Operation data management method and system based on digitization

Abstract

The invention relates to the technical field of data management, in particular to a digitization-based operation data management method and system, which comprises a business processing layer and a business application layer, acquires multi-source data, performs preprocessing and format conversion on the acquired multi-source data to obtain standardized data, and simultaneously, performs operation data management on the basis of a set trigger condition. Performing relation mining on the standardized data based on the constructed knowledge graph model, and performing dynamic early warning at the same time; performing double-board collaborative analysis based on the standardized data, and performing task intelligent scheduling; early warning and visual display are carried out on a three-dimensional matrix of time, space and responsibility until a task is completed, unified analysis can be carried out on multi-source data, the multi-dimensional dynamic analysis capability is achieved, and the intelligence of decision making is ensured.

Description

Technical Field

[0001] This invention relates to the field of data management technology, and in particular to a digital-based operational data management method and system. Background Technology

[0002] Currently, enterprise digital operations in healthcare generally employ three types of independent systems: data warehouse systems: using ETL tools (such as Informatica) to periodically extract CRM / ERP data and establish offline data marts; BI analysis tools: using tools such as Tableau to generate static reports; and task management systems: based on manual task assignment from OA systems. Existing enterprise digital operations commonly suffer from the following problems: CRM, ERP, and supply chain system data are stored independently, with heterogeneous formats, making unified analysis impossible and lacking multi-dimensional dynamic analysis capabilities, resulting in weak decision support. Summary of the Invention

[0003] The purpose of this invention is to provide a digital-based operational data management method and system that can perform unified analysis of multi-source data and has multi-dimensional dynamic analysis capabilities to ensure intelligent decision-making.

[0004] To achieve the above objectives, in a first aspect, the present invention provides a digital-based operational data management method, comprising the following steps: Acquire multi-source data, and preprocess and convert the acquired multi-source data to obtain standardized data; Based on the standardized data, perform collaborative analysis of the dual-kanban system and intelligent task scheduling; Early warnings and visualizations are provided based on a three-dimensional matrix of time, space, and responsibility.

[0005] This involves acquiring multi-source data, preprocessing and format conversion of the acquired multi-source data to obtain standardized data, including: It can acquire all data from CRM, ERP and supply chain systems in real time and automatically identify field semantics using a smart recognizer; The acquired multi-source data is cleaned, and data is filled in when missing values ​​are detected. All data is converted into standardized data and stored in a database.

[0006] The method further includes: Based on the set trigger conditions, the system performs relationship mining on standardized data using the constructed knowledge graph model, and simultaneously provides dynamic early warnings.

[0007] The method further includes, after performing relationship mining on the acquired data based on the constructed knowledge graph model: Data is refined using daily, monthly, and quarterly granular methods.

[0008] The process of performing dual-kanban collaborative analysis based on the standardized data and intelligent task scheduling includes: Based on the discovered entity relationships, related entities are located using a dual-Kanban collaborative analysis model. Based on the located associated entities, a scheduling scheme is generated based on the scheduling decision matrix, and tasks are reallocated.

[0009] The process includes generating a scheduling scheme based on the located associated entities and a scheduling decision matrix, and then reallocating tasks, including: Based on the located associated entities and the cleaned multi-source data, a scheduling scheme is generated based on the scheduling decision matrix, and tasks are reallocated. Based on the newly generated scheduling task, task instructions are generated and transmitted to the mobile terminal for display.

[0010] The system includes early warning and visualization based on a three-dimensional matrix of time, space, and responsibility, including: Generate execution instructions based on the newly generated scheduled task; An early warning matrix is ​​constructed based on three dimensions: time axis, space axis, and responsibility axis, and the early warning signal lights are controlled to flash accordingly.

[0011] The method further includes, after controlling the warning signal lights to flash in response to the corresponding warning, the method also includes: Based on the set feedback monitoring time, the completion status of the scheduled task is obtained. If it is not completed, a second warning is triggered, and the dual-kanban collaborative analysis is performed again, and the task is intelligently scheduled.

[0012] The method further includes: If completed, the anomaly marker will be removed from the dual-Kanban collaborative analysis model.

