Enterprise information technology consulting service system based on big data

Abstract

The present invention discloses an enterprise information technology consulting service system based on big data, which belongs to the field of information technology consulting management technology. In order to solve the problems of poor data source management, the complexity of data relationships affecting the difficulty of understanding, and insufficient knowledge management and utilization, the establishment of a data source directory and the optimization of the ETL process ensure the timeliness and accuracy of data, provide a high-quality data source for data analysis, and enhance the accuracy and value of consulting suggestions. The graph generation unit visualizes complex data relationships, promotes in-depth understanding of enterprise operations and market trends, and supports more accurate decision-making. The introduction of demand acquisition and analysis units improves the efficiency and accuracy of demand acquisition, and provides a clear direction and solid foundation for the customization of consulting solutions. The present invention comprehensively improves the system's data processing capabilities, analysis depth, and decision support efficiency, which helps decision makers make accurate judgments quickly.

Description

Technical Field

[0001] The present invention relates to the field of information technology consulting management technology, and in particular to an enterprise information technology consulting service system based on big data. Background Art

[0002] Enterprise information technology consulting services refer to business activities that use computer software, network technology and communication technology to provide enterprises with comprehensive information solutions and services. These services cover information strategy planning, information system design and development, information security consulting, data management and big data analysis, information technology operation and management, etc. Through professional technical consulting and services, enterprise information technology consulting services aim to help enterprises optimize business processes, improve work efficiency, reduce operating costs, and promote technological innovation and industrial upgrading.

[0003] However, there are still the following problems in actual operation:

[0004] Existing systems often face problems such as chaotic data source management, inaccurate or missing information, which makes it difficult to obtain data and affects the accuracy of data analysis and consulting recommendations. In enterprise information technology consulting services, data relationships are complex and changeable, and traditional methods are difficult to display and understand intuitively. At the same time, existing systems often lack effective knowledge management and utilization mechanisms, which makes it difficult for enterprises to quickly obtain the required knowledge and information to support business decisions and innovation activities. Summary of the invention

[0005] The purpose of the present invention is to provide an enterprise information technology consulting service system based on big data to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solutions: an enterprise information technology consulting service system based on big data, comprising:

[0007] Data acquisition module, used to:

[0008] Integrate data sources, obtain data in real time and in batches from data sources based on API interfaces, clean the data, store it through distributed file systems, build data warehouses, and convert data from operational databases to analytical databases through ETL processes;

[0009] Data analysis module for:

[0010] Process and analyze the real-time data in the database, and perform offline batch data processing through the big data processing framework. Put the processed data into the clustering model for analysis and calculation to obtain data pattern analysis results, and display the analysis results through charts;

[0011] Graph building blocks for:

[0012] Connecting data points into a data graph network based on data pattern analysis results, generating a structured knowledge base based on the data graph network, and providing complex queries based on graph structures, including path queries and similarity queries;

[0013] Consulting service modules for:

[0014] Provide enterprise information technology consulting services, obtain the consulting needs of current consultants, analyze the consulting needs of current consultants, call the graph network structured knowledge base for intelligent reasoning based on the consulting needs analysis results, customize solutions based on user behavior, enterprise needs and industry trends and according to the current consultants' enterprise needs, obtain customized solution integration data, generate reports based on the customized solution integration data and recommend them to current consultants;

[0015] Interactive feedback module, used to:

[0016] Generate a user interface that supports multiple interaction methods, including voice, text, and graphics, and generate a user feedback channel.

[0017] Furthermore, the data acquisition module is also used for:

[0018] Establish a data source directory to record the URL, API key, and update frequency information of each data source, including internal enterprise systems, social media, industry reports, customer feedback, device logs, and public data sources;

[0019] For data sources that support API, call the API interface to automatically pull data. For data sources that do not support API and need to crawl web page data, crawl data through web crawlers and verify the obtained raw data.

[0020] Clean, deduplicate and format the raw data obtained from the data source;

[0021] The cleaned data is stored in a distributed file system, and a data warehouse is built. The data is converted from the operational database to the analytical database through the ETL process, and the data is partitioned and indexed according to query requirements.

[0022] Furthermore, the data acquisition module further includes:

[0023] A real-time monitoring module is used to monitor in real time the operating parameters of calling the API interface to automatically pull data, wherein the operating parameters include the number of call requests received by the API interface per unit time, the maximum time to wait for the API interface to respond, and the number of call requests sent to the API interface at the same time per unit time, and the value range of the unit time is 10s-30s;

[0024] The first interface pulls the operation parameter acquisition module, which is used to obtain the first interface pull operation parameters by using the number of call requests received by the API interface per unit time and the longest time to wait for the API interface to respond; wherein, the first interface pulls the operation parameters by the following formula:

[0025]

[0026] Among them, S 01 Indicates the first interface pulls the running parameters; n indicates the number of unit time that the API interface has experienced; C i Indicates the number of call requests received by the API interface corresponding to the i-th unit time; C y represents the reference value corresponding to the number of call requests received by the preset API interface; maxi represents the maximum time interval between two adjacent call requests corresponding to the i-th unit time; T pi T represents the maximum time to wait for the API interface response corresponding to the i-th unit time; z Indicates the median value of the longest time to wait for an API response corresponding to n units of time;

