Intelligent analysis method and system for enterprise digital transformation

Abstract

The invention discloses an intelligent analysis method and system for enterprise digital transformation, and relates to the technical field of enterprise digital transformation, and the method comprises the following specific steps: perception and preprocessing: employing a network data capture technology to obtain scene factor related text information from multiple channels, according to the method, key information such as policy and regulation update and market dynamic change is captured in real time by utilizing a plurality of information acquisition channels, and a knowledge graph system containing rich enterprise knowledge is constructed; according to the technical scheme of the invention, new scene factors can be deeply associated and accurately matched with knowledge such as business processes and technical architectures inside an enterprise, so that the system can provide more scientific and accurate digital transformation decision suggestions for the enterprise, the enterprise is helped to better cope with external environment changes, the internal management process is optimized, and the business operation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise digital transformation, and specifically to an intelligent analysis method and system for enterprise digital transformation. Background Art

[0002] In today's wave of globalization and informatization, enterprise digital transformation has become a key strategy for enhancing corporate competitiveness, achieving business innovation and sustainable development. With the rapid development of technologies such as big data, artificial intelligence, and cloud computing, enterprises are facing unprecedented opportunities and challenges. Digital transformation can not only help enterprises optimize internal management processes and improve operational efficiency, but also promote product and service innovation and enhance market competitiveness. However, in the process of digital transformation, enterprises need to comprehensively consider the complex factors of the internal and external environment and formulate scientific and reasonable transformation strategies.

[0003] Although the importance of enterprise digital transformation is becoming increasingly prominent, traditional digital transformation analysis methods have obvious shortcomings in dealing with complex and changing internal and external environments. On the one hand, traditional methods lack comprehensive perception and in-depth analysis of situational factors such as policy and regulatory updates, market dynamics, and industry emergencies, making it difficult to timely and accurately capture the potential impact of external environmental changes on corporate business and digital transformation. On the other hand, traditional methods lack an effective knowledge reasoning mechanism, making it difficult to deeply associate and match situational factors with internal business processes, technical architecture, market competition trends and other knowledge, thus failing to provide companies with comprehensive and accurate digital transformation decision-making recommendations.

[0004] In response to the above problems, it is necessary to optimize the existing intelligent analysis methods for enterprise digital transformation, and realize comprehensive monitoring and in-depth analysis of internal and external environmental factors of the enterprise through situational perception and knowledge reasoning technology. Therefore, it is of great significance to develop an intelligent analysis method and system for enterprise digital transformation that can comprehensively realize the above characteristics. Summary of the Invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide an intelligent analysis method and system for the digital transformation of enterprises. It can realize continuous monitoring and accurate analysis of internal and external situational factors such as policies and regulations, market dynamics, etc. by building a comprehensive information collection channel. At the same time, it uses knowledge graph technology to build an enterprise knowledge base, and converts the core knowledge such as the enterprise's business processes and technical architecture into nodes and edges in the knowledge graph to achieve effective organization and utilization of knowledge. Through semantic matching and reasoning engines, situational factors are deeply associated and accurately matched with enterprise knowledge, and then the direct impact and potential risks of situational factors on the enterprise's business and digital transformation are analyzed. On this basis, combined with the enterprise's strategic goals and actual situation, intelligent decision-making algorithms are used to generate digital transformation decision recommendations covering short-term operational measures and long-term strategic planning. In addition, the present invention also establishes an evaluation mechanism based on actual application effect feedback to achieve continuous optimization of analysis results and decision recommendations, ensuring that enterprises can adapt to the ever-changing environment and achieve sustainable development during the digital transformation process.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: On the one hand, an intelligent analysis method for enterprise digital transformation, the method comprising the following specific steps:

[0007] Perception and preprocessing: Using web data crawling technology to obtain contextual text information from multiple channels, natural language processing is used to perform part-of-speech tagging and entity recognition before classification. Information extraction algorithms based on semantic association mining are then used to extract key information related to the business.

