A knowledge learning management method and device based on data analysis

Abstract

A knowledge learning management method and device based on data analysis, wherein the method comprises: acquiring a scenario-based behavior data set, the scenario-based behavior data set comprising behavior data of each drugstore employee in different business scenarios, the business scenarios comprising at least a drug recommendation scenario, a drug contraindication reminder scenario, and a special drug consultation scenario; constructing a behavior model according to the scenario-based behavior data set, and extracting behavior characteristic information of the drugstore employee in different business scenarios through the behavior model; determining a knowledge point set and a knowledge blind spot that the drugstore employee needs to master in each business scenario based on the behavior characteristic information; constructing a knowledge graph according to the scenario-based behavior data set, the knowledge blind spot, the knowledge point set, and the association relationship between the knowledge point set and the business scenario; and determining professional learning content of the drugstore employee and a priority corresponding to the professional learning content based on the knowledge graph. The application can comprehensively improve the professional knowledge level of the drugstore employee.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data analysis, in particular to a knowledge learning management method and device based on data analysis. BACKGROUND

[0002] With the rapid development of information technology, big data and artificial intelligence technology gradually penetrate into various industries, especially in the retail industry. In the field of retail pharmacies, improving the professional quality and service level of pharmacy staff not only relates to the competitiveness of enterprises, but also directly affects public health and drug safety.

[0003] In the prior art, there are some solutions for pharmacy staff knowledge management and learning. For example, an online learning system provides standardized training courses for pharmacy staff, which improves the convenience of staff learning to a certain extent.

[0004] However, although the online learning system provides rich course resources, it only assigns fixed learning content according to the position, resulting in uneven professional knowledge level of pharmacy staff, and it is difficult to improve the professional knowledge level of pharmacy staff comprehensively. SUMMARY

[0005] The present application provides a knowledge learning management method and device based on data analysis for improving the professional knowledge level of pharmacy staff.

[0006] In a first aspect of the present application, a knowledge learning management method based on data analysis is provided, applied in a server, the method comprising:

[0007] Obtaining a scenario-based behavior data set, the scenario-based behavior data set comprising behavior data of each pharmacy staff in different business scenarios, the business scenarios at least including a drug recommendation scenario, a drug contraindication reminder scenario, and a special medication consultation scenario; constructing a behavior model according to the scenario-based behavior data set, extracting behavior feature information of the pharmacy staff in different business scenarios through the behavior model; determining a knowledge point set and a knowledge blind area that the pharmacy staff needs to master in each business scenario based on the behavior feature information; constructing a knowledge graph according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set, and the association relationship between the knowledge point set and the business scenario; determining professional learning content of the pharmacy staff and a priority corresponding to the professional learning content based on the knowledge graph.

[0008] Optionally, determining the knowledge point set that the pharmacy staff needs to master in the business scenario and the knowledge blind area of the pharmacy staff based on the behavior feature information, specifically comprising:

[0009] According to the behavior characteristic information, a preset knowledge demand prediction model is used to determine a knowledge point set that the drug store staff needs to master in a business scenario; the scenario-based behavior data set and the knowledge point set are associated and analyzed to determine a knowledge blind area of the drug store staff, and the knowledge blind area is a knowledge point set that the drug store staff does not master to a preset requirement.

[0010] Optionally, the scenario-based behavior data set and the knowledge point set are associated and analyzed to determine a knowledge blind area of the drug store staff, and the method specifically comprises:

[0011] The behavior characteristic information is converted into a behavior characteristic vector, and the knowledge point set is converted into a knowledge characteristic vector; an association strength matrix between the behavior characteristic vector and the knowledge characteristic vector is obtained through a preset bidirectional attention model according to the behavior characteristic vector and the knowledge characteristic vector; a confidence score is given to an association value in the association strength matrix that exceeds a preset association threshold; and a knowledge point corresponding to an association value with a confidence score less than a preset score threshold is determined as the knowledge blind area.

[0012] Optionally, a knowledge graph is constructed according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set, and an association relationship between the knowledge point set and the business scenario, and the method specifically comprises:

[0013] In the knowledge point set, a mastery degree score of all knowledge points in the knowledge blind area is marked to obtain a target knowledge point set; based on the scenario-based behavior data set and the target knowledge point set, a use feature of the target knowledge point set in the business scenario is analyzed to determine an association relationship between the target knowledge point set and the business scenario; and the knowledge graph is constructed according to the target knowledge point set and the association relationship.

[0014] Optionally, after the knowledge graph is constructed according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set, and the association relationship between the knowledge point set and the business scenario, the method further comprises:

[0015] Experience data and a problem solving scheme of a target drug store staff in a business scenario are obtained, and the target drug store staff is a drug store staff whose problem solving ability meets a preset requirement; the experience data and the problem solving scheme are marked according to knowledge points to obtain a marking result, and the marking result is associated with the business scenario and the knowledge point set to obtain an experience set; and the knowledge point set in the knowledge graph is supplemented according to the experience set.

[0016] Optionally, after the professional learning content of the drug store staff and the priority of the professional learning content corresponding to the professional learning content are determined based on the knowledge graph, the method further comprises:

[0017] In response to a learning request of the pharmacy staff, a learning task is created, the learning request carrying a business scenario, a knowledge point set and a knowledge blind area; a knowledge conversion effect generated after the pharmacy staff completes the learning task is obtained, the knowledge conversion effect including knowledge point application of the pharmacy staff and task completion; and the priority of the learning content is adjusted according to the knowledge conversion effect.

[0018] Optionally, a knowledge learning management method based on data analysis is applied to a server, and the method further includes: obtaining emotional interaction data of the pharmacy staff, calculating an emotional value of the pharmacy staff through a preset emotional prediction model according to the emotional interaction data, the emotional interaction data including voice data and expression information; judging a learning state of the pharmacy staff based on the emotional value, the learning state including a negative state, an anxious state and a positive state; and generating a target learning task based on the professional learning content and the priority corresponding to the professional learning content when the learning state is the negative state or the anxious state, the target learning task being a learning content with a learning difficulty and a learning form meeting preset requirements.