[0027] The second interface pulls the operation parameter acquisition module, which is used to obtain the second interface pull operation parameter by using the number of call requests sent to the API interface at the same time in the unit time; wherein the second interface pulls the operation parameter by the following formula:

[0028]

[0029] Among them, S 02 Indicates the second interface pulls the running parameters; n indicates the number of unit time that the API interface has experienced; N maxi represents the maximum number of call requests sent to the API interface at the same time in the unit time corresponding to the i-th unit time; C zi Indicates the total number of call requests sent to the API interface in the i-th unit time; f i It represents the change coefficient of the number of call requests corresponding to the i-th unit time, and the change coefficient of the number of call requests corresponding to each unit time is obtained by the following formula:

[0030]

[0031] Wherein, m represents the number of times multiple call requests are sent to the API interface at the same time corresponding to the i-th unit time; N j represents the number of call requests sent corresponding to the number of times that multiple call requests are sent to the API interface at the same time by the jth call request corresponding to the i-th unit time; C z Indicates the total number of call requests sent to the API interface per unit time;

[0032] The pull operation quality index parameter acquisition module is used to obtain the pull operation quality index parameter by using the first interface to pull the operation parameter and the second interface to pull the operation parameter, wherein the pull operation quality index parameter is obtained by the following formula:

[0033]

[0034] Among them, S represents the operation quality index parameter; S 01 Indicates that the first interface pulls the operating parameters; S 02 Indicates that the second interface pulls the operating parameters;

[0035] A comparison module, used for comparing the pull operation quality index parameter with a preset index parameter threshold;

[0036] The request quantity setting module is used to set a quantity limit on the number of call requests received by the API interface per unit time when the pull operation quality index parameter is lower than a preset index parameter threshold.

[0037] Furthermore, the request quantity setting module includes:

[0038] A first data extraction module, used to extract the first interface pull operation parameters and the second interface pull operation parameters;

[0039] A second data extraction module, used to extract the difference between the pulling operation quality index parameter and a preset index parameter threshold;

[0040] A quantity upper limit value setting module, used to obtain a quantity upper limit value corresponding to the number of call requests by using the first interface pull operation parameter and the second interface pull operation parameter combined with the difference between the pull operation quality index parameter and a preset index parameter threshold;

[0041] The upper limit of the number of call requests is obtained by the following formula:

[0042]

[0043] Among them, C up Indicates the upper limit of the number of call requests; Cmax and C min Indicates the maximum and minimum number of call requests received by the API interface within n units of time; C z represents the total number of call requests sent to the API interface per unit time; S represents the operation quality indicator parameter; S 01 Indicates that the first interface pulls the operating parameters; S 02 Indicates that the second interface pulls the operating parameters; S y Indicates the preset indicator parameter threshold.

[0044] Furthermore, the data analysis module is also used to:

[0045] The stream processing framework is used to capture and process real-time data streams, detect patterns, trends, and anomalies in the data, mine patterns and associations in the data through cluster analysis, and display real-time analysis results in the form of dashboards and real-time charts.

[0046] Furthermore, the graph construction module includes:

[0047] A graph generation unit is used to:

[0048] Convert the data pattern analysis results output by the data processing module into a data graph network, and define nodes and edges in the graph according to the data pattern analysis results, wherein the nodes include users, products and events, and the edges include purchase relationships and association relationships;

[0049] A data graph is constructed through a graph processing framework, data points are connected into a network, and attribute information of nodes and edges is stored. The generated graph is optimized to remove redundant nodes and edges and merge similar nodes.

[0050] Furthermore, the graph construction module further includes:

[0051] Knowledge base building blocks for:

[0052] Based on the data graph network, a structured knowledge base is constructed, key information including entities, attributes and relationships is extracted from the data graph, structured knowledge items are generated, and the knowledge items are converted into a matrix form;

[0053] Store structured knowledge in the knowledge base system, provide complex query functions based on graph structure, regularly update the data in the knowledge base, and provide maintenance tools for adding, deleting, modifying and querying the knowledge base.

[0054] Furthermore, the consulting service module also includes:

[0055] Requirements acquisition unit, used to:

[0056] Responsible for collecting and understanding consulting needs from consultants, receiving consulting needs through web forms, voice assistants, and instant messaging tools, parsing consulting needs, extracting consulting needs information, including consulting topics, specific issues, and expected goals, and organizing the parsed consulting needs information into a structured form;

[0057] Requirements Analysis Unit, used to:

[0058] Based on the consulting demand information obtained, assist humans in conducting research on industry background, enterprise status, and technology trends, break down the consulting demand information into actionable tasks and problem points, determine the specific requirements and constraints for each task and problem point, evaluate the feasibility and priority of the consulting demand information based on tasks and problem points, and generate demand analysis results.

[0059] Furthermore, the consulting service module also includes:

[0060] Customized solution unit for:

[0061] Based on the results of demand analysis, relevant knowledge items, cases and best practices are searched in the graph network structured knowledge base, and solutions are inferred based on user behavior, enterprise needs and industry trends. According to the inference results and the actual situation of the enterprise, solutions are customized, including technology selection, implementation steps and expected results.

