Enterprise integrated management system and method based on AI large model and digital experience

Abstract

The invention relates to the technical field of enterprise management, in particular to an enterprise comprehensive management system and method based on an AI large model and digital experience, and the system comprises a problem improvement subsystem and a data mining subsystem. The problem improvement subsystem comprises a problem acquisition module used for acquiring problem data; the problem distribution module is used for sending the problem data to a corresponding person in charge for processing; the reason analysis module is used for analyzing generation reasons corresponding to the corresponding problem data based on the received problem data to form generation reason data; the measure determination and execution module is used for formulating corresponding improvement measure data according to the generation reason data and distributing the improvement measure data to corresponding personnel for execution; the evaluation feedback module is used for acquiring evaluation of the user on the problem analysis processing process to form evaluation data; and the storage module stores the problem data, the generation reason data, the improvement measure data and the evaluation data into a comprehensive database to form a structured data set.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise management, and particularly relates to an enterprise comprehensive management system and method based on an AI large model and digital experience. Background Art

[0002] With the rapid development of information technology, the amount of data accumulated by enterprises and organizations has increased exponentially. Effective data analysis and mining are crucial for enhancing enterprise competitiveness, and can assist in decision-making, optimizing business processes, predicting market trends, etc.

[0003] In current enterprise data mining practices, building and training an effective data mining model is usually a complex and time-consuming process, with the following problems:

[0004] 1. To ensure the effectiveness and accuracy of the model, staff need to manually sort and count historical problems, and label and preprocess them. This not only increases the workload but also easily introduces human errors.

[0005] 2. Since it is a retrospective analysis based on historical problems, the constructed model may not accurately reflect the current or future actual problem situations, thus affecting the timeliness and applicability of the model.

[0006] 3. Traditional methods are difficult to respond to newly emerging problems in a timely manner, and there is often a long time delay from the generation of a problem to its final solution, lacking real-time performance.

[0007] 4. From problem identification, data collection, feature engineering to model training, each step requires a large amount of human and technical resources, and the entire process is inefficient.

[0008] Based on this, there is an urgent need for an enterprise comprehensive management system and method based on an AI large model and digital experience, which can solve the deficiencies in the prior art, and realize real-time recording of the whole process from problem generation to solution through a problem improvement subsystem, ensuring the authenticity, reliability of the data required by the model and the timeliness of data collection. Summary of the Invention

[0009] One of the objectives of the present invention is to provide an enterprise comprehensive management system and method based on an AI large model and digital experience, which can solve the deficiencies in the prior art, and realize real-time recording of the whole process from problem generation to solution through a problem improvement subsystem, ensuring the authenticity, reliability of the data required by the model and the timeliness of data collection.

[0010] To achieve the above objective, an enterprise comprehensive management system based on an AI large model and digital experience is provided, including a problem improvement subsystem and a data mining subsystem;

[0011] The problem improvement subsystem includes:

[0012] A problem acquisition module, which is used to acquire problem data and publish it on the enterprise platform;

[0013] A problem allocation module, which is used to send the problem data to the corresponding person in charge for processing;

[0014] A cause analysis module, which is used to, when the person in charge receives the corresponding problem data, analyze the cause corresponding to the received problem data based on the received problem data, form the corresponding cause data, and associate it with the corresponding problem data;

[0015] A measure determination and execution module, which is used to formulate the corresponding improvement measure data according to the obtained cause data, associate it with the corresponding cause data, and distribute the improvement measure data to the corresponding personnel for execution;

[0016] An evaluation feedback module, which is used to obtain the evaluation of the user on the problem analysis and processing process and form evaluation data;

[0017] A storage module, which is used to store the problem data, cause data, improvement measure data, and evaluation data in the comprehensive database to form a structured data set;

[0018] The data mining subsystem includes:

[0019] A model training module, which trains a generative AI large model according to the structured data set in the comprehensive database of the problem improvement subsystem to obtain an enterprise management AI model;

[0020] An interaction module, which is used to obtain the management question information corresponding to the user, generate feedback information based on the enterprise management AI model, and form an enterprise management data report to reply to the user.