[0019] In a second aspect of the present application, a knowledge learning management device based on data analysis is provided, including:

[0020] The acquisition module is configured to acquire a scenario-based behavior data set, the scenario-based behavior data set including behavior data of each pharmacy staff in different business scenarios, the business scenarios including at least a drug recommendation scenario, a drug contraindication reminding scenario and a special medication consultation scenario; the extraction module is configured to construct a behavior model according to the scenario-based behavior data set, and extract behavior characteristic information of the pharmacy staff in different business scenarios through the behavior model;

[0021] The first determination module is configured to determine a knowledge point set and a knowledge blind area that the pharmacy staff needs to master in each business scenario based on the behavior characteristic data;

[0022] The construction module is configured to construct a knowledge graph according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set and an association relationship of the knowledge point set and the business scenarios;

[0023] The second determination module is configured to determine professional learning content of the pharmacy staff and a priority corresponding to the professional learning content based on the knowledge graph.

[0024] In a third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory being configured to store instructions, the user interface and the network interface both being configured to communicate with other devices, and the processor being configured to execute the instructions stored in the memory to enable the electronic device to perform the method described in any one of the above aspects.

[0025] In a fourth aspect of the present application, a computer-readable storage medium is provided, which stores instructions that, when executed, perform the method of any of the above.

[0026] In summary, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0027] 1. By deeply mining the scenario-based behavior data and accurately extracting the behavior characteristics, the knowledge gaps of the pharmacy staff in the actual business scenarios are dynamically captured, and the knowledge point set and knowledge blind spot that need to be mastered are accurately identified. Further combining the association between scenario-based behavior data and business scenarios, a knowledge graph is constructed to optimize the organization and presentation of knowledge structure and dynamically display the association between knowledge points and their applicability in scenarios. Based on the knowledge graph, the learning content of different pharmacy staff is determined and prioritized, which realizes the accurate recommendation of learning content according to the professional knowledge level and business needs of pharmacy staff, improves the pertinence of pharmacy staff's professional knowledge learning, and thus comprehensively improves the professional knowledge level of pharmacy staff.

[0028] 2. By mining the complex association between behavior characteristics and knowledge characteristics through a bidirectional attention model, the mastery degree of pharmacy staff on knowledge points is dynamically captured; combining confidence score filtering of low-quality association values ensures the scientificity and accuracy of knowledge blind spot identification. It can comprehensively locate the weak links of pharmacy staff in knowledge mastery, and also provide a reliable basis for the recommendation of personalized learning content.

[0029] 3. By quantifying the mastery degree of the knowledge blind spot, the key knowledge points that pharmacy staff urgently need to master are accurately extracted, and the use characteristics of the target knowledge points in the context of business scenarios are analyzed, the associated path between the target knowledge points and the business scenarios is dynamically modeled, and the construction of the knowledge graph is ensured to be targeted and practical. The constructed knowledge graph not only intuitively presents the relationship between knowledge points and their role in business scenarios, but also provides a basis for the recommendation and priority sorting of subsequent learning content.

[0030] 4. By introducing experience data, the association between knowledge points in the knowledge graph is further expanded and supplemented, overcoming the limitations of relying solely on static knowledge point analysis, and realizing the dynamic updating and self-optimization of the knowledge graph. By integrating experience data and the knowledge graph, the content dimension of knowledge points is enriched, and the applicability of the knowledge graph in actual business scenarios is improved, which can more accurately guide pharmacy staff to solve actual problems, significantly improve learning efficiency and business ability, and further help improve the overall efficiency and service quality of pharmacy operations.

[0031] 5. Through practice evaluation of the understanding and application ability of the knowledge of the pharmacy staff, the learning effect is quantified and feedback is closed. Further, according to the knowledge conversion effect, the priority of learning content is dynamically adjusted, so that the learning resources are efficiently allocated to the key points, thereby accelerating the process of converting knowledge into actual business ability. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 is a flowchart of a knowledge learning management method based on data analysis in an embodiment of the present application;

[0033] Figure 2 is a structural diagram of a knowledge learning management system based on data analysis in an embodiment of the present application;

[0034] Figure 3 is a structural diagram of an electronic device in an embodiment of the present application.

[0035] The following items are explained: 201, acquisition module; 202, extraction module; 203, first determination module; 204, construction module; 205, second determination module; 206, labeling module; 207, learning module; 208, generation module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0036] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in conjunction with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0037] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific way.

[0038] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first", "second", etc. are used only for the purpose of description and should not be understood as indicating or implying relative importance or implicitly indicating the technical features indicated. Therefore, the features defined as "first", "second", etc. can explicitly or implicitly include one or more of the features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0039] Figure 1 is a flowchart of a knowledge learning management method based on data analysis in an embodiment of the present application.

[0040] Referring to Figure 1 The knowledge learning management method based on data analysis in an embodiment of the present application is applied to a server, and the method comprises:

[0041] S101, acquiring a scenario-based behavior data set, the scenario-based behavior data set comprising behavior data of each pharmacy staff in different business scenarios, the business scenarios comprising at least a drug recommendation scenario, a drug contraindication reminder scenario, and a special medication consultation scenario;

[0042] In step S101, the scenario-based behavior data set comprises behavior data of each pharmacy staff in different business scenarios, wherein the business scenarios comprise at least a drug recommendation scenario, a drug contraindication reminder scenario, and a special medication consultation scenario, and can also include extended scenarios such as a health guidance scenario, a drug promotion scenario, and a complaint handling scenario. Behavior data can be collected in various ways, and these methods can be used alone or in combination to ensure comprehensive coverage of the behavior characteristics of pharmacy staff. For example, through the POS system record, the behavior data of the pharmacy staff in the drug sales and recommendation scenarios can be obtained, such as the types of drug recommendations, the execution of promotion activities, etc.; through voice interaction data collection (such as recording equipment or intelligent question and answer terminals), the communication content between the pharmacy staff and the customers can be captured to analyze their language expression ability and professional knowledge application; through video monitoring analysis, the behavior of the pharmacy staff in the service scenario can be recorded, such as whether to actively receive customers or actively recommend drugs. Customer feedback data reflects the subjective evaluation of customers on the service of pharmacy staff through questionnaires or online evaluations, including scores on professionalism and service attitude. IoT device data (such as health detectors, etc.) can be used to collect operation behavior data of pharmacy staff in technical assistance means.