[0062] The report recommends units for:

[0063] Fill the solution content into the report template to automatically generate a complete consulting report, and recommend the generated report to consultants via email or instant messaging tools.

[0064] Furthermore, the interactive feedback module is also used to:

[0065] Feedback collection unit, used to:

[0066] Generate user feedback channels, including web forms, emails, and instant messaging tools, and automatically collect feedback submitted by users in the feedback channels through back-end services, and organize and classify them for subsequent analysis and processing;

[0067] Feedback response unit for:

[0068] Process and respond to collected user feedback, extract keywords from the text content in user feedback, identify user concerns, and classify feedback issues based on analysis results. Problem categories include feature suggestions, error reports, and service evaluations. Based on problem classification and user historical data, generate personalized replies and solutions, and return them to users through user feedback channels.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] 1. The invention establishes a data source directory and records detailed information of each data source, which helps system administrators to better manage and maintain data sources, ensures the timeliness and accuracy of data, and reduces data acquisition problems caused by inaccurate or missing data source information. It converts data from an operational database to an analytical database through the ETL process, and partitions and indexes data according to query requirements, which can significantly improve the response speed and performance of data queries. The optimized data storage and query mechanism provides a richer and higher-quality data source for the data analysis module, enabling the system to more comprehensively and deeply analyze various aspects of enterprise information technology consulting services, thereby providing enterprises with more accurate and valuable consulting advice.

[0071] 2. The graph generation unit of the present invention converts the data pattern analysis results output by the data processing module into a data graph network. By defining nodes and edges, complex data relationships become intuitive and easy to understand, which helps enterprises to have a deeper understanding of user behavior, product characteristics and market trends, and thus make more accurate decisions. The data graph constructed by the graph processing framework not only connects data points into a network, but also stores the attribute information of nodes and edges, optimizes the organization and storage of data, and makes data query and analysis more efficient. The knowledge base construction unit constructs a structured knowledge base based on the data graph network, extracts key information from the graph and generates structured knowledge entries, which facilitates the storage, retrieval and utilization of knowledge. Enterprises can quickly obtain the required knowledge and information through the knowledge base to support business decision-making and innovation activities.

[0072] 3. The demand acquisition unit of the present invention receives consulting needs through diversified channels, which not only improves the convenience of user interaction, but also significantly improves the efficiency and accuracy of demand acquisition through automated parsing and structured organization, which helps consultants to understand customer needs more accurately and lays a solid foundation for subsequent analysis and solution customization. After obtaining the consulting demand information, the demand analysis unit conducts in-depth research on the industry background, corporate status, and technological trends, and refines the consulting needs into actionable tasks and problem points, which not only enhances the depth of understanding of the consulting needs, but also provides clear guidance for subsequent solution customization by evaluating feasibility and priority. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 This is a module schematic diagram of the enterprise information technology consulting service system based on big data of the present invention. DETAILED DESCRIPTION

[0074] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0075] In order to solve the problems that existing systems often face, such as chaotic data source management, inaccurate or missing information, which makes it difficult to obtain data and affects the accuracy of data analysis and consulting suggestions, in enterprise information technology consulting services, data relationships are complex and changeable, and traditional methods are difficult to intuitively display and understand. At the same time, existing systems often lack effective knowledge management and utilization mechanisms, which makes it difficult for enterprises to quickly obtain the required knowledge and information to support business decisions and innovation activities. Technical issues, please refer to Figure 1 , the present invention provides the following technical solutions:

[0076] The enterprise information technology consulting service system based on big data includes:

[0077] Data acquisition module, used to:

[0078] Integrate data sources, obtain data in real time and in batches from data sources based on API interfaces, clean the data, store it through distributed file systems, build data warehouses, and convert data from operational databases to analytical databases through ETL processes;

[0079] Data analysis module for:

[0080] Process and analyze the real-time data in the database, and perform offline batch data processing through the big data processing framework. Put the processed data into the clustering model for analysis and calculation to obtain data pattern analysis results, and display the analysis results through charts;

[0081] Graph building blocks for:

[0082] Connecting data points into a data graph network based on data pattern analysis results, generating a structured knowledge base based on the data graph network, and providing complex queries based on graph structures, including path queries and similarity queries;

[0083] Consulting service modules for:

[0084] Provide enterprise information technology consulting services, obtain the consulting needs of current consultants, analyze the consulting needs of current consultants, call the graph network structured knowledge base for intelligent reasoning based on the consulting needs analysis results, customize solutions based on user behavior, enterprise needs and industry trends and according to the current consultants' enterprise needs, obtain customized solution integration data, generate reports based on the customized solution integration data and recommend them to current consultants;

[0085] Interactive feedback module, used to:

[0086] Generate a user interface that supports multiple interaction methods, including voice, text, and graphics, and generate a user feedback channel.

[0087] In the above embodiment, through data source integration and real-time batch data acquisition, the system can comprehensively and timely collect data from various aspects such as internal enterprise systems, social media, industry reports, customer feedback, equipment logs, and public data sources. Data cleaning and distributed file system storage ensure the quality and accessibility of the data, providing a solid foundation for subsequent data analysis. The ETL process realizes a smooth transition from an operational database to an analytical database, improving data processing efficiency and analysis accuracy.