[0008] Knowledge graph construction steps: Collect multi-source data within the enterprise, use knowledge extraction algorithms based on pattern matching and semantic understanding to identify entities, relationships, and attributes, integrate knowledge through knowledge fusion algorithms based on entity similarity measurement and conflict resolution, and use graph databases to store knowledge to form a knowledge graph system;

[0009] Association matching: Use a deep learning-based semantic feature extraction model to convert contextual factor information and knowledge in the knowledge graph into low-dimensional vectors. Calculate vector similarity using a similarity measurement formula improved based on cosine similarity, and determine association matching relationships based on a set threshold.

[0010] Influence reasoning: Build a set of inference rules based on associations and professional knowledge, use rule-based reasoning to determine whether the situational factor information and knowledge meet the rule conditions to derive direct influences, and use reasoning models to analyze the knowledge graph to deduce indirect influences.

[0011] Decision suggestion generation and optimization: Establish a decision suggestion template library. Based on the influencing reasoning results, corporate strategic goals, resource status and business status, select the template with the highest matching degree through the template selection algorithm to generate decision suggestions. Evaluate the effect by collecting business data after implementation, and adjust and optimize the knowledge graph, reasoning rules and template library accordingly.

[0012] Furthermore, in the perception and preprocessing steps, the core information related to the enterprise business is extracted through an information extraction algorithm based on semantic association mining, and the algorithm formula is:

[0013]

[0014] Among them, S rel (E1, E2) represents the semantic association strength between two entities E1 and E2. By calculating the semantic association strength between entities, we can determine which information is relevant to the enterprise business and extract the core information. is the set of semantic association paths between entities E1 and E2, sim(s) is the semantic similarity of path s, which is used to measure the semantic similarity between the two entities connected by the path, w(s) is the weight of path s, which reflects the importance of the path in the semantic association, and E1 and E2 are entities identified from text information.

[0015] Furthermore, in the knowledge graph construction step, multi-source data within the enterprise is collected, including business process documents, technical architecture information, market competition situation analysis reports and financial statement data. Data mining tools and natural language processing technology are used to identify entity objects, relationships between entities and attributes of entities from the above multi-source data. A method based on similarity calculation and entity alignment is used to integrate the knowledge extracted from different data sources, eliminate duplicate knowledge records and conflicts between knowledge, and with the help of graph database storage technology, the integrated knowledge is stored in the form of a graph structure.

[0016] Furthermore, in the knowledge graph construction step, a method based on similarity calculation and entity alignment is used to integrate the knowledge extracted from different data sources to eliminate duplicate knowledge records and conflicts between knowledge. The calculation method is:

[0017] Sim(E1,E2)=β×Sim name (E1,E2)+(1-β)×Sim attr (E1,E2)

[0018] Among them, Sim(E1, E2) is the overall similarity between two entities E1 and E2, which is used to determine whether the entities extracted from different data sources are the same entity, so as to perform knowledge fusion and eliminate duplication and conflict. β is a weight parameter used to balance the relative importance of entity name similarity and attribute similarity in the overall similarity calculation. name (E1, E2) is the name similarity of entities E1 and E2, Sim attr (E1, E2) is the attribute similarity between entities E1 and E2, where E1 and E2 are entities extracted from different data sources.

[0019] Furthermore, in the association matching step, for the new situational factor information obtained in the perception and preprocessing steps, the semantic representation technology in natural language processing is used to convert the textual information into a low-dimensional vector form to extract its semantic features. For each entity and relationship in the knowledge graph, the semantic representation technology is used to convert it into a low-dimensional vector form to form a knowledge vector. A similarity measurement method based on vector space is used to calculate the similarity value between the new situational factor information vector and the knowledge vector in the knowledge graph. A similarity threshold is set, and the situational factor information with a similarity value greater than the threshold is associated and matched with the corresponding knowledge in the knowledge graph, thereby determining the specific association relationship between the situational factors and the enterprise knowledge.

