Method and apparatus for generating an enterprise improvement task based on a diagnostic assessment

Abstract

The application provides an enterprise improvement task generation method and device based on diagnosis evaluation. The method comprises the following steps: obtaining initial index data of a target enterprise, preprocessing the initial index data to obtain target data; inputting the target data into a pre-constructed weighted linear scoring model to obtain scores of the target enterprise in each dimension; determining an evaluation result of the target enterprise according to the scores of each dimension and preset reference values of each dimension, wherein the evaluation result comprises a weak point determination result, a risk determination result and an advantage determination result; and determining a corresponding improvement task according to the evaluation result. Through the above method, the target enterprise is scored based on the initial index data of the target enterprise, and the corresponding improvement task is automatically generated according to the score result, so that the efficiency and accuracy of enterprise improvement can be improved.

Description

Technical Field

[0001] This invention relates to the field of enterprise digital diagnostics technology, and more specifically to a method and apparatus for generating enterprise improvement tasks based on diagnostic evaluation. Background Technology

[0002] In existing technologies, enterprise diagnosis, evaluation, and improvement management primarily employ template-based diagnostic assessment methods. Traditional enterprise diagnostic tools collect enterprise data through pre-set questionnaires, calculate scores for each dimension using fixed formulas, and generate diagnostic reports. This method relies on manual form completion, resulting in low data collection efficiency, and the rigid scoring standards make it difficult to adapt to the differentiated needs of enterprises in different industries and of different sizes. Summary of the Invention

[0003] This application aims to provide a method and apparatus for generating enterprise improvement tasks based on diagnostic evaluation, so as to improve the efficiency and accuracy of enterprise improvement.

[0004] Firstly, a method for generating enterprise improvement tasks based on diagnostic assessment is provided, the method comprising: Obtain initial performance data for the target company; The initial index data is preprocessed to obtain the target data; The target data is input into a pre-built weighted linear scoring model to obtain the target company's scores in each dimension; The evaluation results of the target company are determined based on the scores of each dimension and the preset benchmark values ​​of each dimension. The evaluation results include the weakness assessment results, risk assessment results, and strength assessment results. Based on the evaluation results, the corresponding improvement tasks will be determined.

[0005] Optionally, the initial indicator data is preprocessed to obtain the target data, including: Based on the Z-score method, determine the standard deviation multiple of each target data point from the mean. Target data whose standard deviation multiple is greater than a preset value are identified as abnormal data; If the initial data contains missing values, the missing values ​​are filled using the K-nearest neighbor imputation method to obtain the target data.

[0006] Optionally, the evaluation result of the target enterprise is determined based on the scores of each dimension and the preset benchmark values ​​of each dimension, including: If the score in any dimension is lower than the preset benchmark value by more than a first preset proportion, or if the linear regression slope of the score in any dimension is negative within a preset time period, the target enterprise is determined to be a weak point in the current dimension.

[0007] Optionally, determining the evaluation result of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension further includes: The risk coefficients of the target company in various dimensions are determined based on preset industry risk factors; If the risk coefficient is greater than the first threshold, the target company is determined to be at risk in the current dimension.

[0008] Optionally, if the risk coefficient is greater than a first threshold, the target enterprise is determined to be at risk in the current dimension, including: If the risk coefficient is greater than the first threshold and less than or equal to the second threshold, the target enterprise is determined to be of medium risk in the current dimension; wherein the second threshold is greater than the first threshold.

[0009] If the risk coefficient is greater than the second threshold, the target company is determined to be high-risk in the current dimension.

[0010] Optionally, determining the evaluation result of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension further includes: If the score in any dimension is higher than the benchmark by more than a second preset proportion, and the standard deviation of the score in that dimension within a preset time period is less than a preset standard deviation threshold, then the target company is determined to have an advantage in the current dimension.

[0011] Optionally, based on the evaluation results, corresponding improvement tasks are determined, including: The evaluation results are matched with task templates in the task template library to obtain target tasks that match the evaluation results; Based on the target enterprise, the parameters of the target task are adjusted to obtain the improvement task corresponding to the evaluation result.

