An enterprise technology management service system and method based on artificial intelligence

Abstract

The present invention proposes an enterprise technology management service system and method based on artificial intelligence, which relates to the technical field of enterprise technology management services, and obtains information on the types of enterprise technology knowledge needs and divides demand consultation data packets; obtains knowledge type information and divides technology knowledge data packets; fills the demand consultation data packets according to the technology knowledge data packets corresponding to the demand consultation data packets, calculates the consultation progress coefficient, and determines the consultation progress status according to the consultation progress coefficient. After the consultation progress is completed, the consultation accuracy of each demand consultation data packet is calculated, and the consultation abnormal block is determined according to the consultation accuracy. The knowledge information of the consultation abnormal block is re-acquired until the consultation is completed and there is no consultation abnormal block in the data. The present invention realizes the comprehensive integration and efficient matching of consultation needs and knowledge resources, ensures the accuracy and reliability of the consultation results, and meets the diversified technology knowledge demand services of enterprises.

Description

Technical Field

[0001] The present invention proposes an enterprise technology management service system and method based on artificial intelligence, which relates to the technical field of enterprise technology management services, and specifically to the technical field of enterprise technology management services based on artificial intelligence. Background Art

[0002] At present, enterprise technology consulting faces problems such as information fragmentation, cumbersome processes, inaccurate results, delayed knowledge updates, lack of personalized intelligent services, and data security risks. Traditional consulting methods are difficult to meet the needs of enterprises for efficient and accurate consulting services. The lack of a systematic consulting library and knowledge base makes it difficult to integrate and match consulting needs with knowledge resources. Consulting efficiency is low and accuracy is low. Summary of the invention

[0003] The present invention provides an enterprise technology management service system and method based on artificial intelligence to solve the above problems:

[0004] The present invention proposes an enterprise technology management service system and method based on artificial intelligence, the method comprising:

[0005] S1. Obtain demand type information based on enterprise technology consulting demand information, divide the demand type information into demand consulting data packets, and then obtain a demand data packet sequence, and combine them to obtain an enterprise technology consulting database;

[0006] S2. Acquire knowledge category information according to preset science and technology management information, divide the knowledge category information into science and technology knowledge data packets, and then acquire a sequence of knowledge data packets, and combine them to obtain a science and technology knowledge base;

[0007] S3, filling the demand consultation data package according to the scientific and technological knowledge data package corresponding to the demand consultation data package, calculating the consultation progress coefficient, determining the consultation progress status according to the consultation progress coefficient, and obtaining the progress status determination result;

[0008] S4. After the consultation progress is completed, the consultation accuracy of each required consultation data packet is calculated, the consultation exception block is determined according to the consultation accuracy, and the knowledge information of the consultation exception block is re-acquired until there is no consultation exception block in the consultation completion data.

[0009] Furthermore, the S1 includes:

[0010] Acquire enterprise technology consulting demand information, classify the enterprise technology consulting demand information according to preset information categories, and obtain multiple categories of demand category information;

[0011] Dividing the demand type information into data packets according to the demand progress to obtain a plurality of demand consultation data packets, and sorting the demand consultation data packets according to the demand progress to obtain a demand data packet sequence;

[0012] Combine the demand data packet sequences of all demand type information to obtain the enterprise technology consulting library.

[0013] Further, the S2 includes:

[0014] Building a scientific and technological knowledge base through a big data method according to preset scientific and technological management information, classifying the scientific and technological knowledge base according to preset information types, and obtaining multiple types of knowledge type information;

[0015] Dividing the knowledge type information into data packets according to the knowledge progress to obtain a plurality of scientific and technological knowledge data packets, and sorting the scientific and technological knowledge data packets according to the knowledge progress to obtain a knowledge data packet sequence;

[0016] The knowledge data packet sequences of the knowledge category information are combined to obtain a scientific and technological knowledge base.

[0017] Further, the S3 includes:

[0018] According to the demand type information, a scientific and technological knowledge data packet corresponding to each demand consultation data packet is obtained in the scientific and technological knowledge base, and the data information of the demand consultation data packet is filled according to the data information of the scientific and technological knowledge data packet to obtain demand filling information;

[0019] Calculate the consultation progress coefficient based on the demand filling information, the scientific and technological knowledge data package and the demand consultation data package, compare the consultation progress coefficient with a preset progress coefficient threshold, and obtain a progress comparison result;

[0020] The progress status of the consultation progress is determined according to the progress comparison result to obtain the progress status determination result.

[0021] Further, the S4 includes:

[0022] When the progress status is determined to be completed, obtain the consultation completion data;

[0023] Calculating the consultation accuracy of each required consultation data packet according to the consultation completion data, comparing the consultation accuracy with a preset accuracy threshold, and obtaining an accuracy comparison result;

[0024] The consultation exception block is determined according to the accuracy comparison result, and the knowledge information of the consultation exception block is reacquired until the consultation completion data does not contain the consultation exception block.

[0025] Furthermore, the system comprises:

[0026] The demand data acquisition module is used to obtain demand type information based on the enterprise technology consulting demand information, divide the demand type information into demand consulting data packets, and then obtain the demand data packet sequence, and combine them to obtain the enterprise technology consulting library;

[0027] The knowledge data acquisition module is used to acquire knowledge category information according to preset science and technology management information, divide the knowledge category information into science and technology knowledge data packets, and then acquire a sequence of knowledge data packets, and combine them to obtain a science and technology knowledge base;

[0028] A demand knowledge filling module is used to fill the demand consultation data package according to the scientific and technological knowledge data package corresponding to the demand consultation data package, calculate the consultation progress coefficient, determine the consultation progress status according to the consultation progress coefficient, and obtain the progress status determination result;

[0029] The precise exception handling module is used to calculate the consultation accuracy of each required consultation data packet after the consultation progress is completed, determine the consultation exception block according to the consultation accuracy, and re-acquire the knowledge information of the consultation exception block until there is no consultation exception block in the consultation completion data.

[0030] Furthermore, the demand data acquisition module includes:

[0031] Acquire enterprise technology consulting demand information, classify the enterprise technology consulting demand information according to preset information categories, and obtain multiple categories of demand category information;

[0032] Dividing the demand type information into data packets according to the demand progress to obtain a plurality of demand consultation data packets, and sorting the demand consultation data packets according to the demand progress to obtain a demand data packet sequence;

[0033] Combine the demand data packet sequences of all demand type information to obtain the enterprise technology consulting library.