[0020] Furthermore, in the association matching step, a similarity measurement method based on vector space is used to calculate the similarity value between the new situational factor information vector and the knowledge vector in the knowledge graph. The calculation method is:

[0021]

[0022] Among them, Sim cos-improved (V1, V2) is the similarity between the improved vectors V1 and V2, which is used to calculate the similarity between the situational factor information vector and the knowledge vector in the knowledge graph. V1 and V2 represent the situational factor information vector and the knowledge vector in the knowledge graph, respectively. They are low-dimensional vector representations obtained by semantic feature extraction. V1·V2 is the dot product of vectors V1 and V2, which is used to measure the similarity between the two vectors in direction. γ is the adjustment parameter, d is the dimension of the vector, and v 1i and v 2i : Represents the i-th element of vectors V1 and V2 respectively.

[0023] Furthermore, in the impact reasoning step, based on the association relationship between the situational factors and enterprise knowledge determined in the association matching step, combined with the professional knowledge and experience in the enterprise business field, a set of inference rules containing causal relationships and conditional relationships is constructed. Rule-based reasoning technology is used, and new situational factor information and related knowledge in the knowledge graph are used as input. Reasoning operations are performed based on the constructed inference rule set to analyze the direct impact of situational factors on each specific link of the enterprise's current business, including procurement, production, sales and after-sales. A graph-based reasoning model is used, based on the knowledge graph, to analyze the connection relationship and information transmission between the nodes in the graph, and to infer the indirect impact that situational factors may have on the enterprise's business and digital transformation at different stages.

[0024] Furthermore, the decision suggestion generation and optimization selects the template with the highest matching degree to generate the decision suggestion through a template selection algorithm based on a comprehensive evaluation of multiple factors. The template selection algorithm is:

[0025]

[0026] Among them, Score template (T k ) is the template T k The comprehensive score of w is used to evaluate the applicability of the template in generating decision recommendations. i is factor F i The weight is used to measure the importance of different factors in selecting templates. factor (F i ,T k ) is the factor F i Template T k The score of template T k In case of satisfying factor F i The ability of the aspect, m is the total number of factors used to evaluate the template, T k is the kth template in the decision suggestion template library, including short-term operation measure templates and long-term strategic planning templates. i These are the factors used to evaluate the template, including the urgency of situational factors, the enterprise's resource constraints, and market trends.

[0027] In another aspect, an intelligent analysis system for enterprise digital transformation includes the following components:

[0028] Situational Awareness and Preprocessing Module: This module connects multiple information collection channels to continuously and comprehensively monitor various situational factors. When new situational events occur, it uses information collection and natural language processing technologies to obtain information and preprocess it for detailed classification and in-depth analysis.

[0029] Knowledge graph construction module: collects multi-source data within the enterprise, uses knowledge extraction and knowledge fusion knowledge graph construction technology to convert enterprise knowledge into nodes and edges in the knowledge graph, and thus builds a knowledge graph system;

[0030] Association matching module: This module performs semantic analysis and feature extraction on new situational factor information, and uses semantic matching technology to deeply associate and accurately match it with various types of knowledge in the knowledge graph. It also determines the association relationship between situational factors and enterprise knowledge by calculating similarity.

[0031] Impact Reasoning Module: Leveraging the knowledge graph's reasoning engine, based on the associations determined by the association matching module, and applying reasoning rules and algorithms, this module conducts an in-depth analysis of the direct and indirect impacts of situational factors on various aspects of the company's current business and the different stages of its digital transformation.

[0032] Decision-making recommendation generation and optimization module: Based on the analysis results of the impact reasoning module, combined with the company's strategic goals and actual situation, the module uses intelligent decision-making algorithms to generate digital transformation decision recommendations, including short-term specific operational measures and long-term strategic planning ideas. At the same time, this module establishes an evaluation mechanism based on feedback from the actual application effects of the company's digital transformation. As situational factors change and the knowledge graph is updated and improved, the analysis results and decision recommendations are continuously optimized.

