A method, system, and storage medium for detecting tissue health

Abstract

The embodiment of the specification provides a method, system and storage medium for detecting health status of an organization, comprising obtaining at least one health detection index item and enterprise data of a target organization, analyzing the enterprise data based on the at least one health detection index item, and determining at least one health detection index value of the target organization; obtaining a standard health detection index corresponding to the at least one health detection index value, and determining health assessment data of the target organization based on the at least one health detection index value and the corresponding standard health detection index; determining recommended learning content based on the health assessment data and the enterprise data; and determining a regular evaluation plan based on a preset method.

Description

Technical Field

[0001] This specification relates to the fields of enterprise analytics and machine learning, and in particular to a method, system, and storage medium for detecting organizational health status. Background Technology

[0002] From a life cycle perspective, a company has four life stages: startup, growth, development, and sustainable development. A company's life begins in the startup stage, but not every company can naturally grow and smoothly enter the next stage. Many, even the vast majority, companies linger in one stage for a long time until they die. A business organization is an organism; during its development cycle, with changes in internal and external environmental factors, companies will almost always encounter internal or external problems.

[0003] To reasonably quantify enterprise conditions, CN110110898A discloses an industry analysis method based on enterprise health indicators. This existing technology uses a machine learning model to predict data from unknown target enterprises and determine the predicted results. However, due to the limited functionality of the model, the prediction results are relatively simple and have low accuracy.

[0004] Therefore, it is desirable to provide a method, system, and storage medium for detecting organizational health status, enabling timely diagnosis of business operations and team conditions, and prompt detection of problems arising during operations. Summary of the Invention

[0005] This specification provides one or more embodiments of a method for detecting organizational health status. The method includes: acquiring at least one health monitoring indicator for a target enterprise; acquiring enterprise data of the target enterprise; analyzing the enterprise data based on the at least one health monitoring indicator to determine at least one health monitoring indicator value for the target enterprise; acquiring standard health monitoring indicators corresponding to the at least one health monitoring indicator value; determining health assessment data of the target enterprise based on the at least one health monitoring indicator value and the corresponding standard health monitoring indicator; determining recommended learning content based on the health assessment data and the enterprise data; and determining a periodic assessment plan based on a preset method.

[0006] One embodiment of this specification provides an organizational health status detection system, comprising: an acquisition module for acquiring at least one health detection indicator item of a target enterprise; acquiring enterprise data of the target enterprise; analyzing the enterprise data based on the at least one health detection indicator item to determine the at least one health detection indicator value of the target enterprise; acquiring the standard health detection indicator corresponding to the at least one health detection indicator value; a determination module for determining health assessment data of the target enterprise based on the at least one health detection indicator value and the corresponding standard health detection indicator; a recommendation module for determining recommended learning content based on the health assessment data and the enterprise data; and a periodic assessment module for determining a periodic assessment plan based on a preset method.

[0007] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes a method for detecting the health status of an organization. Attached Figure Description

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0009] Figure 1 These are exemplary schematic diagrams of an organization health status detection system according to some embodiments of this specification;

[0010] Figure 2 This is an exemplary flowchart of a method for detecting tissue health status according to some embodiments of this specification;

[0011] Figure 3 This is an exemplary flowchart illustrating the determination of recommended learning content according to some embodiments of this specification;

[0012] Figure 4 These are exemplary schematic diagrams illustrating the determination and evaluation of learning outcomes according to some embodiments of this specification;

[0013] Figure 5 This is an exemplary schematic diagram of a knowledge graph according to some embodiments of this specification. Detailed Implementation

[0014] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0015] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0016] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0017] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0018] Figure 1 This is an exemplary schematic diagram of an organization health status detection system according to some embodiments of this specification. In some embodiments, the organization health status detection system 100 may include a processor 110, an acquisition module 120, a determination module 130, a recommendation module 140, and a periodic assessment module 150. The processor 110 can implement a method for detecting organization health status by controlling the acquisition module 120, the determination module 130, the recommendation module 140, and the periodic assessment module 150.

[0019] Processor 110 can process data and / or information obtained from other devices or system components. Based on this data, information, and / or processing results, the processor can execute program instructions to perform one or more functions described in this specification. For example, processor 110 can receive enterprise data acquired by acquisition module 120, analyze it, and transmit the results back to acquisition module 120.

[0020] In some embodiments, the acquisition module 120 can be used to acquire at least one health monitoring indicator item and enterprise data of the target enterprise, and analyze the enterprise data based on the health monitoring indicator item to determine at least one health monitoring indicator value of the target enterprise. More information about health monitoring indicator items, enterprise data, and health monitoring indicator values ​​can be found in [link to relevant documentation]. Figure 2 And related content.

[0021] In some embodiments, the acquisition module 120 can determine the range of health testing indicators for at least one health testing indicator item included in at least one industry type based on big data, and determine the corresponding standard health testing indicator based on the range of health testing indicators for at least one health testing indicator item. More information on the range of health testing indicators and standard health testing indicators can be found in [link to relevant documentation]. Figure 2 And related content.

[0022] In some embodiments, the determining module 130 can be used to determine the health assessment data of a target enterprise based on at least one health assessment indicator and a corresponding standard health assessment indicator. For details regarding the health assessment data, please refer to... Figure 2 And related content.

[0023] In some embodiments, the recommendation module 140 can be used to determine recommended learning content based on health assessment data and enterprise data. Further details regarding recommended learning content can be found in [link to relevant documentation]. Figure 2 And related content.

[0024] In some embodiments, the recommendation module 140 may determine candidate learning content based on health assessment data and enterprise data; predict the learning effect and evaluation of the candidate learning content; perform at least one round of iterative updates on the candidate learning content; and, in response to the satisfaction of preset conditions, obtain the iteration results and determine recommended learning content based on the iteration results. More information on iterative updates can be found in [link to relevant documentation]. Figure 3 And related content.