[0012] Secondly, a diagnostic assessment-based enterprise improvement task generation device is provided, characterized in that the device comprises: The acquisition module is used to acquire the initial indicator data of the target company; The preprocessing module is used to preprocess the initial indicator data to obtain the target data; The scoring module is used to input the target data into a pre-built weighted linear scoring model to obtain the target company's scores in each dimension; The first determining module is used to determine the evaluation results of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension. The evaluation results include the weakness determination results, the risk determination results, and the strength determination results. The second determining module is used to determine the corresponding improvement tasks based on the evaluation results.

[0013] Thirdly, an electronic device is provided, comprising: The memory is configured to store instructions; The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the enterprise improvement task generation method based on diagnostic evaluation provided in the first aspect of the embodiments of this application.

[0014] Fourthly, a machine-readable storage medium is provided, wherein instructions are stored on the machine-readable storage medium, the instructions being used to cause a machine to execute the above-described enterprise improvement task generation method based on diagnostic evaluation.

[0015] Based on the aforementioned method for generating enterprise improvement tasks based on diagnostic evaluation, initial indicator data of the target enterprise is obtained. This initial indicator data is preprocessed to obtain target data. The target data is then input into a pre-constructed weighted linear scoring model to obtain the target enterprise's scores in each dimension. The evaluation results for the target enterprise are determined based on the scores in each dimension and the preset benchmark values ​​for each dimension. These evaluation results include weakness assessment results, risk assessment results, and strength assessment results. Corresponding improvement tasks are then determined based on the evaluation results. In this way, by scoring the target enterprise based on its initial indicator data and automatically generating corresponding improvement tasks based on the scoring results, the efficiency and accuracy of enterprise improvement can be improved. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the enterprise improvement task generation method based on diagnostic evaluation provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of the enterprise improvement task generation device based on diagnostic evaluation provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0018] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0019] The method and apparatus for generating enterprise improvement tasks based on diagnostic evaluation provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0020] Please see Figure 1 This is a flowchart illustrating a method for generating enterprise improvement tasks based on diagnostic evaluation, provided in an embodiment of this application. This method is applied to electronic devices. Figure 1 As shown, the method includes the following steps S100 to S500.

[0021] Step S100: Obtain the initial indicator data of the target company.

[0022] In this embodiment, the initial indicator data of the target enterprise may include, but is not limited to, enterprise sales data, procurement data, inventory data, quality data, production data, and marketing data. Specifically, the initial indicator data of the target enterprise can be collected through API connections to Enterprise Resource Planning (ERP), Manufacturing Execution System (MES), and financial systems, or through methods such as form entry and document upload (OCR+LLM parsing).

[0023] In a specific example, ERP can collect metrics including sales data (sales revenue, gross profit, gross profit margin, collection rate, overdue collection amount, order volume, order delivery cycle, on-time delivery rate, number of customers, customer repurchase rate, customer churn rate, and percentage of top customers, etc.), procurement and supply chain data (purchase amount, purchase cost, purchase timeliness rate, supplier on-time delivery rate, purchase unit price fluctuation, return rate, and percentage of non-conforming purchases, etc.), inventory and warehousing data (total inventory, inventory turnover rate, inventory age distribution, safety stock achievement rate, stockout rate, and amount and percentage of obsolete materials, etc.), and production planning data (plan achievement rate, production scheduling accuracy rate, and order insertion rate, etc.).

[0024] In a specific example, the metrics that MES can collect may include production efficiency data (output, capacity utilization, output per capita, production cycle, overall equipment efficiency, uptime, failure rate, and downtime, etc.), quality data (first-pass yield, rework rate, scrap rate, defective product rate, quality inspection pass rate, number of quality anomalies, and number of customer complaints about quality issues), and process control data (process cycle time, work-in-process quantity, process pass rate, production order completion rate, and work order delay rate, etc.).

[0025] In a specific example, financial system metrics may include profitability data (operating revenue, operating costs, net profit, net profit margin, period expense ratio, operating efficiency, accounts receivable turnover days, accounts payable turnover days, inventory turnover days, and total asset turnover, etc.), solvency and risk data (debt-to-equity ratio, current ratio, quick ratio, net cash flow, operating cash flow, and operating net profit, etc.), and cost and expense data (unit product cost, manufacturing overhead ratio, and labor cost ratio).