[0021] The technical principle and effect of this solution: In this solution, first, the problem improvement subsystem will acquire problem data and publish it on the enterprise platform for all personnel in the entire enterprise to view. Secondly, it will also send the problem data to the corresponding person in charge, who will process it. And after receiving the corresponding problem data, the cause of the corresponding problem data will be analyzed immediately to generate the cause data, which will be associated with the problem data immediately after generation. Of course, after finding the cause, the corresponding improvement measure data will be formulated and distributed to the corresponding processing personnel for execution to solve the problem data. At the same time, during this process, the evaluation of the problem analysis and processing process will be collected, and the problem data, cause data, improvement measure data, and evaluation data will be associated to realize the full-process association and sharing from the generation to the solution of the problem and the evaluation of the later solution.

[0022] After storing the structured data set in the database, the generative AI large model is trained using the structured data set in the database to obtain an enterprise management AI model. Different from the traditional method that requires a large amount of manual summarization and annotation of historical problems, the problem improvement subsystem of this system realizes the full-process automation from problem acquisition to storage. This means that there is no longer a need to consume a large amount of manpower for data collation and preprocessing, reducing human errors and greatly improving efficiency. That is, to solve the deficiencies in the existing technology, the problem improvement subsystem realizes the real-time recording of the whole process from problem generation to solution, ensuring the authenticity, reliability of the data required by the model, and the timeliness of data collection.

[0023] Traditional model training relies on static historical data, while this system can instantly capture and process newly emerging problems through the real-time monitoring and feedback mechanism of the problem improvement subsystem. This real-time data stream is directly used to generate a structured data set, ensuring that the data for model training always remains up-to-date and reflects the real situation of the current business.

[0024] This system not only collects problem data, but also ensures that each problem is accompanied by detailed cause of generation, solution, and user evaluation information through the cause analysis module, measure determination and execution module, and evaluation feedback module. These highly correlated data form a structured data set, greatly improving the quality and integrity of the training data, making model training more accurate and effective.

[0025] Every decision point is well-documented, and the whole process from problem generation to solution is recorded, forming a clear data chain. This not only enhances the credibility of the model output results, but also provides transparent and traceable decision-making basis for the management layer, making AI-based suggestions more persuasive and operable.

[0026] The interaction module can use the AI model trained with high-quality structured data sets to provide more personalized and timely feedback to users, forming a detailed enterprise management data report. Compared with the long waiting and uncertain results in the traditional method, users can obtain a more satisfactory experience and service.

[0027] Furthermore, it also includes a data analysis subsystem;

[0028] The data analysis subsystem includes:

[0029] A multi-source information collection module, which is used to obtain the required multi-source index information data through multi-source data collection paths within a preset time period;

[0030] The BI analysis module is used to select and load an indicator information analysis model, and based on the indicator information analysis model, perform data analysis on the corresponding multi-source indicator information data to form corresponding indicator analysis data;

[0031] The dashboard module is used to form a corresponding indicator dashboard based on each indicator analysis data when the data analysis of each indicator information in the multi-source indicator information data is completed;

[0032] The problem generation module is used to analyze each indicator analysis data in the indicator dashboard according to the formed indicator dashboard, identify the corresponding problem data, and send the problem data to the problem improvement subsystem.

[0033] Beneficial effects: In this solution, within a preset time period, the required multi-source indicator information data is obtained through a multi-source data collection path. This ensures the diversity and comprehensiveness of the data sources, covering all aspects of business operations and laying a solid foundation for subsequent in-depth analysis.

[0034] Select and load appropriate indicator information analysis models, and based on these models, conduct in-depth analysis on the multi-source indicator information data to form detailed indicator analysis data. This intelligent analysis method not only improves the data processing efficiency but also can uncover potential patterns and trends hidden in the data.