[0013] Secondly, the present invention provides a digital-based operational data management system, which is applied to a digital-based operational data management method as provided in the first aspect. The digital-based operational data management system includes a business processing layer and a business application layer. The business processing layer is used to acquire multi-source data, preprocess and convert the acquired multi-source data to obtain standardized data, and at the same time, based on the set trigger conditions, perform relationship mining on the standardized data based on the constructed knowledge graph model, and perform dynamic early warning. The business application layer is used to perform collaborative analysis of dual dashboards based on the standardized data and to perform intelligent task scheduling; it provides early warnings and visualizations from a three-dimensional matrix of time, space, and responsibility until the task is completed.

[0014] This invention discloses a digital-based operational data management method and system. The digital-based operational data management system includes a business processing layer and a business application layer. It acquires multi-source data, preprocesses and converts the acquired multi-source data to obtain standardized data, and simultaneously mines relationships in the standardized data based on a constructed knowledge graph model based on set trigger conditions, while providing dynamic early warnings. Based on the standardized data, it performs dual-kanban collaborative analysis and intelligent task scheduling. It provides early warnings and visualizations from a three-dimensional matrix of time, space, and responsibility until the task is completed. It can perform unified analysis of multi-source data and has multi-dimensional dynamic analysis capabilities to ensure intelligent decision-making. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.

[0016] Figure 1 This is a schematic diagram illustrating the steps of a digital-based operational data management method according to the first embodiment of the present invention.

[0017] Figure 2 This is a flowchart illustrating a digital-based operational data management method provided by the present invention.

[0018] Figure 3 This is a flowchart illustrating step S101 provided by the present invention.

[0019] Figure 4 This is a schematic diagram illustrating the key relationships in the knowledge graph provided by this invention.

[0020] Figure 5 This is a flowchart illustrating step S103 provided by the present invention.

[0021] Figure 6 This is a schematic diagram of the structure of a digital-based operational data management system according to the second embodiment of the present invention.

[0022] Figure 7 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0023] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application.

[0024] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0025] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0026] The first embodiment of this application is as follows: Please see Figures 1-5 This invention provides a digital-based operational data management method, comprising the following steps: S101. Acquire multi-source data, and preprocess and convert the acquired multi-source data to obtain standardized data.

[0027] Specifically, such as Figure 3The system acquires all data from CRM, ERP, and supply chain systems in real time and uses an intelligent recognizer to automatically identify field semantics. The mapping rule of the intelligent recognizer is: source system field - target field. The conversion logic is based on the graded level, corresponding to high and low value, for example, A-level → high value, C-level → low value. The monetary unit is automatically and uniformly converted. For example, when a "customer health level" field is added to CRM, it automatically matches to the "customer value tag" dimension in the data lake; when the source system field is ERP's contract amount, it automatically matches to the "payment benchmark value" dimension in the data lake, and the monetary unit is automatically and uniformly converted. The intelligent recognizer can achieve automatic field semantic recognition through deep learning models. For example, recurrent neural networks (RNNs) or their variants (such as Long Short-Term Memory networks (LSTM) or gated recurrent units (GRUs)) can be used to process text sequence data. These models can learn semantic information in text, thereby recognizing the semantics of fields. Furthermore, an attention mechanism can be introduced to allow the model to focus more on important text segments, thereby improving the accuracy of semantic recognition. The intelligent recognizer can employ a joint model to simultaneously recognize multiple semantic actions. For example, a joint model can simultaneously recognize semantic actions related to information slots (e.g., "want to go" corresponding to "attraction A") and semantic actions related to the overall sentence structure (e.g., "how do I get there?"). This joint model can be trained through multi-task learning, enabling it to handle multiple semantic recognition tasks simultaneously, improving its generalization ability and recognition accuracy. Intelligent recognizers can incorporate contextual information to enhance semantic recognition accuracy. For instance, when processing user input, considering previous input helps to better understand the semantics of the current input. This approach is particularly suitable for dialogue systems, effectively resolving ambiguity and accurately determining the user's true intent through context.

[0028] Then, it is input into a unified data model for self-repair and cleaning. For example, when the repayment amount field is detected to be empty, the system automatically associates the contract amount with the historical repayment rate to generate an estimate, intelligently fills in the calculated data, marks the data font color as yellow, and converts it into unified standardized data, which is then stored in a database or a standardized data lake.