[0034] Furthermore, the knowledge data acquisition module includes:

[0035] Building a scientific and technological knowledge base through a big data method according to preset scientific and technological management information, classifying the scientific and technological knowledge base according to preset information types, and obtaining multiple types of knowledge type information;

[0036] Dividing the knowledge type information into data packets according to the knowledge progress to obtain a plurality of scientific and technological knowledge data packets, and sorting the scientific and technological knowledge data packets according to the knowledge progress to obtain a knowledge data packet sequence;

[0037] The knowledge data packet sequences of the knowledge category information are combined to obtain a scientific and technological knowledge base.

[0038] Furthermore, the required knowledge filling module includes:

[0039] According to the demand type information, a scientific and technological knowledge data packet corresponding to each demand consultation data packet is obtained in the scientific and technological knowledge base, and the data information of the demand consultation data packet is filled according to the data information of the scientific and technological knowledge data packet to obtain demand filling information;

[0040] Calculate the consultation progress coefficient based on the demand filling information, the scientific and technological knowledge data package and the demand consultation data package, compare the consultation progress coefficient with a preset progress coefficient threshold, and obtain a progress comparison result;

[0041] The progress status of the consultation progress is determined according to the progress comparison result to obtain the progress status determination result.

[0042] Furthermore, the precise exception handling module includes:

[0043] When the progress status is determined to be completed, obtain the consultation completion data;

[0044] Calculating the consultation accuracy of each required consultation data packet according to the consultation completion data, comparing the consultation accuracy with a preset accuracy threshold, and obtaining an accuracy comparison result;

[0045] The consultation exception block is determined according to the accuracy comparison result, and the knowledge information of the consultation exception block is reacquired until the consultation completion data does not contain the consultation exception block.

[0046] Beneficial effects of the invention: This application proposes an enterprise technology management service system and method based on artificial intelligence, which realizes the comprehensive integration and efficient matching of consulting needs and knowledge resources by constructing a systematic consulting library and knowledge base. The system introduces consulting accuracy calculation and exception handling mechanisms to ensure the accuracy and reliability of consulting results. At the same time, it focuses on regular updating of the knowledge base and the provision of personalized services to meet the diverse needs of enterprises. In addition, data security and privacy protection are strengthened to ensure the security and reliability of the consulting process. This application aims to solve many pain points in the prior art and improve the overall effectiveness of enterprise technology consulting. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic diagram of an enterprise technology management service method based on artificial intelligence. DETAILED DESCRIPTION

[0048] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0049] In one embodiment of the present invention, an enterprise technology management service system and method based on artificial intelligence are proposed by the present invention, and the method includes:

[0050] S1. Obtain demand type information based on enterprise technology consulting demand information, divide the demand type information into demand consulting data packets, and then obtain a demand data packet sequence, and combine them to obtain an enterprise technology consulting database;

[0051] S2. Acquire knowledge category information according to preset science and technology management information, divide the knowledge category information into science and technology knowledge data packets, and then acquire a sequence of knowledge data packets, and combine them to obtain a science and technology knowledge base;

[0052] S3, filling the demand consultation data package according to the scientific and technological knowledge data package corresponding to the demand consultation data package, calculating the consultation progress coefficient, determining the consultation progress status according to the consultation progress coefficient, and obtaining the progress status determination result;

[0053] S4. After the consultation progress is completed, the consultation accuracy of each required consultation data packet is calculated, the consultation exception block is determined according to the consultation accuracy, and the knowledge information of the consultation exception block is re-acquired until there is no consultation exception block in the consultation completion data.

[0054] The working principle of the above technical solution is as follows: the system first identifies and obtains specific demand type information through the input of enterprise technology consulting demand information. These demands may involve multiple aspects such as technology research and development knowledge demand and product innovation knowledge demand. The acquired demand type information is refined and classified to form a time series demand consulting data packet. Each data packet contains detailed information of a specific demand. These data packets are sorted according to a certain time series to form a demand data packet sequence and build an enterprise technology consulting library. The system extracts and classifies knowledge type information based on preset technology management information. These knowledge types cover various professional knowledge and cases required for enterprise technology management. The knowledge type information is subdivided to generate technology knowledge data packets. Each data packet contains detailed knowledge content of a specific field or theme, such as technical principles, application cases, policy interpretation, etc. The technology knowledge data packets are organized into a sequence and built into a technology knowledge base for rapid retrieval and matching. The system matches the demand consulting data packet with the technology knowledge data packet, and uses the information in the knowledge base to fill in and answer the consulting data packet. During the consultation process, the system calculates the consultation progress coefficient in real time, which reflects the completion degree and efficiency of the consultation task. According to the consultation progress coefficient, the system determines the consultation progress status, such as normal, accelerated, delayed, etc., so as to adjust the consultation strategy and resource allocation in time. After the consultation progress is completed, the system evaluates the accuracy of the consultation results of each demand consultation data package. The consultation accuracy is determined by comparing the difference between the actual consultation results and the expected goals. If the consultation accuracy is found to be lower than the preset standard, the system identifies the consultation abnormal block, that is, the consultation part with problems. The knowledge information of the consultation abnormal block is re-acquired and re-consulted until there is no consultation abnormal block in the consultation completion data, ensuring the accuracy and reliability of the consultation results.

[0055] The technical effects of the above technical solution are: through automated demand classification and knowledge matching, the manual processing time is significantly reduced, and the response speed and efficiency of consulting services are improved. Real-time consulting progress management and accuracy assessment mechanism ensure the controllability of the consulting process and the accuracy of the results, reducing errors and omissions. According to the consulting progress and accuracy feedback, the system can flexibly adjust resource allocation and improve resource utilization efficiency. Fast and accurate consulting services can meet the scientific and technological management needs of enterprises, improve user satisfaction and trust, and enhance corporate competitiveness. The construction and continuous optimization of the scientific and technological knowledge base promotes the accumulation and sharing of internal knowledge in enterprises, and helps to form a virtuous cycle of knowledge inheritance.

[0056] In one embodiment of the present invention, the S1 includes:

[0057] Obtain enterprise technology consulting demand information, classify the enterprise technology consulting demand information according to preset information categories, and obtain multiple categories of demand category information; the preset category information includes scientific research project information, scientific research results information, and scientific research process information, etc.