[0043] The collected behavior data needs to be cleaned, classified, and labeled to be converted into a scenario-based behavior dataset. Invalid or noisy data is removed through data cleaning, such as removing background noise in audio recordings or invalid video segments. Data classification divides behavior data by scenario, such as drug recommendation, drug contraindication reminder, and special medication consultation. Finally, data labeling adds labels to the data (such as whether the behavior is standard or the contraindication reminder is accurate), and integrates them into a unified dataset to obtain a scenario-based behavior dataset.

[0044] S102, according to the scenario-based behavior dataset, a behavior model is constructed to extract behavior feature information of the pharmacy staff in different business scenarios through the behavior model;

[0045] Based on the scenario-based behavior dataset, a behavior model is constructed for each business scenario to analyze the specific behavior patterns of the pharmacy staff in that scenario. According to the data characteristics and scenario requirements of each scenario behavior data in the scenario-based behavior dataset, a suitable modeling method is selected. For example, in the drug recommendation scenario, a behavior model can be constructed through rule modeling, classification algorithm, or association analysis technique. By analyzing the types of drugs recommended by the pharmacy staff, the basis for recommendation (such as customer symptoms, age, gender, etc.), and customer feedback data (such as purchase rate, evaluation, etc.), the recommendation pattern of the pharmacy staff can be identified. For example, the model can determine whether the pharmacy staff prefer to recommend high-priced drugs, whether they provide alternative solutions, or whether they can adjust the recommended content according to customer needs. In the contraindication reminder scenario, for voice interaction data, natural language processing techniques can be used to extract the reminder content; for structured data (such as operation logs), statistical analysis can be used to identify the regularity of the reminder behavior. The accuracy, coverage, and customer response (such as whether to further consult) of the pharmacy staff's reminder of drug contraindications are analyzed. For example, the model can identify whether the pharmacy staff missed important contraindication reminders or whether they provided personalized guidance based on customer health information (such as chronic disease history, allergy history). In the special medication consultation scenario, modeling of this scenario can combine voice data (for analyzing consultation content) and customer feedback data to achieve deep learning techniques. The behavior model analyzes whether the pharmacy staff's medication recommendations for special populations (such as pregnant women, children, and the elderly) or special diseases are standardized, whether they provide specific guidance based on customer individual needs, and customer feedback on the recommendations. For example, the behavior model can identify whether the pharmacy staff accurately answered the customer's questions or whether they provided sufficient detailed medication guidance.

[0046] The behavior characteristics information of the pharmacy staff in different scenarios is extracted through the behavior model. These characteristics reflect the operation habits, ability level and behavior patterns of the pharmacy staff in specific business scenarios. For example, in the medicine recommendation scenario, the extracted characteristics can include recommendation accuracy, recommendation basis rationality, customer demand matching degree and customer acceptance of recommendation (such as purchase rate). In the contraindication reminder scenario, the extracted characteristics can include the comprehensiveness, accuracy of the reminder content and customer response. In the special medication consultation scenario, the extracted characteristics can include the standardization of the suggestion, the degree of individualization and the customer satisfaction.

[0047] S103, determining a set of knowledge points that the pharmacy staff needs to master in the business scenario according to the behavior characteristic information through a preset knowledge demand prediction model;

[0048] The construction of the preset knowledge demand prediction model is based on the correlation analysis between the past business data of the pharmacy and the behavior characteristics and knowledge mastery of the pharmacy staff. For example, by analyzing the impact of knowledge point deficiency on the behavior performance of the pharmacy staff, a mapping relationship between behavior characteristics and knowledge points is established. Specifically, the establishment of the knowledge demand prediction model includes the following aspects: defining the knowledge point library that the pharmacy staff needs to master (such as medicine classification, drug contraindication, special population medication guidance, etc.), collecting historical data (such as training records, behavior performance, customer feedback), summarizing the correlation rules between behavior characteristics and knowledge demand (such as low recommendation accuracy may be associated with “lack of knowledge of drug indications”), and forming preliminary prediction ability through machine learning or rule engine.

[0049] In step S102, the behavior characteristic information of the pharmacy staff in different business scenarios has been extracted by the behavior model, and the behavior characteristic information becomes the direct input of the knowledge demand prediction model. The knowledge demand prediction model obtains the mastery degree and deficiency of the knowledge points of the pharmacy staff in a specific scenario by analyzing the association between the behavior characteristic information and the knowledge point mastery. For example, the model analyzes the recommendation accuracy and the basis rationality of the pharmacy staff in the drug recommendation scenario to determine whether they lack drug classification knowledge or recommendation logic knowledge; analyzes the coverage rate and accuracy of the contraindication reminder to determine whether they need to supplement the drug contraindication classification knowledge or individualized guidance method; analyzes the standardization and customer feedback of the special drug consultation to determine whether they need to master the special population drug knowledge (such as children, pregnant women, etc.) or disease-related drug regimen. The knowledge demand prediction model maps the behavior characteristic information and the knowledge point demand, and finally outputs the knowledge point set that the pharmacy staff needs to master in different business scenarios. For example, for the pharmacy staff with general performance in the drug recommendation scenario, the model may output “drug indication knowledge” and “drug replacement scheme knowledge” as the priority learning content; for the pharmacy staff with low contraindication reminder coverage rate, the model may output “drug contraindication classification knowledge” and “drug interaction knowledge” as the key learning direction; for the pharmacy staff with poor special drug consultation ability, the model may output “child drug risk assessment knowledge” and “elderly chronic disease drug guidance” and other knowledge points.

[0050] In step S104, the behavior characteristic information is first vectorized, and the behavior characteristics of the pharmacy staff in different business scenarios are converted into numerical behavior characteristic vectors; secondly, the knowledge point set predicted in step S103 is vectorized, and the knowledge points are converted into numerical knowledge characteristic vectors. The behavior characteristics and knowledge point characteristics are converted into a unified numerical representation form, laying a foundation for subsequent bidirectional matching and analysis.

[0051] In step S102, the scenario-based behavior data set has extracted the behavior characteristic information of the pharmacy staff in different business scenarios through the behavior model. The behavior characteristic information of the pharmacy staff in each business scenario is mapped to a high-dimensional vector space through a numerical method. Each behavior characteristic corresponds to one dimension of the vector, and the characteristic value is normalized or standardized for unified quantification. For example, the recommendation accuracy is normalized to the range [0, 1]. For non-numeric features (such as recommendation method classification, behavior label, etc.), One-Hot Encoding or Embedding technology can be used for processing.