[0033] Compared with existing technologies, this intelligent analysis method and system for enterprise digital transformation has the following beneficial effects:

[0034] 1. The present invention uses multiple information collection channels to capture key information such as policy and regulatory updates, market dynamics, etc. in real time, and constructs a knowledge graph system containing rich enterprise knowledge. It can deeply associate and accurately match new situational factors with internal business processes, technical architecture and other knowledge of the enterprise, so that the system can provide enterprises with more scientific and accurate digital transformation decision-making recommendations, help enterprises better respond to changes in the external environment, optimize internal management processes, and improve business operation efficiency.

[0035] 2. By establishing an evaluation mechanism based on feedback on the actual application effects of enterprise digital transformation, the present invention can collect and analyze in real time the actual effect data of enterprises in the process of implementing decision-making recommendations. Based on these data, the analysis results and decision-making recommendations are evaluated, and the knowledge graph, inference rules and decision-making algorithms are adjusted and optimized according to the evaluation results, so that the system can continuously adapt to changes in the internal and external environment of the enterprise, provide enterprises with more practical and forward-looking digital transformation decision-making recommendations, and help enterprises achieve sustainable development.

[0036] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0038] Figure 1 A flowchart of an intelligent analysis method for enterprise digital transformation;

[0039] Figure 2 This is a structural diagram of an intelligent analysis system for enterprise digital transformation. DETAILED DESCRIPTION

[0040] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0041] Example 1

[0042] A large manufacturing company mainly produces auto parts, with business covering parts design, production, sales and after-sales service. The company faces problems such as frequent updates of automotive industry policies and regulations (such as environmental protection standards and safety regulations), fierce market competition leading to large fluctuations in market demand, and challenges brought by industry technological innovation. It urgently needs digital transformation to enhance its competitiveness.

[0043] Every hour, we capture information on situational factors such as policy and regulatory updates (such as updates on environmental protection standards related to new energy vehicle parts), market demand fluctuations (such as seasonal changes in demand for parts for different models), and industry technological innovation trends (such as the application of new materials in automotive parts) from multiple channels such as the websites of relevant government departments (such as the websites of the Ministry of Industry and Information Technology and the Ministry of Environmental Protection), automotive industry news media, and professional market research institutions. We perform word segmentation, part-of-speech tagging, and entity recognition on the captured information, and classify the information into policy and regulation categories, market dynamics categories, technological innovation categories, etc. We use information extraction methods to extract core points related to the company's production process, product quality, market share, and other businesses, such as the specific restrictions on pollutant emissions in the production process of a new environmental protection policy.

[0044] Collect business process documents (such as parts production process, supply chain management process), technical architecture information (such as technical parameters of production equipment, technical roadmap of product development), market competition situation analysis reports, financial statements and other data from the enterprise every month, identify entities (such as production workshops, R&D departments, key parts products, major customers, etc.), relationships (such as the collaborative relationship between production workshops and R&D departments, the supply and demand relationship between products and customers) and attributes (such as specifications of parts products, performance indicators of production equipment) from these data, and use methods based on similarity calculation and entity alignment to integrate the extracted knowledge and eliminate duplication and conflict. The calculation method is: Sim(E1, E2) = β × Sim name (E1,E2)+(1-β)×Sim attr (E1, E2), where Sim(E1, E2) is the overall similarity between two entities E1 and E2, which is used to determine whether the entities extracted from different data sources are the same entity, thereby performing knowledge fusion and eliminating duplication and conflict. β is a weight parameter used to balance the relative importance of entity name similarity and attribute similarity in the overall similarity calculation. Sim name (E1, E2) is the name similarity of entities E1 and E2, Sim attr (E1, E2) is the attribute similarity between entities E1 and E2. E1 and E2 are entities extracted from different data sources. With the help of a graph database, the integrated knowledge is constructed into a knowledge graph. For example, the "production workshop" is used as a node, which is connected to the "R&D department" node through a "collaboration relationship" edge, and the relevant attribute information such as the collaboration content and frequency is annotated.

