Consultation service system based on big data acquisition and analysis

Abstract

The invention provides a consultation service system based on big data collection and analysis, and the system comprises a data collection module which is used for obtaining consultation service data from a plurality of data sources, and obtaining original consultation service data; the data cleaning and preprocessing module is used for cleaning and preprocessing the collected original consultation service data to obtain preprocessed data; the data analysis and mining module is used for analyzing and mining the preprocessed data to obtain feature data; and the decision support module is used for generating a decision suggestion report by utilizing the feature data. According to the technical scheme, the data acquisition module, the data cleaning and preprocessing module, the data analysis and mining module and the decision support module are arranged, so that the quality and efficiency of consultation service are improved.

Description

Background Art

[0002] With the rapid development of informatization and digitalization, data has become an important asset for enterprises and society. Especially in the consulting service industry, the value of data is more prominent. Traditional consulting services mainly rely on the experience and subjective judgment of experts, which often seems to be inadequate in the face of complex and changing market environments. The rise of big data technology has brought new opportunities to the consulting service industry. Through big data technology, massive data can be collected, analyzed and mined, thus providing a more scientific and objective basis for decision-making. Summary of the invention

[0003] The present application provides a consulting service system based on big data collection and analysis to improve the quality and efficiency of consulting services.

[0004] In the first aspect, a consulting service system based on big data collection and analysis is provided, including:

[0005] A data collection module is used to obtain consulting service data from multiple data sources to obtain original consulting service data;

[0006] A data cleaning and preprocessing module, used to clean and preprocess the collected original consulting service data to obtain preprocessed data;

[0007] A data analysis and mining module is used to analyze and mine the preprocessed data to obtain feature data;

[0008] The decision support module is used to generate a decision recommendation report using the characteristic data.

[0009] In the above technical scheme, a data acquisition module is set up to obtain consulting service data from multiple data sources to obtain original consulting service data; a data cleaning and preprocessing module is set up to clean and preprocess the collected original consulting service data to obtain preprocessed data; a data analysis and mining module is set up to analyze and mine the preprocessed data to obtain feature data; a decision support module is set up to generate a decision recommendation report using the feature data; the quality and efficiency of consulting services are improved.

[0010] In a specific implementation scheme, the data acquisition module includes a data acquisition unit and a data acquisition interface unit.

[0011] In a specific implementation scheme, the data cleaning and preprocessing module includes a duplicate data removal unit, a missing value filling unit, an error data correction unit and a data format conversion unit.

[0012] In a specific implementation scheme, the data analysis and mining module includes a data analysis unit and a data mining unit.

[0013] In a specific implementation scheme, the data analysis and mining module also includes a data optimization unit.

[0014] In a specific implementation scheme, the decision support module includes a specific question unit, a trend prediction unit and a risk assessment unit.

[0015] In a specific implementation scheme, the decision support module uses a large language model.

[0016] In a specific implementation scheme, it also includes: a data storage module, wherein:

[0017] The data storage module is used to store the pre-processed data.

[0018] In a specific implementation scheme, the data storage module includes a distributed file unit and a distributed database.

[0019] In a specific implementation scheme, it also includes: a user interface module, wherein:

[0020] The user interface module includes a user demand input unit, an analysis result display unit and a decision suggestion report unit, and is used to interact with the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A structural block diagram of the consulting service system based on big data collection and analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The present application is further described in detail below through the accompanying drawings and embodiments. Through these descriptions, the characteristics and advantages of the present application will become clearer and more specific.

[0023] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise noted.

[0024] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0025] To facilitate understanding of the consulting service system based on big data collection and analysis provided by the embodiment of the present application, its application scenario is first explained. The consulting service system based on big data collection and analysis provided by the embodiment of the present application is used to improve the quality and efficiency of consulting services. In today's rapid development of informatization and digitalization, data has become an important asset for enterprises and society. Especially in the consulting service industry, the value of data is more prominent. Traditional consulting services mainly rely on the experience and subjective judgment of experts, which often seems to be powerless in the face of a complex and changing market environment. The rise of big data technology has brought new opportunities to the consulting service industry. Through big data technology, massive data can be collected, analyzed and mined, thereby providing a more scientific and objective basis for decision-making. For this reason, the embodiment of the present application provides a consulting service system based on big data collection and analysis to improve the quality and efficiency of consulting services. The following is a detailed description of the embodiment in conjunction with specific drawings.