[0035] According to the formed indicator dashboard, the system automatically analyzes each indicator analysis data, identifies possible problem data, and sends these problems to the problem improvement subsystem. This process realizes the early warning and timely handling of problems, avoiding greater losses caused by the accumulation of problems.

[0036] Furthermore, the problem acquisition module includes:

[0037] The first acquisition module is used to obtain the identified problem data from the data analysis subsystem;

[0038] The second acquisition module is used to obtain the problem data uploaded by the user;

[0039] The release module is used to release the problem data to the enterprise platform after obtaining the problem data.

[0040] Beneficial effects: In this solution, the source of problem data can be obtained not only from the data analysis subsystem. This way of obtaining ensures that all problems automatically detected during business operations can be captured in a timely manner, avoiding human omissions. It can also be uploaded by users. This way not only supplements the situations that may be missed by automated detection, but also encourages employees to actively participate in problem reporting, enhancing internal communication and collaboration within the enterprise. That is, through the combination of automated tools and user feedback, the system can obtain high-quality problem data, thus providing a reliable basis for subsequent problem improvement and model training.

[0041] Publicly releasing the problems to the enterprise platform increases the transparency of the problem handling process, prompting each department to more actively assume responsibilities and quickly take actions to solve the existing problems.

[0042] Furthermore, the interaction module includes:

[0043] A type recognition module, which is used to obtain the management question information corresponding to the user, determine the interaction level corresponding to the user according to the management question information corresponding to the user, and determine the corresponding question type based on the interaction level, forming a set of question types corresponding to the user;

[0044] A processing module, which is used to identify and match the question type corresponding to the management question information corresponding to the user based on the set of question types corresponding to the user, and judge whether the question type corresponding to the management question information is in the set of question types corresponding to the user. If not, a reminder message is fed back to the user. Otherwise, according to the question type corresponding to the management question information, the corresponding enterprise management AI model is retrieved from the database, the management question information is used as input data and input into the enterprise management AI model, and the corresponding feedback information is output. And based on a preset feedback template, the feedback information is integrated into a corresponding enterprise management data report and replied to the user.

[0045] Beneficial effects: In this solution, by judging whether the question type of the user's technical question information is in the set of question types, it is determined whether the user has the permission to execute the feedback information corresponding to the management question information. Through this step of judgment, the user can immediately receive confirmation or reminder information about the question type, ensuring that the problem can be correctly processed. Through strict question type matching, it prevents invalid or irrelevant questions from occupying system resources, ensuring that resources are used for users with real needs.

[0046] Furthermore, the interaction module further includes:

[0047] A restriction module, which is used to count the number of times when the judgment result is negative, form the corresponding number of unauthorized access times, and restrict the acquisition of the management question information corresponding to the user based on the corresponding number of unauthorized access times according to a preset question restriction strategy.

[0048] Beneficial effects: In this solution, during the process of users uploading technical question information, the number of times when the question type is not in the question type set is counted, and combined with the corresponding question restriction strategy, the corresponding question restriction is implemented to prevent users from frequently submitting invalid or irrelevant questions, avoid the abuse of system resources, improve the proportion of valid questions on the platform by restricting invalid questions, enable technical personnel to focus more on solving practical problems, and improve the overall service quality. For normal users, a relaxed question environment is maintained; for users who frequently have unauthorized access, the restriction intensity is gradually increased, which not only maintains system security but also does not overly affect the user experience.

[0049] Furthermore, the preset question restriction strategy is as follows:

[0050] If the number of unauthorized access times corresponding to the user is less than or equal to the first preset number threshold, the acquisition of the management question information corresponding to the user is not restricted;

[0051] If the number of unauthorized access times corresponding to the user is greater than the first preset number threshold and less than or equal to the second preset number threshold, then within the preset time period, the number of acquisition times for acquiring the management question information corresponding to the user does not exceed the acquisition number threshold, and when matching the question types corresponding to the management question information of the user, a preset proportion of the question types in the question type set corresponding to the user is prohibited from being matched;

[0052] If the number of unauthorized access times corresponding to the user is greater than the second preset number threshold, then within the preset time period, the acquisition of the management question information corresponding to the user is prohibited.