[0025] In some embodiments, the recommendation module 140 may further determine improvement items for the target enterprise based on enterprise data, and recommend improvement schemes based on these improvement items. Further details regarding the recommended improvement schemes can be found in [link to relevant documentation]. Figure 2 And related content.

[0026] In some embodiments, the periodic evaluation module 150 may determine a periodic evaluation plan based on a preset method. More information on preset methods and periodic evaluation plans can be found in [link to relevant documentation]. Figure 2 And related content.

[0027] It should be noted that the above description of the organization health monitoring system 100 and its modules is for convenience only and should not be construed as limiting this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. In some embodiments, Figure 1 The acquisition module 120, determination module 130, recommendation module 140, and periodic evaluation module 150 disclosed herein can be different modules within a single system, or a single module can implement the functions of two or more of the aforementioned modules. For example, the modules can share a single storage module, or each module can have its own separate storage module. Such variations are all within the scope of protection of this specification.

[0028] Figure 2 This is an exemplary flowchart of a method for detecting tissue health status according to some embodiments of this specification. In some embodiments, process 200 may be performed by tissue health status detection system 100. Figure 2 As shown, process 200 includes the following steps.

[0029] Step 210: Obtain at least one health monitoring indicator from the target company.

[0030] The target enterprise refers to the enterprise or company that needs to undergo organizational health monitoring, which can include enterprises or companies of various industries.

[0031] Health monitoring indicators are metrics used to evaluate the health status of an organization. Examples include customers, customer value, effective market, financial strength, operational efficiency, size, and profitability.

[0032] Enterprises can be categorized into different organizational types based on their different life stages. These life stages refer to the various phases of a company's development, such as the startup phase, growth phase, pioneer phase, and leader phase. Correspondingly, companies can be classified as entrepreneurial organizations, growth organizations, pioneer organizations, and leader organizations.

[0033] In some embodiments, different business life stages correspond to different health monitoring indicators. For example, health monitoring indicators for entrepreneurial organizations may include customers, customer value, products, customer value of products, and the entrepreneurial team; health monitoring indicators for growth-oriented organizations may include effective customers, effective markets, effective scale, and effective growth; health monitoring indicators for pioneering organizations may include corporate financial capabilities, corporate operational capabilities, and the core team; and health monitoring indicators for leading organizations may include scale and profitability, product technological leadership, and contribution to social development.

[0034] In some embodiments, different health assessment indicators can be assigned different weights. The company's health assessment data can be determined based on the weighted result of the health assessment indicator values ​​corresponding to different health assessment indicators. Further explanation regarding health assessment data can be found in step 250 and its related description. Health item weights can be determined in various ways, such as pre-setting them.

[0035] In some embodiments, the processor can construct an enterprise information vector of the target enterprise based on data such as the target enterprise's industry sector (e.g., finance, technology, construction, etc.), enterprise type (e.g., small enterprise, medium-sized enterprise, etc.), and life stage. Based on the target enterprise's enterprise information vector, the processor can determine at least one health detection indicator item of the target enterprise and its corresponding health item weight in the vector database.

[0036] A vector database is a database used for storing, indexing, and querying vectors. Through a vector database, similarity queries and other vector management can be performed quickly on a large number of vectors. In some embodiments, the vector database includes multiple reference enterprise information vectors, at least one health monitoring indicator item corresponding to each of the multiple reference enterprise information vectors, and its health item weight. The reference enterprise information vectors can be vectors composed of data from other enterprises, such as industry sector, enterprise type, and life cycle stage.

[0037] At least one health monitoring indicator and its weight corresponding to the reference enterprise information vector can be determined based on historical indicator data from other enterprises. The historical indicator data may include enterprise information (such as industry sector, enterprise type, life stage, etc.) and corresponding indicator information (such as at least one health monitoring indicator and its weight). In some embodiments, a vector database can be constructed based on multiple reference enterprise information vectors and the corresponding health monitoring indicator and its weight.

[0038] The processor can determine, based on enterprise information vectors, reference enterprise information vectors that meet matching conditions from a vector database as target enterprise information vectors, and determine at least one health detection indicator item and its weight corresponding to the target enterprise information vector as at least one health detection indicator item and its corresponding weight for the target enterprise. Here, matching conditions refer to the judgment conditions used to determine the target enterprise information vector. In some embodiments, matching conditions may include vector distance less than a distance threshold, minimum vector distance, etc. The distance threshold may be a system default value, a manually preset value, etc.

[0039] Step 220: Obtain the target company's enterprise data.

[0040] Enterprise data refers to data related to the operation, organization, and health of an enterprise. For example, enterprise data can include data related to personnel, operations, products, sales, services, and finances.

[0041] Enterprise data can be obtained in various ways. For example, enterprise data can be obtained based on the target company's historical annual reports.

[0042] In some embodiments, the processor can also acquire enterprise data through organizational surveys. Organizational surveys are methods for collecting enterprise data using structured data collection methods and measurement techniques. Organizational survey methods include: constructing at least one closed-ended question based on at least one health monitoring indicator to determine an electronic questionnaire; collecting questionnaire data for each employee of the target enterprise through the electronic questionnaire; and conducting team evaluation analysis on the collected questionnaire data for all employees to obtain enterprise data for the target enterprise. Here, team evaluation analysis refers to an evaluation method that, under the guidance of experts, reaches a unified understanding of individual evaluation results (i.e., questionnaire data for each employee).

[0043] In some embodiments, to reduce the impact of interfering data, the processor can also filter the data obtained through electronic questionnaires. For example, filtering can remove data that is filled out randomly, misplaced, or significantly off-target. The filtering method can be preset in advance. For example, multiple options can be set in advance for employees to choose from when designing the questionnaire; another example is to check the occurrence rate of the same option in the questionnaires submitted by employees, and questionnaires with an excessively high occurrence rate of the same option (such as option A occurring more than 90% of the time) cannot be submitted.