[0026] Step S200: Preprocess the initial index data to obtain the target data.

[0027] In this embodiment, after obtaining the initial indicator data, the initial indicator data is preprocessed. First, outlier detection is performed, which can be done using the Z-score method to calculate the standard deviation multiple of each data point from the mean. In a specific example, for a dataset of a certain indicator, its mean is calculated. and standard deviation For each data point Calculate the Z-score: .

[0028] If |Z|>m, it is marked as abnormal and automatically highlighted in red to remind the operator to confirm. The specific value of m can be determined according to the actual situation.

[0029] After outlier detection, missing value processing is performed on the target data. Specifically, the KNN nearest neighbor imputation method based on industry benchmarks can be used to fill in missing values ​​for the indicators. In a specific example, using industry benchmark data as the reference space, the nearest neighbor number k=3 is set. For indicator samples with missing values, the three closest valid samples of the same type in the feature space are selected, and their mean is used to fill in the missing values, thereby improving the integrity of the dataset while preserving the data distribution characteristics.

[0030] Step S300: Input the target data into a pre-built weighted linear scoring model to obtain the target company's scores in each dimension.

[0031] In this embodiment, the weighted linear scoring model takes preprocessed target data as input and calculates the target company's sub-scores for each dimension through a linear weighted summation method. In constructing the weighting system, an initial stage can employ an industry expert experience-based pre-setting method, combining the operational management patterns of manufacturing enterprises, industry-standard diagnostic criteria, and business importance levels to assign differentiated initial weights to each level of indicators, ensuring that the scoring logic aligns with the company's actual management scenarios. Simultaneously, different standardized mapping methods are used for positive, negative, and moderate indicators to eliminate dimensional differences and ensure that each indicator has a unified and comparable scoring basis. The weighted linear scoring model can be trained based on the target company's historical data and possesses a continuous iterative optimization mechanism. After accumulating sufficient historical diagnostic data and actual operating results data, the expert-preset weights are dynamically corrected and optimized through correlation analysis, regression fitting, and weight sensitivity verification, gradually weakening the influence of subjective experience and strengthening data-driven characteristics. This makes the weight allocation more aligned with the company's own operational patterns, improving the accuracy and reference value of the diagnostic results. The final output comprehensive score and dimensional scores can be directly used for company scoring.

[0032] Step S400: Determine the evaluation results of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension. The evaluation results include the weakness judgment results, risk judgment results, and strength judgment results.

[0033] In this embodiment, the target company has preset benchmark values ​​for each dimension. These benchmark values ​​can be determined based on industry associations, industry benchmarks in public databases, and benchmarks of companies of similar size. After obtaining the target company's scores for each dimension, the scores for each dimension can be compared with the preset benchmark values ​​for their corresponding dimensions to obtain the evaluation results for the target company. The evaluation results may include weakness assessment results, risk assessment results, and strength assessment results.

[0034] Step S500: Determine the corresponding improvement tasks based on the evaluation results.

[0035] In this embodiment, after obtaining the evaluation results, the results are matched with task templates in the task template library to obtain target tasks that match the evaluation results. The task template library is built based on historical successful projects, and each task template in the library contains a template ID, tags (such as "weak digital infrastructure"), a set of task nodes, and preconditions (such as "XX survey needs to be completed first"). Semantic matching of the tags in the evaluation results with the tags in the task templates yields task templates that match the target company. Then, the parameters of the target task are adjusted based on the actual situation of the target company to obtain the improvement tasks corresponding to the evaluation results.

[0036] Through steps S100-S500, initial indicator data of the target company is obtained. This initial data is preprocessed to obtain target data. The target data is then input into a pre-constructed weighted linear scoring model to obtain the target company's scores across each dimension. Based on these scores and preset benchmark values ​​for each dimension, the evaluation results for the target company are determined. These evaluation results include weakness assessments, risk assessments, and strength assessments. Corresponding improvement tasks are then determined based on the evaluation results. In this way, by scoring the target company based on its initial indicator data and automatically generating corresponding improvement tasks based on the scoring results, the efficiency and accuracy of enterprise improvement can be improved.