[0053] Beneficial effects: In this solution, by setting different thresholds to restrict the question-asking behavior of users, it can effectively prevent malicious users or automated programs from abusing system resources, thereby protecting the stability of the system and the security of data. Different levels of restriction measures are set in the strategy, showing tolerance to users who make mistakes occasionally, while implementing stricter restrictions on users who frequently violate regulations.

[0054] The present invention provides an enterprise comprehensive management method based on an AI large model and digital experience, using the above-mentioned enterprise comprehensive management system based on an AI large model and digital experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a logic block diagram of the enterprise comprehensive management system based on an AI large model and digital experience in Embodiment 1 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] The following is a further detailed description through specific embodiments:

[0057] Embodiment 1

[0058] An enterprise integrated management system based on an AI large model and digital experience is basically as Figure 1 shown, including a data analysis subsystem, a problem improvement subsystem, and a data mining subsystem;

[0059] The data analysis subsystem includes:

[0060] A multi-source information collection module, which is used to obtain the required multi-source index information data through multi-source data collection paths within a preset time period; in this embodiment, the multi-source data collection paths include the enterprise platform of users, chat tools, or short video platforms, etc.

[0061] A BI analysis module, which is used to select and load an index information analysis model, and based on the index information analysis model, perform data analysis on the corresponding multi-source index information data to form corresponding index analysis data; in this implementation, the corresponding index information analysis model is pre-trained, and in this embodiment, the existing BP neural network technology is used for model construction.

[0062] A dashboard module, which is used to form a corresponding index dashboard based on each index analysis data when the data analysis of each index information in the multi-source index information data is completed;

[0063] A problem generation module, which is used to analyze each index analysis data in the index dashboard according to the formed index dashboard, identify the corresponding problem data, and send the problem data to the problem improvement subsystem.

[0064] The problem improvement subsystem includes:

[0065] A problem acquisition module, which is used to acquire problem data and publish it on the enterprise platform;

[0066] The problem acquisition module includes:

[0067] A first acquisition module, which is used to acquire the identified problem data from the data analysis subsystem;

[0068] A second acquisition module, which is used to acquire problem data uploaded by users; in this embodiment, when personnel in the enterprise encounter problems during normal times, such as a certain part often having a certain problem, they can publish the corresponding problems on the enterprise platform. At this time, according to the problems raised by this person, they are pushed to the corresponding person in charge, such as the maintenance personnel mainly responsible for maintenance.

[0069] A publishing module, which is used to publish the problem data on the enterprise platform after acquiring the problem data.

[0070] A problem allocation module, which is used to send problem data to the corresponding person in charge for processing;

[0071] A cause analysis module, which is used to analyze the cause corresponding to the received problem data based on the received problem data when the person in charge receives the corresponding problem data, form corresponding cause data, and associate it with the corresponding problem data; In this embodiment, when the user receives the problem data, the problem will be analyzed to inform the cause and published on the enterprise platform to be associated with the corresponding problem data. In the enterprise platform, each person in the enterprise can be both the publisher and the handler of the problem. The multi-role play makes each person in the enterprise more sticky to the enterprise platform and has better interactivity.

[0072] A measure determination and execution module, which is used to formulate corresponding improvement measure data according to the obtained cause data, associate it with the corresponding cause data, and distribute the improvement measure data to the corresponding personnel for execution;

[0073] An evaluation and feedback module, which is used to obtain the user's evaluation of the problem analysis and processing process and form evaluation data;

[0074] A storage module, which stores the problem data, cause data, improvement measure data, and evaluation data into a comprehensive database to form a structured data set;

[0075] The data mining subsystem includes:

[0076] A model training module, which trains a generative AI large model according to the structured data set in the comprehensive database of the problem improvement subsystem to obtain an enterprise management AI model;

[0077] An interaction module, which is used to obtain the user's corresponding management question information, generate feedback information based on the enterprise management AI model, and form an enterprise management data report to reply to the user.