[0044] In one or more embodiments of this specification, effective and reliable corporate data can be obtained through organizational survey methods, thereby providing a more accurate understanding of the organizational status of the enterprise.

[0045] Step 230: Analyze the enterprise data based on at least one health monitoring indicator to determine at least one health monitoring indicator value for the target enterprise.

[0046] A health monitoring indicator value refers to the actual measured value for a specific health monitoring indicator. Each health monitoring indicator can correspond to a health monitoring indicator value, and a given health monitoring indicator value reflects the health status of that indicator. Health monitoring indicator values ​​can be represented numerically, with higher values ​​indicating higher health status. Health monitoring indicator values ​​can also be represented as vectors.

[0047] In some embodiments, the processor can analyze enterprise data based on at least one health monitoring indicator to determine at least one health monitoring indicator value for the target enterprise. For example, the processor can perform analysis and processing through data processing (such as relevant algorithms), computer technology (such as machine learning models), etc., to determine the health monitoring indicator value corresponding to each of the at least one health monitoring indicator.

[0048] Step 240: Obtain the standard health test indicator corresponding to at least one health test indicator value.

[0049] Standard health monitoring indicators refer to the normal values / ranges of a certain health monitoring indicator for a target company.

[0050] Standard health monitoring indicators can be determined in a variety of ways. In some embodiments, the standard health monitoring indicators of a target enterprise can be preset based on prior experience.

[0051] In some embodiments, the processor can determine the range of health testing indicators for at least one health testing indicator item included in the target industry type based on big data; and determine the corresponding standard health testing indicators based on the range of health testing indicators for at least one health testing indicator item.

[0052] The target industry type refers to the industry type that is the same as the target company's industry type.

[0053] Big data can include enterprise data from other companies in the target industry. This big data can be acquired through third-party platforms.

[0054] The range of health monitoring indicators refers to the normal range of health monitoring indicator values ​​for a specific health monitoring indicator item for all enterprises within the target industry type.

[0055] In some embodiments, for each of the at least one health detection indicator items, the processor can process (e.g., fusion processing) the enterprise data of all enterprises within the target industry type based on big data and through data processing methods (e.g., statistical algorithms, data mining algorithms, etc.) to determine the health detection indicator range corresponding to each health detection indicator item.

[0056] The processor can determine the corresponding standard health test indicator based on the health test indicator range of at least one health test indicator item in multiple ways. In some embodiments, the processor can determine the median value of the health test indicator range corresponding to a certain health test indicator item as the standard health test indicator corresponding to that health test indicator item. In some embodiments, the processor can also determine the health test indicator range corresponding to a certain health test indicator item as the standard health test indicator corresponding to that health test indicator item.

[0057] In one or more embodiments of this specification, standard health testing indicators are determined based on big data, and more accurate data can be obtained through extensive data analysis in combination with the actual situation of the industry.

[0058] Step 250: Determine the health assessment data of the target enterprise based on at least one health test indicator value and the corresponding standard health test indicator.

[0059] Health assessment data refers to data related to assessing the health status of an organization. In some embodiments, health assessment data may include a total health assessment score and multiple health assessment scores. The total health assessment score is a score evaluating the overall health status of the organization; the multiple health assessment scores are scores evaluating the health status of various health monitoring indicators of the organization.

[0060] The health assessment score corresponding to a certain health testing indicator can be determined in various ways based on the health testing indicator value and the corresponding standard health testing indicator. In some embodiments, the processor can determine the health assessment score corresponding to the health testing indicator as the difference between the health testing indicator value and the corresponding standard health testing indicator, or the difference between the health testing indicator value and the corresponding range of health testing indicators. In some embodiments, the processor can also score the difference between the health testing indicator value and the corresponding standard health testing indicator, or the difference between the health testing indicator value and the corresponding range of health testing indicators, according to a scoring standard, and determine the scoring result as the health assessment score corresponding to the health testing indicator. An exemplary scoring standard could be that the larger the difference, the lower the health assessment score corresponding to the health testing indicator.

[0061] In some embodiments, the target enterprise's total health assessment score can be determined based on the health assessment score of each health detection indicator and the corresponding health item weight. For example, it can be determined by a weighted sum of the health item weights and health assessment scores. Further explanation of the health item weights can be found in step 210 and its related description.

[0062] In some embodiments, health assessment data may also include visible and potential problems reflecting the company’s poor health status.

[0063] In some embodiments, the processor can identify health assessment scores below a first preset threshold as visible problems, and health assessment scores above the first preset threshold and below a second preset threshold as potential problems. The first and second preset thresholds are threshold conditions related to the health assessment score, with the first preset threshold being less than the second preset threshold. The first and second preset thresholds can be system default values, empirical values, manually preset values, or any combination thereof, and can be set according to actual needs; this specification does not impose any restrictions on this.

[0064] Step 260: Based on health assessment data and enterprise data, determine recommended learning content.

[0065] Recommended learning materials are those suggested to company personnel for study. By learning from these materials, company personnel can improve the health of their organization. Company personnel can include company leaders, managers, and general employees.

[0066] In some embodiments, the recommended learning content may include at least one digital course and at least one case study.

[0067] Digital courses refer to learning materials designed to solve problems encountered by a company at a specific stage. Examples include books on improving the motivation of ordinary employees and books on improving the management skills of managers. Case studies refer to the analysis and explanation of typical examples of actual health situations occurring within a company. Examples include cases on improving production efficiency and cases on expanding customer base.

[0068] Recommended learning content can be determined in several ways. In some embodiments, recommended learning content can be determined based on the job positions of employees within the organization. For example, recommended learning content for managers may include books on management and management case studies.

[0069] In some embodiments, the processor can construct a preset comparison table based on reference health assessment data of multiple reference enterprises, reference enterprise data, and corresponding reference recommended learning content; and determine the recommended learning content of the target enterprise based on the target enterprise's health assessment data and enterprise data through the preset comparison table.