[0037] In this embodiment, after determining the corresponding improvement tasks based on the evaluation results, a directed acyclic graph (DAG) is constructed using the task nodes in the template as vertices and dependencies as edges. The Kahn algorithm (an in-degree-based topology sorting algorithm) is used for topology sorting to obtain the execution order, thus completing the task tree construction. A random forest model can be used to predict the expected effect of each task (inputs are feature vectors such as weakness type, industry, company size, and historical success rate of similar tasks; output is a regression prediction of the score improvement, such as "expected score improvement of 8-12 points in digital transformation"). Based on the output prediction results, users are helped to prioritize high-value tasks.

[0038] In this embodiment of the application, after the improved task is generated, the improved task can be assigned to the member with the least load and matching skills based on the skill tags of each member of the target enterprise and their current task load using the minimum load priority algorithm.

[0039] In this embodiment of the application, task assignment can also be combined with task priority. High-risk rectification tasks are prioritized as urgent with short deadlines (e.g., ≤24 hours); medium-risk rectification tasks are prioritized as high-level with medium deadlines (e.g., ≤3 days); weakness improvement tasks are prioritized as medium-level with longer deadlines (e.g., ≤7 days); strength enhancement suggestions do not generate mandatory tasks, but only recommended suggestions (which can be selectively adopted).

[0040] In this embodiment, project records can be automatically created: project_name = "[Diagnosis Type] + Company Name + Improvement Project", start_date = today, end_date = calculated based on the latest deadline. A chapter is created for each task node, and each task chapter has independent editing permissions, approval processes, and status tracking (pending assignment / in execution / pending review / completed). A workflow engine is used to define task stages, including task assignment, in execution, review, and closure. The system maintains a predecessor task counter (predecessor_count) for each task node, with an initial value of the number of dependent tasks. When a task is marked as "completed," the system iterates through all successor nodes with that task as a predecessor, decrementing their predecessor_count by 1. When the predecessor_count of a successor node becomes 0, the task status is automatically updated from "blocked" to "pending execution," and a notification is pushed to the responsible party. When all task statuses are "completed," the system automatically advances to the "review" stage and pushes a review notification to the evaluation initiator.

[0041] In this embodiment, scheduled tasks can be scanned periodically, such as every 2 hours. If a task is found to be overdue, an email and app notification will be sent to the responsible person and their superior. The evaluation initiator can confirm "pass" or "fail" for each task. Failed tasks are automatically reopened and reassigned to the original responsible person. After the improvement task is completed, the score of that dimension is re-evaluated, the improvement value is calculated, and stored in the database. The random forest prediction model is retrained periodically (e.g., quarterly) with new data. When the score of a weakness improves to a certain extent (e.g., ≥10 points) and remains stable for a period of time (e.g., 3 months), the improvement plan (task template + actual execution parameters) is automatically stored in the knowledge base and marked "successful". Tasks with score improvements below a threshold (e.g., <2 points) or delays exceeding a certain percentage (e.g., 50%) are automatically marked "to be optimized" for subsequent analysis by staff.

[0042] In some implementations, the evaluation result of the target enterprise is determined based on the scores of each dimension and the preset benchmark values ​​for each dimension, including: If the score in any dimension is lower than the preset benchmark value by more than a first preset proportion, or if the linear regression slope of the score in any dimension is negative within a preset time period, the target enterprise is determined to be a weak point in the current dimension.

[0043] Specifically, weaknesses can be determined based on two conditions: Condition 1: The current score is lower than the industry benchmark by a certain percentage (e.g., lower than 90%); Condition 2: The linear regression slope of the score time series (the most recent 3 periods) is negative (continuously declining). If either condition is met, it is classified as a "weakness"; otherwise, it is classified as a "concern item".

[0044] In some implementations, determining the evaluation result of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension further includes: The risk coefficients of the target company in various dimensions are determined based on preset industry risk factors; If the risk coefficient is greater than the first threshold, the target company is determined to be at risk in the current dimension.

[0045] Specifically, the risk coefficient (RiskScore) is calculated as follows: RiskScore = (1 - Current Score / Industry Benchmark) × Weight × (1 + Preset Industry Risk Factor), where the preset industry risk factor is determined based on industry characteristics, such as a safety risk factor of 0.5 for the chemical industry. If the risk coefficient exceeds the first threshold, the target company is deemed to have a risky assessment result in the current dimension. The specific risk type can be automatically identified and matched based on keywords in the indicator name, such as safety, compliance, and finance.