[0026] refer to Figure 1 , Figure 1 A structural block diagram of the consulting service system based on big data collection and analysis provided in an embodiment of the present application.

[0027] exist Figure 1 In the embodiment of the present application, a consulting service system based on big data collection and analysis is provided, including:

[0028] A data collection module is used to obtain consulting service data from multiple data sources to obtain original consulting service data;

[0029] A data cleaning and preprocessing module, used to clean and preprocess the collected original consulting service data to obtain preprocessed data;

[0030] A data analysis and mining module is used to analyze and mine the preprocessed data to obtain feature data;

[0031] The decision support module is used to generate a decision recommendation report using the characteristic data.

[0032] In the above technical scheme, a data acquisition module is set up to obtain consulting service data from multiple data sources to obtain original consulting service data; a data cleaning and preprocessing module is set up to clean and preprocess the collected original consulting service data to obtain preprocessed data; a data analysis and mining module is set up to analyze and mine the preprocessed data to obtain feature data; a decision support module is set up to generate a decision recommendation report using the feature data; the quality and efficiency of consulting services are improved.

[0033] In a specific implementation scheme, the data acquisition module includes a data acquisition unit and a data acquisition interface unit.

[0034] Specifically, the data acquisition module is responsible for acquiring data from multiple data sources, including structured data, semi-structured data and unstructured data. The data acquisition unit is electrically connected to the data acquisition interface unit. The data acquisition interface unit includes an API interface, a Web crawler interface, and a database connection interface, which are respectively used to connect to corresponding data sources.

[0035] In the consulting service system, structured data, semi-structured data and unstructured data include:

[0036] 1. Structured Data

[0037] Structured data refers to data that has a fixed data model and is logically expressed and implemented by a two-dimensional table structure, strictly following data format and length specifications. It is stored and managed through a relational database. Specifically, structured data includes:

[0038] Basic customer information: such as name, age, contact information, etc. This data is usually stored in the database in the form of a table for quick query and update.

[0039] Service records: including service time, service content, service fees, etc. These data help consulting agencies understand the service process and quality, and make subsequent improvements.

[0040] Business data: such as sales, market share, etc. These data are important bases for consulting agencies to conduct market analysis and business forecasts.

[0041] The advantage of structured data is that it is easy to query and analyze because the data has clear fields, types, and relationships. However, its flexibility is relatively poor, and the data schema needs to be defined in advance, that is, the name, type, length and other attributes of each field must be determined.

[0042] 2. Semi-structured data

[0043] Semi-structured data is a data type between structured data and unstructured data. It has certain organization and rules, but does not conform to the format of traditional relational databases or tables. Semi-structured data uses tags, labels, key-value pairs, etc. to represent the hierarchy and semantics of data. Specifically, semi-structured data includes:

[0044] Log files: record the system operation status and user operation behaviors, which are of great significance for diagnosing problems and optimizing system performance.

[0045] Social media data: such as user comments and feedback on social media such as Weibo and WeChat. These data help consulting firms understand public opinion and market dynamics.

[0046] Email: A record of correspondence between clients and consulting organizations, containing important service requests and problem feedback.

[0047] Semi-structured data has greater flexibility and scalability, and can adapt to different scenarios and needs. At the same time, it is easier to parse and process than unstructured data.

[0048] 3. Unstructured Data

[0049] Unstructured data refers to data that is not organized and stored in a fixed format or rules. It includes data in the form of text, images, audio, video, etc. Unstructured data includes:

[0050] Customer feedback: Such as customer comments on social media, recordings of complaint calls, etc., these data provide customers' direct feedback and opinions on the service.

[0051] Market research report: presented in the form of a document or PPT, containing a large amount of market analysis and forecast information.

[0052] Promotional materials: such as advertising videos, posters, etc. These data help consulting agencies understand competitors' promotional strategies and market positioning.

[0053] The advantage of unstructured data is its richness and diversity, which can provide more comprehensive and accurate data analysis results. However, its challenge is that it is difficult to query and analyze directly, and requires the use of specific technologies and tools to parse and process.

[0054] In a specific implementation scheme, 1. the API interface is used to connect to data sources that provide API services, such as social media platforms, online shopping websites, etc. These data sources usually provide structured or semi-structured data through API interfaces. Including:

[0055] The first docking unit is used to determine the API interface address and parameters;

[0056] A first acquisition unit, used to acquire data through code calling;

[0057] The first parsing unit is used to process the data returned by the API, including parsing data in JSON or XML format.