[0070] In some embodiments, a preset lookup table can be constructed based on historical data of reference companies obtained from a third-party platform, showing the correspondence between reference health assessment data, reference company data, and recommended learning content for multiple different reference companies. In some embodiments, the processor can search the preset lookup table based on the target company's health assessment data and company data to determine reference companies that are similar to the target company, and then determine the recommended learning content corresponding to the reference companies as the recommended learning content for the target company.

[0071] In some embodiments, the processor may also determine candidate learning content based on health assessment data and enterprise data; and perform at least one round of iterative updates on the candidate learning content to determine recommended learning content. See related explanations. Figure 3 .

[0072] Step 270: Determine the periodic evaluation plan based on the preset method.

[0073] A periodic assessment plan can be a plan to periodically assess the health status of an organization. In some embodiments, a periodic assessment plan may include the assessment cycle, assessment content, etc.

[0074] In some embodiments, the preset method may determine the assessment cycle based on the enterprise's life cycle stage and the assessment content based on health assessment data. For example, the processor may determine that organizations with longer life cycles correspond to longer assessment cycles; or, for example, the processor may determine health detection indicators in the health assessment data whose health assessment scores are below a health assessment threshold as assessment content. The health assessment threshold refers to the threshold used to determine the assessment content and can be preset based on experience.

[0075] In one or more embodiments of this specification, the method for detecting organizational health status can promptly identify problems existing in an enterprise, take corrective measures, and maintain the health of the enterprise organization; it can also provide feedback on visible and potential problems of poor organizational health status and resolve them in a timely manner; and it can detect the organizational health status of an enterprise and recommend learning content in a targeted manner to improve the organizational health status of the enterprise.

[0076] In some embodiments, the processor may further determine improvement items for the target enterprise based on the target enterprise's enterprise data, and recommend improvement schemes based on the improvement items.

[0077] Improvement items refer to health monitoring indicators that need improvement. For example, improvement items could be the product itself, the product's customer value, etc.

[0078] An improvement plan refers to a scheme to improve upon existing improvement items within a company. An improvement plan may include the content of the improvement, the timeline for implementation, etc.

[0079] Improvement items can be determined based on experience. For example, when product output declines, the improvement item can be identified as the product itself. Similarly, when product sales decline, the improvement item can be identified as the customer value of the product.

[0080] In some embodiments, the processor can determine improvement items for the target company based on enterprise data.

[0081] The processor can determine the health assessment score corresponding to each health monitoring indicator based on enterprise data, and identify health monitoring indicators with health assessment scores below a second preset threshold as improvement items. For further explanation of the second preset threshold, please refer to the relevant description above.

[0082] Improvement plans can be determined based on experience. For example, when product output declines, the improvement plan can be determined to include increasing employee work efficiency, with an improvement period of one month.

[0083] In some embodiments, the processor may recommend improvements based on the improvements.

[0084] In some embodiments, the processor can identify improvement items as improvement content and determine the improvement time based on the corresponding health assessment score of the improvement item. For example, the lower the health assessment score, the longer the improvement time corresponds to the improvement item. The processor can then push / recommend the determined improvement plan to the user.

[0085] In one or more embodiments of this specification, the processor determines improvement items based on the target company's enterprise data and further determines recommended improvement schemes, which can specifically improve the problems that the company has, enabling the company to develop better.

[0086] Figure 3 This is an exemplary flowchart illustrating the determination of recommended learning content according to some embodiments of this specification. In some embodiments, process 300 may be executed by recommendation module 130. Figure 3 As shown, process 300 includes the following steps.

[0087] Step 310: Based on health assessment data and enterprise data, determine candidate learning content.

[0088] Candidate learning content refers to learning materials that are proposed to be recommended to employees of the target company. Candidate learning content may include at least one candidate digital course and at least one candidate case study.

[0089] In some embodiments, the candidate learning content corresponding to the first iteration (hereinafter referred to as the initial candidate learning content) can be determined based on the target enterprise's health assessment data and enterprise data. For example, the initial candidate learning content can be determined through a preset lookup table, and related explanations can be found in step 260. In some embodiments, the candidate learning content corresponding to subsequent iterations can be derived from the results of updating the candidate learning content in the previous round. Further explanations regarding replacing and updating candidate learning content can be found in the relevant sections below.

[0090] Step 320: Predict the learning effect and evaluation of the candidate learning content.

[0091] Learning effectiveness refers to the improvement in a specific health indicator after employees of a target company have learned the learning content. For example, learning effectiveness could be an increase in product output or improved employee efficiency. In some embodiments, learning effectiveness can be reflected in the improvement value of a health indicator after a department has learned the learning content. In some embodiments, learning effectiveness can be reflected in the improvement value of an individual's personal qualities after employees have learned the learning content. For more information on health indicators, please refer to [link to relevant documentation]. Figure 2 For more information on the personal qualities section, please refer to [link / reference]. Figure 4 .

[0092] Evaluation refers to the ratings given by employees of the target company to the learning content. For example, an evaluation could be for a specific digital course. Each digital course and each case study can correspond to one evaluation.

[0093] In some embodiments, the learning effectiveness and evaluation of a candidate learning content can be predicted based on relevant data from a reference enterprise. For example, the processor can use the learning effectiveness and evaluation of the reference enterprise when it learns the same learning content as the candidate learning content as the learning effectiveness and evaluation of the candidate learning content.

[0094] In some embodiments, the processor can also construct a learning content graph based on enterprise data and candidate learning content, and process the learning content graph using a prediction model to predict learning effectiveness and evaluation. The prediction model is a machine learning model. Further details can be found in [link to relevant documentation]. Figure 4 , Figure 5 .

[0095] Step 330: Perform at least one round of iterative updates on the candidate learning content.

[0096] In some embodiments, at least one round of iterative updates to the candidate learning content can be performed based on steps 331 to 335. It should be noted that the order of steps 331 to 335 is not restrictive. For example, step 334 or step 335 can be performed after step 333, step 334 can be performed after step 335, and step 332 can be performed after step 334. The order can be determined according to the actual situation.