[0088] In the above embodiment, the data analysis module not only processes real-time data, but also uses the big data processing framework to perform offline batch data processing, thereby improving the breadth and depth of data processing. The application of clustering models enables the system to mine data patterns from massive data and display the results through charts, making complex data analysis results intuitive and easy to understand.

[0089] In the above embodiment, the graph construction module constructs a data graph network based on the data pattern analysis results and generates a structured knowledge base, which helps to reveal the intrinsic connections and potential laws between the data. The provided graph structure complex query function enhances the system's knowledge retrieval and reasoning capabilities, making consulting services more accurate and efficient.

[0090] In the above embodiment, the consulting service module can accurately obtain and analyze the consulting needs of consultants, and perform intelligent reasoning based on user behavior, enterprise needs and industry trends, so as to customize a consulting service plan that meets the actual situation of the enterprise. The generated customized report not only contains rich data and analysis results, but also provides specific suggestions and improvement measures, which helps enterprises make more scientific and reasonable decisions.

[0091] In the above embodiment, the interactive feedback module supports multiple interactive modes, meets the interactive needs of different users, improves the system's usability and user experience, and the establishment of user feedback channels enables enterprises to timely understand users' satisfaction with consulting services and improvement suggestions, which helps to continuously optimize the system and improve service quality.

[0092] The data acquisition module is also used to:

[0093] Establish a data source directory to record the URL, API key, and update frequency information of each data source, including internal enterprise systems, social media, industry reports, customer feedback, device logs, and public data sources;

[0094] For data sources that support API, call the API interface to automatically pull data. For data sources that do not support API and need to crawl web page data, crawl data through web crawlers and verify the obtained raw data.

[0095] Clean, deduplicate and format the raw data obtained from the data source;

[0096] The cleaned data is stored in a distributed file system, and a data warehouse is built. The data is converted from the operational database to the analytical database through the ETL process, and the data is partitioned and indexed according to query requirements.

[0097] In the above embodiment, establishing a data source directory and recording detailed information of each data source helps system administrators to better manage and maintain data sources, ensure the timeliness and accuracy of data, and reduce data acquisition problems caused by inaccurate or missing data source information. It supports automatic data pulling through API interfaces and also has the ability to crawl web page data. This enables the system to flexibly handle various types of data sources, reduce manual intervention, and improve the efficiency and accuracy of data processing.

[0098] In the above embodiment, the cleaned data is stored in a distributed file system and managed and organized using a data warehouse, so that large-scale data sets can be efficiently stored and accessed. At the same time, the data is converted from an operational database to an analytical database through the ETL process, and the data is partitioned and indexed according to query requirements, which can significantly improve the response speed and performance of data queries. The optimized data storage and query mechanism provides a richer and higher-quality data source for the data analysis module, enabling the system to more comprehensively and deeply analyze various aspects of enterprise information technology consulting services, thereby providing enterprises with more accurate and valuable consulting advice.

[0099] Specifically, the data acquisition module further includes:

[0100] A real-time monitoring module is used to monitor in real time the operating parameters of calling the API interface to automatically pull data, wherein the operating parameters include the number of call requests received by the API interface per unit time, the maximum time to wait for the API interface to respond, and the number of call requests sent to the API interface at the same time per unit time, and the value range of the unit time is 10s-30s;

[0101] The first interface pull operation parameter acquisition module is used to obtain the first interface pull operation parameters by using the number of call requests received by the API interface per unit time and the longest time to wait for the API interface response; wherein the first interface pull operation parameters are obtained by the following formula:

[0102]

[0103] Among them, S 01 Indicates the first interface pulls the running parameters; n indicates the number of unit time that the API interface has experienced; C i Indicates the number of call requests received by the API interface corresponding to the i-th unit time; C y Indicates the reference value corresponding to the number of call requests received by the preset API interface; T maxi represents the maximum time interval between two adjacent call requests corresponding to the i-th unit time; T pi T represents the maximum time to wait for the API interface response corresponding to the i-th unit time; z Indicates the median value of the longest time to wait for an API response corresponding to n units of time;

[0104] The second interface pulls the operation parameter acquisition module, which is used to obtain the second interface pull operation parameter by using the number of call requests sent to the API interface at the same time in the unit time; wherein the second interface pulls the operation parameter by the following formula:

[0105]

[0106] Among them, S 02 Indicates the second interface pulls the running parameters; n indicates the number of unit time that the API interface has experienced; N maxi represents the maximum number of call requests sent to the API interface at the same time in the unit time corresponding to the i-th unit time; C zi Indicates the total number of call requests sent to the API interface in the i-th unit time; f i It represents the change coefficient of the number of call requests corresponding to the i-th unit time, and the change coefficient of the number of call requests corresponding to each unit time is obtained by the following formula:

[0107]

[0108] Wherein, m represents the number of times multiple call requests are sent to the API interface at the same time corresponding to the i-th unit time; N j represents the number of call requests sent corresponding to the number of times that multiple call requests are sent to the API interface at the same time by the jth call request corresponding to the i-th unit time; C z Indicates the total number of call requests sent to the API interface per unit time;

[0109] The pull operation quality index parameter acquisition module is used to obtain the pull operation quality index parameter by using the first interface to pull the operation parameter and the second interface to pull the operation parameter, wherein the pull operation quality index parameter is obtained by the following formula:

[0110]

[0111] Among them, S represents the operation quality index parameter; S 01 Indicates that the first interface pulls the operating parameters; S 02 Indicates that the second interface pulls the operating parameters;

[0112] A comparison module, used for comparing the pull operation quality index parameter with a preset index parameter threshold;

[0113] The request quantity setting module is used to set a quantity limit on the number of call requests received by the API interface per unit time when the pull operation quality index parameter is lower than a preset index parameter threshold.