[0029] The system automatically identifies multiple core entities. Based on set trigger conditions, it performs relationship mining on standardized data in the database using a constructed knowledge graph model to generate association chains. When the task completion rate falls below a threshold, it automatically pushes a risk warning for repayment in the associated region. Graph Neural Network (GNN) technology is introduced when constructing the knowledge graph model. Identified core entities are used as nodes, and relationships between entities are used as edges to build the knowledge graph. Learning and analyzing the knowledge graph through GNN enables more effective mining of complex relationships between entities. Examples of relationship mining are shown in Table 1.

[0030] Table 1 Examples of Relationship Mining

[0031] like Figure 4 As shown, when the "Doctor A → Project X → Contract Y → Specialist B" link is identified: Project X delay is detected → Contract Y payment risk is automatically predicted, triggering a "red highlight warning" in Specialist B's task list.

[0032] The complete process of generating a related chain is as follows: Step 1: Automatically identify core entities Data labeling: The system scans standardized data in the database (such as customer information, contract records, project progress, etc.) and automatically identifies key objects (called "entities"). For example: Identify "Doctor A" as a person entity. Identify "Project X" as a project entity. Identify "Contract Y" as the contract entity. Area B is identified as a regional entity. The identification is based on the semantic features of the data fields (such as the patterns in field names or content, such as "doctor's name" or "contract number").

[0033] Entity Classification: The system categorizes entities according to preset types (e.g., doctor → responsible party, contract → business object), laying the foundation for subsequent association analysis.

[0034] Step 2: Set trigger conditions Define alert rules: Administrators pre-configure business rules as "triggers", for example: The same doctor was responsible for a project that was delayed three times in a row. The monthly payment collection rate in a certain region is below 80%. The rate of commissioner task acceptance has fallen below the threshold.

[0035] Step 3: Relationship mining based on knowledge graph Building a network of connections: The system treats entities as "points" and the relationships between entities as "lines," forming a dynamic knowledge network (knowledge graph). For example: Doctor A → Responsible for → Project X Project X → Related → Contract Y Contract Y → Ownership → Area B Dynamic scanning relationships: When a trigger condition is activated (such as "Doctor A's projects are continuously delayed"), the system immediately scans for relevant entities in the knowledge graph. Locate doctor A; Track all projects under its responsibility (e.g., Project X); Further identify the contracts (e.g., Contract Y) and regions (e.g., Region B) associated with the project.

[0036] Generate risk links: Integrate scanning paths into a complete chain: Doctor A → Project X (high delay) → Contract Y (payment risk) → Area B (performance gap) This link reveals the transmission path from individual execution problems to business risks.

[0037] Step 4: Generate the association chain and application Output Visual Links: The system transforms the mined relationships into readable relational chains (as shown in text and image reports), for example: Early warning link Attending Physician: Physician A; Problematic Project: Project X (delayed 3 times); Affected Contract: Contract Y (Estimated loss of 2 million RMB); Risk area: Zone B.

[0038] Trigger dynamic response: Automatically execute actions based on the link content: Send a red highlighted warning to the regulatory officer's terminal; Mark the area with a yellow risk symbol; The task scheduling module is activated to reallocate resources (such as changing doctors).

[0039] The beneficial effects are: proactive early warning, no longer relying on manual investigation, the system automatically identifies hidden correlation chains from massive amounts of data, such as "doctor efficiency → project delay → payment risk → regional performance".

[0040] Accurate attribution, using knowledge graphs to pinpoint the specific responsible party (e.g., doctor A) and the scope of impact (e.g., area B), avoids ambiguity of responsibility.

[0041] The dynamic response chain drives subsequent operations in real time (such as task scheduling and secondary early warning), forming a closed loop of "discovery-analysis-processing".

[0042] Multi-granularity calculations are performed at three analysis levels: daily, monthly, and quarterly. At the daily level, the calculation method directly aggregates raw transaction data, accurately pinpointing single-day anomalies. At the monthly level, the calculation method dynamically segments data according to natural weeks, eliminating interference from sudden data surges at the end of the month. At the quarterly level, the calculation method uses a weighted moving average algorithm with a seasonal adjustment coefficient, primarily adding an industry volatility coefficient based on the weight of each month in the quarter, smoothing out seasonal fluctuations. The process is: quarterly granularity identifies abnormal sales trends → monthly granularity locates the problematic month → daily granularity pinpoints the faulty day.