[0045] Semantic representation technology is used to convert newly acquired situational factor information (such as new environmental protection policy information) and knowledge in the knowledge graph (such as knowledge related to the company's production process) into low-dimensional vectors. The vector similarity is calculated using a similarity measurement method based on vector space. It is found that the restrictions on pollutant emissions in the new environmental protection policy are related to the emission indicators of a certain link in the company's production process. The correlation between the two is determined by the following calculation method: Among them, Sim cos-improved (V1, V2) is the similarity between the improved vectors V1 and V2, which is used to calculate the similarity between the situational factor information vector and the knowledge vector in the knowledge graph. V1 and V2 represent the situational factor information vector and the knowledge vector in the knowledge graph, respectively. They are low-dimensional vector representations obtained by semantic feature extraction. V1·V2 is the dot product of vectors V1 and V2, which is used to measure the similarity between the two vectors in direction. γ is the adjustment parameter, d is the dimension of the vector, and v 1i and v 2i : Represents the i-th element of vectors V1 and V2 respectively.

[0046] Based on the experience and historical data of the company's business experts, a set of inference rules is constructed, such as "If environmental protection policies lower the emission limits for a certain type of pollutant, the company needs to adjust the corresponding processing links in the production process." The new environmental protection policy information and production process-related knowledge in the knowledge graph are input to infer the direct impact, that is, the company needs to adjust the existing production process to meet the new environmental protection requirements. Using a graph-based reasoning model, indirect impacts are analyzed, such as how adjustments to the production process may lead to changes in raw material procurement needs, as well as the need for maintenance and upgrades of production equipment.

[0047] The template library contains templates for short-term operational measures (such as specific steps for adjusting production processes and plans for purchasing new environmentally friendly equipment) and templates for long-term strategic planning ideas (such as laying out the research and development direction of environmentally friendly parts and components and establishing long-term cooperative relationships with environmentally friendly technology suppliers). Based on the results of impact reasoning, combined with the company's strategic goals (such as becoming a leading environmental protection company in the industry), resource status (existing funds and technical personnel reserves) and business status, appropriate templates are selected from the template library to generate decision recommendations, such as purchasing new sewage treatment equipment in the short term to meet new emission requirements, increasing investment in the research and development of environmentally friendly parts in the long term, and collecting production data (such as output and scrap rate) and cost data (such as raw material procurement costs and equipment maintenance costs) through the company's ERP system every quarter to evaluate the implementation effect of the decision recommendations.

[0048] Based on the evaluation results, the production process knowledge in the knowledge graph, the relevant rules in the inference rule set, and the templates in the decision recommendation template library are adjusted and optimized. For example, if it is found that the scrap rate increases after the new production process is adjusted, the production process-related knowledge and inference rules are adjusted, and the specific content about the production process adjustment in the decision recommendation template is updated.

[0049] Example 2

[0050] A financial services company provides a variety of financial services, including banking, securities, and insurance. It faces challenges such as evolving financial regulatory policies (such as interest rate adjustments and strengthened risk management requirements), financial market fluctuations (such as stock market fluctuations and exchange rate fluctuations), and diversified customer needs (such as personalized wealth management needs and growing demand for mobile payments). Digital transformation is crucial for improving service quality and risk management capabilities. The company captures information from relevant online channels hourly on contextual factors such as updates to financial regulatory policies (such as new capital adequacy requirements), changes in financial market conditions (such as stock index fluctuations and bond yields), and customer demand trends (such as increased demand for mobile payment convenience). The company then performs word segmentation, part-of-speech tagging, and entity recognition on this information, categorizing it into policies and regulations, market dynamics, and customer needs. It also extracts key points related to the company's business (such as lending, investment, and customer service), such as the impact of new capital adequacy requirements on the company's loan limits and investment portfolio.

