  • An intelligent question generation method for knowledge point analysis

    CN119886320B

  • Process approval method and system based on attached multi-dimensional structure data

    CN120198071A