[0058] 2. Web crawler interface, used to crawl unstructured data from web pages, such as text, pictures, videos, etc. Including:

[0059] A second docking unit, used to determine the URL of a target web page;

[0060] The second acquisition unit is used to write a crawler program to simulate a browser request and acquire web page content;

[0061] The second parsing unit is used to parse the webpage content and extract the required data.

[0062] Database connection interface, used to connect to relational databases (such as MySQL, Oracle) or non-relational databases (such as MongoDB, Cassandra) to obtain structured data. Including:

[0063] The third docking unit is used to determine the type, address, user name and password information of the database; and to write a database connection code to establish a connection with the database;

[0064] The third acquisition unit is used to write SQL query statements or use database client tools to acquire required data;

[0065] The third parsing unit is used to process the data returned by the database and convert it into a specific data format.

[0066] In the above technical solution,

[0067] In the context of big data technology, the data acquisition interface unit acts as a bridge to connect different data sources, allowing data to be collected and processed efficiently and accurately. Specifically, it includes:

[0068] 1. API interface: efficient and stable: The API interface directly calls the services provided by the target system, avoiding the complex parsing and conversion processes that may be involved in traditional data collection methods, thereby improving the efficiency of data collection; it can ensure the stability and reliability of data transmission. Easy to maintain: When the target system is updated or changed, the API interface is usually updated accordingly to adapt to the new data format or interface specification. This makes the API interface relatively simple to maintain and reduces the risk of data collection interruption caused by system updates. Data specification: The API interface provides a unified data access method, which makes the collected data consistent and standardized, facilitating subsequent data processing and analysis. High security: When collecting data through the API interface, you can set identity authentication and access control to effectively protect the security and privacy of the data.

[0069] 2. Web crawler interface: Strong flexibility: The Web crawler interface can handle various web page structures and data formats, and flexibly collect data from different websites. Large amount of data: The Web crawler interface can automatically traverse and collect a large amount of web page data, providing a rich data source for big data analysis. Strong adaptability: The Web crawler interface can adapt to the updates and changes of web pages, and ensure the continuity and accuracy of data collection by constantly updating crawler strategies and algorithms.

[0070] 3. Database connection interface: Direct access: The database connection interface allows direct access to data in the database without going through the middle layer or third-party services, thereby improving the speed and efficiency of data access. Data integrity: Data collected through the database connection interface usually has higher integrity because the data in the database has undergone strict verification and storage processes. Easy to integrate: The database connection interface can be integrated with various data processing and analysis tools to facilitate subsequent data processing and analysis work.

[0071] In summary, when using big data technology, the API interface, Web crawler interface and database connection interface in the data acquisition interface unit each have unique advantages. These advantages enable them to efficiently connect to the corresponding data sources and provide rich, accurate and reliable data support for big data analysis.

[0072] In a specific implementation scheme, the data cleaning and preprocessing module includes a duplicate data removal unit, a missing value filling unit, an error data correction unit and a data format conversion unit.

[0073] Specifically, the data cleaning and preprocessing module is used to clean and preprocess the collected raw data, including removing duplicate data, filling missing values, correcting erroneous data, and converting data formats.

[0074] In big data technology, data cleaning and preprocessing modules are crucial. They mainly process data, including removing duplicate data, filling missing values, correcting erroneous data, and converting data formats to improve data quality and availability.

[0075] In a specific implementation scheme, the data analysis and mining module includes a data analysis unit and a data mining unit.

[0076] Specifically, the data analysis and mining module is the core part of the system, responsible for analyzing and mining the stored data. Analysis methods include statistical analysis, machine learning, deep learning, text mining, etc. Through these methods, useful information and patterns in the data can be extracted to provide support for decision-making.

[0077] In a specific implementation scheme, the data analysis and mining module also includes a data optimization unit.

[0078] Preferably, a particle swarm optimization (PSO) algorithm is used for data analysis and mining, including:

[0079] The particle swarm initialization unit is used to randomly generate a group of particles and randomly assign an initial position and velocity to each particle;

[0080] The fitness calculation unit is used to calculate the fitness value of each particle according to the fitness function of the problem;

[0081] The individual optimal position updating unit is used to check the fitness of each particle's current position and the individual's historical optimal position. If the current position is better, the individual optimal position is updated.

[0082] The group optimal position unit is updated to check the individual optimal positions of all particles and select the position with the best fitness as the group optimal position.