[0052] The knowledge point set predicted in step S103 is numerically processed and converted into a knowledge feature vector. The knowledge point set includes knowledge points that the pharmacy staff needs to master in a specific business scenario, such as "drug classification knowledge", "indication knowledge", "drug replacement scheme knowledge", etc. When vectorizing, first map each knowledge point to a dimension in the vector, and all knowledge points in the scene together form a high-dimensional vector space. For a knowledge point set without priority setting, binary representation (such as setting 1 for a knowledge point that needs to be mastered and 0 for a knowledge point that does not need to be mastered) or mean initialization (such as setting the default value of all knowledge points to 1.0 or 0.5) can be used to equally represent the state of each knowledge point. In addition, if there is a hierarchical structure of knowledge points (such as basic knowledge and extended knowledge), the hierarchical relationship between knowledge points can be further represented by nested vectors.

[0053] S105, obtaining the association strength matrix between the behavior feature vector and the knowledge feature vector through a preset bidirectional attention model according to the behavior feature vector and the knowledge feature vector;

[0054] The bidirectional attention model is a mechanism based on deep learning, which is used to establish the importance weight between two information sources. For example, for the behavior feature vector, the model can calculate the dependence of each behavior feature (such as recommendation accuracy, comprehensive nature of taboo reminders) on different knowledge points (such as drug indication knowledge, drug taboo classification knowledge); at the same time, for the knowledge feature vector, the model will also calculate the importance of each knowledge point to different behavior features. This bidirectional calculation can comprehensively reflect the association relationship between behavior and knowledge.

[0055] The output of the bidirectional attention model is an association strength matrix, where each element is an association value, indicating the association strength between a behavior feature and a knowledge feature. The rows of the matrix represent different dimensions of the behavior feature vector (such as recommendation accuracy, reminder accuracy, etc.), and the columns represent different dimensions of the knowledge feature vector (such as drug classification knowledge, personalized reminder knowledge, etc.). The association strength value is usually a normalized value (such as between 0 and 1), indicating the strength of the association relationship.

[0056] S106, performing confidence scoring on the association values in the association strength matrix that exceed a preset association threshold;

[0057] The association values in the association strength matrix represent the strength of the association between behavior features and knowledge features, but not all association values have practical significance. Therefore, a preset association threshold (such as 0.5 or 0.7) is needed to filter out low association values and only keep behavior-knowledge pairs with strong association. For example, only when the association value between a behavior feature (such as recommendation conversion rate) and a knowledge feature (such as drug indication knowledge) exceeds the threshold, will its confidence be further evaluated.

[0058] In the confidence score of the association value exceeding the preset association threshold, the reliability of the association relationship is quantitatively evaluated by comprehensively considering multiple factors. The calculation of the confidence score mainly depends on the following three aspects: the absolute size of the association strength value (the closer the association value is to 1, the higher the score is); the historical association frequency of the behavior characteristics and the knowledge characteristics (such as whether the association of the behavior and the knowledge point appears multiple times in the historical data, and the higher the frequency, the higher the score is); and the importance weight of the knowledge point (if there is no preset weight, equal weight or dynamically generated weight can be used). The confidence score can be calculated by weighted summation or product formula, and the contribution values of various factors are integrated to finally generate a score result in the range of 0-1. Finally, a set of association values with confidence scores is obtained, which provides a basis for identifying knowledge blind spots.

[0059] S107, determining the knowledge points corresponding to the association values with confidence scores less than a preset score threshold as knowledge blind spots;

[0060] In step S107, for the set of association values with confidence scores, further filter out the association values with confidence scores lower than the preset score threshold, and determine the knowledge points corresponding to these association values as the knowledge blind spots of the pharmacy staff. The knowledge blind spot refers to the knowledge point that the pharmacy staff cannot effectively master or correctly use in a specific business scenario.

[0061] The confidence score threshold is a further screening standard for identifying behavior-knowledge associations with low reliability. For example, if the confidence score of a certain association value is lower than the threshold (such as 0.6), it indicates that the reliability of the association relationship is insufficient, which may reflect that the pharmacy staff has insufficient knowledge or blind spots in mastering the knowledge point. For the association values with confidence scores lower than the threshold, extract the knowledge points corresponding to the association values and determine them as the knowledge blind spots. For example, if a certain pharmacy staff performs poorly in the comprehensive nature of contraindication reminders, and the association confidence score of "drug contraindication classification knowledge" is lower than the threshold, it can be determined that the knowledge blind spot of the pharmacy staff includes "drug contraindication classification knowledge".

[0062] S108, constructing a knowledge graph according to the scenario-based behavior data set, the knowledge blind spot, the knowledge point set, and the association relationship between the knowledge point set and the business scenario;

[0063] Specifically, the mastery degree scores of all knowledge points in the knowledge blind spot are marked in the knowledge point set to obtain a target knowledge point set; based on the scenario-based behavior data set and the target knowledge point set, the use characteristics of the target knowledge point set in the business scenario are analyzed to determine the association relationship between the target knowledge point set and the business scenario; and the knowledge graph is constructed according to the target knowledge point set and the association relationship.

[0064] First, the mastery level of the knowledge points in the knowledge blind area is scored. Specifically, according to the data performance (such as task completion rate, operation accuracy, etc.) in the scenario behavior data set, the knowledge points in each knowledge blind area are scored, and the score range is usually [0, 1], where 0 represents complete non-mastery and 1 represents complete mastery. For example, for the knowledge blind area "drug classification knowledge" and "indication knowledge" of a drug store employee in the drug recommendation scenario, the scoring can be calculated through its recommendation accuracy and other characteristics to be 0.2 and 0.5, respectively, indicating low and general mastery. The scored knowledge blind area knowledge point set is combined with the knowledge point set that needs to be mastered in the business scenario to obtain the target knowledge point set.