[0114] The technical effect of the above technical solution is: the real-time monitoring module can monitor the operating parameters of the API interface in real time, including the number of call requests, response waiting time and the number of concurrent requests, providing an accurate data basis for subsequent parameter acquisition and analysis. Through the first interface pull operation parameter acquisition module and the second interface pull operation parameter acquisition module, multiple operating parameters of the API interface can be comprehensively considered, and the first interface pull operation parameters and the second interface pull operation parameters can be calculated respectively, and these two parameters together reflect the operating status of the API interface.

[0115] The module for obtaining the pull operation quality index parameter uses the first interface to pull the operation parameter and the second interface to pull the operation parameter, and calculates the pull operation quality index parameter through a specific formula. The parameter quantifies the operation quality of the API interface, which is convenient for subsequent comparison and judgment. When the pull operation quality index parameter is lower than the preset index parameter threshold, the request quantity setting module will automatically set a quantity limit on the number of call requests received per unit time of the API interface to protect the stable operation of the API interface and prevent service crashes or response delays caused by overload. Through the implementation of the above technical solution, the operation status of the API interface can be monitored in real time, and intelligent adjustments can be made when necessary, thereby effectively improving the stability and reliability of the API interface. The stable operation and rapid response of the API interface can directly improve the user experience and reduce user dissatisfaction and complaints caused by interface failures or response delays.

[0116] In summary, this technical solution effectively improves the stability and reliability of the API interface, optimizes the user experience, and provides more powerful technical support for applications and services that rely on the API interface through a series of steps such as real-time monitoring, comprehensive operation parameter evaluation, quantification of operation quality indicators, and intelligent request quantity limitation.

[0117] Specifically, the request quantity setting module includes:

[0118] A first data extraction module, used to extract the first interface pull operation parameters and the second interface pull operation parameters;

[0119] A second data extraction module, used to extract the difference between the pulling operation quality index parameter and a preset index parameter threshold;

[0120] A quantity upper limit value setting module, used to obtain a quantity upper limit value corresponding to the number of call requests by using the first interface pull operation parameter and the second interface pull operation parameter combined with the difference between the pull operation quality index parameter and a preset index parameter threshold;

[0121] The upper limit of the number of call requests is obtained by the following formula:

[0122]

[0123] Among them, C up Indicates the upper limit of the number of call requests; C max and C min Indicates the maximum and minimum number of call requests received by the API interface within n units of time; C z represents the total number of call requests sent to the API interface per unit time; S represents the operation quality indicator parameter; S 01Indicates that the first interface pulls the operating parameters; S 02 Indicates that the second interface pulls the operating parameters; S y Indicates the preset indicator parameter threshold.

[0124] The technical effect of the above technical solution is: through the first data extraction module and the second data extraction module, the first interface pull operation parameters, the second interface pull operation parameters, and the difference between the pull operation quality index parameters and the preset index parameter threshold can be accurately extracted. These data provide an accurate basis for the subsequent setting of the upper limit of quantity. The upper limit setting module can dynamically calculate the upper limit of the number of call requests according to the actual operating status of the API interface (including the first interface pull operation parameters, the second interface pull operation parameters) and the difference between the pull operation quality index parameters and the preset threshold. This dynamic setting method can better adapt to the operation changes of the API interface and improve the accuracy and effectiveness of the setting.

[0125] By setting an upper limit on the number of call requests, the load of the API interface can be effectively controlled to prevent service crashes or response delays caused by too many call requests. This improves the stability and reliability of the API interface. The technical solution can dynamically adjust the upper limit on the number of call requests according to the actual operating status and needs of the API interface, thereby optimizing the allocation and use of resources. This helps to improve resource utilization and reduce resource waste. Through the implementation of the above technical solution, the stable operation and rapid response of the API interface can be ensured, thereby enhancing the user experience. When using applications or services that rely on the API interface, users can experience a smoother and more stable service quality.

[0126] To sum up, this technical solution provides more powerful technical support and guarantee for applications and services that rely on API interfaces through a series of steps and effects such as refined data extraction, dynamic quantity upper limit setting, improving the stability of API interfaces, optimizing resource allocation, and enhancing user experience.

[0127] The data analysis module is also used to:

[0128] The stream processing framework is used to capture and process real-time data streams, detect patterns, trends, and anomalies in the data, mine patterns and associations in the data through cluster analysis, and display real-time analysis results in the form of dashboards and real-time charts.

[0129] In the above embodiment, by capturing and processing real-time data streams through the stream processing framework, the system can instantly analyze key indicators such as current market dynamics, user behavior, system performance, etc., can quickly respond to market changes, adjust business strategies, optimize user experience, and quickly resolve potential problems. The real-time analysis results are displayed in the form of dashboards and real-time charts, so that decision makers can intuitively understand the business's operating conditions and market trends, which helps decision makers make quick and accurate judgments and provides strong support for the company to formulate strategic plans and marketing strategies.