[0058] The demand type information is divided into data packets according to the demand progress, and multiple demand consultation data packets are obtained. The demand consultation data packets are sorted according to the demand progress to obtain a demand data packet sequence; the demand progress is the sorting of complete demand information of the demand type information at each stage, and each demand consultation data packet is the complete demand information of each stage. The demand progress is, for example, the stage demand progress of the scientific research process.

[0059] Combine the demand data packet sequences of all demand type information to obtain the enterprise technology consulting library.

[0060] The working principle of the above technical solution is as follows: the system first obtains the enterprise's technology consulting demand information through various channels (such as demand forms submitted by enterprises, online platforms, emails, etc.). This information may include knowledge demand content in various aspects such as scientific research project application, scientific research results transformation, and scientific research process management. The consulting demand information obtained is classified according to the preset information types. The preset type information is usually based on the actual needs of enterprise technology management, such as demand information for scientific research project information, scientific research results information, and scientific research process information. This step ensures the orderliness and manageability of the information. For each type of demand information, the system further divides it according to the demand progress. The demand progress refers to the complete demand information set of demand type information at different stages or links. For example, in the scientific research process, it may include the same type of information in multiple stages such as project establishment, program design, experimental implementation, data analysis, and results summary. The complete demand information of each stage is encapsulated into a demand consulting data package. Then, according to the natural order of the demand progress (such as time order), these data packages are sorted to form a demand data package sequence. The system combines all types of demand data package sequences to form an enterprise technology consulting library. This consulting database is a structured information collection that contains the knowledge demand information of various aspects of enterprise science and technology management, as well as the detailed requirements of these needs at different stages. The establishment of the consulting database enables enterprises to easily query, retrieve and use this information to support their science and technology decision-making and management work.

[0061] The technical effect of the above technical solution is that through automated information classification and data packet division, enterprises can manage a large amount of technology consulting demand information more efficiently. This not only reduces the time and cost of manual processing, but also improves the accuracy and consistency of information. The constructed enterprise technology consulting database provides strong support for the enterprise's technology decision-making. Decision makers can quickly obtain the required information, understand the needs at different stages, and make decisions. The establishment of the consulting database promotes information sharing and collaboration among various departments within the enterprise. Different departments and teams can access the consulting database according to their needs, obtain relevant information, and communicate and collaborate on this basis to jointly promote the technological development of the enterprise. For institutions or teams that provide technology consulting services, building an enterprise technology consulting database can improve the quality of service. They can understand the needs of enterprises more accurately based on the information in the consulting database and provide more professional and personalized consulting services. The consulting database is a dynamic information system that can be continuously updated and improved as the needs of enterprise technology consulting change. By regularly reviewing and evaluating the content and use of the consulting database, enterprises can discover existing problems and deficiencies and take corresponding measures to improve and optimize.

[0062] In one embodiment of the present invention, S2 includes:

[0063] Building a scientific and technological knowledge base through a big data method according to preset scientific and technological management information, classifying the scientific and technological knowledge base according to preset information types, and obtaining multiple types of knowledge type information;

[0064] The knowledge type information is divided into data packets according to the knowledge progress to obtain multiple scientific and technological knowledge data packets, and the scientific and technological knowledge data packets are sorted according to the knowledge progress to obtain a knowledge data packet sequence; the knowledge progress is the sorting of the complete knowledge information of the knowledge type information at each stage, and each scientific and technological knowledge data packet is the complete knowledge information of each stage. The knowledge progress is, for example, the stage knowledge progress of the scientific and technological process.

[0065] The knowledge data packet sequences of the knowledge category information are combined to obtain a scientific and technological knowledge base.

[0066] The working principle of the above technical solution is: using big data methods, collect, integrate and analyze data related to preset science and technology management information from various data sources (such as academic papers, patent documents, industry reports, expert experience, etc.). These data cover a wide range of scientific and technological fields, including but not limited to basic research, applied research and development, technological innovation, market trends, etc. Through pre-processing steps such as cleaning, deduplication, and formatting of these data, valuable scientific and technological knowledge information is extracted. Based on the preset information types, the extracted scientific and technological knowledge information is classified. These preset information types may include technical principles, experimental methods, case analysis, policy interpretation, market trends, etc. The purpose of classification is to facilitate subsequent data management and application and ensure the structuring and orderliness of the knowledge base. For each type of knowledge information, data packets are divided according to their knowledge progress. Knowledge progress refers to the integrity and depth of knowledge information at different stages or links. For example, in the scientific and technological process, it may include multiple stages such as basic theory, experimental design, experimental results, data analysis, and conclusion summary. The complete knowledge information of each stage is encapsulated into a scientific and technological knowledge data packet. Then, according to the natural order of knowledge progress (such as time order), these data packets are sorted to form a sequence of knowledge data packets. All kinds of knowledge data packet sequences are combined to build a complete scientific and technological knowledge base. This knowledge base is a systematic and structured knowledge collection, which contains all kinds of knowledge information required for enterprise science and technology management, as well as the detailed content and logical relationship of these knowledge information at different stages. By building a scientific and technological knowledge base through big data methods, valuable scientific and technological knowledge information can be quickly extracted from massive data, greatly improving the efficiency of knowledge acquisition. Enterprises can easily obtain the required knowledge resources to support their scientific and technological decision-making and innovation activities.

[0067] The technical effect of the above technical solution is: the knowledge base is classified and sorted according to the preset information types, so that enterprises can manage and use this knowledge information more conveniently. Different departments and teams can quickly locate the required knowledge resources according to their needs, improving the efficiency and quality of knowledge management. The science and technology knowledge base is a dynamically updated system that can be continuously updated and improved with the changes in scientific and technological development. The establishment of the knowledge base promotes knowledge sharing and collaboration among different departments and teams within the enterprise. Users can obtain the required knowledge resources by accessing the knowledge base, and communicate and collaborate on this basis to jointly promote the technological development of the enterprise. The science and technology knowledge base provides comprehensive, accurate and timely scientific and technological knowledge support for enterprise decision makers. Decision makers can analyze and judge based on the information in the knowledge base, formulate more scientific and reasonable decision plans, reduce decision risks and improve decision results.