[0065] Using the behavior data in the scenario behavior data set, the usage frequency and performance of each target knowledge point in different business scenarios are counted, such as the usage frequency of "drug classification knowledge" in the drug recommendation scenario and the influence on the recommendation accuracy, and the usage characteristics of "drug substitution knowledge" in the special drug consultation scenario and the contribution to the consultation success rate. According to these statistical results, the association between the target knowledge points and the business scenarios is determined, and an association matrix is generated, where each association value represents the association between the target knowledge point and a certain business scenario (such as a number in the range of [0, 1], the closer to 1, the stronger the association). Based on the target knowledge point set and the association strength of the target knowledge point with a certain business scenario, a knowledge graph containing knowledge points and business scenarios is constructed. The nodes of the knowledge graph include two categories: one is the knowledge point node in the target knowledge point set, and the other is the business scenario node (such as drug recommendation, contraindication reminder, special drug consultation, etc. scenario). The edges in the knowledge graph represent the relationship between the nodes, including the hierarchical or logical relationship between the knowledge points (such as "drug classification knowledge" is the basis of "drug recommendation logical knowledge") and the association between the knowledge points and the business scenarios. The weight of the edge represents the association relationship, for example, the association weight between "drug classification knowledge" and the drug recommendation scenario is 0.9.

[0066] S109, based on the knowledge graph, determine the professional learning content of the pharmacy staff and the priority of the professional learning content; combine the association weight of knowledge points and business scenarios to select knowledge points with higher association weight in the business scenario, to ensure that the professional learning content is closely related to business value. For example, if the mastery level score of "drug contraindication knowledge" is 0.3 and the association weight in the contraindication reminder scenario is 0.8, this knowledge point should be included in the learning content. Finally, the knowledge point list that the pharmacy staff needs to learn is extracted directly from the knowledge graph. These knowledge points are both the knowledge gaps of the pharmacy staff and the important knowledge points with high demand in the business scenario. After determining the professional learning content, set the priority for each learning content through the existing information in the knowledge graph. The priority is based on two key indicators: one is the mastery level score of the knowledge point (the lower the score, the higher the priority), and the other is the association weight of the knowledge point and the business scenario (the higher the weight, the higher the priority). Weight the two indicators to calculate the comprehensive priority score of each knowledge point: priority score = a·(1-mastery level score) + b·knowledge point and business scenario association value, where a and b are weight parameters used to balance the importance of mastery level and business demand. Finally, sort the learning content according to the priority score. For example, if the mastery level score of "drug replacement scheme knowledge" is 0.4 and the business scenario association weight is 0.7, while the mastery level score of "drug contraindication knowledge" is 0.2 and the association weight is 0.8, the priority of "drug contraindication knowledge" is higher. In this way, a learning content list sorted by priority is output, providing clear guidance for the learning plan of pharmacy staff.

[0067] Optionally, the following steps can be performed after step S108 of the embodiment shown in the figure: Figure 1

[0068] Obtain the problem solving scheme and experience data of the target pharmacy staff in the business scenario, and the target pharmacy staff is the pharmacy staff whose problem solving ability meets the preset requirements; label the problem solving scheme and experience data according to the knowledge points to obtain the labeling result, associate the labeling result with the business scenario and the knowledge point set to obtain the experience set; according to the experience set, supplement the knowledge point set in the knowledge graph.

[0069] ​The target pharmacy staff refers to a pharmacy staff who has problem-solving ability meeting preset requirements in a business scenario. Specific standards can include: the pharmacy staff's operation record in the business scenario proves that he or she can efficiently solve problems, or his or her behavior performance (such as customer satisfaction, problem-solving rate, etc.) reaches a certain level. The preset requirements can be set according to specific scenarios, for example, the pharmacy staff's success rate of recommendation in the drug recommendation scenario reaches a certain proportion, or he or she can accurately identify the contraindicated drug combination in the contraindication reminding scenario. After determining the target pharmacy staff, the problem-solving solutions and experience data formed by the target pharmacy staff in the business scenario are obtained. These data mainly come from the pharmacy staff's actual operation record, case sharing, and decision-making logic formed in the working process. For example, in the drug recommendation scenario, the pharmacy staff may record the basis for recommending a certain drug, the strategy for communicating with the customer, and the final recommendation result; in the contraindication reminding scenario, the pharmacy staff may provide experience data for identifying drug contraindications. These problem-solving solutions and experience data can be obtained through operation log extraction, case analysis, interview questionnaire, etc., to ensure that various problem-solving methods and experience summaries in actual business are covered.

[0070] The problem-solving solutions and experience data formed by the target pharmacy staff in the business scenario are compared with the knowledge point set, and the specific knowledge points involved are labeled one by one. The labeling process can be completed through a knowledge point extraction algorithm based on natural language processing, for example, labeling a certain experience data as involving "drug classification knowledge", "drug contraindication knowledge", etc. The labeling result can clearly show the correspondence between each solution and experience data and the knowledge points, so as to combine abstract knowledge points with specific solutions in actual operation scenarios.

[0071] After completing the labeling, the labeling result is further associated with the business scenario and the knowledge point set to form an experience set. The experience set is a structured data form that contains problem-solving solutions, related knowledge points, and their application information in specific business scenarios. For example, an experience record can be described as: "In the drug recommendation scenario, 'drug classification knowledge' and 'indication knowledge' are applied, and the problem of selecting a certain drug is solved, finally improving the recommendation accuracy."

[0072] Finally, according to the generated experience set, the knowledge point set in the knowledge graph is supplemented and improved. By analyzing the experience set, new knowledge points not included in the knowledge graph can be found, or the definition of existing knowledge points can be supplemented. For example, a certain experience record may reflect a new knowledge point of "special drug substitution knowledge", or provide more application scenarios for the existing "drug contraindication knowledge". These newly added knowledge points and their associated relationships are supplemented into the knowledge graph, and the association weights of the knowledge points and the business scenarios are updated to ensure the structural integrity and real-time nature of the knowledge graph.

[0073] Optionally, after step S109 of the illustrated embodiment, the following steps can be performed: Figure 1

[0074] In response to a learning request from a pharmacy staff member, a learning task is created, the learning request carrying a business scenario, a set of knowledge points, and a knowledge blind spot; a knowledge conversion effect produced after the pharmacy staff member completes the learning task is obtained, the knowledge conversion effect including a knowledge point application situation of the pharmacy staff member and a task completion situation; and a priority of learning content is adjusted according to the knowledge conversion effect.