[0078] The interaction module includes:

[0079] A type recognition module, which is used to obtain the user's corresponding management question information, determine the user's corresponding interaction level according to the user's corresponding management question information, and determine the corresponding question type based on the interaction level to form the question type set corresponding to the user;

[0080] A processing module, which is used to identify and match the question type corresponding to the management question information of the user based on the set of question types corresponding to the user, and determine whether the question type corresponding to the management question information is in the set of question types corresponding to the user. If not, a reminder message is fed back to the user. Otherwise, according to the question type corresponding to the management question information, the corresponding enterprise management AI model is retrieved from the database, the management question information is used as input data and input into the enterprise management AI model, and the corresponding feedback information is output. Based on a preset feedback template, the feedback information is integrated into a corresponding enterprise management data report and replied to the user.

[0081] A restriction module, which is used to count the number of times when the judgment result is negative, form the corresponding unauthorized access times, and restrict the acquisition of the management question information corresponding to the user based on the corresponding unauthorized access times according to a preset question restriction policy.

[0082] The preset question restriction policy is as follows:

[0083] If the unauthorized access times corresponding to the user are less than or equal to the first preset number threshold, the acquisition of the management question information corresponding to the user is not restricted;

[0084] If the unauthorized access times corresponding to the user are greater than the first preset number threshold and less than or equal to the second preset number threshold, then within a preset time period, the number of acquisition times corresponding to the acquisition of the management question information corresponding to the user does not exceed the acquisition number threshold, and when matching the question type corresponding to the management question information of the user, a preset proportion of the question types in the set of question types corresponding to the user are prohibited from being matched;

[0085] If the number of unauthorized accesses corresponding to the user is greater than the second preset number threshold, then within a preset time period, obtaining the management question information corresponding to the user is prohibited. In this embodiment, the preset time period is dynamically variable, not only different within two different thresholds, but also within the same threshold, the corresponding preset time period will increase with the difference between the number of unauthorized accesses and the corresponding threshold. For example, when the number of unauthorized accesses corresponding to the user is greater than the first preset number threshold and less than or equal to the second preset number threshold, the initial preset time period is A. As the number of unauthorized accesses of the user increases, for every increase of one-tenth of the difference between the second preset number threshold and the first preset number threshold, the corresponding preset time period increases by a, that is, the preset time period T = A + na, where n is the number of times of increasing one-tenth of the difference between the second preset number threshold and the first preset number threshold. When the number of unauthorized accesses corresponding to the user is greater than the second preset number threshold, the initial preset time period is A + 10a. After that, for every increase of 10 times in the number of unauthorized accesses of the user, the corresponding preset time period increases by b. When the preset time period increases to the tenth time, the corresponding preset time period directly becomes 24 hours.

[0086] This embodiment also discloses an enterprise comprehensive management method based on an AI large model and digital experience, using the above-mentioned enterprise comprehensive management system based on an AI large model and digital experience.

[0087] The above are only embodiments of the present invention. Specific structures and common knowledge such as characteristics that are well known in the art are not described in detail here. Those of ordinary skill in the art know all the common general technical knowledge in the technical field to which the invention belongs before the application date or priority date, can know all the existing technologies in this field, and have the ability to apply the conventional experimental means before this date. Those of ordinary skill in the art can, under the inspiration given in this application, combine their own abilities to improve and implement this solution. Some typical well-known structures or well-known methods should not become obstacles for those of ordinary skill in the art to implement this application. It should be noted that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can still be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application should be based on the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to explain the content of the claims.