[0130] In the above embodiment, the system can detect anomalies in the data, such as abnormal transactions, system failures, abnormal user behavior, etc. The enterprise can reduce potential risks and losses and improve the security and stability of the business. The application of data mining technologies such as cluster analysis enables the system to mine potential patterns and associations from massive data, which helps enterprises to gain an in-depth understanding of the market and users, discover new business opportunities, optimize products and services, and enhance market competitiveness.

[0131] Graph building blocks, including:

[0132] A graph generation unit is used to:

[0133] Convert the data pattern analysis results output by the data processing module into a data graph network, and define nodes and edges in the graph according to the data pattern analysis results, wherein the nodes include users, products and events, and the edges include purchase relationships and association relationships;

[0134] Build a data graph through a graph processing framework, connect data points into a network, store the attribute information of nodes and edges, optimize the generated graph, remove redundant nodes and edges, and merge similar nodes;

[0135] Knowledge base building blocks for:

[0136] Based on the data graph network, a structured knowledge base is constructed, key information including entities, attributes and relationships is extracted from the data graph, structured knowledge items are generated, and the knowledge items are converted into a matrix form;

[0137] Store structured knowledge in the knowledge base system, provide complex query functions based on graph structure, regularly update the data in the knowledge base, and provide maintenance tools for adding, deleting, modifying and querying the knowledge base.

[0138] In the above embodiment, the graph generation unit converts the data pattern analysis results output by the data processing module into a data graph network. By defining nodes (such as users, products and events) and edges (such as purchase relationships and association relationships), complex data relationships become intuitive and easy to understand, which helps companies to have a deeper understanding of user behavior, product characteristics and market trends, and thus make more accurate decisions.

[0139] In the above embodiment, the data graph constructed by the graph processing framework not only connects the data points into a network, but also stores the attribute information of the nodes and edges, optimizes the organization and storage of the data, and makes data query and analysis more efficient. At the same time, the operations of removing redundant nodes and edges and merging similar nodes further improve the quality and consistency of the data. The knowledge base construction unit constructs a structured knowledge base based on the data graph network, extracts key information from the graph and generates structured knowledge entries, which facilitates the storage, retrieval and utilization of knowledge. Enterprises can quickly obtain the required knowledge and information through the knowledge base to support business decisions and innovation activities.

[0140] In the above embodiment, the structured knowledge base provides a complex query function based on a graph structure, enabling enterprises to perform multi-dimensional data analysis and reasoning, helping enterprises to discover potential connections and patterns between data and tap into new business opportunities and value.

[0141] The consulting service module also includes:

[0142] Requirements acquisition unit, used to:

[0143] Responsible for collecting and understanding consulting needs from consultants, receiving consulting needs through web forms, voice assistants, and instant messaging tools, parsing consulting needs, extracting consulting needs information, including consulting topics, specific issues, and expected goals, and organizing the parsed consulting needs information into a structured form;

[0144] Requirements Analysis Unit, used to:

[0145] Based on the consulting demand information obtained, assist humans in conducting research on industry background, enterprise status, and technology trends, break down the consulting demand information into actionable tasks and problem points, determine the specific requirements and constraints for each task and problem point, evaluate the feasibility and priority of the consulting demand information based on the tasks and problem points, and generate demand analysis results;

[0146] Customized solution unit for:

[0147] Based on the results of demand analysis, relevant knowledge items, cases and best practices are searched in the graph network structured knowledge base, and solutions are inferred based on user behavior, enterprise needs and industry trends. According to the inference results and the actual situation of the enterprise, solutions are customized, including technology selection, implementation steps and expected results.

[0148] The report recommends units for:

[0149] Fill the solution content into the report template to automatically generate a complete consulting report, and recommend the generated report to consultants via email or instant messaging tools.

[0150] In the above embodiment, the demand acquisition unit receives consulting needs through a variety of channels, which not only improves the convenience of user interaction, but also significantly improves the efficiency and accuracy of demand acquisition through automated parsing and structured organization, which helps consultants to understand customer needs more accurately and lays a solid foundation for subsequent analysis and solution customization. After obtaining the consulting demand information, the demand analysis unit conducts in-depth research on the industry background, corporate status, and technological trends, and refines the consulting needs into actionable tasks and problem points, which not only enhances the depth of understanding of the consulting needs, but also provides clear guidance for subsequent solution customization by evaluating feasibility and priority.

[0151] In the above embodiment, the solution customization unit uses the rich knowledge items, cases and best practices in the graph network structured knowledge base, and combines user behavior, enterprise needs and industry trends to reason about solutions, which can ensure the pertinence and innovation of the solution, and improve the efficiency and quality of solution formulation. By combining the reasoning results with the actual situation of the enterprise, the solution customization unit can customize practical and targeted solutions, which helps the enterprise better understand and implement consulting advice.