[0097] Step 331: Update candidate learning content based on the replacement learning content.

[0098] Replacement learning content refers to learning content that updates candidate learning content. Replacement learning content may include at least one digital course for replacement and / or at least one case study for replacement. In some embodiments, replacement learning content can be determined based on the historical learning content of a reference enterprise. For example, historical learning content from the reference enterprise that differs from the current candidate learning content can be used as replacement learning content. Another example is historical learning content from the reference enterprise that showed better learning outcomes, which can be used as replacement learning content. In some embodiments, a replacement learning content database consisting of at least one replacement learning content can be predetermined.

[0099] In some embodiments, in each iteration, the processor can update the candidate learning content based on the replacement learning content using a preset replacement rule. An exemplary preset replacement rule could be replacing a preset number of candidate learning content items with lower evaluation rankings. The preset number can be preset by the system or manually.

[0100] As an example only, the target company's candidate learning content includes candidate digital course A, candidate case study B, and candidate digital course C. The corresponding evaluation ranking is: the evaluation of candidate case study B is higher than that of candidate digital course C, and the evaluation of candidate digital course C is higher than that of candidate digital course A. The preset quantity is 1. Then the processor can randomly select replacement digital course A1 from the replacement learning content database and update candidate digital course A to replacement digital course A1. The updated candidate learning content includes replacement digital course A1, candidate case study B, and candidate digital course C.

[0101] Step 332: Predict the learning effect and evaluation of the updated candidate learning content.

[0102] In some embodiments, in each iteration, the processor can predict the learning performance and evaluation of the updated candidate learning content. The prediction method for the learning performance and evaluation of the updated candidate learning content is the same as the prediction method for the learning performance and evaluation of the candidate learning content before the update; see [link to documentation] for details. Figure 4 , Figure 5 Relevant parts.

[0103] Step 333: Based on the learning outcomes before and after the update, determine whether to retain the replaced learning content.

[0104] The learning effect before the update refers to the learning effect of the candidate learning content before the update (i.e., the candidate learning content corresponding to the previous iteration), while the learning effect after the update refers to the learning effect of the candidate learning content after the candidate learning content is updated based on the replacement learning content (i.e., the candidate learning content corresponding to the current iteration).

[0105] In some embodiments, whether to retain the replacement learning content used to update the candidate learning content in each iteration can be determined based on the learning performance before and after the update. When the learning performance before the update is better than the learning performance after the update, it is determined that the replacement learning content should not be retained, and the processor executes step 334. When the learning performance after the update is better than the learning performance before the update, the replacement learning content is retained, that is, the candidate learning content updated based on the replacement learning content can be used for the next iteration, and the processor executes step 335.

[0106] Step 334: In response to not retaining the replacement learning content, update the replacement learning content and further update the candidate learning content.

[0107] In some embodiments, when replacement learning content in the candidate learning content is not retained, the processor may update the replacement learning content. In some embodiments, the processor may randomly select new replacement learning content from the replacement learning content database to update the previously selected replacement learning content.

[0108] In some embodiments, after updating the replacement learning content, the candidate learning content can be further updated based on the updated replacement learning content.

[0109] As a specific example, the updated candidate learning content includes replacement digital course A1, candidate case B, and candidate digital course C. When it is determined that replacement digital course A1 will not be retained, the processor can randomly select replacement digital course A2 from the replacement learning content database and update replacement digital course A1 to replacement digital course A2. Based on the updated replacement digital course A2, the candidate learning content is further updated to obtain the updated candidate learning content including replacement digital course A2, candidate case B, and candidate digital course C.

[0110] In some embodiments, after further updating the candidate learning content, the processor can return to execute steps 332 and 333, that is, predict the learning effect and evaluation corresponding to the updated candidate learning content, and determine whether to retain the replacement learning content based on the learning effect before and after this update, until it is determined that the updated replacement learning content should be retained, and then proceed to step 335; otherwise, steps 334, 332 and 333 are executed repeatedly.

[0111] Step 335: In response to retaining the replacement learning content, determine whether the preset conditions are met.

[0112] Preset conditions refer to the conditions for ending the iterative update. In some embodiments, preset conditions may include reaching the maximum number of iterations, the predicted learning effect corresponding to the candidate learning content meeting an effect threshold, etc. The maximum number of iterations and the effect threshold can be preset in advance. When the preset conditions are met, the processor executes step 340. When the preset conditions are not met, the processor sequentially and cyclically executes steps 334, 332, and 333, and while retaining the updated replacement learning content, proceeds to step 335 to perform the next round of iteration, until the preset conditions are met, at which point the iteration ends.

[0113] In subsequent iterations, the candidate learning content for each iteration is the result of the previous iteration, and the specific iteration update method is the same as the first round. For example, the candidate learning content updated in the first round in the example above can be used as the candidate learning content for the next iteration.

[0114] In some embodiments, the iterative updates to the candidate learning content can be performed at regular intervals. The interval between each iteration can be determined based on health assessment data. For example, a higher total health assessment score corresponds to a longer iteration update time.

[0115] Step 340: In response to the preset conditions being met, obtain the iteration results.

[0116] The iteration result refers to the candidate learning content after the iteration update is completed. In some embodiments, the processor may determine the candidate learning content after the iteration update is completed as the iteration result.

[0117] Step 350: Based on the iteration results, determine the recommended learning content.

[0118] In some embodiments, the processor can determine the iteration results as recommended learning content, that is, the processor can determine the candidate learning content after the iteration update as recommended learning content.

[0119] In one or more embodiments of this specification, candidate learning content is determined by health assessment data and enterprise data, and the candidate learning content is updated based on predicted learning effects and evaluations to further determine recommended learning content. This can make the recommended learning content more in line with the actual situation of the enterprise while improving learning effectiveness and better improving the health of the enterprise organization.