[0043] S102. Perform dual-kanban collaborative analysis based on the standardized data and perform intelligent task scheduling.

[0044] Specifically, based on the entity relationships mined from standardized data using a knowledge graph model, simultaneous data input and collaborative analysis are performed on two categories: secondary customer dashboard marketing analysis and operations dashboard project analysis. Related entities are then identified. For example, in the secondary customer dashboard: June payment achievement rate in Zone B is 72% (below the threshold of 80%), and in the operations dashboard: the delivery delay rate for the related project CT report is 35%. The system automatically establishes a link between payment shortfall, delivery delay, and responsible personnel, identifying the related entities, the responsible doctor, and the supervisor. Simultaneously, a problem location report is output: "Related project CT delivery delay" (Responsible doctor: Wang Wu, Supervisor: Zhang San).

[0045] For the marketing analysis and operational dashboard project analysis of secondary customer dashboards, independent data analysis models are constructed separately. In the secondary customer dashboard, customer profiling technology is introduced to generate detailed customer profiles based on information such as customer transaction history and preferences. For example, for customers in Zone B, their industry distribution and product demand characteristics are analyzed to provide a basis for marketing strategy formulation.

[0046] The operations dashboard employs project management theory to monitor and analyze project metrics such as schedule, quality, and cost in real time. For example, Gantt charts are used to display project progress, and cost analysis models are used to evaluate the project's cost-effectiveness.

[0047] To achieve collaborative analysis between the two dashboards, a data-sharing mechanism and correlation analysis algorithms are built, enabling the two dashboards to exchange data in real time. For example, when the secondary customer dashboard detects a low customer collection rate in a certain area, the operations dashboard can automatically analyze the delivery status of related projects in that area, identify potential problems, and generate a problem location report.

[0048] Based on the problem location report corresponding to the located associated entity, the problem location report and the cleaned multi-source data are input into the scheduling decision matrix. A multi-objective optimization algorithm is introduced to generate scheduling schemes based on three aspects: load assessment, capacity matching, and urgency judgment. Tasks are then reassigned, for example, with Doctor Li Si replacing Wang Wu. Based on the newly generated scheduling tasks, task instructions are generated and transmitted to the mobile terminal for display. The scheduling decision logic is shown in Table 2.

[0049] Table 2 Scheduling Decision Logic

[0050] The dual-dashboard collaborative analysis approaches the data from two dimensions simultaneously: the Secondary Customer Dashboard focuses on business results, such as sales revenue and collection rate; the Operations Dashboard monitors the execution process, such as project progress and delivery timeliness. Data from both dashboards is compared within a knowledge graph to automatically pinpoint the problem chain: the Secondary Customer Dashboard identifies performance gaps (insufficient collection in Area B) → linking to specific contracts; the Operations Dashboard identifies execution bottlenecks (delayed CT report) → linking to the responsible physician and supervisor. This automatically establishes a link from collection gaps → delivery delays → responsible personnel.

[0051] The generated scheduling scheme is divided into three aspects: burden reduction, personnel replacement, and upgrade.

[0052] Reduce workload: Some of the tasks assigned to specialist Zhang San are transferred to other available specialists; Replace personnel: Highly efficient doctor Li Si replaces Wang Wu in handling CT report tasks; Escalation: Due to the "red emergency" status, the high-level approval process is automatically triggered. Then, a task is pushed to Li Si's mobile terminal: "Process CT report immediately (original person in charge: Wang Wu)"; a notification is sent to Zhang San: "Transfer non-core tasks, focus on collecting payments from major clients in Zone B." The secondary customer dashboard (results) and the operations dashboard (process) are linked for analysis to avoid the buck-passing phenomenon of "sales complaining about slow delivery, and delivery blaming sales for accepting orders indiscriminately."

[0053] S103. Provide early warnings and visualizations from a three-dimensional matrix of time, space, and responsibility.