[0075] When a pharmacy staff member initiates a learning request, the system first generates a learning task related to the actual work according to the business scenario, the set of knowledge points, and the knowledge blind spot. These learning tasks simulate problems that may be encountered in real business scenarios and are designed in combination with knowledge points that the pharmacy staff member has not yet fully mastered (i.e., the knowledge blind spot). For example, for a learning request in the context of drug recommendation, the learning task may require the pharmacy staff member to recommend appropriate drugs in a specific situation and explain their indications and contraindications according to customer needs. When creating the learning task, the system will automatically select knowledge points related to the pharmacy staff member's knowledge blind spot according to the association between knowledge points and business scenarios in the knowledge graph.

[0076] After the pharmacy staff member completes the learning task, the system will evaluate the knowledge conversion effect. The knowledge conversion effect includes two parts: first, the application situation of the knowledge points, i.e., whether the pharmacy staff member correctly used the relevant knowledge points in the task; second, the task completion situation, i.e., the overall performance of the pharmacy staff member in solving problems in the learning task, such as whether the task is completed, how efficiently it is completed, and the quality of the solution. For example, in the drug recommendation task, the system will evaluate whether the pharmacy staff member correctly applied "drug classification knowledge", "indication knowledge", "drug contraindication knowledge", and other relevant knowledge points, and score whether the final recommended drug meets the scene requirements. These results can be quantified into specific indicators, such as knowledge point mastery scores and task success rates, to comprehensively reflect the learning effect of the pharmacy staff member.

[0077] According to the knowledge conversion effect of the pharmacy staff member, the system dynamically adjusts the priority of the learning content to ensure that the next stage of learning is more efficient and accurate. If the knowledge conversion effect shows that certain knowledge points have not been correctly applied or there are obvious knowledge blind spots in the task, the system will increase the learning priority of these knowledge points and intensify the training of related content in subsequent learning tasks. For example, if the pharmacy staff member fails to correctly identify the interaction between drugs in the contraindication reminder task, the system will increase the priority of "drug interaction knowledge" and design more related scenarios for the pharmacy staff member to practice. Conversely, for knowledge points that have already been mastered, the priority can be reduced, so that more learning resources are invested in content that has not yet been mastered.

[0078] ​Optionally, in Figure 1 In the embodiment shown, the method further comprises:

[0079] Obtaining emotional interaction data of the pharmacy staff, calculating an emotional value of the pharmacy staff through a preset emotional prediction model based on the emotional interaction data, the emotional interaction data including voice data and expression information; judging a learning state of the pharmacy staff based on the emotional value, the learning state including a negative state, an anxious state, and a positive state; when the learning state is the negative state or the anxious state, generating a target learning task based on professional learning content and a priority corresponding to the professional learning content, the target learning task being a learning content with a learning difficulty and a learning form meeting preset requirements.

[0080] During the learning process, the system collects emotional interaction data of the pharmacy staff in real time, which includes voice data and expression information. Voice data can come from the voice input of the pharmacy staff when interacting with the system, including features such as tone, speed, and volume; expression information is captured by a camera or sensor to capture changes in the pharmacy staff's facial expressions, such as raised eyebrows and drooping corners of the mouth.

[0081] After obtaining the emotional interaction data, the system processes the data using a preset emotional prediction model to calculate the emotional value of the pharmacy staff. The emotional prediction model is based on machine learning or deep learning algorithms, combining voice features (such as the smoothness of tone, the speed of speech) and expression features (such as facial muscle movement trajectories, expression classification results) to predict the emotional value of the pharmacy staff. The emotional value is usually a quantitative score that reflects the current emotional state of the pharmacy staff. For example, a low-pitched tone, a slowed speech, and no significant changes in facial expressions may correspond to a lower emotional value, while a light and cheerful tone, a moderate speech, and a smile may correspond to a higher emotional value.

[0082] Based on the calculated emotional value, the system classifies the learning state of the pharmacy staff, which includes a negative state, an anxious state, and a positive state. Specifically, when the emotional value is low (such as below a preset threshold), the system judges that the pharmacy staff is in a negative state, showing a lack of motivation and scattered attention; when the emotional value is high but volatile, the system judges that the pharmacy staff is in an anxious state, which may show tension and unease; when the emotional value is high and stable, the system judges that the pharmacy staff is in a positive state, i.e., with sufficient learning motivation and high concentration.

[0083] When the system detects that the pharmacy staff is in a negative state or an anxious state, in order to avoid the further influence of bad mood on learning effect, the system generates target learning tasks according to the professional learning content of the pharmacy staff and the corresponding priority. At this time, the learning difficulty meets the preset requirements, such as reducing the difficulty of the learning task, preferentially selecting the content easy to understand, and helping the pharmacy staff to find the sense of achievement in learning. For example, the pharmacy staff is focused on selecting related content of the part of the basic knowledge they have mastered, and avoiding setting too complex learning tasks. And the learning form meets the preset requirements, such as adjusting the learning form to more interesting, interactive or lightweight content, for example, using video explanation, game-based question and answer or case analysis, etc., to reduce learning pressure and stimulate the learning interest of the pharmacy staff.

[0084] Referring to Figure 2 A structural schematic diagram of a knowledge learning management system based on data analysis provided for an embodiment of the present application, a knowledge learning management system 200 based on data analysis specifically includes:

[0085] The acquisition module 201 is configured to acquire a scenario-based behavior data set, the scenario-based behavior data set including behavior data of each pharmacy staff in different business scenarios, the business scenarios including at least a drug recommendation scenario, a drug contraindication reminding scenario, and a special medication consultation scenario;

[0086] The extraction module 202 is configured to construct a behavior model according to the scenario-based behavior data set, and extract behavior feature information of the pharmacy staff in different business scenarios through the behavior model;

[0087] The first determination module 203 is configured to determine a knowledge point set and a knowledge blind area that the pharmacy staff needs to master in each business scenario based on the behavior feature data;

[0088] The construction module 204 is configured to construct a knowledge graph according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set, and the association relationship between the knowledge point set and the business scenario;

[0089] The second determination module 205 is configured to determine professional learning content of the pharmacy staff and a priority corresponding to the professional learning content based on the knowledge graph.