[0068] In one embodiment of the present invention, S3 includes:

[0069] According to the demand type information, a scientific and technological knowledge data packet corresponding to each demand consultation data packet is obtained in the scientific and technological knowledge base, and the data information of the demand consultation data packet is filled according to the data information of the scientific and technological knowledge data packet to obtain demand filling information;

[0070] Calculate the consultation progress coefficient based on the demand filling information, the scientific and technological knowledge data package and the demand consultation data package, compare the consultation progress coefficient with a preset progress coefficient threshold, and obtain a progress comparison result;

[0071] The calculation formula of the consultation progress coefficient is:

[0072]

[0073] Among them, D zx is the consultation progress coefficient, B x is the total number of demand consultation data packets, X li is the number of knowledge questions in the i-th demand consultation data package, T li is the number of answers to the knowledge filling of the i-th scientific and technological knowledge data package, B z is the total number of scientific and technological knowledge data packets, S z is the total amount of data in the scientific and technological knowledge data package, S t is the total amount of data in the scientific and technological knowledge data package, S x The total amount of data to fill the information required;

[0074] The progress status of the consultation progress is determined according to the progress comparison result to obtain the progress status determination result.

[0075] When the consultation progress coefficient is greater than the preset progress coefficient threshold, the consultation progress is determined to be completed, otherwise, it is in an unfinished state.

[0076] The working principle of the above technical solution is as follows: the system will search for the corresponding scientific and technological knowledge data package of each demand consultation data package in the scientific and technological knowledge base according to the demand type information. This step is completed based on the preset information type classification and data package division to ensure the accurate match between demand and knowledge. After finding the corresponding scientific and technological knowledge data package, the system will use the data information therein to fill in the consultation information in the demand consultation data package. This includes supplementing missing detailed information, correcting erroneous data, and improving incomplete analysis. The filled information is called demand filling information, which more comprehensively reflects the actual needs of the demand consultation data package; the system will calculate the consultation progress coefficient based on the demand filling information, the scientific and technological knowledge data package and the original demand consultation data package. This coefficient is a quantitative indicator used to evaluate the degree of completion and progress status of the consultation work. The calculated consultation progress coefficient will be compared with the preset progress coefficient threshold. The threshold is used to distinguish the completion status and incomplete status of the consultation progress. When the consultation progress coefficient is greater than the threshold, the consultation progress is determined to be in the completed state; otherwise, it is in the incomplete state.

[0077] The technical effect of the above technical solution is: through the automated matching of demand and knowledge and the process of filling in information, the system can quickly and accurately respond to the enterprise's technology consulting needs. This not only improves the efficiency of consulting work, but also ensures the quality and accuracy of consulting results. The introduction of the consulting progress coefficient provides a quantitative indicator for the evaluation of consulting progress. Enterprises can clearly understand the completion and progress status of consulting work, which is convenient for timely adjustment and optimization of consulting plans. Based on the progress status determination results of the consulting progress coefficient, enterprises can make decisions more scientifically. For completed demand consulting, enterprises can take quick action; for unfinished demand consulting, enterprises can analyze the reasons and take corresponding measures to speed up the progress. By understanding the actual situation of consulting progress, enterprises can allocate resources more reasonably. For consulting projects with lagging progress, enterprises can invest more resources and manpower to ensure their completion on time; for consulting projects ahead of schedule, enterprises can adjust resource allocation to support other more important work. The calculation of the consulting progress coefficient and the progress status determination results can also serve as the basis for continuous improvement of enterprise technology consulting management. Enterprises can continuously optimize consulting processes and management methods by analyzing the changing trends and influencing factors of consulting progress, and improve overall consulting efficiency and quality.

[0078] In one embodiment of the present invention, the S4 includes:

[0079] When the progress status is determined to be completed, obtain the consultation completion data (i.e. all demand filling information);

[0080] Calculating the consultation accuracy of each required consultation data packet according to the consultation completion data, comparing the consultation accuracy with a preset accuracy threshold, and obtaining an accuracy comparison result;

[0081] The accuracy of each required consultation data package:

[0082]

[0083] Among them, X zx is the consulting accuracy of the demand consulting data package, u is the total number of consulting tasks in the demand consulting data package, T lo The amount of knowledge filling answer data for the oth consulting task, X lo is the amount of knowledge question data for the oth consulting task, AT lo and BX lo is the vector representation of the oth consultation task of the two texts, (AT lo ·BX lo ) represents the vector AT of the oth consulting task of the two texts lo and BX lo The dot product of |AT lo | and |BX lo | are the vectors AT of the oth consulting task of the two texts respectively lo and BX lo The modulus (length) of the word; in text similarity calculation, the text can be converted into a vector (for example, using TF-IDF or word embedding technology);

[0084] Determine the consultation exception block based on the accuracy comparison result, and re-acquire the knowledge information of the consultation exception block (the re-acquisition includes replacing the scientific and technological knowledge data packet corresponding to the demand consultation data packet and re-filling the information) until the consultation is completed and there is no consultation exception block in the data.

[0085] When the consultation accuracy is greater than a preset accuracy threshold, the data packet requiring consultation is determined to be a normal consultation block, otherwise, it is a abnormal consultation block.

[0086] The working principle of the above technical solution is as follows: when the progress status is determined to be completed, the system will first collect and organize all the filled demand consultation data packets to form consultation completion data. These data contain all the information that has been filled and corrected according to the scientific and technological knowledge base, and are the final results of the consultation work. The system will calculate the consultation accuracy of each demand consultation data packet according to the preset accuracy evaluation method. Consultation accuracy is a quantitative indicator used to measure the degree of closeness between the consultation result and the actual situation or expected goal. The calculated consultation accuracy will be compared with the preset accuracy threshold. This threshold is used to distinguish between normal and abnormal consultation results. When the consultation accuracy is greater than the threshold, the demand consultation data packet is determined to be a normal consultation block, indicating that the consultation result is in line with expectations; otherwise, it is an abnormal consultation block, indicating that there are problems or deficiencies in the consultation result. For the demand consultation data packet determined to be an abnormal consultation block, the system will re-acquire the knowledge information. This includes replacing the scientific and technological knowledge data packet corresponding to the abnormal block, and re-filling and correcting the information. During the re-acquisition process, the system may consider a variety of factors, such as the timeliness, authority, and relevance of the knowledge package, to ensure that the re-acquired knowledge information can more accurately meet the consultation needs. The process of re-acquisition and re-filling is repeated until there are no more consultation exception blocks in the consultation completion data.