[0054] Specifically, based on the newly generated scheduling task, execution instructions are generated; these instructions and multi-granularity calculation results are input into a three-dimensional early warning dashboard to construct an early warning matrix along three dimensions: time axis, spatial axis, and responsibility axis. The early warning indicator lights are then controlled to flash accordingly, such as... Figure 5As shown, a three-color warning system (red, yellow, and green) is generally used: red light: regional payment achievement rate <80% for 3 consecutive days; yellow light: doctor task receipt delay rate >30%; green light: regional quarterly deliverables exceeded target. Based on the set feedback monitoring time, the completion status of the scheduled tasks is obtained, such as whether the new responsible personnel have completed the tasks within the set time and whether the regional payment rate has rebounded within 24 hours. If not completed, a secondary warning is triggered, and the dual-kanban collaborative analysis is re-performed, and intelligent task scheduling is carried out. If completed, the abnormal marker is removed from the dual-kanban collaborative analysis model, and the doctor's ability score is updated.

[0055] The timeline is used to track key deadlines, with warning rules as follows: Red light: Task not started 24 hours before deadline (e.g., contract not signed until 1 day remaining); Yellow light: Task progress is 50% behind schedule (e.g., project is more than halfway through but only 20% completed); Green light: Key milestones completed 48 hours ahead of schedule.

[0056] The spatial axis is used to scan for regional anomalies. Warning rules: Red light: Regional indicators fail to meet the target for 3 consecutive days (e.g., collection rate in area B < 70%); Yellow light: Daily indicator drops by 30% (e.g., sales in North China plummet on the same day); Green light: Regional targets are exceeded.

[0057] The responsibility axis is used to identify the executor. Warning rules: Red light: The responsible person's task delay rate > 40% (e.g., Doctor Wang Wu reports a delay rate of 45%); Yellow light: The responsible person's workload > 120% (e.g., Specialist Zhang San is handling 8 tasks simultaneously); Green light: The responsible person's historical completion rate > 95%.

[0058] The entire process of visual dynamic early warning is as follows: Step 1: Three-dimensional risk fusion The system overlays signals from three dimensions to generate a comprehensive early warning command: enter: Timeline: Contract in Zone B expires in 2 days (yellow light); Space axis: Area B has a shortfall of 3 million in repayments (red light); Responsibility axis: Specialist Zhang San's load is 135% (red light); Output command: "Send a red alert to Zhang San in Zone B: Contract Y is on the verge of default, and 3 million must be recovered within 48 hours!"

[0059] Step 2: Multi-terminal visualization presentation The corresponding area on the map display screen will flash red and a countdown will pop up; the administrator's computer will display the information from three dimensions: time, space, and responsibility, and the responsible person's mobile phone will push a warning message and the screen will flash red.

[0060] Step 3: Closed-loop processing and feedback Successfully processed: Zhang San recovered the payment within 24 hours → System automatically: The red light on the B area map turns green; Zhang San's load drops to 90% (yellow light goes out); The large screen displays "Crisis in B area resolved".

[0061] Processing failure: Unfinished for more than 48 hours → Automatic system response: Upgrade to double red light flashing (time + space dimension); push voice alarm to Zhang San and his superiors; activate emergency dispatch: automatically split the task to Li Si and Wang Wu.

[0062] Replace experience-based decision-making with data: Avoid simply overloading employees (load assessment). Do not assign critical tasks to novices (skill matching); automate the entire process from problem identification (dual Kanban boards) → precise task assignment (scheduling) → performance tracking (monitoring).

[0063] The second embodiment of this application is as follows: Please see Figure 6 The present invention provides a digital-based operational data management system, which is applied to a digital-based operational data management method as provided in the first embodiment. The digital-based operational data management system includes a business processing layer and a business application layer. The business processing layer is used to acquire multi-source data, preprocess and convert the acquired multi-source data to obtain standardized data, and at the same time, based on the set trigger conditions, perform relationship mining on the standardized data based on the constructed knowledge graph model, and perform dynamic early warning. The business application layer is used to perform collaborative analysis of dual dashboards based on the standardized data and to perform intelligent task scheduling; it provides early warnings and visualizations from a three-dimensional matrix of time, space, and responsibility until the task is completed.

[0064] In this implementation, a B / S architecture is adopted, accessible via a browser. First, the business processing layer acquires multi-source data and preprocesses and converts the acquired data to obtain standardized data. Simultaneously, based on set trigger conditions and a constructed knowledge graph model, relationship mining is performed on the standardized data, along with dynamic early warnings. Data is refined according to daily, monthly, and quarterly granularity. The business application layer performs dual-kanban collaborative analysis based on the standardized data from the business processing layer and performs intelligent task scheduling. Early warnings and visualizations are provided from a three-dimensional matrix of time, space, and responsibility until the task is completed. This approach enables unified analysis of multi-source data and possesses multi-dimensional dynamic analysis capabilities, ensuring intelligent decision-making.