[0152] In the above embodiment, the report recommendation unit automatically fills the content of the solution into the report template, generates a complete consulting report, and recommends it to consultants through channels such as email and instant messaging tools, which simplifies the report production process, improves the timeliness and professionalism of the report, and enhances customer satisfaction. The entire consulting service module achieves comprehensive optimization of the consulting service process through automated demand acquisition, in-depth demand analysis, intelligent solution customization, and automated report generation and recommendation, improves the efficiency and quality of consulting services, reduces service costs, and enhances the company's competitiveness and customer satisfaction.

[0153] The interactive feedback module is also used to:

[0154] Feedback collection unit, used to:

[0155] Generate user feedback channels, including web forms, emails, and instant messaging tools, and automatically collect feedback submitted by users in the feedback channels through back-end services, and organize and classify them for subsequent analysis and processing;

[0156] Feedback response unit for:

[0157] Process and respond to collected user feedback, extract keywords from the text content in user feedback, identify user concerns, and classify feedback issues based on analysis results. Problem categories include feature suggestions, error reports, and service evaluations. Based on problem classification and user historical data, generate personalized replies and solutions, and return them to users through user feedback channels.

[0158] In the above embodiment, by generating a variety of user feedback channels, the system can more conveniently collect real user feedback, so that the system can timely understand and solve the problems encountered by users during use, thereby improving user satisfaction. The feedback collection unit automatically collects and organizes the feedback submitted by users through the back-end service, which provides convenience for subsequent analysis and processing, reduces the need for manual intervention, and improves the efficiency of feedback processing. The feedback response unit performs in-depth text analysis and keyword extraction on the collected user feedback to identify the user's concerns. According to the analysis results and problem classification, the system can generate personalized replies and solutions. This personalized processing method makes the reply closer to the actual needs of users and improves the efficiency and effectiveness of problem solving.

[0159] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. The enterprise information technology consulting service system based on big data is characterized by: include: Data acquisition module, used to: Integrate data sources, obtain data in real time and in batches from data sources based on API interfaces, clean the data, store it through distributed file systems, build data warehouses, and convert data from operational databases to analytical databases through ETL processes; Data analysis module for: Process and analyze the real-time data in the database, and perform offline batch data processing through the big data processing framework. Put the processed data into the clustering model for analysis and calculation to obtain the data pattern analysis results, and display the analysis results through charts; Graph building blocks for: Connecting data points into a data graph network based on data pattern analysis results, generating a structured knowledge base based on the data graph network, and providing complex queries based on graph structures, including path queries and similarity queries; Consulting service modules for: Provide enterprise information technology consulting services, obtain the consulting needs of current consultants, analyze the consulting needs of current consultants, call the graph network structured knowledge base for intelligent reasoning based on the consulting needs analysis results, customize solutions based on user behavior, enterprise needs and industry trends and according to the current consultants' enterprise needs, obtain customized solution integration data, generate reports based on the customized solution integration data and recommend them to current consultants; Interactive feedback module, used to: Generate a user interface that supports multiple interaction modes, including voice, text, and graphics, and generate a user feedback channel; Wherein, the data acquisition module is also used for: Create a data source directory to record the URL, API key, and update frequency information of each data source, including internal enterprise systems, social media, industry reports, customer feedback, device logs, and public data sources; For data sources that support API, call the API interface to automatically pull data. For data sources that do not support API and need to crawl web page data, crawl data through web crawlers and verify the obtained original data. Clean, deduplicate and format the raw data obtained from the data source; Store the cleaned data in a distributed file system and build a data warehouse. Use the ETL process to convert data from the operational database to the analytical database, and partition and index the data according to query requirements. The data acquisition module further includes: A real-time monitoring module is used to monitor in real time the operating parameters of calling the API interface to automatically pull data, wherein the operating parameters include the number of call requests received by the API interface per unit time, the maximum time to wait for the API interface to respond, and the number of call requests sent to the API interface at the same time per unit time, and the value range of the unit time is 10s-30s; The first interface pulls the operation parameter acquisition module, which is used to obtain the first interface pull operation parameters by using the number of call requests received by the API interface per unit time and the longest time to wait for the API interface to respond; wherein, the first interface pulls the operation parameters by the following formula: Among them, S 01 Indicates the first interface pulls the running parameters; n indicates the number of unit time that the API interface has experienced; C i Indicates the number of call requests received by the API interface corresponding to the i-th unit time; C y Indicates the reference value corresponding to the number of call requests received by the preset API interface; T maxi represents the maximum time interval between two adjacent call requests corresponding to the i-th unit time; T pi T represents the maximum time to wait for the API interface response corresponding to the i-th unit time; z Indicates the median value of the longest time to wait for an API response corresponding to n units of time; The second interface pulls the operation parameter acquisition module, which is used to obtain the second interface pull operation parameter by using the number of call requests sent to the API interface at the same time in the unit time; wherein the second interface pulls the operation parameter by the following formula: Among them, S 02 Indicates the second interface pulls the running parameters; n indicates the number of unit time that the API interface has experienced; N maxi represents the maximum number of call requests sent to the API interface at the same time in the unit time corresponding to the i-th unit time; C zi Indicates the total number of call requests sent to the API interface in the i-th unit time; f i It represents the change coefficient of the number of call requests corresponding to the i-th unit time, and the change coefficient of the number of call requests corresponding to each unit time is obtained by the following formula: Where m represents the number of times multiple call requests are sent to the API interface at the same time corresponding to the i-th unit time; N j represents the number of call requests sent corresponding to the number of times multiple call requests are sent to the API interface at the same time corresponding to the i-th unit time; C z Indicates the total number of call requests sent to the API interface per unit time; The pull operation quality index parameter acquisition module is used to obtain the pull operation quality index parameter by using the first interface to pull the operation parameter and the second interface to pull the operation parameter, wherein the pull operation quality index parameter is obtained by the following formula: Among them, S represents the operation quality index parameter; S 01 Indicates that the first interface pulls the operating parameters; S 02 Indicates that the second interface pulls the operating parameters; A comparison module, used for comparing the pull operation quality index parameter with a preset index parameter threshold; The request quantity setting module is used to set a quantity limit on the number of call requests received by the API interface per unit time when the pull operation quality index parameter is lower than a preset index parameter threshold.