Claims

1. An integrated enterprise management system based on AI big model and digital experience, characterized by: Includes problem improvement subsystem and data mining subsystem; The problem improvement subsystem includes: The problem acquisition module is used to obtain problem data and publish it to the enterprise platform; The problem allocation module is used to send the problem data to the corresponding person in charge for processing; A cause analysis module is used to analyze the cause of the corresponding problem data based on the received problem data when the person in charge receives the corresponding problem data, form corresponding cause data, and associate it with the corresponding problem data; The measure determination and execution module is used to formulate corresponding improvement measure data according to the obtained cause data, associate it with the corresponding cause data, and distribute the improvement measure data to the corresponding personnel for execution; Evaluation feedback module, used to obtain the user's evaluation of the problem analysis and processing process to form evaluation data; A storage module, used to store the problem data, cause data, improvement measure data and evaluation data into a comprehensive database to form a structured data set; The data mining subsystem includes: The model training module trains the generative AI large model based on the structured data set of the comprehensive database in the problem improvement subsystem to obtain the enterprise management AI model; The interactive module is used to obtain the management question information corresponding to the user, generate feedback information based on the enterprise management AI model, and form an enterprise management data report to reply to the user.

2. According to claim 1, the enterprise integrated management system based on AI big model and digital experience is characterized by: It also includes a data analysis subsystem; The data analysis subsystem includes: The multi-source information acquisition module is used to obtain the required multi-source indicator information data through the multi-source data acquisition path within a preset time period; BI analysis module, used to select and load the indicator information analysis model, and based on the indicator information analysis model, perform data analysis on the corresponding multi-source indicator information data to form corresponding indicator analysis data; The dashboard module is used to form a corresponding indicator dashboard based on the analysis data of each indicator when the data analysis of each indicator information in the multi-source indicator information data is completed; The problem generation module is used to analyze the various indicator analysis data in the indicator dashboard according to the formed indicator dashboard, identify the corresponding problem data and send the problem data to the problem improvement subsystem.

3. The enterprise integrated management system based on AI big model and digital experience according to claim 2 is characterized by: The question acquisition module includes: A first acquisition module is used to acquire the identified problem data from the data analysis subsystem; The second acquisition module is used to obtain the question data uploaded by the user; The publishing module is used to publish the problem data to the enterprise platform after obtaining the problem data.

4. The enterprise integrated management system based on AI big model and digital experience according to claim 3 is characterized by: The interaction module includes: A type identification module is used to obtain the management question information corresponding to the user, and determine the interaction level corresponding to the user according to the management question information corresponding to the user, and determine the corresponding question type based on the interaction level to form a question type set corresponding to the user; The processing module is used to identify and match the question type corresponding to the management question information corresponding to the user based on the question type set corresponding to the user, and determine whether the question type corresponding to the management question information is in the question type set corresponding to the user. If not, a reminder message is fed back to the user. Otherwise, according to the question type corresponding to the management question information, the corresponding enterprise management AI model is retrieved from the database, the management question information is used as input data, and is input into the enterprise management AI model, the corresponding feedback information is output, and based on a preset feedback template, the feedback information is integrated into the corresponding enterprise management data report and replied to the user.

5. The enterprise integrated management system based on AI big model and digital experience according to claim 4 is characterized by: The interaction module also includes: The restriction module is used to count the number of times the judgment result is negative, form the corresponding number of unauthorized access, and according to the preset question restriction strategy, based on the corresponding number of unauthorized access, restrict the acquisition of the management question information corresponding to the user.

6. The enterprise integrated management system based on AI big model and digital experience according to claim 5 is characterized by: The preset question restriction strategy is: If the number of unauthorized accesses corresponding to the user is less than or equal to the first preset number threshold, the acquisition of the management question information corresponding to the user is not restricted; If the number of unauthorized accesses corresponding to the user is greater than a first preset number threshold and less than or equal to a second preset number threshold, then in a preset time period, the number of acquisitions corresponding to the acquisition of the management question information corresponding to the user does not exceed the acquisition number threshold, and when matching the question types corresponding to the management question information corresponding to the user, matching of the question types corresponding to the user with a preset proportion is prohibited; If the number of unauthorized accesses corresponding to the user is greater than a second preset number threshold, then in the preset time period, obtaining the management question information corresponding to the user is prohibited.

7. An integrated enterprise management method based on AI big models and digital experience, characterized by: An enterprise integrated management system based on AI big model and digital experience using any one of claims 1 to 6 above.

Images