[0087] The technical effect of the above technical solution is: through the calculation of consulting accuracy and abnormality determination, the system can timely discover and deal with problems and deficiencies in consulting results. This helps to improve the overall quality of consulting work and ensure that consulting results are more accurate and reliable. The system can flexibly adjust consulting strategies and methods according to the comparison results of consulting accuracy. For the re-acquisition and re-filling of abnormal blocks, the system can automatically select more appropriate scientific and technological knowledge data packages for filling, thereby enhancing the adaptability and flexibility of consulting services. The process of consulting exception handling is actually an optimization of the consulting process. Through continuous trial and error and adjustment, the system can gradually find the process and method that best suits the current consulting needs, thereby improving the efficiency and effectiveness of consulting work. High-quality consulting results can significantly improve customer satisfaction with consulting services. By ensuring the accuracy and reliability of consulting results, the system can win the trust and recognition of customers, thereby bringing more business opportunities and benefits to enterprises. The problems and deficiencies found in the process of consulting exception handling can also serve as a basis for continuous improvement of the scientific and technological knowledge base. Enterprises can continuously optimize and update the content in the knowledge base based on these feedbacks to make it more in line with actual needs and industry standards.

[0088] In one embodiment of the present invention, the system comprises:

[0089] The demand data acquisition module is used to obtain demand type information based on the enterprise technology consulting demand information, divide the demand type information into demand consulting data packets, and then obtain the demand data packet sequence, and combine them to obtain the enterprise technology consulting library;

[0090] The knowledge data acquisition module is used to acquire knowledge category information according to preset science and technology management information, divide the knowledge category information into science and technology knowledge data packets, and then acquire a sequence of knowledge data packets, and combine them to obtain a science and technology knowledge base;

[0091] A demand knowledge filling module is used to fill the demand consultation data package according to the scientific and technological knowledge data package corresponding to the demand consultation data package, calculate the consultation progress coefficient, determine the consultation progress status according to the consultation progress coefficient, and obtain the progress status determination result;

[0092] The precise exception handling module is used to calculate the consultation accuracy of each required consultation data packet after the consultation progress is completed, determine the consultation exception block according to the consultation accuracy, and re-acquire the knowledge information of the consultation exception block until there is no consultation exception block in the consultation completion data.

[0093] The working principle of the above technical solution is as follows: the system first identifies and obtains specific demand type information through the input of enterprise technology consulting demand information. These demands may involve multiple aspects such as technology research and development knowledge demand and product innovation knowledge demand. The acquired demand type information is refined and classified to form a time series demand consulting data packet. Each data packet contains detailed information of a specific demand. These data packets are sorted according to a certain time series to form a demand data packet sequence and build an enterprise technology consulting library. The system extracts and classifies knowledge type information based on preset technology management information. These knowledge types cover various professional knowledge and cases required for enterprise technology management. The knowledge type information is subdivided to generate technology knowledge data packets. Each data packet contains detailed knowledge content of a specific field or theme, such as technical principles, application cases, policy interpretation, etc. The technology knowledge data packets are organized into a sequence and built into a technology knowledge base for rapid retrieval and matching. The system matches the demand consulting data packet with the technology knowledge data packet, and uses the information in the knowledge base to fill in and answer the consulting data packet. During the consultation process, the system calculates the consultation progress coefficient in real time, which reflects the completion degree and efficiency of the consultation task. According to the consultation progress coefficient, the system determines the consultation progress status, such as normal, accelerated, delayed, etc., so as to adjust the consultation strategy and resource allocation in time. After the consultation progress is completed, the system evaluates the accuracy of the consultation results of each demand consultation data package. The consultation accuracy is determined by comparing the difference between the actual consultation results and the expected goals. If the consultation accuracy is found to be lower than the preset standard, the system identifies the consultation abnormal block, that is, the consultation part with problems. The knowledge information of the consultation abnormal block is re-acquired and re-consulted until there is no consultation abnormal block in the consultation completion data, ensuring the accuracy and reliability of the consultation results.

[0094] The technical effects of the above technical solution are: through automated demand classification and knowledge matching, the manual processing time is significantly reduced, and the response speed and efficiency of consulting services are improved. Real-time consulting progress management and accuracy assessment mechanism ensure the controllability of the consulting process and the accuracy of the results, reducing errors and omissions. According to the consulting progress and accuracy feedback, the system can flexibly adjust resource allocation and improve resource utilization efficiency. Fast and accurate consulting services can meet the scientific and technological management needs of enterprises, improve user satisfaction and trust, and enhance corporate competitiveness. The construction and continuous optimization of the scientific and technological knowledge base promotes the accumulation and sharing of internal knowledge in enterprises, and helps to form a virtuous cycle of knowledge inheritance.

[0095] In one embodiment of the present invention, the demand data acquisition module includes:

[0096] Obtain enterprise technology consulting demand information, classify the enterprise technology consulting demand information according to preset information categories, and obtain multiple categories of demand category information; the preset category information includes scientific research project information, scientific research results information, and scientific research process information, etc.

[0097] The demand type information is divided into data packets according to the demand progress, and multiple demand consultation data packets are obtained. The demand consultation data packets are sorted according to the demand progress to obtain a demand data packet sequence; the demand progress is the sorting of complete demand information of the demand type information at each stage, and each demand consultation data packet is the complete demand information of each stage. The demand progress is, for example, the stage demand progress of the scientific research process.

[0098] Combine the demand data packet sequences of all demand type information to obtain the enterprise technology consulting library.

[0099] The working principle of the above technical solution is as follows: the system first obtains the enterprise's technology consulting demand information through various channels (such as demand forms submitted by enterprises, online platforms, emails, etc.). This information may include knowledge demand content in various aspects such as scientific research project application, scientific research results transformation, and scientific research process management. The consulting demand information obtained is classified according to the preset information types. The preset type information is usually based on the actual needs of enterprise technology management, such as demand information for scientific research project information, scientific research results information, and scientific research process information. This step ensures the orderliness and manageability of the information. For each type of demand information, the system further divides it according to the demand progress. The demand progress refers to the complete demand information set of demand type information at different stages or links. For example, in the scientific research process, it may include the same type of information in multiple stages such as project establishment, program design, experimental implementation, data analysis, and results summary. The complete demand information of each stage is encapsulated into a demand consulting data package. Then, according to the natural order of the demand progress (such as time order), these data packages are sorted to form a demand data package sequence. The system combines all types of demand data package sequences to form an enterprise technology consulting library. This consulting database is a structured information collection that contains knowledge demand information in all aspects of enterprise science and technology management, as well as detailed requirements of these needs at different stages. The establishment of the consulting database enables enterprises to easily query, retrieve and use this information to support their science and technology decision-making and management work.