[0090] Optionally, the first determination module 203 is specifically configured to:

[0091] determine the knowledge point set that the pharmacy staff needs to master in the business scenario through a preset knowledge demand prediction model according to the behavior feature information; and perform association analysis on the scenario-based behavior data set and the knowledge point set to determine the knowledge blind area of the pharmacy staff, the knowledge blind area being a knowledge point set whose mastery degree does not meet a preset requirement.

[0092] Optionally, the first determination module 203 is further specifically configured to:

[0093] The behavior feature information is converted into a behavior feature vector, and the knowledge point set is converted into a knowledge feature vector; an association strength matrix between the behavior feature vector and the knowledge feature vector is obtained through a preset bidirectional attention model according to the behavior feature vector and the knowledge feature vector; a confidence score is performed on an association value in the association strength matrix that exceeds a preset association threshold; and a knowledge point corresponding to the association value with a confidence score less than a preset score threshold is determined as a knowledge blind area.

[0094] Optionally, the construction module 204 is specifically configured to:

[0095] The mastery degree scores of all knowledge points in the knowledge blind area are marked in the knowledge point set, to obtain a target knowledge point set; the use features of the target knowledge point set in the business scenario are analyzed based on the scenario-based behavior data set and the target knowledge point set, to determine the association relationship between the target knowledge point set and the business scenario; and the knowledge graph is constructed according to the target knowledge point set and the association relationship.

[0096] Optionally, the system further includes a marking module 206, which is specifically configured to:

[0097] The problem solving scheme and experience data of the target pharmacy staff in the business scenario are obtained, the target pharmacy staff being a pharmacy staff whose problem solving ability meets a preset requirement; the problem solving scheme and experience data are marked according to the knowledge points, to obtain a marking result; the marking result is associated with the business scenario and the knowledge point set, to obtain an experience set; and the knowledge point set in the knowledge graph is supplemented according to the experience set.

[0098] Optionally, the system further includes a learning module 207, which is specifically configured to:

[0099] In response to a learning request of the pharmacy staff, a learning task is created, the learning request carrying a business scenario, a knowledge point set and a knowledge blind area; a knowledge conversion effect generated after the pharmacy staff completes the learning task is obtained, the knowledge conversion effect including a knowledge point application situation and a task completion situation of the pharmacy staff; and the priority of the learning content is adjusted according to the knowledge conversion effect.

[0100] Optionally, the system further includes a generation module 208, which is specifically configured to:

[0101] Emotion interaction data of the pharmacy staff is obtained, and an emotion value of the pharmacy staff is calculated through a preset emotion prediction model according to the emotion interaction data, the emotion interaction data including voice data and expression information; a learning state of the pharmacy staff is judged based on the emotion value, the learning state including a negative state, an anxious state and a positive state; and a target learning task is generated based on professional learning content and a priority corresponding to the professional learning content when the learning state is the negative state or the anxious state, the target learning task being learning content with a learning difficulty and a learning form meeting preset requirements.

[0102] It should be noted that the apparatus provided in the above examples is only exemplified by the above division of functional modules when realizing its functions. In actual applications, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions. In addition, the apparatus and method embodiments provided in the above examples belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be described here.

[0103] The embodiment also discloses an electronic device, which refers to Figure 3 The electronic device can include at least one processor 301, at least one communication bus 302, a user interface 303, a network interface 304, and at least one memory 305.

[0104] The communication bus 302 is used to realize the connection and communication between the components.

[0105] The user interface 303 can include a display screen (Display) and a camera (Camera), and the optional user interface 303 can further include a standard wired interface and a wireless interface.

[0106] The network interface 304 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0107] The processor 301 can include one or more processing cores. The processor 301 connects various parts of the server through various interfaces and lines, executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be realized in at least one of the hardware forms of a digital signal processing (Digital Signal Processing, DSP), a field-programmable gate array (Field-Programmable Gate Array, FPGA), and a programmable logic array (Programmable Logic Array, PLA). The processor 301 can be integrated with a combination of one or more of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU), and a modem. Among them, the CPU is mainly used to process the operating system, user interface and application programs; the GPU is used to render and draw the content to be displayed on the display screen; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 301, but can be realized by a separate chip.

[0108] The memory 305 can include a random access memory (RAM) and can also include a read-only memory (ROM). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 305 can include a program storage area and a data storage area, where the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, etc.; the data storage area can store data involved in the various method embodiments described above, etc. The memory 305 can optionally be at least one storage device located away from the aforementioned processor 301. As shown, the memory 305, as a computer storage medium, can include an operating system, a network communication module, a user interface module, and an application program of a knowledge learning management method based on data analysis. Figure 3

[0109] In the electronic device shown, the user interface 303 is mainly used to provide an interface for user input and obtain data input by the user; and the processor 301 can be used to call the application program of the knowledge learning management method based on data analysis stored in the memory 305, and when executed by one or more processors 301, the electronic device performs the method of one or more of the above embodiments. Figure 3

[0110] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0111] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0112] ​​In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments is merely illustrative, and the division of units can be changed according to actual conditions, such as a combination or integration of some units, or a deletion of some features, or an addition of some features. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0114] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0115] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium 305. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium 305 and includes a number of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium 305 includes: a U disk, a mobile hard disk, a magnetic or optical disk, and various media that can store program codes.