[0046] In this embodiment, risk can be further subdivided into high risk and medium risk. If the risk coefficient is greater than a first threshold (e.g., 0.6) and less than or equal to a second threshold (e.g., 0.8), the target company's evaluation result in the current dimension is determined to be medium risk; wherein the second threshold is greater than the first threshold. If the risk coefficient is greater than the second threshold (e.g., 0.8), the target company's evaluation result in the current dimension is determined to be high risk. The specific values ​​of the first and second thresholds can be determined based on the actual situation of the target company.

[0047] In some implementations, determining the evaluation result of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension further includes: If the score in any dimension is higher than the benchmark by more than a second preset proportion, and the standard deviation of the score in that dimension within a preset time period is less than a preset standard deviation threshold, then the target company is determined to have an advantage in the current dimension.

[0048] Specifically, an advantage can be determined based on two conditions. Condition 1: The current score is higher than the industry benchmark by a certain percentage (e.g., higher than 110%); Condition 2: The standard deviation of the scores over the past three periods is small (e.g., ≤5%, indicating high stability). When both conditions are met, the target company is classified as having an advantage in the current dimension.

[0049] In one specific embodiment of this application, the generation of a digital transformation diagnosis and improvement task for a manufacturing enterprise is taken as an example.

[0050] A manufacturing company conducted a digital transformation diagnosis, and the system collected data from multiple dimensions, including its specialized and innovative development, digital transformation, lean operation management, and quality management system.

[0051] Evaluation and scoring: The system calculates scores for each dimension, with the digital transformation dimension scoring 58 points (lower than the industry benchmark of 65 points), the lean operations management dimension scoring 62 points (lower than the industry benchmark of 70 points), and the quality management system dimension scoring 85 points (higher than the industry benchmark of 80 points).

[0052] Result classification: Weaknesses: Digital transformation (score 58, below benchmark), Lean operations management (score 62, below benchmark) Risk: In the safety production dimension, the equipment failure rate exceeds the threshold, and the risk level is "high". Strengths: Quality management system dimension (score 85, above the benchmark) Weakness Improvement Task Generation: For weaknesses in digital transformation, the system automatically breaks down the task tree as follows: ① Enterprise Digital Status Survey (3 days, assigned to: Technical Director) → ② Digital Solution Design (5 days, assigned to: Solution Expert) → ③ System Selection and Procurement (7 days, assigned to: Procurement Manager) → ④ System Deployment and Training (10 days, assigned to: Implementation Team). For weaknesses in lean operations, the following tasks are generated: ① Lean Production Training (2 days, assigned to: Production Supervisor) → ② Value Stream Mapping (3 days, assigned to: Lean Expert) → ③ Establishment of Improvement Proposal Mechanism (5 days, assigned to: Operations Director).

[0053] Risk remediation task generation: For equipment with high failure rate risk, the system automatically creates emergency remediation tasks: ① Comprehensive equipment inspection (1 day, assigned by: equipment engineer) → ② Failure cause analysis (2 days, assigned by: maintenance supervisor) → ③ Preventive maintenance plan development (3 days, assigned by: equipment manager), with a deadline of 24 hours.

[0054] Advantage enhancement suggestion generation: Based on the advantages of the quality management system, the system automatically generates suggestions such as: ① standardizing quality management experience into SOPs and storing them in the knowledge base; ② highlighting the advantages of quality management system certification in tender documents; ③ sharing successful experiences with peer clients as marketing materials.

[0055] Execution and Closure: All tasks are automatically synchronized to the project management platform. Progress is tracked in real time during task execution, and effect data is automatically fed back to the evaluation model upon completion.

[0056] Results: The evaluation showed that the task generation cycle was shortened from 3 days to 3 minutes, the shortcoming identification accuracy was 92%, and the risk response time was shortened from 2 days to 8 hours.

[0057] In one specific embodiment of this application, the generation of project diagnosis and improvement tasks by a consulting firm is taken as an example.

