Medical insurance settlement list intelligent management method and system based on knowledge graph

Abstract

The invention provides a knowledge graph-based intelligent management method and system for a medical insurance settlement list, and the method comprises the steps: carrying out the analysis of obtained medical insurance settlement list data, obtaining a business keyword, carrying out the correlation matching of the business keyword in a pre-constructed medical insurance knowledge graph, and obtaining a medical insurance settlement entity; verifying the medical insurance settlement entity based on the medical insurance knowledge graph to obtain an entity verification result; if the entity verification result accords with reasonability, performing priority logic matching based on a first entity attribute of the medical insurance settlement entity and a second entity attribute of a medical insurance reimbursement rule in the medical insurance knowledge graph, and determining a settlement reimbursement rule of the medical insurance settlement entity; and determining a medical insurance settlement reimbursement proportion based on the settlement reimbursement rule, and determining a medical insurance settlement reimbursement amount based on the medical insurance settlement reimbursement proportion and the actual settlement amount of the medical insurance settlement entity. According to the invention, the change of the medical insurance settlement rule is quickly responded, and the efficiency and accuracy of medical insurance settlement are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and system for intelligent management of medical insurance settlement lists based on a knowledge graph. Background Art

[0002] With the continuous advancement of medical informatization, intelligent management of medical insurance settlement lists has become key to improving the efficiency of medical insurance settlement. However, most current medical insurance settlement list management methods have exposed significant shortcomings when dealing with the complex and ever-changing medical insurance and settlement rules. Medical insurance rules are constantly updated with social development and medical needs, and settlement rules are becoming increasingly sophisticated. Traditional management methods rely on fixed rule bases and manual adjustment models. Whenever the rules change, staff need to manually modify the rule base one by one. This is not only time-consuming and labor-intensive, but also prone to rule conflicts due to human errors, affecting settlement accuracy. At the same time, the integration of newly issued rules and regulations with existing rules also faces many difficulties. The inability to quickly respond to rule changes has led to a significant reduction in medical insurance settlement efficiency, seriously restricting the high-quality development of medical insurance settlement work. Summary of the Invention

[0003] The present invention provides a method and system for intelligent management of medical insurance settlement lists based on knowledge graphs, aiming to achieve rapid response to changes in medical insurance settlement rules and improve the efficiency and accuracy of medical insurance settlement.

[0004] In a first aspect, the present invention provides a method for intelligently managing medical insurance settlement lists based on a knowledge graph, comprising:

[0005] Parse the acquired medical insurance settlement list data to obtain business keywords, and associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity;

[0006] Verify the medical insurance settlement entity based on the medical insurance knowledge graph to obtain an entity verification result; the verification includes verification of treatment methods, treatment dosage, reimbursement scope and rationality of treatment costs;

[0007] If the entity verification result is reasonable, priority logic matching is performed based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rule of the medical insurance settlement entity;

[0008] The medical insurance settlement and reimbursement ratio is determined based on the settlement and reimbursement rules, and the medical insurance settlement and reimbursement amount is determined based on the medical insurance settlement and reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

[0009] In a second aspect, the present invention further provides a medical insurance settlement list intelligent management system based on a knowledge graph, which is applied to the medical insurance settlement list intelligent management method based on a knowledge graph as described in the first aspect; the medical insurance settlement list intelligent management system based on a knowledge graph includes:

[0010] The settlement entity matching module is used to parse the acquired medical insurance settlement list data to obtain business keywords, and then associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity;

[0011] An entity verification module is used to verify the medical insurance settlement entity based on the medical insurance knowledge graph to obtain an entity verification result; the verification includes the rationality verification of the treatment method, the rationality verification of the treatment dosage, and the rationality verification of the reimbursement scope;

[0012] A reimbursement rule matching module is configured to, if the entity verification result conforms to rationality, perform priority logic matching based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rule of the medical insurance settlement entity;

[0013] The medical insurance list settlement module is used to determine the medical insurance settlement reimbursement ratio based on the settlement and reimbursement rules, and to determine the medical insurance settlement reimbursement amount based on the medical insurance settlement and reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

[0014] In a third aspect, the present invention also provides an electronic device comprising: a memory for storing a computer software program; and a processor for reading and executing the computer software program, thereby implementing any of the above-mentioned methods for intelligent management of medical insurance settlement lists based on knowledge graphs.

[0015] In a fourth aspect, the present invention also provides a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements any of the above-mentioned methods for intelligent management of medical insurance settlement lists based on knowledge graphs.