[0100] The technical effect of the above technical solution is that through automated information classification and data packet division, enterprises can manage a large amount of technology consulting demand information more efficiently. This not only reduces the time and cost of manual processing, but also improves the accuracy and consistency of information. The constructed enterprise technology consulting database provides strong support for the enterprise's technology decision-making. Decision makers can quickly obtain the required information, understand the needs at different stages, and make decisions. The establishment of the consulting database promotes information sharing and collaboration among various departments within the enterprise. Different departments and teams can access the consulting database according to their needs, obtain relevant information, and communicate and collaborate on this basis to jointly promote the technological development of the enterprise. For institutions or teams that provide technology consulting services, building an enterprise technology consulting database can improve the quality of service. They can understand the needs of enterprises more accurately based on the information in the consulting database and provide more professional and personalized consulting services. The consulting database is a dynamic information system that can be continuously updated and improved as the needs of enterprise technology consulting change. By regularly reviewing and evaluating the content and use of the consulting database, enterprises can discover existing problems and deficiencies and take corresponding measures to improve and optimize.

[0101] In one embodiment of the present invention, the knowledge data acquisition module includes:

[0102] Building a scientific and technological knowledge base through a big data method according to preset scientific and technological management information, classifying the scientific and technological knowledge base according to preset information types, and obtaining multiple types of knowledge type information;

[0103] The knowledge type information is divided into data packets according to the knowledge progress to obtain multiple scientific and technological knowledge data packets, and the scientific and technological knowledge data packets are sorted according to the knowledge progress to obtain a knowledge data packet sequence; the knowledge progress is the sorting of the complete knowledge information of the knowledge type information at each stage, and each scientific and technological knowledge data packet is the complete knowledge information of each stage. The knowledge progress is, for example, the stage knowledge progress of the scientific and technological process.

[0104] The knowledge data packet sequences of the knowledge category information are combined to obtain a scientific and technological knowledge base.

[0105] The working principle of the above technical solution is: using big data methods, collect, integrate and analyze data related to preset science and technology management information from various data sources (such as academic papers, patent documents, industry reports, expert experience, etc.). These data cover a wide range of scientific and technological fields, including but not limited to basic research, applied research and development, technological innovation, market trends, etc. Through pre-processing steps such as cleaning, deduplication, and formatting of these data, valuable scientific and technological knowledge information is extracted. Based on the preset information types, the extracted scientific and technological knowledge information is classified. These preset information types may include technical principles, experimental methods, case analysis, policy interpretation, market trends, etc. The purpose of classification is to facilitate subsequent data management and application and ensure the structuring and orderliness of the knowledge base. For each type of knowledge information, data packets are divided according to their knowledge progress. Knowledge progress refers to the integrity and depth of knowledge information at different stages or links. For example, in the scientific and technological process, it may include multiple stages such as basic theory, experimental design, experimental results, data analysis, and conclusion summary. The complete knowledge information of each stage is encapsulated into a scientific and technological knowledge data packet. Then, according to the natural order of knowledge progress (such as time order), these data packets are sorted to form a sequence of knowledge data packets. All kinds of knowledge data packet sequences are combined to build a complete scientific and technological knowledge base. This knowledge base is a systematic and structured knowledge collection, which contains all kinds of knowledge information required for enterprise science and technology management, as well as the detailed content and logical relationship of these knowledge information at different stages. By building a scientific and technological knowledge base through big data methods, valuable scientific and technological knowledge information can be quickly extracted from massive data, greatly improving the efficiency of knowledge acquisition. Enterprises can easily obtain the required knowledge resources to support their scientific and technological decision-making and innovation activities.

[0106] The technical effect of the above technical solution is: the knowledge base is classified and sorted according to the preset information types, so that enterprises can manage and use this knowledge information more conveniently. Different departments and teams can quickly locate the required knowledge resources according to their needs, improving the efficiency and quality of knowledge management. The science and technology knowledge base is a dynamically updated system that can be continuously updated and improved with the changes in scientific and technological development. The establishment of the knowledge base promotes knowledge sharing and collaboration among different departments and teams within the enterprise. Users can obtain the required knowledge resources by accessing the knowledge base, and communicate and collaborate on this basis to jointly promote the technological development of the enterprise. The science and technology knowledge base provides comprehensive, accurate and timely scientific and technological knowledge support for enterprise decision makers. Decision makers can analyze and judge based on the information in the knowledge base, formulate more scientific and reasonable decision plans, reduce decision risks and improve decision results.

[0107] In one embodiment of the present invention, the required knowledge filling module includes:

[0108] According to the demand type information, a scientific and technological knowledge data packet corresponding to each demand consultation data packet is obtained in the scientific and technological knowledge base, and the data information of the demand consultation data packet is filled according to the data information of the scientific and technological knowledge data packet to obtain demand filling information;

[0109] Calculate the consultation progress coefficient based on the demand filling information, the scientific and technological knowledge data package and the demand consultation data package, compare the consultation progress coefficient with a preset progress coefficient threshold, and obtain a progress comparison result;

[0110] The calculation formula of the consultation progress coefficient is:

[0111]

[0112] Among them, D zx is the consultation progress coefficient, B x is the total number of demand consultation data packets, X li is the number of knowledge questions in the i-th demand consultation data package, T li is the number of answers to the knowledge filling of the i-th scientific and technological knowledge data package, B z is the total number of scientific and technological knowledge data packets, S z is the total amount of data in the scientific and technological knowledge data package, S t is the total amount of data in the scientific and technological knowledge data package, S x The total amount of data to fill the information required;

[0113] The progress status of the consultation progress is determined according to the progress comparison result to obtain the progress status determination result.

[0114] When the consultation progress coefficient is greater than the preset progress coefficient threshold, the consultation progress is determined to be completed, otherwise, it is in an unfinished state.

[0115] The working principle of the above technical solution is as follows: the system will search for the corresponding scientific and technological knowledge data package of each demand consultation data package in the scientific and technological knowledge base according to the demand type information. This step is completed based on the preset information type classification and data package division to ensure the accurate match between demand and knowledge. After finding the corresponding scientific and technological knowledge data package, the system will use the data information therein to fill in the consultation information in the demand consultation data package. This includes supplementing missing detailed information, correcting erroneous data, and improving incomplete analysis. The filled information is called demand filling information, which more comprehensively reflects the actual needs of the demand consultation data package; the system will calculate the consultation progress coefficient based on the demand filling information, the scientific and technological knowledge data package and the original demand consultation data package. This coefficient is a quantitative indicator used to evaluate the degree of completion and progress status of the consultation work. The calculated consultation progress coefficient will be compared with the preset progress coefficient threshold. The threshold is used to distinguish the completion status and incomplete status of the consultation progress. When the consultation progress coefficient is greater than the threshold, the consultation progress is determined to be in the completed state; otherwise, it is in the incomplete state.