[0058] After completing a digital transformation project for a company, a consulting firm used this system to conduct a project review and diagnosis.

[0059] Evaluation and scoring: The system collected project delivery data, in which the customer satisfaction dimension scored 72 points (below the benchmark of 80 points), the delivery timeliness dimension scored 68 points (below the benchmark of 75 points), and the knowledge accumulation dimension scored 88 points (above the benchmark of 70 points).

[0060] Result classification: Weaknesses: Customer satisfaction (72 points), Timeliness of delivery (68 points) Strengths: Knowledge Accumulation (88 points) Weakness Improvement Task Generation: For weaknesses in customer satisfaction, the system generates the following improvement tasks: ① Optimize customer needs survey form (2 days) → ② Establish deliverable quality review process (3 days) → ③ Improve customer satisfaction survey mechanism (1 day). For weaknesses in delivery timeliness, the system generates: ① Establish project milestone management mechanism (3 days) → ② Optimize task dependencies (2 days) → ③ Configure overdue early warning mechanism (1 day).

[0061] Advantage enhancement suggestions: Based on the advantage of knowledge accumulation, the system suggests: ① Storing successful cases of this project in the knowledge base; ② Extracting standardized templates for reuse in subsequent projects; ③ Highlighting knowledge management capabilities in project application materials.

[0062] Execution and Closed Loop: After the task was completed, customer satisfaction improved from 72 to 85 points, and delivery timeliness improved from 68 to 90 points.

[0063] Results: The incidence of recurring problems in similar projects decreased by 45%, and the project delivery cycle was shortened by 25%.

[0064] In one specific embodiment of this application, the root cause weakness is prioritized for treatment using a multi-weakness causal analysis approach.

[0065] A company's diagnostic results revealed several weaknesses: insufficient R&D investment (score 45), weak product innovation capability (score 48), and low market share (score 52). The system, through knowledge graph causal analysis, found that insufficient R&D investment was the root weakness, while weak product innovation capability and low market share were derivative weaknesses.

[0066] Root cause identification: The system prioritizes and recommends improvement solutions for "insufficient R&D investment" and generates a task tree: ① R&D budget replanning (2 days) → ② R&D team expansion plan (5 days) → ③ R&D project management process optimization (3 days).

[0067] Results: After addressing the root causes of weaknesses, the product innovation score improved from 48 to 65, and the market share increased from 52 to 60, thus avoiding ineffective improvements.

[0068] This application automates the process from manual interpretation of diagnostic reports to manual task creation, achieving a fully automated workflow from assessment to task generation. The assessment-to-task generation cycle is reduced from several days in the traditional method to minutes, significantly improving efficiency. Through knowledge graph causal analysis and industry benchmark comparison, root causes and weaknesses are accurately identified, greatly improving the accuracy of weakness identification. An automated assessment-to-task mapping mechanism ensures that each identified weakness and risk generates a corresponding task, reducing the rate of missed improvement measures from a high level compared to manual methods to an extremely low level. Emergency rectification tasks are automatically generated for high-risk items, with high priority and short deadlines, significantly shortening the average response time for high-risk issues. Successful improvement cases are automatically stored in a knowledge base, allowing for intelligent recommendations for reuse during subsequent diagnoses, reducing the recurrence rate of similar problems.

[0069] Please see Figure 2 This is a schematic diagram of the structure of an enterprise improvement task generation device based on diagnostic evaluation provided in an embodiment of this application. A second aspect of this application provides an enterprise improvement task generation device based on diagnostic evaluation, the device comprising: The acquisition module is used to acquire the initial indicator data of the target company; The preprocessing module is used to preprocess the initial indicator data to obtain the target data; The scoring module is used to input the target data into a pre-built weighted linear scoring model to obtain the target company's scores in each dimension; The first determining module is used to determine the evaluation results of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension. The evaluation results include the weakness determination results, the risk determination results, and the strength determination results. The second determining module is used to determine the corresponding improvement tasks based on the evaluation results.

[0070] The enterprise improvement task generation apparatus based on diagnostic evaluation provided in the second aspect of this application can implement the various processes implemented in the above method embodiments and achieve the same beneficial effects. To avoid repetition, it will not be described again here.