[0016] In a fifth aspect, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for intelligent management of medical insurance settlement lists based on knowledge graphs.

[0017] The embodiment of the present invention provides an intelligent management method for medical insurance settlement lists based on knowledge graphs. It performs entity matching and verification of the rationality of treatment methods, treatment dosages, reimbursement scopes, and treatment costs through the medical insurance knowledge graph and the medical insurance settlement list data. Therefore, it can accurately verify the rationality of the business in the medical insurance settlement list data, and then perform priority logic judgment through entity attributes and the medical insurance knowledge graph to ensure that complex and changeable rules can be executed in an orderly manner in actual settlements to avoid rule conflicts. Medical insurance reimbursement is then performed according to the medical insurance settlement reimbursement ratio determined by the settlement and reimbursement rules. Therefore, no matter how the medical insurance settlement rules change, the medical insurance settlement list can be verified for rationality, reimbursement rules can be matched, reimbursement ratios can be determined, and reimbursement amounts can be settled through the medical insurance knowledge graph. The entire process does not require a large amount of manual intervention, can quickly respond to changes in medical insurance settlement rules, and improves the efficiency and accuracy of medical insurance settlement. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of a method for intelligent management of medical insurance settlement lists based on a knowledge graph provided by an embodiment of the present invention;

[0019] Figure 2 This is a schematic diagram of the structure of the medical insurance settlement list intelligent management system based on the knowledge graph provided by an embodiment of the present invention;

[0020] Figure 3 An embodiment diagram of an electronic device provided by an embodiment of the present invention;

[0021] Figure 4 An embodiment diagram of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0024] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0025] Optional, see Figure 1 , Figure 1 This is a flow chart of the method for intelligent management of medical insurance settlement lists based on knowledge graphs provided by the present invention. In the embodiment of the present invention, the execution subject of the method for intelligent management of medical insurance settlement lists based on knowledge graphs is the medical insurance intelligent management system. Therefore, the method for intelligent management of medical insurance settlement lists based on knowledge graphs includes:

[0026] Step 10: parse the acquired medical insurance settlement list data to obtain business keywords, and associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity.

[0027] Optionally, when medical insurance settlement and reimbursement are required, the medical insurance settlement list data is input into the medical insurance intelligent management system, or the medical insurance settlement list data is sent to the medical insurance intelligent management system via a terminal device. Therefore, after obtaining the medical insurance settlement list data, the medical insurance intelligent management system parses the data. The embodiment of the present invention uses natural language processing (NLP) technology to extract business keywords from the data, where business keywords generally include disease names, drug names, examination items, treatment methods, etc.

[0028] Furthermore, the medical insurance intelligent management system will associate and match the extracted business keywords with the pre-built medical insurance knowledge graph. The medical insurance knowledge graph is a structured knowledge base containing a large number of medical insurance-related concepts, entities and the relationships between them. Therefore, the nodes matching the business keywords are searched in the knowledge graph to determine the medical insurance settlement entity, that is, the specific medical insurance business object related to the settlement list.

[0029] In one example, a medical insurance settlement statement reads, "A patient was hospitalized for pneumonia and received ceftriaxone sodium for anti-infective treatment. A chest CT scan was performed, resulting in a 5-day hospitalization." NLP technology was used to extract business keywords such as "pneumonia," "ceftriaxone sodium," "chest CT scan," and "hospitalization" from this statement. Next, a search was performed in the medical insurance knowledge graph, revealing that "pneumonia" corresponds to a disease entity in the knowledge graph, "ceftriaxone sodium" corresponds to a drug entity, "chest CT scan" corresponds to an examination item entity, and "hospitalization" corresponds to a treatment method entity. This yielded the medical insurance settlement entity for the statement.

[0030] Step 20: Verify the medical insurance settlement entity based on the medical insurance knowledge graph to obtain the entity verification result. The verification includes the treatment method, treatment dosage, reimbursement scope, and reasonableness of treatment costs.

[0031] Furthermore, the medical insurance settlement entities are verified through the medical insurance knowledge graph. This verification includes: treatment method verification, checking whether the current treatment method complies with conventional treatment methods for the disease; treatment dosage verification, determining whether the drug dosage and number of examination items are within a reasonable range; reimbursement scope verification, confirming whether the relevant drugs and examination items are included in the medical insurance reimbursement catalog; and treatment cost rationality verification, evaluating whether the treatment costs are reasonable based on local medical insurance policies and market prices. Therefore, the medical insurance intelligent management system verifies each medical insurance settlement entity one by one based on the medical insurance policies, medical knowledge, and other information stored in the knowledge graph, obtaining entity verification results, as described in steps 201 to 205.