[0120] It should be noted that the above descriptions of processes 200 and 300 are for illustrative purposes only and do not limit the scope of this specification. Those skilled in the art can make various modifications and changes to processes 200 and 300 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0121] Figure 4 These are exemplary schematic diagrams illustrating the determination and evaluation of learning outcomes according to some embodiments of this specification.

[0122] In some embodiments, the processor may obtain a learning content map 430 based on enterprise data 410 and candidate learning content 420; and process the learning content map 430 and enterprise data 440 based on a prediction model 450 to determine the learning effect 460 and evaluation 470.

[0123] In some embodiments, the processor can obtain a learning content graph 430 based on enterprise data 410 and candidate learning content 420. For example, the processor can construct the learning content graph based on enterprise personnel, their personal qualities, the enterprise organization, case studies, digital courses, etc. For details regarding enterprise data and candidate learning content, please refer to [link to relevant documentation]. Figure 2 , Figure 3 And related content.

[0124] A learning content graph is a data structure composed of nodes and edges, with edges connecting nodes. Nodes and edges can have attributes. In some embodiments, a learning content graph can be a graph reflecting the attributes and relationships between enterprise data and candidate learning content. It should be noted that one learning content graph can correspond to one enterprise employee; that is, a learning content graph includes only one employee node.

[0125] The learning content graph can include a variety of nodes and edges.

[0126] In some embodiments, the learning content graph may include enterprise data nodes and learning content nodes. The learning content nodes may be determined based on candidate learning content.

[0127] Enterprise data nodes refer to nodes corresponding to the enterprise data of the target enterprise. In some embodiments, enterprise data nodes may include personnel nodes, department nodes, health item nodes, and personal quality item nodes.

[0128] A personnel node is a node generated based on the personnel of a target company. The attributes of a personnel node can reflect the relevant characteristics of the company's personnel. In some embodiments, the attributes of a personnel node may include gender, age, job title, length of service, etc.

[0129] A department node is a node generated based on a department of a target company (such as the human resources department). The attributes of a department node can reflect the relevant characteristics of the company's departments. In some embodiments, the attributes of a department node may include functions and size, etc.

[0130] A health item node is a node generated based on the health monitoring indicators of a target company. Each health item node can correspond one-to-one with every health monitoring indicator of the target company. The attributes of a health item node can reflect the relevant characteristics of the health monitoring indicators. In some embodiments, the attributes of a health item node may include the health monitoring indicator. In some embodiments, each department in the target company can correspond to one health monitoring indicator, and different health item nodes can correspond to different departments. For more information on health monitoring indicators, please refer to [link to relevant documentation]. Figure 2 And its related descriptions.

[0131] Personal competency item nodes are nodes generated based on the personal competencies of employees within a target company. The attributes of these nodes reflect relevant characteristics of each employee's personal competency. In some embodiments, the attributes of personal competency item nodes may include education level, professional level, effort level, and comprehension ability. Different personal competency item nodes may have different attributes.

[0132] A learning content node refers to a node corresponding to learning content related to solving the target enterprise's problems. In some embodiments, learning content nodes may include digital course nodes and case study nodes.

[0133] A digital course node is a node generated from a digital course. The attributes of a digital course node can reflect the relevant characteristics of the digital course. In some embodiments, the attributes of a digital course node may include the digital course name, digital course rating, and average learning time. Average learning time refers to the average time required to learn the course, used to assess learning costs. Digital course rating refers to the evaluation corresponding to the digital course. For more information on ratings, please refer to [link to relevant documentation]. Figure 3 And its related descriptions.

[0134] A case node is a node generated from a case study. The attributes of a case node can reflect the relevant characteristics of the case. In some embodiments, the attributes of a case node may include case name, department attribute, case evaluation, and average learning time. Case evaluation refers to the assessment of the case. Department attribute refers to the correspondence between the case and a department within the company. For example, Case A belongs to the finance department. For more information on evaluation, please refer to [link to relevant documentation]. Figure 3 .

[0135] Multiple nodes can be connected by edges, and the properties of the edges can reflect the relationships between the nodes. When there is a relationship between two nodes, they are connected by an edge.

[0136] In some embodiments, the edges of the learning content graph may include multiple types. For example, first-type edges, second-type edges, third-type edges, fourth-type edges, and fifth-type edges, etc.

[0137] The first type of edge refers to the edge between a person node and a department node. A learning content graph can contain multiple first-type edges, representing the relationships between a person within a company and multiple departments within that company. The attributes of the first-type edge can reflect the relationships between the person node and the department node. In some embodiments, the attributes of the first-type edge can include leadership (indicating that the person in the company has a leadership role in the department), participation (indicating that the person in the company has a participation role in the department), etc.

[0138] The second type of edge refers to the edge between a department node and a health item node. The attributes of this second type of edge reflect the association between the department node and the health item node. In some embodiments, the attributes of the second type of edge may include a first weight, a health assessment score, etc. The first weight refers to the weight of the health monitoring indicator item corresponding to the health item. In some embodiments, the determination method of the first weight and health assessment score of the health monitoring indicator item corresponding to the department is similar to the determination method of the health assessment score and health item weight of the enterprise. For more details, please refer to [link to documentation]. Figure 2 And its related descriptions.

[0139] The third type of edge refers to the edge between a personnel node and a personal quality item node. The attributes of the third type of edge can reflect the association between the personnel node and the personal quality item node. In some embodiments, the attributes of the third type of edge can include a score. The score refers to a rating describing the personal qualities of an employee in a company. Different personal quality items can correspond to different scores. In some embodiments, the score can be determined based on company personnel information and personal quality items. For example, the higher the education level of an employee, the higher the score of the third type of edge connecting the personnel node and the personal quality item node representing the education level. In some embodiments, the attributes of the third type of edge can also include a second weight. The second weight can represent the importance of a particular personal quality item to an employee in a company. The second weight can be based on empirical presets.