[0116] The technical effect of the above technical solution is: through the automated matching of demand and knowledge and the process of filling in information, the system can quickly and accurately respond to the enterprise's technology consulting needs. This not only improves the efficiency of consulting work, but also ensures the quality and accuracy of consulting results. The introduction of the consulting progress coefficient provides a quantitative indicator for the evaluation of consulting progress. Enterprises can clearly understand the completion and progress status of consulting work, which is convenient for timely adjustment and optimization of consulting plans. Based on the progress status determination results of the consulting progress coefficient, enterprises can make decisions more scientifically. For completed demand consulting, enterprises can take quick action; for unfinished demand consulting, enterprises can analyze the reasons and take corresponding measures to speed up the progress. By understanding the actual situation of consulting progress, enterprises can allocate resources more reasonably. For consulting projects with lagging progress, enterprises can invest more resources and manpower to ensure their completion on time; for consulting projects ahead of schedule, enterprises can adjust resource allocation to support other more important work. The calculation of the consulting progress coefficient and the progress status determination results can also serve as the basis for continuous improvement of enterprise technology consulting management. Enterprises can continuously optimize consulting processes and management methods by analyzing the changing trends and influencing factors of consulting progress, and improve overall consulting efficiency and quality.

[0117] In one embodiment of the present invention, the precise exception handling module includes:

[0118] When the progress status is determined to be completed, obtain the consultation completion data (i.e. all demand filling information);

[0119] Calculating the consultation accuracy of each required consultation data packet according to the consultation completion data, comparing the consultation accuracy with a preset accuracy threshold, and obtaining an accuracy comparison result;

[0120] The accuracy of each required consultation data package:

[0121]

[0122] Among them, X zx is the consulting accuracy of the demand consulting data package, u is the total number of consulting tasks in the demand consulting data package, T lo The amount of knowledge filling answer data for the oth consulting task, X lo is the amount of knowledge question data for the oth consulting task, AT lo and BX lo is the vector representation of the oth consultation task of the two texts, (AT lo ·BX lo ) represents the vector AT of the oth consulting task of the two texts lo and BX lo The dot product of |AT lo | and |BX lo | are the vectors AT of the oth consulting task of the two texts respectively lo and BX lo The modulus (length) of the text; in text similarity calculation, the text can be converted into a vector (for example, using TF-IDF or word embedding technology);

[0123] Determine the consultation exception block based on the accuracy comparison result, and re-acquire the knowledge information of the consultation exception block (the re-acquisition includes replacing the scientific and technological knowledge data packet corresponding to the demand consultation data packet and re-filling the information) until the consultation is completed and there is no consultation exception block in the data.

[0124] When the consultation accuracy is greater than a preset accuracy threshold, the data packet requiring consultation is determined to be a normal consultation block, otherwise, it is a abnormal consultation block.

[0125] The working principle of the above technical solution is as follows: when the progress status is determined to be completed, the system will first collect and organize all the filled demand consultation data packets to form consultation completion data. These data contain all the information that has been filled and corrected according to the scientific and technological knowledge base, and are the final results of the consultation work. The system will calculate the consultation accuracy of each demand consultation data packet according to the preset accuracy evaluation method. Consultation accuracy is a quantitative indicator used to measure the degree of closeness between the consultation result and the actual situation or expected goal. The calculated consultation accuracy will be compared with the preset accuracy threshold. This threshold is used to distinguish between normal and abnormal consultation results. When the consultation accuracy is greater than the threshold, the demand consultation data packet is determined to be a normal consultation block, indicating that the consultation result is in line with expectations; otherwise, it is an abnormal consultation block, indicating that there are problems or deficiencies in the consultation result. For the demand consultation data packet determined to be an abnormal consultation block, the system will re-acquire the knowledge information. This includes replacing the scientific and technological knowledge data packet corresponding to the abnormal block, and re-filling and correcting the information. During the re-acquisition process, the system may consider a variety of factors, such as the timeliness, authority, and relevance of the knowledge package, to ensure that the re-acquired knowledge information can more accurately meet the consultation needs. The process of re-acquisition and re-filling is repeated until there are no more consultation exception blocks in the consultation completion data.

[0126] The technical effect of the above technical solution is: through the calculation of consulting accuracy and abnormality determination, the system can timely discover and deal with problems and deficiencies in consulting results. This helps to improve the overall quality of consulting work and ensure that consulting results are more accurate and reliable. The system can flexibly adjust consulting strategies and methods according to the comparison results of consulting accuracy. For the re-acquisition and re-filling of abnormal blocks, the system can automatically select more appropriate scientific and technological knowledge data packages for filling, thereby enhancing the adaptability and flexibility of consulting services. The process of consulting exception handling is actually an optimization of the consulting process. Through continuous trial and error and adjustment, the system can gradually find the process and method that best suits the current consulting needs, thereby improving the efficiency and effectiveness of consulting work. High-quality consulting results can significantly improve customer satisfaction with consulting services. By ensuring the accuracy and reliability of consulting results, the system can win the trust and recognition of customers, thereby bringing more business opportunities and benefits to enterprises. The problems and deficiencies found in the process of consulting exception handling can also serve as a basis for continuous improvement of the scientific and technological knowledge base. Enterprises can continuously optimize and update the content in the knowledge base based on these feedbacks to make it more in line with actual needs and industry standards.