[0051] Every month, we collect internal business process documents (such as loan approval processes and customer service processes), technical architecture information (such as financial transaction system architecture and customer information management system function introduction), market competition situation analysis reports, financial statements and other data to identify entities (such as different business departments, financial products, customer groups, etc.), relationships (such as the collaborative relationship between business departments, the matching relationship between financial products and customer groups) and attributes (such as the yield rate, risk level, customer credit rating of financial products, etc.), integrate the extracted knowledge, eliminate duplication and conflicts, and use the graph database to build a knowledge graph. For example, we use the "loan business department" as a node, which is connected to the "investment business department" node through the "business collaboration relationship" edge, and mark the attribute information such as the business scope and frequency of the collaboration.

[0052] Convert new situational factor information (such as interest rate policy adjustment information) and knowledge in the knowledge graph (such as knowledge related to corporate loan business) into low-dimensional vectors, calculate vector similarity, and determine the correlation between interest rate policy adjustments and knowledge such as loan interest rate setting and loan approval standards in corporate loan business.

[0053] Construct a set of inference rules, such as "If interest rates fall, the company's loan business demand may increase, and the loan approval process and risk assessment standards need to be adjusted." Infer the direct impact, that is, the company needs to simplify the loan approval process and adjust risk assessment indicators to cope with the possible increase in loan demand. At the same time, infer the indirect impact, such as the increase in loan business demand may have an impact on the company's liquidity management, requiring the investment portfolio to ensure sufficient funds, and at the same time, the workload and service quality requirements of the customer service department will also increase.

[0054] The template library contains templates for short-term operational measures (such as adjusting the specific steps of the loan approval process and increasing customer service staff training programs) and templates for long-term strategic planning ideas (such as optimizing investment portfolio strategies and developing customer risk assessment models based on big data). Based on the impact reasoning results, combined with the company's strategic goals (such as increasing market share and enhancing risk management capabilities), resource status (existing funds and technical personnel reserves) and business status, decision-making recommendations are generated, such as increasing the number of loan approval personnel in the short term to cope with business volume growth, and increasing investment in big data technology research and development in the long term to improve risk management levels.

[0055] Every quarter, the company collects data such as the number of loan approvals, customer satisfaction, and liquidity indicators through its business information system to evaluate the implementation effect of decision recommendations. Based on the evaluation results, the loan business knowledge in the knowledge graph, the relevant rules in the inference rule set, and the templates in the decision recommendation template library are adjusted and optimized. If it is found that the approval efficiency does not meet expectations after adding more loan approval personnel, the relevant knowledge and inference rules of the loan approval process will be adjusted, and the content on personnel allocation and process optimization in the decision recommendation template will be updated.

[0056] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent analysis method for enterprise digital transformation, characterized by: The method comprises the following specific steps: Perception and preprocessing: Using web data crawling technology to obtain contextual text information from multiple channels, natural language processing is used to perform part-of-speech tagging and entity recognition before classification. Information extraction algorithms based on semantic association mining are then used to extract key information related to the business. Knowledge graph construction steps: Collect multi-source data within the enterprise, use knowledge extraction algorithms based on pattern matching and semantic understanding to identify entities, relationships, and attributes, integrate knowledge through knowledge fusion algorithms based on entity similarity measurement and conflict resolution, and use graph databases to store knowledge to form a knowledge graph system; Association matching: Use a deep learning-based semantic feature extraction model to convert contextual factor information and knowledge in the knowledge graph into low-dimensional vectors. Calculate vector similarity using a similarity measurement formula improved based on cosine similarity, and determine association matching relationships based on a set threshold. Influence reasoning: Build a set of inference rules based on associations and professional knowledge, use rule-based reasoning to determine whether the situational factor information and knowledge meet the rule conditions to derive direct influences, and use reasoning models to analyze the knowledge graph to deduce indirect influences. Decision suggestion generation and optimization: Establish a decision suggestion template library. Based on the influencing reasoning results, corporate strategic goals, resource status and business status, select the template with the highest matching degree through the template selection algorithm to generate decision suggestions. Evaluate the effect by collecting business data after implementation, and adjust and optimize the knowledge graph, reasoning rules and template library accordingly.