[0083] The particle speed and position update unit is used to update the speed and position of the particle through the individual historical optimal position and the group optimal position, as well as the inertia weight, the individual acceleration factor and the social acceleration factor.

[0084] The termination condition judgment unit is used to check whether the termination condition is met and complete the data analysis and mining.

[0085] In the above technical solution, the particle swarm algorithm is used for data analysis and mining, and its advantages include: 1. Strong global search capability: The particle swarm algorithm simulates the flight behavior of particles in the search space and uses the individual's historical experience and group information for search and optimization. This mechanism enables the algorithm to search in the entire solution space and avoid falling into the local optimal solution. 2. Simple principle and easy implementation: The concept of the particle swarm algorithm is simple and easy to program. 3. Relatively few parameters: Compared with other optimization algorithms, the particle swarm algorithm requires fewer parameters to be adjusted. The main parameters include the number of particles, inertia weight, individual acceleration factor, and social acceleration factor. These parameters can be designed and adjusted according to specific problems and algorithm effects. 4. Fast convergence speed: It has a fast convergence speed. Since the algorithm constantly approaches the individual optimal position and the group optimal position during the iteration process, it can quickly find the optimal solution or a solution close to the optimal solution of the problem. 5. The memory requirement for the computer is not large: The particle swarm algorithm does not need to store a large amount of intermediate results and auxiliary information during operation, so the memory requirement for the computer is relatively small. This makes the algorithm more efficient and practical when processing large-scale data sets.

[0086] In a specific implementation scheme, the decision support module includes a specific question unit, a trend prediction unit and a risk assessment unit.

[0087] Specifically, the specific problem unit is used to generate solutions to specific problems; the trend prediction unit is used to generate trend prediction reports; the risk assessment unit is used to generate risk assessment reports. The decision support module needs to combine the knowledge and experience of experts in the field to ensure the rationality and practicality of decision suggestions.

[0088] In a specific implementation scheme, the decision support module uses a large language model.

[0089] Specifically, the large language model classifies structured data, semi-structured data, and unstructured data, generates decision recommendation reports, and merges them through intelligent algorithms to obtain the final decision recommendation report. The process includes:

[0090] 1. Data classification module: classifies the feature data and assigns it to corresponding modules; including:

[0091] 1. Structured data unit, used for:

[0092] Data merging and connection: Use the JOIN operation of the relational database or the merge function in data processing tools (such as Pandas) to merge or connect data from multiple tables to obtain more comprehensive information.

[0093] Data transformation and reshaping: Converting data into a form suitable for analytical purposes, such as data pivoting.

[0094] 2. Semi-structured data unit, used for:

[0095] Extract structured information: Extract structured information such as key-value pairs and tags from semi-structured data.

[0096] Data collation: Organize the extracted structured information to ensure data consistency and accuracy.

[0097] 3. Unstructured data unit, used for:

[0098] Text processing: Use natural language processing (NLP) techniques, such as word segmentation, stem extraction, word frequency statistics, sentiment analysis, etc., to process text data.

[0099] Image and video processing: Use computer vision algorithms for feature extraction and image classification, such as using convolutional neural networks (CNNs) for image classification and object detection.

[0100] Audio processing: including audio signal processing, audio recognition and speech emotion analysis, etc., applicable to speech recognition, speech synthesis and other fields.

[0101] Preferably, a decision tree algorithm is used for data classification, which has the following advantages: 1. Easy to understand and explain: The structure of the decision tree is clear and intuitive, similar to the human decision-making process, making the results of the model very easy to understand and explain, and the logic and basis of the classification can be intuitively understood through the decision tree. 2. Processing multivariate data: Decision trees can handle data sets with multiple features without the need for additional selection or transformation of features. The most important features can be automatically selected for splitting based on the inherent structure of the data. 3. Processing missing values: The decision tree algorithm can handle data sets containing missing values, and can make up for this defect through other splitting points. 4. Visualization: The visualization of the decision tree makes the results of the model more intuitive and easy to understand. Through the visualization tool, you can clearly see the selection basis of each splitting point, the importance of the features, and the results of the classification.

[0102] 2. Generate decision-making recommendation sub-report module, including:

[0103] 1. Structured data reporting unit: used to generate decision recommendation reports for structured data using machine learning models.

[0104] 2. Semi-structured data report: Conduct in-depth analysis of semi-structured data to explore its correlations and trends; and generate decision-making recommendation reports for semi-structured data based on business rules and actual needs.