[0065] Regarding the system in the above embodiments, the specific ways in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated here.

[0066] For the system embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0067] Accordingly, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; and, when the one or more programs are executed by the one or more processors, causing the one or more processors to implement the digital-based operational data management method described above. Figure 7 The diagram shown is a hardware structure diagram of any device with data processing capabilities, which is part of a digital operation data management system provided in an embodiment of the present invention. (Except for...) Figure 7 In addition to the processor, memory, and network interface shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0068] Accordingly, this application also provides a computer-readable storage medium storing computer instructions thereon, which, when executed by a processor, implement the aforementioned digital-based operational data management method. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0069] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0070] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A digital-based operational data management method, characterized in that, Includes the following steps: Acquire multi-source data, and preprocess and convert the acquired multi-source data to obtain standardized data; Based on the standardized data, perform collaborative analysis of the dual-kanban system and intelligent task scheduling; Early warnings and visualizations are provided based on a three-dimensional matrix of time, space, and responsibility.

2. The digital-based operational data management method as described in claim 1, characterized in that, Acquire multi-source data, and preprocess and convert the acquired multi-source data to obtain standardized data, including: It can acquire all data from CRM, ERP and supply chain systems in real time and automatically identify field semantics using a smart recognizer; The acquired multi-source data is cleaned, and data is filled in when missing values ​​are detected. All data is converted into standardized data and stored in a database.

3. The digital-based operational data management method as described in claim 2, characterized in that, The method further includes: Based on the set trigger conditions, the system performs relationship mining on standardized data using the constructed knowledge graph model, and simultaneously provides dynamic early warnings.

4. The digital-based operational data management method as described in claim 3, characterized in that, After performing relationship mining on the acquired data based on the constructed knowledge graph model, the method further includes: Data is refined using daily, monthly, and quarterly granular methods.

5. The digital-based operational data management method as described in claim 3, characterized in that, Based on the standardized data, a dual-kanban collaborative analysis is performed, and intelligent task scheduling is carried out, including: Based on the discovered entity relationships, related entities are located using a dual-Kanban collaborative analysis model. Based on the located associated entities, a scheduling scheme is generated based on the scheduling decision matrix, and tasks are reallocated.

6. The digital-based operational data management method as described in claim 5, characterized in that, Based on the located associated entities, a scheduling scheme is generated based on the scheduling decision matrix, and tasks are reallocated, including: Based on the located associated entities and the cleaned multi-source data, a scheduling scheme is generated based on the scheduling decision matrix, and tasks are reallocated. Based on the newly generated scheduling task, task instructions are generated and transmitted to the mobile terminal for display.

7. The digital-based operational data management method as described in claim 6, characterized in that, Early warnings and visualizations are provided based on a three-dimensional matrix of time, space, and responsibility, including: Generate execution instructions based on the newly generated scheduled task; An early warning matrix is ​​constructed based on three dimensions: time axis, space axis, and responsibility axis, and the early warning signal lights are controlled to flash accordingly.

8. The digital-based operational data management method as described in claim 7, characterized in that, After controlling the warning signal lights to flash as a warning, the method further includes: Based on the set feedback monitoring time, the completion status of the scheduled task is obtained. If it is not completed, a second warning is triggered, and the dual-kanban collaborative analysis is performed again, and the task is intelligently scheduled.

9. The digital-based operational data management method as described in claim 8, characterized in that, The method further includes: If completed, the anomaly marker will be removed from the dual-Kanban collaborative analysis model.

10. A digital-based operational data management system, applied to the digital-based operational data management method as described in claim 1, characterized in that, The digital-based operational data management system includes a business processing layer and a business application layer; The business processing layer is used to acquire multi-source data, preprocess and convert the acquired multi-source data to obtain standardized data, and at the same time, based on the set trigger conditions, perform relationship mining on the standardized data based on the constructed knowledge graph model, and perform dynamic early warning. The business application layer is used to perform collaborative analysis of dual dashboards based on the standardized data and to perform intelligent task scheduling; it provides early warnings and visualizations from a three-dimensional matrix of time, space, and responsibility until the task is completed.

Images