[0071] Please see Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. A third aspect of this application provides an electronic device 3000, including a processor 3100 and a memory 3200. The memory 3200 stores machine-executable instructions that can be executed by the processor 1100. The processor 1100 can execute the machine-executable instructions to implement the above-mentioned enterprise improvement task generation method based on diagnostic evaluation.

[0072] In some embodiments, this application also provides a machine-readable storage medium storing instructions that, when executed by a processor, cause the processor to implement the above-described enterprise improvement task generation method based on diagnostic evaluation.

[0073] In some embodiments, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the enterprise improvement task generation method based on diagnostic evaluation according to the above embodiments.

[0074] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0076] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0077] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0078] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0079] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0080] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0081] Furthermore, various different embodiments of the present invention can be combined in any way, as long as they do not violate the spirit of the present invention, they should also be regarded as the content disclosed by the present invention.

Claims

1. A method for generating enterprise improvement tasks based on diagnostic evaluation, characterized in that, The method includes: Obtain initial performance data for the target company; The initial index data is preprocessed to obtain the target data; The target data is input into a pre-built weighted linear scoring model to obtain the target company's scores in each dimension; The evaluation results of the target company are determined based on the scores of each dimension and the preset benchmark values ​​of each dimension. The evaluation results include the weakness assessment results, risk assessment results, and strength assessment results. Based on the evaluation results, the corresponding improvement tasks will be determined.

2. The method according to claim 1, characterized in that, The preprocessing of the initial indicator data to obtain the target data includes: Based on the Z-score method, determine the standard deviation multiple of each target data point from the mean. Target data whose standard deviation multiple is greater than a preset value are identified as abnormal data; If the initial data contains missing values, the missing values ​​are filled using the K-nearest neighbor imputation method to obtain the target data.

3. The method according to claim 1, characterized in that, The step of determining the evaluation result of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension includes: If the score in any dimension is lower than the preset benchmark value by more than a first preset proportion, or if the linear regression slope of the score in any dimension is negative within a preset time period, the target enterprise is determined to be a weak point in the current dimension.

4. The method according to claim 1, characterized in that, The step of determining the evaluation result of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension also includes: The risk coefficients of the target company in various dimensions are determined based on preset industry risk factors; If the risk coefficient is greater than the first threshold, the target company is determined to be at risk in the current dimension.

5. The method according to claim 4, characterized in that, If the risk coefficient is greater than the first threshold, the target company is determined to be at risk in the current dimension, including: If the risk coefficient is greater than the first threshold and less than or equal to the second threshold, the target enterprise is determined to be of medium risk in the current dimension; wherein the second threshold is greater than the first threshold. If the risk coefficient is greater than the second threshold, the target company is determined to be high-risk in the current dimension.

6. The method according to claim 1, characterized in that, The step of determining the evaluation result of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension also includes: If the score in any dimension is higher than the benchmark by more than a second preset proportion, and the standard deviation of the score in that dimension within a preset time period is less than a preset standard deviation threshold, then the target company is determined to have an advantage in the current dimension.

7. The method according to claim 1, characterized in that, Based on the evaluation results, corresponding improvement tasks are determined, including: The evaluation results are matched with task templates in the task template library to obtain target tasks that match the evaluation results; Based on the target enterprise, the parameters of the target task are adjusted to obtain the improvement task corresponding to the evaluation result.

8. A device for generating enterprise improvement tasks based on diagnostic evaluation, characterized in that, The device includes: The acquisition module is used to acquire the initial indicator data of the target company; The preprocessing module is used to preprocess the initial indicator data to obtain the target data; The scoring module is used to input the target data into a pre-built weighted linear scoring model to obtain the target company's scores in each dimension; The first determining module is used to determine the evaluation results of the target enterprise based on the scores of each dimension and the preset benchmark values ​​of each dimension. The evaluation results include the weakness determination results, the risk determination results, and the strength determination results. The second determining module is used to determine the corresponding improvement tasks based on the evaluation results.

9. An electronic device, characterized in that, include: The memory is configured to store instructions; A processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the enterprise improvement task generation method based on diagnostic assessments as described in any one of claims 1 to 7.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to execute the enterprise improvement task generation method based on diagnostic assessment according to any one of claims 1 to 7.

Images