[0105] 3. Structured data report: Use a combination of NLP and computer vision technologies to deeply understand and analyze structured data, extract key information (including sentiment tendencies, image features), and ultimately generate a decision-making recommendation report for structured data.

[0106] 3. Consolidated reporting module: including

[0107] The report preprocessing unit is used to unify the formats of the three generated decision recommendation reports.

[0108] The report merging and optimization unit is used to merge the three decision recommendation reports using the metamodel algorithm and optimize the merged report (including removing duplicate information and adjusting the report structure) to ensure the accuracy and readability of the report; the optimized merged report is the final decision recommendation report; this report integrates the analysis results of structured data, semi-structured data and unstructured data, and provides decision makers with comprehensive and accurate decision recommendations.

[0109] In the above technical solution, the advantages of using the metamodel algorithm for report merging include: 1. Improving information integration efficiency: The metamodel algorithm can significantly reduce the amount of calculation by constructing a mathematical model that is similar to the source model, thereby speeding up the speed of report merging. This feature enables the metamodel algorithm to quickly integrate information and improve the efficiency of report merging when processing a large number of complex data sources. 2. Optimizing the management process: Report merging often involves data aggregation and analysis of multiple departments or projects. The use of the metamodel algorithm can more clearly display the work progress and results of each department or project, which helps senior management to better understand the operation of each business segment. In this way, more effective resource allocation and decision adjustments can be made based on the merged report to optimize the overall management process. 3. Enhanced decision support: When constructing an approximate model, the metamodel algorithm can capture the key characteristics and parameter relationships of the source model. Therefore, in the process of report merging, the metamodel algorithm can retain and integrate these key information to provide more accurate and comprehensive data support for management. This helps management to have a deeper understanding of the company's operating conditions and market environment, so as to make more wise and effective decisions. 4. Adaptability and flexibility: The metamodel algorithm has strong adaptability and flexibility. It can flexibly adjust the model structure and parameters according to different data sources and report contents to adapt to various complex consolidation requirements. In addition, the metamodel algorithm also supports dynamic updates and expansions, so that the report consolidation system can be continuously optimized as the business develops and data changes. 5. Improve data quality and accuracy: Report consolidation through the metamodel algorithm can reduce human intervention and errors, and improve data quality and accuracy. The metamodel algorithm can automatically process and analyze data, avoiding omissions, duplications or errors that may occur during manual integration.

[0110] In summary, by classifying and processing different types of data, generating corresponding decision-making recommendation reports, and then using intelligent algorithms to merge and optimize, we can finally obtain a comprehensive and accurate decision-making recommendation report. This process provides strong support for decision makers and helps them make more informed decisions.

[0111] In a specific implementation scheme, it also includes: a data storage module, wherein:

[0112] The data storage module is used to store the pre-processed data.

[0113] In a specific implementation scheme, the data storage module includes a distributed file unit and a distributed database.

[0114] Specifically, considering the scale and complexity of big data, distributed file units (such as HDFS) and distributed databases (such as HBase) are used to store data.

[0115] In the above technical solution, the advantages of distributed file units include: High scalability: HDFS supports horizontal expansion. By simply adding data nodes, the storage capacity of the system can be easily expanded to cope with the growing scale of big data. High fault tolerance: HDFS adopts a data copy mechanism to store multiple copies of the data blocks of each file on different data nodes. This redundant storage method ensures the reliability and accessibility of the data. Even if a data node fails, the data can be restored from other nodes to ensure the continuity of the service. Cost-effectiveness: HDFS is designed to run on ordinary commercial hardware, which can significantly reduce storage costs compared to traditional high-cost storage solutions. Optimized data throughput: The architectural optimization of HDFS ensures high-throughput data access, which is very suitable for processing large-scale data sets. Its data block size and replication strategy and other designs all help to improve the efficiency of data processing.