[0032] Continuing with the above embodiment, for the settlement list of the above-mentioned "pneumonia" treatment, in terms of treatment method verification, the knowledge graph shows that conventional treatment methods for pneumonia include the use of antibiotics and necessary imaging examinations. The current "cefotaxime sodium anti-infection treatment" and "chest CT examination" are in line with the routine and have passed the verification. When verifying the treatment dosage, the knowledge graph is queried for the conventional dosage range of ceftriaxone sodium for pneumonia, and it is found that the dosage in the list is within a reasonable range, and the verification is passed. In the reimbursement scope verification, it is confirmed that ceftriaxone sodium and chest CT examination are both in the medical insurance reimbursement catalog, and the verification is passed. For the verification of the rationality of treatment costs, referring to the cost standards for hospitalization for pneumonia in the local medical insurance policy and the market prices of ceftriaxone sodium and chest CT examinations, it is found that the total cost of the settlement list is reasonable and has passed the verification. Therefore, the entity verification result of the medical insurance settlement entity is finally obtained as meeting the requirements.

[0033] In step 30, if the entity verification result is reasonable, priority logic matching is performed based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rules of the medical insurance settlement entity.

[0034] Furthermore, if the entity verification result is reasonable, the medical insurance intelligent management system will perform priority logic matching based on the first entity attribute of the medical insurance settlement entity (such as disease type, treatment method, drug category, etc.) and the second entity attribute of the medical insurance reimbursement rules in the medical insurance knowledge graph.

[0035] The medical insurance knowledge graph in this embodiment of the present invention also stores multiple medical insurance reimbursement rules, each corresponding to different entity attribute conditions and priorities. Therefore, the medical insurance intelligent management system matches the attributes of the medical insurance settlement entity with the attributes of the reimbursement rules according to the preset priority order, finds the most suitable reimbursement rule, and determines the settlement and reimbursement rules for the medical insurance settlement entity, as shown in steps 301 to 304.

[0036] Continuing with the aforementioned medical insurance settlement entity for pneumonia treatment, its first entity attributes include the disease being pneumonia, the treatment being hospitalization, and the medication being ceftriaxone sodium. The medical insurance reimbursement rules in the medical insurance knowledge graph are as follows: Rule A specifies hospitalization for pneumonia using a cataloged antibiotic with an 80% reimbursement rate; Rule B specifies general hospitalization with a 70% reimbursement rate. Because Rule A is more specific and fully matches the attributes of the medical insurance settlement entity, and Rule A has a higher priority than Rule B, the medical insurance intelligent management system determines that the settlement and reimbursement rule for this medical insurance settlement entity is Rule A, which results in an 80% reimbursement rate.

[0037] Step 40: Determine the medical insurance settlement and reimbursement ratio based on the settlement and reimbursement rules, and determine the medical insurance settlement and reimbursement amount based on the medical insurance settlement and reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

[0038] Furthermore, the medical insurance intelligent management system determines the medical insurance settlement reimbursement ratio based on the rules and obtains the actual settlement amount of the medical insurance settlement entity. Furthermore, the medical insurance intelligent management system calculates the medical insurance settlement reimbursement amount by multiplying the reimbursement ratio by the actual settlement amount. Continuing with the above example, it is known that the reimbursement ratio determined by the medical insurance settlement entity for the pneumonia treatment is 80%, and the actual settlement amount of the settlement list is 5,000 yuan. The medical insurance intelligent management system determines that the medical insurance settlement reimbursement amount for the medical insurance settlement list is 4,000 yuan by calculating 5,000 × 80% = 4,000 yuan.

[0039] The embodiment of the present invention performs entity matching and verification of the rationality of treatment methods, treatment dosage, reimbursement scope and treatment costs through the medical insurance knowledge graph and the medical insurance settlement list data, so that the rationality of the business in the medical insurance settlement list data can be accurately verified, and then priority logic judgment is performed through entity attributes and the medical insurance knowledge graph to ensure that complex and changeable rules can be executed in an orderly manner in actual settlement to avoid rule conflicts, and then medical insurance reimbursement is performed according to the medical insurance settlement reimbursement ratio determined by the settlement and reimbursement rules. Therefore, no matter how the medical insurance settlement rules change, the medical insurance settlement list can be verified for rationality, reimbursement rules can be matched, reimbursement ratios can be determined and reimbursement amounts can be settled through the medical insurance knowledge graph. The entire process does not require a large amount of manual intervention, can quickly respond to changes in medical insurance settlement rules, and improves the efficiency and accuracy of medical insurance settlement.