[0127] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An enterprise technology management service method based on artificial intelligence, characterized in that: The method comprises: S1. Obtain demand type information based on enterprise technology consulting demand information, divide the demand type information into demand consulting data packets, and then obtain a demand data packet sequence, and combine them to obtain an enterprise technology consulting database; Wherein, the S1 includes: Acquire enterprise technology consulting demand information, classify the enterprise technology consulting demand information according to preset information categories, and obtain multiple categories of demand category information; Dividing the demand type information into data packets according to the demand progress to obtain a plurality of demand consultation data packets, and sorting the demand consultation data packets according to the demand progress to obtain a demand data packet sequence; Combine the demand data package sequences of all demand type information to obtain the enterprise technology consulting database; S2. Acquire knowledge category information according to preset science and technology management information, divide the knowledge category information into science and technology knowledge data packets, and then acquire a sequence of knowledge data packets, and combine them to obtain a science and technology knowledge base; Wherein, the S2 includes: Building a scientific and technological knowledge base through a big data method according to preset scientific and technological management information, classifying the scientific and technological knowledge base according to preset information types, and obtaining multiple types of knowledge type information; Dividing the knowledge type information into data packets according to the knowledge progress to obtain a plurality of scientific and technological knowledge data packets, and sorting the scientific and technological knowledge data packets according to the knowledge progress to obtain a knowledge data packet sequence; Combining the knowledge data packet sequences of the knowledge category information to obtain a scientific and technological knowledge base; S3, filling the demand consultation data package according to the scientific and technological knowledge data package corresponding to the demand consultation data package, calculating the consultation progress coefficient, determining the consultation progress status according to the consultation progress coefficient, and obtaining the progress status determination result; Wherein, the S3 includes: According to the demand type information, a scientific and technological knowledge data packet corresponding to each demand consultation data packet is obtained in the scientific and technological knowledge base, and the data information of the demand consultation data packet is filled according to the data information of the scientific and technological knowledge data packet to obtain demand filling information; Calculate the consultation progress coefficient based on the demand filling information, the scientific and technological knowledge data package and the demand consultation data package, compare the consultation progress coefficient with a preset progress coefficient threshold, and obtain a progress comparison result; The calculation formula of the consultation progress coefficient is: Among them, D zx is the consultation progress coefficient, B x is the total number of demand consultation data packets, X li is the number of knowledge questions in the i-th demand consultation data package, T li is the number of answers to the knowledge filling of the i-th scientific and technological knowledge data package, B z is the total number of scientific and technological knowledge data packets, S z is the total amount of data in the scientific and technological knowledge data package, S t is the total amount of data in the scientific and technological knowledge data package, S x The total amount of data to fill the information required; Determine the progress status of the consultation progress according to the progress comparison result and obtain the progress status determination result; S4. After the consultation progress is completed, the consultation accuracy of each required consultation data packet is calculated, the consultation exception block is determined according to the consultation accuracy, and the knowledge information of the consultation exception block is re-acquired until there is no consultation exception block in the consultation completion data.

2. According to the enterprise technology management service method based on artificial intelligence as described in claim 1, it is characterized in that: The S4 includes: When the progress status is determined to be completed, obtain the consultation completion data; Calculating the consultation accuracy of each required consultation data packet according to the consultation completion data, comparing the consultation accuracy with a preset accuracy threshold, and obtaining an accuracy comparison result; The consultation exception block is determined according to the accuracy comparison result, and the knowledge information of the consultation exception block is reacquired until the consultation completion data does not contain the consultation exception block.

3. An enterprise technology management service system based on artificial intelligence, characterized in that: The system comprises: The demand data acquisition module is used to obtain demand type information based on the enterprise technology consulting demand information, divide the demand type information into demand consulting data packets, and then obtain the demand data packet sequence, and combine them to obtain the enterprise technology consulting library; Wherein, the demand data acquisition module includes: Acquire enterprise technology consulting demand information, classify the enterprise technology consulting demand information according to preset information categories, and obtain multiple categories of demand category information; Dividing the demand type information into data packets according to the demand progress to obtain a plurality of demand consultation data packets, and sorting the demand consultation data packets according to the demand progress to obtain a demand data packet sequence; Combine the demand data package sequences of all demand type information to obtain the enterprise technology consulting database; The knowledge data acquisition module is used to acquire knowledge category information according to preset science and technology management information, divide the knowledge category information into science and technology knowledge data packets, and then acquire a sequence of knowledge data packets, and combine them to obtain a science and technology knowledge base; Wherein, the knowledge data acquisition module includes: Building a scientific and technological knowledge base through a big data method according to preset scientific and technological management information, classifying the scientific and technological knowledge base according to preset information types, and obtaining multiple types of knowledge type information; Dividing the knowledge type information into data packets according to the knowledge progress to obtain a plurality of scientific and technological knowledge data packets, and sorting the scientific and technological knowledge data packets according to the knowledge progress to obtain a knowledge data packet sequence; Combining the knowledge data packet sequences of the knowledge category information to obtain a scientific and technological knowledge base; A demand knowledge filling module is used to fill the demand consultation data package according to the scientific and technological knowledge data package corresponding to the demand consultation data package, calculate the consultation progress coefficient, determine the consultation progress status according to the consultation progress coefficient, and obtain the progress status determination result; Wherein, the required knowledge filling module includes: According to the demand type information, a scientific and technological knowledge data packet corresponding to each demand consultation data packet is obtained in the scientific and technological knowledge base, and the data information of the demand consultation data packet is filled according to the data information of the scientific and technological knowledge data packet to obtain demand filling information; Calculate the consultation progress coefficient based on the demand filling information, the scientific and technological knowledge data package and the demand consultation data package, compare the consultation progress coefficient with a preset progress coefficient threshold, and obtain a progress comparison result; The calculation formula of the consultation progress coefficient is: Among them, D zx is the consultation progress coefficient, B x is the total number of demand consultation data packets, X li is the number of knowledge questions in the i-th demand consultation data package, T li is the number of answers to the knowledge filling of the i-th scientific and technological knowledge data package, B z is the total number of scientific and technological knowledge data packets, S z is the total amount of data in the scientific and technological knowledge data package, S t is the total amount of data in the scientific and technological knowledge data package, S x The total amount of data to fill the information required; Determine the progress status of the consultation progress according to the progress comparison result and obtain the progress status determination result; The precise exception handling module is used to calculate the consultation accuracy of each required consultation data packet after the consultation progress is completed, determine the consultation exception block according to the consultation accuracy, and re-acquire the knowledge information of the consultation exception block until there is no consultation exception block in the consultation completion data.

4. According to claim 3, an enterprise technology management service system based on artificial intelligence is characterized in that: The precise exception handling module comprises: When the progress status is determined to be completed, obtain the consultation completion data; Calculating the consultation accuracy of each required consultation data packet according to the consultation completion data, comparing the consultation accuracy with a preset accuracy threshold, and obtaining an accuracy comparison result; The consultation exception block is determined according to the accuracy comparison result, and the knowledge information of the consultation exception block is reacquired until the consultation completion data does not contain the consultation exception block.

Images