[0116] In the above technical solutions, the advantages of distributed databases such as HBase include: High scalability: HBase can be easily expanded to hundreds or even thousands of servers to meet the needs of large-scale data storage and concurrent access. This scalability enables HBase to cope with the growing amount of data and access pressure. High fault tolerance: HBase uses distributed storage and replication technology to tolerate server failures or data center failures and ensure high availability and reliability of data. This fault tolerance is essential for maintaining the integrity of big data. High-speed read and write: HBase uses a combination of memory and hard disk storage to provide low-latency read and write operations. This makes HBase particularly suitable for real-time analysis and high-concurrency read and write scenarios. Flexible data model: HBase provides a flexible column family and column data model, which can be used to model data according to actual needs. This flexibility enables HBase to adapt to various complex data structures and application scenarios. Powerful data processing capabilities: HBase supports a variety of data operations and query functions, including range queries, filters, aggregate functions, etc. These functions enable HBase to meet complex data processing needs and provide strong support for big data analysis.

[0117] In summary, using distributed file units (such as HDFS) and distributed databases (such as HBase) to store big data has significant advantages such as high scalability, high fault tolerance, cost-effectiveness, and optimized data throughput and read and write speed. These advantages make distributed storage and distributed databases ideal for processing large-scale data sets, providing a solid foundation for the application and development of big data technology.

[0118] In a specific implementation scheme, it also includes: a user interface module, wherein:

[0119] The user interface module includes a user demand input unit, an analysis result display unit and a decision suggestion report unit, and is used to interact with the user.

[0120] Specifically, the user interface module is used to interact with the user, including inputting user requirements, displaying analysis results and decision suggestions. Preferably, the user interface module includes a Web interface unit, a mobile application unit and a desktop application unit.

[0121] In the above technical solution, the consulting service system using big data technology and big language model can 1. Improve the efficiency of consulting services: Combining big data technology and big language model, the consulting service system can respond to users' questions in real time and provide efficient services; it can save users' time and improve user satisfaction. 2. Reduce enterprise costs: Through the automated and intelligent consulting service system, it can reduce labor costs and training costs; it can enable enterprises to focus more on the development and innovation of core businesses. 3. Improve user experience: Based on powerful language understanding and generation capabilities, as well as personalized service recommendations, the consulting service system can provide users with a more intelligent and personalized service experience; it can enhance user loyalty and improve the brand reputation of the enterprise.

[0122] Those skilled in the art will appreciate that the present application may be implemented as a system, method or computer program product.

[0123] Therefore, the present disclosure may be specifically implemented in the following forms, namely: it may be completely hardware, it may be completely software (including firmware, resident software, microcode, etc.), or it may be a combination of hardware and software, generally referred to herein as a "circuit", "module" or "system". In addition, in some embodiments, the present application may also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium may contain computer-readable program code.

[0124] Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0125] Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art can change, modify, replace and modify the above embodiments within the scope of the present application. On this basis, a variety of replacements and improvements can be made to the present application, all of which fall within the scope of protection of the present application.

Claims

1. A consulting service system based on big data collection and analysis, characterized in that: include: A data collection module is used to obtain consulting service data from multiple data sources to obtain original consulting service data; A data cleaning and preprocessing module, used to clean and preprocess the collected original consulting service data to obtain preprocessed data; A data analysis and mining module is used to analyze and mine the preprocessed data to obtain feature data; The decision support module is used to generate a decision recommendation report using the characteristic data.

2. The consulting service system based on big data collection and analysis according to claim 1 is characterized in that: The data acquisition module includes a data acquisition unit and a data acquisition interface unit.

3. The consulting service system based on big data collection and analysis according to claim 2 is characterized in that: The data cleaning and preprocessing module includes a duplicate data removal unit, a missing value filling unit, an error data correction unit and a data format conversion unit.

4. The consulting service system based on big data collection and analysis according to claim 3 is characterized in that: The data analysis and mining module includes a data analysis unit and a data mining unit.

5. The consulting service system based on big data collection and analysis according to claim 4 is characterized in that: The data analysis and mining module also includes a data optimization unit.

6. The consulting service system based on big data collection and analysis according to claim 5 is characterized in that: The decision support module includes a specific question unit, a trend prediction unit and a risk assessment unit.

7. The consulting service system based on big data collection and analysis according to claim 6 is characterized in that: The decision support module adopts a large language model.

8. The consulting service system based on big data collection and analysis according to claim 7 is characterized in that: Also includes: Data storage module, wherein The data storage module is used to store the pre-processed data.

9. The consulting service system based on big data collection and analysis according to claim 8 is characterized in that: The data storage module includes a distributed file unit and a distributed database.

10. The consulting service system based on big data collection and analysis according to claim 9 is characterized in that: Also includes: A user interface module, wherein The user interface module includes a user demand input unit, an analysis result display unit and a decision suggestion report unit, and is used to interact with the user.

Images