[0040] In one embodiment, steps 201 to 205 are described as follows:

[0041] Step 201: If there is no direct relationship between any first target entity and second target entity in the medical insurance settlement entity in the medical insurance knowledge graph, the first target entity and the second target entity are used as endpoints, and the path traversal is performed in the medical insurance knowledge graph with a preset step size to obtain an initial indirect path, and the indirect association mode of the medical insurance business logic of each initial indirect path is determined to determine the target indirect path.

[0042] Optionally, for any first target entity and second target entity in the medical insurance settlement entity, if it is determined that the first target entity and the second target entity have a direct relationship in the medical insurance knowledge graph, the medical insurance intelligent management system determines that the medical insurance settlement entity meets the rationality of the treatment method.

[0043] Furthermore, if it is determined that the first target entity and the second target entity do not have a direct relationship in the medical insurance knowledge graph, the medical insurance intelligent management system uses these two entities as endpoints and traverses the path in the medical insurance knowledge graph according to a preset step size. The preset step size can be set based on the complexity of the knowledge graph, for example, 2-5 steps, that is, connecting the two endpoints through a maximum of 2-5 intermediate nodes. During the traversal process, the medical insurance intelligent management system obtains all possible initial indirect paths.

[0044] Furthermore, the medical insurance intelligent management system analyzes the medical insurance business logic of each initial indirect path to determine whether it conforms to common association patterns in medical insurance business, such as disease-symptom-treatment methods, drugs-indications-diseases, etc., and screens out target indirect paths that meet the requirements.

[0045] In the medical insurance settlement entity for hospitalization for pneumonia, for example, the first target entity is "chest CT examination" and the second target entity is "cefotaxime sodium", which do not have a direct relationship in the medical insurance knowledge graph. The preset step size is set to 3, and "chest CT examination" and "cefotaxime sodium" are used as endpoints to traverse the knowledge graph, and three initial indirect paths are obtained: Path 1 is "chest CT examination-pneumonia diagnosis-antibiotic treatment-cefotaxime sodium"; Path 2 is "chest CT examination-lung imaging features-bacterial infection-cefotaxime sodium"; Path 3 is "chest CT examination-doctor's diagnosis recommendation-medication plan-cefotaxime sodium". Then, the medical insurance intelligent management system analyzes the medical insurance business logic of each path and finds that Path 1 and Path 2 conform to the conventional association pattern of disease diagnosis and treatment, and drug use, while the "doctor's diagnosis recommendation-medication plan" association of Path 3 is not clear and specific enough, and finally Path 1 and Path 2 are determined as the target indirect paths.

[0046] Step 202: Commonly associate entities whose occurrence frequency of each entity in the target indirect path is greater than a preset frequency threshold.

[0047] Furthermore, a preset frequency threshold is set, for example, 30%. For the target indirect path determined in step 201, the medical insurance intelligent management system counts the frequency of occurrence of each entity in the path. If the frequency of occurrence of an entity in all target indirect paths is greater than the threshold, it is identified as a public associated entity.

[0048] Continuing with the target indirect pathway 1 (Chest CT Examination - Pneumonia Diagnosis - Antibiotic Treatment - Ceftriaxone Sodium) and Path 2 (Chest CT Examination - Lung Imaging Characteristics - Bacterial Infection - Ceftriaxone Sodium), the system counts the frequency of each entity. The endpoint entities "Chest CT Examination" and "Ceftriaxone Sodium" appear at a 100% frequency, while "Pneumonia Diagnosis" appears at a 50% frequency, "Antibiotic Treatment" appears at a 50% frequency, "Lung Imaging Characteristics" appears at a 50% frequency, and "Bacterial Infection" appears at a 50% frequency. Setting the preset frequency threshold to 30%, "Chest CT Examination," "Ceftriaxone Sodium," "Pneumonia Diagnosis," "Antibiotic Treatment," "Lung Imaging Characteristics," and "Bacterial Infection" are all identified as common related entities.

[0049] Step 203: Determine the first scene matching strength and the second scene matching strength based on the matching relationship between the entity type of the common associated entity and the entity scenes of the first target entity and the second target entity, and determine the first entity association strength and the second entity association strength based on the entity distance between the common associated entity and the first target entity and the second target entity, respectively.