[0140] The fourth type of edge refers to the edge between a digital course node and a personal competency item node. The attributes of the fourth type of edge can reflect the association between the digital course node and the personal competency item node. In some embodiments, the attributes of the fourth type of edge may include a third weight. The third weight can represent the degree of association between a digital course and a particular personal competency item. The third weight can be obtained through empirical presets.

[0141] In some embodiments, a fourth type of edge can be used to connect a digital course node and a personal competency item node when a first association condition is met. In some embodiments, the first association condition includes a first association degree satisfying a first association threshold. The first association threshold can be preset. The first association degree refers to the degree of association between a digital course and a personal competency item.

[0142] For example, the first degree of association can be determined by the following formula (1): in, Indicates the first degree of relevance. This represents the score of an employee of a certain company for personal quality item i. The third weight represents the fourth type of edge between the node corresponding to personal quality item i and the node corresponding to digital course j.

[0143] The fifth type of edge refers to the edge between a case node and a health item node. The attributes of the fifth type of edge reflect the association between the case node and the health item node. In some embodiments, the attributes of the fifth type of edge may include a fourth weight. The fourth weight can represent the degree of association between a case and a certain health indicator item.

[0144] In some embodiments, the fourth weight can be preset based on experience. In some embodiments, when the case node and the health item node meet the second association condition, they can be connected by a fifth type of edge. In some embodiments, the second association condition may include the similarity between the case and the department meeting a similarity threshold, and the second association degree meeting a second association threshold. The similarity threshold and the second association threshold can be preset. The similarity between the case and the department refers to the vector similarity between the case's department attribute and the department. The first association degree refers to the degree of association between a case and a department.

[0145] For example, the second degree of association can be determined by the following formula (2): in, Indicates the second degree of relevance. This represents the evaluation corresponding to case f. This represents the fourth weight of the fifth type of edge between the node corresponding to personal quality item g and the node corresponding to case f. The evaluation of a particular case can be determined through statistical analysis.

[0146] The attributes of nodes and edges can be determined using various methods based on the underlying data. For example, the attributes of a personal quality item node can be obtained from the personal information files of company personnel; similarly, the attributes of a department node can be determined based on company data. The data source can be the method described in other embodiments, or other methods. The data can include current data, data preset based on experience, historical data, etc.

[0147] This is merely an example and may be referenced. Figure 5 The following embodiments are for understanding purposes only; however, the accompanying drawings are merely illustrative of some implementation methods and do not constitute a limitation on the implementation. Figure 5 The nodes and edges in the learning content graph 430 shown are only a portion; the learning content graph may also include other nodes and edges.

[0148] like Figure 5 As shown, the learning content graph 430 includes only one personnel node A. Personal competency node A and personal competency node B are connected to personnel node A via second-type edges a and b, respectively. Personal competency node A is connected to digital course node A via fourth-type edge a, and personal competency node B is connected to digital course nodes B and C via fourth-type edges b and c, respectively. Employee node A is connected to department node A and department node B via first-type edges a and b, respectively. Department node A and department node B are connected to health node A and health node B via third-type edges a and b, respectively. Health node A is connected to case node B and case node C via fifth-type edges b and c, respectively; health node B is connected to case node A via fifth-type edge a.

[0149] In some embodiments provided in this specification, the learning content graph represents content related to enterprise data and learning content using nodes, and uses edges to describe the relationships between nodes. Through this clear representation, the learning content graph clarifies the internal structure of the enterprise, enabling faster identification of the causes of enterprise problems, discovery of the core issues for solving them, and proposal of targeted solutions. This plays a crucial role in monitoring and maintaining the health of the enterprise.

[0150] In some embodiments, the processor can process the learning content map 430 and enterprise data 440 based on the prediction model 450 to determine the learning effect 460 and the evaluation 470. The learning effect output by the prediction model each time may include the improvement value of a person's personal qualities after learning the digital courses and cases, as well as the improvement value of the corresponding health monitoring indicator of the person's department. The evaluation output may include the person's evaluation of each digital course and case after learning the digital courses and cases. Further explanation regarding enterprise data, learning effect, and evaluation can be found in [link to relevant documentation]. Figure 2 , Figure 3 And its related descriptions.

[0151] The predictive model is a machine learning model. In some embodiments, the predictive model can be a graph neural network (GNN) model. The predictive model can also be other graph models, such as a graph convolutional neural network (GCNN) model, or additional processing layers can be added to the graph neural network model, or its processing methods can be modified.

[0152] In some embodiments, the input to the prediction model 450 may include a learning content map 430 and enterprise data 440, and the output may include learning performance 460 and evaluation 470.

[0153] The predictive model is trained on training data using the same or different processing devices. The training data includes training samples and labels. In some embodiments, the training samples may be a reference learning content graph of a reference enterprise and enterprise data of the reference enterprise. The reference learning content graph may be determined based on enterprise data of the reference enterprise obtained from a third-party platform. The nodes and their attributes, edges and their attributes of the reference learning content graph are similar to those described above. Labels may be the learning outcomes and evaluations corresponding to the reference learning content graph. Evaluation labels can be obtained through the operation of different organizations or departments.

[0154] In some embodiments, a prediction model can be trained based on a large number of labeled training samples. Specifically, labeled training samples are input into an initial prediction model, and the initial prediction model is trained based on the labels until conditions such as the loss function being less than a threshold, convergence, or the training period reaching a threshold are met, thus obtaining a trained prediction model. In some embodiments, training can be performed based on the training samples using various methods. For example, training can be performed using gradient descent.

[0155] It should be noted that the processor can construct an initial learning content graph based on enterprise data and the initial candidate learning content corresponding to the first round of iterations. The learning content graph can be updated simultaneously while updating the candidate learning content. For example, the learning content graph can be updated based on the updated digital courses and case studies.