2. The enterprise information technology consulting service system based on big data according to claim 1, characterized in that: Request quantity setting module, including: A first data extraction module, used to extract the first interface pull operation parameters and the second interface pull operation parameters; A second data extraction module, used to extract the difference between the pulling operation quality index parameter and a preset index parameter threshold; A quantity upper limit value setting module, used to obtain a quantity upper limit value corresponding to the number of call requests by using the first interface pull operation parameter and the second interface pull operation parameter combined with the difference between the pull operation quality index parameter and a preset index parameter threshold; The upper limit of the number of call requests is obtained by the following formula: Among them, C up Indicates the upper limit of the number of call requests; C max and C min Indicates the maximum and minimum number of call requests received by the API interface within n units of time; C z It indicates the total number of call requests sent to the API interface per unit time; S indicates the operation quality indicator parameter; S 01 Indicates that the first interface pulls the operating parameters; S 02 Indicates that the second interface pulls the operating parameters; S y Indicates the preset indicator parameter threshold.

3. The enterprise information technology consulting service system based on big data according to claim 1, characterized in that: The data analysis module is also used for: The stream processing framework is used to capture and process real-time data streams, detect patterns, trends, and anomalies in the data, mine patterns and associations in the data through cluster analysis, and display real-time analysis results in the form of dashboards and real-time charts.

4. The enterprise information technology consulting service system based on big data according to claim 1, characterized in that: The graph construction module comprises: A graph generation unit is used to: Convert the data pattern analysis results output by the data processing module into a data graph network, and define nodes and edges in the graph according to the data pattern analysis results, wherein the nodes include users, products and events, and the edges include purchase relationships and association relationships; A data graph is constructed through a graph processing framework, data points are connected into a network, and attribute information of nodes and edges is stored. The generated graph is optimized to remove redundant nodes and edges and merge similar nodes.

5. The enterprise information technology consulting service system based on big data according to claim 4, characterized in that: The graph construction module further includes: Knowledge base building blocks for: Based on the data graph network, a structured knowledge base is constructed, key information including entities, attributes and relationships is extracted from the data graph, structured knowledge items are generated, and the knowledge items are converted into a matrix form; Store structured knowledge in the knowledge base system, provide complex query functions based on graph structure, regularly update the data in the knowledge base, and provide maintenance tools for adding, deleting, modifying and querying the knowledge base.

6. The enterprise information technology consulting service system based on big data according to claim 1, characterized in that: The consulting service module also includes: Requirements acquisition unit, used to: Responsible for collecting and understanding consulting needs from consultants, receiving consulting needs through web forms, voice assistants, and instant messaging tools, parsing consulting needs, extracting consulting needs information, including consulting topics, specific issues, and expected goals, and organizing the parsed consulting needs information into a structured form; Requirements Analysis Unit, used to: Based on the consulting demand information obtained, assist humans in conducting research on industry background, enterprise status, and technology trends, break down the consulting demand information into actionable tasks and problem points, determine the specific requirements and constraints for each task and problem point, evaluate the feasibility and priority of the consulting demand information based on tasks and problem points, and generate demand analysis results.

7. The enterprise information technology consulting service system based on big data according to claim 6, characterized in that: The consulting service module also includes: Customized solution unit for: Based on the results of demand analysis, relevant knowledge items, cases and best practices are searched in the graph network structured knowledge base, and solutions are inferred based on user behavior, enterprise needs and industry trends. According to the inference results and the actual situation of the enterprise, solutions are customized, including technology selection, implementation steps and expected results. The report recommends units for: Fill the solution content into the report template to automatically generate a complete consulting report, and recommend the generated report to consultants via email or instant messaging tools.

8. The enterprise information technology consulting service system based on big data according to claim 1, characterized in that: The interactive feedback module is also used for: Feedback collection unit, used to: Generate user feedback channels, including web forms, emails, and instant messaging tools, and automatically collect feedback submitted by users in the feedback channels through back-end services, and organize and classify them for subsequent analysis and processing; Feedback response unit for: Process and respond to collected user feedback, extract keywords from the text content in user feedback, identify user concerns, and classify feedback issues based on analysis results. Problem categories include feature suggestions, error reports, and service evaluations. Based on problem classification and user historical data, generate personalized replies and solutions, and return them to users through user feedback channels.

Images