[0050] Furthermore, the medical insurance intelligent management system performs matching analysis based on the entity type of the public associated entity (such as diseases, drugs, examination items, etc.) and the entity scenarios of the first target entity and the second target entity (such as diagnosis scenarios, treatment scenarios, etc.). Optionally, the embodiment of the present invention uses the Jaccard similarity coefficient formula to calculate the scene matching strength, and the formula is: J(A, B) = |A∩B| / |A∪B|, where A and B represent the entity type set and the entity scenario set, respectively. Further, the medical insurance intelligent management system determines the entity association strength based on the shortest path length between the public associated entity and the first target entity and the second target entity in the knowledge graph, using the formula S = 1 / d, where S is the entity association strength and d is the shortest path length. Therefore, through these two formulas, the medical insurance intelligent management system calculates the first scene matching strength, the second scene matching strength, the first entity association strength, and the second entity association strength, respectively.

[0051] Continuing with the public associated entity "pneumonia diagnosis", it belongs to the diagnosis type entity. The entity scene corresponding to the first target entity "chest CT examination" is the diagnosis auxiliary examination scene, and the entity scene corresponding to the second target entity "cefotaxime sodium" is the treatment medication scene. For example, the entity type set of "pneumonia diagnosis" is A1, the entity scene set of "chest CT examination" is B1, and the entity scene set of "cefotaxime sodium" is B2. By calculating J(A1, B1) and J(A1, B2), the first scene matching strength and the second scene matching strength are obtained. In the knowledge graph, the shortest path length from "pneumonia diagnosis" to "chest CT examination" is 1, and the shortest path length to "cefotaxime sodium" is 2. Therefore, the calculated first entity association strength is 1, and the second entity association strength is 0.5. Calculation is performed on all public associated entities to obtain the strength value of each entity.

[0052] In step 204, if both the first scenario matching strength and the second scenario matching strength are greater than the preset matching strength threshold, and both the first entity association strength and the second entity association strength are less than or equal to the preset association strength threshold, then it is determined that the medical insurance settlement entity meets the treatment mode rationality requirements. Otherwise, it does not meet the requirements.

[0053] Furthermore, the medical insurance intelligent management system compares the first scenario matching strength and the second scenario matching strength with a preset matching strength threshold (e.g., 0.6), and simultaneously compares the first entity association strength and the second entity association strength with a preset association strength threshold (e.g., 0.8). Only when both the first scenario matching strength and the second scenario matching strength are greater than the preset matching strength threshold, and both the first entity association strength and the second entity association strength are less than or equal to the preset association strength threshold, is it determined that the medical insurance settlement entity meets the rationality of the treatment method; otherwise, it is determined that the treatment method does not meet the rationality.

[0054] In one embodiment, after calculation, the minimum values ​​of the first scenario matching strength and the second scenario matching strength corresponding to all common related entities are 0.7 and 0.65, respectively, both greater than the preset matching strength threshold of 0.6; the maximum values ​​of the first entity association strength and the second entity association strength are 0.7 and 0.75, respectively, both less than or equal to the preset association strength threshold of 0.8. At this point, the medical insurance settlement entity is determined to meet the treatment rationality requirements. If any strength value does not meet the requirements, the treatment rationality requirement is determined to be unacceptable.

[0055] Step 205: If the medical insurance settlement entity meets the rationality of the treatment method, the rationality of the treatment dosage of the medical insurance settlement entity is verified based on the medical insurance knowledge graph to obtain an entity verification result.

[0056] Furthermore, if the medical insurance settlement entity meets the rationality of the treatment method, the medical insurance intelligent management system verifies the rationality of the treatment dosage of the medical insurance settlement entity based on the medical insurance knowledge graph to obtain the entity verification result, as described in steps 2051 to 2055.

[0057] The embodiment of the present invention can analyze the relationship between each entity in the medical insurance settlement entity, not only to determine whether the treatment method is reasonable, but also to verify the rationality of the treatment amount based on the rationality of the treatment method. Therefore, it can accurately verify the rationality of the business in the medical insurance settlement list data, thereby being able to quickly respond to changes in medical insurance settlement rules, improve the efficiency and accuracy of medical insurance settlement, and ensure the healthy and stable operation of the medical insurance system.

[0058] In one embodiment, steps 2051 to 2055 are described as follows:

[0059] Step 2051: construct a local association network based on the nodes and node edges related to the first target entity and the second target entity in the medical insurance knowledge graph, and filter the nodes and node edges related to the treatment dosage in the local association network to obtain actual treatment dosage data.