2. The intelligent analysis method for enterprise digital transformation according to claim 1, characterized in that: In the perception and preprocessing steps, the core information related to the enterprise business is extracted through an information extraction algorithm based on semantic association mining. The algorithm formula is: Among them, S rel (E1, E2) represents the semantic association strength between two entities E1 and E2. By calculating the semantic association strength between entities, we can determine which information is relevant to the enterprise business and extract the core information. is the set of semantic association paths between entities E1 and E2, sim(s) is the semantic similarity of path s, which is used to measure the semantic similarity between the two entities connected by the path, w(s) is the weight of path s, which reflects the importance of the path in the semantic association, and E1 and E2 are entities identified from text information.

3. The intelligent analysis method for enterprise digital transformation according to claim 1, characterized in that: In the knowledge graph construction step, multi-source data within the enterprise is collected, including business process documents, technical architecture information, market competition situation analysis reports and financial statement data. Data mining tools and natural language processing technology are used to identify entity objects, relationships between entities and attributes of entities from the above multi-source data. A method based on similarity calculation and entity alignment is used to integrate the knowledge extracted from different data sources to eliminate duplicate knowledge records and conflicts between knowledge. With the help of graph database storage technology, the integrated knowledge is stored in the form of a graph structure, where nodes represent entities and edges represent relationships between entities, thereby constructing a knowledge graph system.

4. The intelligent analysis method for enterprise digital transformation according to claim 3 is characterized in that: In the knowledge graph construction step, a method based on similarity calculation and entity alignment is used to integrate the knowledge extracted from different data sources to eliminate duplicate knowledge records and conflicts between knowledge. The calculation method is: Sim(E1,E2)=β×Sim name (E1,E2)+(1-β)×Sim attr (E1,E2) Among them, Sim(E1, E2) is the overall similarity between two entities E1 and E2, which is used to determine whether the entities extracted from different data sources are the same entity, so as to perform knowledge fusion and eliminate duplication and conflict. β is a weight parameter used to balance the relative importance of entity name similarity and attribute similarity in the overall similarity calculation. name (E1, E2) is the name similarity of entities E1 and E2, Sim attr (E1, E2) is the attribute similarity between entities E1 and E2, where E1 and E2 are entities extracted from different data sources.

5. The intelligent analysis method for enterprise digital transformation according to claim 1, characterized in that: In the association matching step, for the new situational factor information obtained in the perception and preprocessing steps, the semantic representation technology in natural language processing is used to convert the textual information into a low-dimensional vector form to extract its semantic features. For each entity and relationship in the knowledge graph, the semantic representation technology is used to convert it into a low-dimensional vector form to form a knowledge vector. A similarity measurement method based on vector space is used to calculate the similarity value between the new situational factor information vector and the knowledge vector in the knowledge graph. A similarity threshold is set, and the situational factor information with a similarity value greater than the threshold is associated and matched with the corresponding knowledge in the knowledge graph, thereby determining the specific association relationship between the situational factors and the enterprise knowledge.