[0116] The above are only exemplary embodiments of the present disclosure, and cannot limit the scope of the present disclosure. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure are still within the scope of the present disclosure. Other embodiments of the present disclosure will be readily apparent to those skilled in the art upon consideration of the disclosure. The present application is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or conventional techniques in the art not described in the present disclosure. The scope and spirit of the present disclosure are defined by the claims. The specification and embodiments are merely exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A knowledge learning management method based on data analysis, characterized by, Applied to a server, the method comprises: acquiring a scenario-based behavior data set, the scenario-based behavior data set comprising behavior data of each pharmacy employee in different business scenarios, the business scenarios comprising at least a medicine recommendation scenario, a drug contraindication prompting scenario, and a special medicine consultation scenario; constructing a behavior model according to the scenario-based behavior data set, and extracting behavior feature information of the pharmacy employee in different business scenarios through the behavior model; determining a knowledge point set and a knowledge blind area that the pharmacy employee needs to master in each business scenario based on the behavior feature information; constructing a knowledge graph according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set, and the association between the knowledge point set and the business scenario; determining professional learning content of the pharmacy employee and a priority corresponding to the professional learning content based on the knowledge graph; the determination of the knowledge point set and the knowledge blind area that the pharmacy employee needs to master in the business scenario based on the behavior feature information specifically comprises: determining the knowledge point set that the pharmacy employee needs to master in the business scenario through a preset knowledge demand prediction model according to the behavior feature information; determining the knowledge blind area of the pharmacy employee by associating and analyzing the scenario-based behavior data set and the knowledge point set, the knowledge blind area being a knowledge point set whose mastery degree does not meet a preset requirement; the preset knowledge demand prediction model judges whether the pharmacy employee lacks medicine classification knowledge or recommendation logic knowledge by analyzing recommendation accuracy and reasonableness of the pharmacy employee in the medicine recommendation scenario; judges whether the pharmacy employee needs to supplement drug contraindication classification knowledge or individualized guidance method by analyzing coverage and accuracy of contraindication prompting; judges whether the pharmacy employee needs to master special population medicine knowledge or disease-related medicine scheme by analyzing standardization and customer feedback of special medicine consultation, the preset knowledge demand prediction model maps behavior feature information and knowledge point demand, and outputs the knowledge point set that the pharmacy employee needs to master in different business scenarios; the associating and analyzing of the scenario-based behavior data set and the knowledge point set to determine the knowledge blind area of the pharmacy employee specifically comprises: converting the behavior feature information into a behavior feature vector and converting the knowledge point set into a knowledge feature vector; obtaining an association strength matrix between the behavior feature vector and the knowledge feature vector through a preset bidirectional attention model according to the behavior feature vector and the knowledge feature vector; confidence scoring is performed on an association value in the association strength matrix that exceeds a preset association threshold; determining a knowledge point corresponding to an association value with a confidence score less than a preset score threshold as the knowledge blind area.

2. The method of claim 1, wherein, the construction of the knowledge graph according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set, and the association between the knowledge point set and the business scenario specifically comprises: labeling a mastery degree score of all knowledge points in the knowledge blind area in the knowledge point set to obtain a target knowledge point set; analyze usage features of the target knowledge point set in the business scenario based on the scenario-based behavior data set and the target knowledge point set, and determine an association relationship between the target knowledge point set and the business scenario; construct a knowledge graph according to the target knowledge point set and the association relationship.

3. The method of claim 1, wherein, After the knowledge graph is constructed according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set, and the association relationship between the knowledge point set and the business scenario, the method further includes: obtaining problem solving solutions and experience data of a target pharmacy employee in the business scenario, the target pharmacy employee being a pharmacy employee whose problem solving ability meets a preset requirement; annotating the problem solving solutions and experience data according to knowledge points to obtain an annotation result, associating the annotation result with the business scenario and the knowledge point set to obtain an experience set; supplementing the knowledge point set in the knowledge graph according to the experience set.

4. The method of claim 1, wherein, After the professional learning content of the pharmacy employee and the priority of the professional learning content are determined based on the knowledge graph, the method further includes: in response to a learning request of the pharmacy employee, creating a learning task, the learning request carrying the business scenario, the knowledge point set, and the knowledge blind area; obtaining a knowledge conversion effect generated after the pharmacy employee completes the learning task, the knowledge conversion effect including knowledge point application of the pharmacy employee and task completion; adjusting the priority of the learning content according to the knowledge conversion effect.

5. The method of claim 1, wherein, The method further includes: obtaining emotional interaction data of the pharmacy employee, calculating an emotional value of the pharmacy employee through a preset emotion prediction model according to the emotional interaction data, the emotional interaction data including voice data and expression information; judging a learning state of the pharmacy employee based on the emotional value, the learning state including a negative state, an anxious state, and a positive state; when the learning state is the negative state or the anxious state, generating a target learning task based on the professional learning content and the priority of the professional learning content, the target learning task being a learning content whose learning difficulty and learning form meet preset requirements.

6. A knowledge learning management system based on data analysis, characterized by, includes: an obtaining module configured to obtain a scenario-based behavior data set, the scenario-based behavior data set including behavior data of each pharmacy employee in different business scenarios, the business scenarios including at least a medicine recommendation scenario, a drug contraindication reminder scenario, and a special medication consultation scenario; an extracting module configured to construct a behavior model according to the scenario-based behavior data set, and extract behavior feature information of the pharmacy employee in different business scenarios through the behavior model; a first determining module configured to determine a knowledge point set and a knowledge blind area that the pharmacy employee needs to master in each business scenario based on the behavior feature data; a constructing module configured to construct a knowledge graph according to the scenario-based behavior data set, the knowledge blind area, the knowledge point set, and an association relationship between the knowledge point set and the business scenario. The second determining module is configured to determine professional learning content of the drugstore staff and a priority corresponding to the professional learning content based on the knowledge graph. The first determining module is specifically configured to determine a knowledge point set that the drugstore staff needs to master in the business scenario by a preset knowledge demand prediction model according to the behavior characteristic information. The scenario-based behavior data set and the knowledge point set are associated and analyzed to determine a knowledge blind area of the drugstore staff, the knowledge blind area being a knowledge point set that the drugstore staff does not master to a preset requirement. The preset knowledge demand prediction model determines whether the drugstore staff lacks drug classification knowledge or recommendation logic knowledge by analyzing recommendation accuracy and reasonableness of the drugstore staff in the drug recommendation scenario; and determines whether the drugstore staff needs to supplement drug contraindication classification knowledge or individualized guidance method by analyzing coverage and accuracy of contraindication reminders. The preset knowledge demand prediction model analyzes the standardization of special medication consultation and customer feedback to determine whether the drugstore staff needs to master special population medication knowledge or disease-related medication scheme. The preset knowledge demand prediction model maps behavior characteristic information and knowledge point demand to output a knowledge point set that the drugstore staff needs to master in different business scenarios. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector.

7. A knowledge learning management apparatus based on data analysis, characterized by, The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector.

8. A computer-readable storage medium comprising instructions, characterized in that, The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior characteristic vector and convert the knowledge point set into a knowledge characteristic vector. The first determining module is further configured to convert the behavior characteristic information into a behavior

Images