[0156] In some embodiments, the learning content graph can be iterated at fixed intervals, the duration of which can be determined based on the enterprise's health assessment results. For example, the higher the enterprise's health assessment score, the longer the corresponding interval. In some embodiments, a learning content graph can be constructed based on the candidate learning content from the first round of iterations; subsequent iterations will update the candidate learning content, and correspondingly, replacement learning content can be added to the learning content graph to update the learning knowledge graph.

[0157] In one or more embodiments of this specification, the learning content graph can be iteratively trained and updated with data at regular intervals, enabling continuous detection of the organization's health status and corresponding updates of the learning content to maintain the organization's health.

[0158] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0159] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0160] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0161] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0162] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0163] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0164] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for detecting tissue health status, characterized in that, The method is executed by a processor and includes: Obtain at least one health monitoring indicator from the target company; Obtain the enterprise data of the target enterprise; Based on the at least one health monitoring indicator, the enterprise data is analyzed to determine at least one health monitoring indicator value for the target enterprise; Obtain the standard health detection index corresponding to the value of the at least one health detection index; Based on the at least one health detection indicator value and the corresponding standard health detection indicator, the health assessment data of the target enterprise is determined; Based on the health assessment data and the enterprise data, recommended learning content is determined; and A periodic evaluation plan is determined based on a pre-defined method; The recommended learning content includes at least one digital course and at least one case study. The determination of the recommended learning content based on the health assessment data and the enterprise data includes: Based on the health assessment data and the enterprise data, candidate learning content is determined; Predict the learning effectiveness and evaluation of the candidate learning content; The candidate learning content is updated at least once, including: The candidate learning content is updated based on the replacement learning content; Based on the enterprise data and the candidate learning content, a learning content graph is obtained. The learning content graph includes enterprise data nodes and learning content nodes. The enterprise data nodes include personnel nodes, department nodes, health item nodes, and personal quality item nodes. The learning content nodes include digital course nodes and case study nodes. The edges of the learning content graph include a first type of edge reflecting the relationship between the personnel node and the department node, a second type of edge reflecting the relationship between the department node and the health item node, a third type of edge reflecting the relationship between the personnel node and the personal quality item node, a fourth type of edge reflecting the relationship between the digital course node and the personal quality item node, and a fifth type of edge reflecting the relationship between the case study node and the health item node. The learning content map and the enterprise data are processed based on a prediction model to predict the learning effect and evaluation of the updated candidate learning content. The prediction model is a machine learning model. Based on the learning outcomes before and after the update, determine whether to retain the replacement learning content; In response to not retaining the replacement learning content, the replacement learning content is updated, and the candidate learning content is also updated; In response to retaining the replaced learning content, determine whether preset conditions are met; If the preset condition is not met, the candidate learning content will continue to be updated. The iteration result is obtained in response to the preset conditions being met. The recommended learning content is determined based on the iteration results.

2. The method as described in claim 1, characterized in that, The standard health testing indicators corresponding to the at least one health testing indicator value include: Based on big data, determine the health detection indicator range of at least one health detection indicator item included in the target industry type; Based on the range of the at least one health testing indicator item, the corresponding standard health testing indicator is determined.

3. The method as described in claim 1, characterized in that, The method further includes: Based on the enterprise data, identify the improvement items for the target enterprise; Based on the aforementioned improvements, an improvement plan is recommended.

4. A system for detecting tissue health status, characterized in that, The system includes: Get module, used for Obtain at least one health monitoring indicator from the target company; Obtain the enterprise data of the target enterprise; Based on the at least one health monitoring indicator, the enterprise data is analyzed to determine at least one health monitoring indicator value for the target enterprise; Obtain the standard health detection index corresponding to the value of the at least one health detection index; The determination module is used to determine the health assessment data of the target enterprise based on the at least one health detection indicator value and the corresponding standard health detection indicator; The recommendation module is used to determine recommended learning content based on the health assessment data and the enterprise data; and The periodic assessment module is used to determine the periodic assessment plan based on preset methods; The recommended learning content includes at least one digital course and at least one case study, and the recommendation module is further used for: Based on the health assessment data and the enterprise data, candidate learning content is determined; Predict the learning effectiveness and evaluation of the candidate learning content; The candidate learning content is updated at least once, including: The candidate learning content is updated based on the replacement learning content; Based on the enterprise data and the candidate learning content, a learning content graph is obtained. The learning content graph includes enterprise data nodes and learning content nodes. The enterprise data nodes include personnel nodes, department nodes, health item nodes, and personal quality item nodes. The learning content nodes include digital course nodes and case study nodes. The edges of the learning content graph include a first type of edge reflecting the relationship between the personnel node and the department node, a second type of edge reflecting the relationship between the department node and the health item node, a third type of edge reflecting the relationship between the personnel node and the personal quality item node, a fourth type of edge reflecting the relationship between the digital course node and the personal quality item node, and a fifth type of edge reflecting the relationship between the case study node and the health item node. The learning content map and the enterprise data are processed based on a prediction model to predict the learning effect and evaluation of the updated candidate learning content. The prediction model is a machine learning model. Based on the learning outcomes before and after the update, determine whether to retain the replacement learning content; In response to not retaining the replacement learning content, the replacement learning content is updated, and the candidate learning content is also updated; In response to retaining the replaced learning content, determine whether preset conditions are met; If the preset condition is not met, the candidate learning content will continue to be updated. The iteration result is obtained in response to the preset conditions being met. The recommended learning content is determined based on the iteration results.

5. The system as described in claim 4, characterized in that, The acquisition module is further used for: Based on big data, determine the health detection indicator range of at least one health detection indicator item included in the target industry type; Based on the range of the at least one health testing indicator item, the corresponding standard health testing indicator is determined.

6. The system as described in claim 4, characterized in that, The recommendation module is further used for: Based on the enterprise data, identify the improvement items for the target enterprise; Based on the aforementioned improvements, an improvement plan is recommended.

7. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer performs the method for detecting tissue health status as described in any one of claims 1-3.

Images