6. The intelligent analysis method for enterprise digital transformation according to claim 5, characterized in that: In the association matching step, a similarity measurement method based on vector space is used to calculate the similarity value between the new situational factor information vector and the knowledge vector in the knowledge graph. The calculation method is: Among them, Sim cos-improved (V1, V2) is the similarity between the improved vectors V1 and V2, which is used to calculate the similarity between the situational factor information vector and the knowledge vector in the knowledge graph. V1 and V2 represent the situational factor information vector and the knowledge vector in the knowledge graph, respectively. They are low-dimensional vector representations obtained by semantic feature extraction. V1·V2 is the dot product of vectors V1 and V2, which is used to measure the similarity between the two vectors in direction. γ is the adjustment parameter, d is the dimension of the vector, and v 1i and v 2i : Represents the i-th element of vectors V1 and V2 respectively.

7. The intelligent analysis method for enterprise digital transformation according to claim 1, characterized in that: In the impact reasoning step, based on the association relationship between the situational factors and enterprise knowledge determined in the association matching step, combined with the professional knowledge and experience in the enterprise business field, a set of inference rules containing causal relationships and conditional relationships is constructed. Rule-based reasoning technology is used, and new situational factor information and related knowledge in the knowledge graph are used as input. Reasoning operations are performed based on the constructed inference rule set to analyze the direct impact of situational factors on each specific link of the enterprise's current business, including procurement, production, sales and after-sales. A graph-based reasoning model is used, based on the knowledge graph, to analyze the connection relationship and information transmission between the nodes in the graph, and to infer the indirect impact that situational factors may have on the enterprise's business and digital transformation at different stages.

8. The intelligent analysis method for enterprise digital transformation according to claim 1, characterized in that: The decision suggestion generation and optimization is to select the template with the highest matching degree to generate decision suggestions through a template selection algorithm based on comprehensive evaluation of multiple factors. The template selection algorithm is as follows: Among them, Score template (T k ) is the template T k The comprehensive score of w is used to evaluate the applicability of the template in generating decision recommendations. i is factor F i The weight is used to measure the importance of different factors in selecting templates. factor (F i ,T k ) is the factor F i Template T k The score of template T k In case of satisfying factor F i The ability of the aspect, m is the total number of factors used to evaluate the template, T k is the kth template in the decision suggestion template library, including short-term operation measure templates and long-term strategic planning templates. i These are the factors used to evaluate the template, including the urgency of situational factors, the enterprise's resource constraints, and market trends.

9. An intelligent analysis system for enterprise digital transformation, the system being applicable to an intelligent analysis method for enterprise digital transformation according to any one of claims 1 to 8, characterized in that: The system includes the following components: Situational Awareness and Preprocessing Module: This module connects multiple information collection channels to continuously and comprehensively monitor various situational factors. When new situational events occur, it uses information collection and natural language processing technologies to obtain information and perform preprocessing for detailed classification and in-depth analysis. Knowledge graph construction module: collects multi-source data within the enterprise, uses knowledge extraction and knowledge fusion knowledge graph construction technology to convert enterprise knowledge into nodes and edges in the knowledge graph, and thus builds a knowledge graph system; Association matching module: This module performs semantic analysis and feature extraction on new situational factor information, and uses semantic matching technology to deeply associate and accurately match it with various types of knowledge in the knowledge graph. It also determines the association relationship between situational factors and enterprise knowledge by calculating similarity. Impact Reasoning Module: Leveraging the knowledge graph's reasoning engine, based on the associations determined by the association matching module, and applying reasoning rules and algorithms, this module conducts an in-depth analysis of the direct and indirect impacts of situational factors on various aspects of the company's current business and the different stages of its digital transformation. Decision-making recommendation generation and optimization module: Based on the analysis results of the impact reasoning module, combined with the company's strategic goals and actual situation, the module uses intelligent decision-making algorithms to generate digital transformation decision recommendations, including short-term specific operational measures and long-term strategic planning ideas. At the same time, this module establishes an evaluation mechanism based on feedback from the actual application effects of the company's digital transformation. As situational factors change and the knowledge graph is updated and improved, the analysis results and decision recommendations are continuously optimized.

Images