[0060] Optionally, the medical insurance intelligent management system, based on the medical insurance knowledge graph, extracts relevant nodes and node edges from the first and second target entities, constructing a local association network. This local association network encompasses all types of information directly or indirectly associated with these two entities within the medical insurance business logic. Within this constructed local association network, the medical insurance intelligent management system selects nodes and node edges related to treatment dosage and obtains actual treatment dosage data. For example, for drug entities, data such as dosage and frequency of use are obtained; for examination item entities, data such as the number of examinations is obtained.

[0061] For the medical insurance settlement entity for continuing hospitalization for pneumonia, the first target entity is "cefotaxime sodium" and the second target entity is "chest CT examination." The medical insurance intelligent management system uses these two entities as the core within the medical insurance knowledge graph, extracts relevant nodes and node edges, and constructs a local association network containing nodes such as "pneumonia," "antibiotic treatment," and "lung imaging diagnosis," and their interrelationships. Within this local association network, nodes and edges related to the dosage and frequency of "cefotaxime sodium" and those related to the frequency of "chest CT examination" are screened out. The actual treatment dosage data obtained is 1.5 grams of ceftriaxone sodium per day, taken once daily, and one chest CT examination performed.

[0062] Step 2052: Determine the standard treatment dosage range under the treatment scenarios of the first target entity and the second target entity based on the medical insurance knowledge graph, and determine the initial treatment dosage difference data based on the actual treatment dosage data and the standard treatment dosage range.

[0063] Furthermore, the medical insurance intelligent management system determines the standard treatment dosage range in the treatment scenarios of the first target entity and the second target entity based on the medical insurance knowledge graph, wherein the standard treatment dosage range is pre-set in the knowledge graph based on multiple factors such as medical standards and medical insurance policies.

[0064] Furthermore, the medical insurance intelligent management system compares the actual treatment dosage data with the standard treatment dosage range, and determines the initial treatment dosage difference data by calculating the difference between the two.

[0065] Continuing with the pneumonia treatment scenario mentioned above, the medical insurance intelligent management system obtained from the medical insurance knowledge graph that, in the pneumonia treatment scenario, the standard daily dosage range of ceftriaxone sodium is 1-2 grams, the frequency of use is 1-2 times a day, and the reasonable number of chest CT examinations is 1-2 times. The actual treatment dosage data (cefotaxime sodium daily dosage of 1.5 grams, used once a day, and 1 chest CT examination) is compared with the standard treatment dosage range. It is calculated that the ceftriaxone sodium dosage is within the standard range, with a difference of 0; the number of chest CT examinations is also within the standard range, with a difference of 0, thus obtaining the initial treatment dosage difference data.

[0066] In step 2053, based on the initial treatment dosage difference data, influencing factors are traversed in the medical insurance knowledge graph to obtain dosage difference correlation factors. The initial treatment dosage difference data is then modified based on the dosage difference correlation factors to obtain target treatment dosage difference data. The dosage difference correlation factors include patient characteristics and treatment environment factors.

[0067] Furthermore, the medical insurance intelligent management system traverses the influencing factors in the medical insurance knowledge graph based on the initial treatment dosage difference data, focusing on the nodes and edges related to patient characteristic factors (such as age, weight, underlying diseases, etc.) and treatment environment factors (such as hospital grade, treatment area, etc.) to obtain these dosage difference related factors. Furthermore, the medical insurance intelligent management system corrects the initial treatment dosage difference data according to these related factors to obtain the target treatment dosage difference data. Optionally, the embodiment of the present invention adopts a correction method based on conditional probability. For patient characteristic factors, for example, the patient feature set is P, and the dosage correction coefficient under different feature combinations is C P For treatment environment factors, for example, the treatment environment set is E, and the dosage correction coefficient under different environment combinations is C E , the correction formula is: D 修正 =D 初始 *C P *C E , where D 修正 The target therapeutic dosage difference data, D 初始 The data are for the difference in initial treatment dosage.

[0068] Continuing with the above pneumonia treatment example, the medical insurance intelligent management system traverses the medical insurance knowledge graph and finds that the patient is 65 years old (an elderly patient, corresponding to a specific correction coefficient), and the treatment hospital is a tertiary-level A hospital (corresponding to different treatment environment correction coefficients). According to the settings in the knowledge graph, the correction coefficient C for the dosage of ceftriaxone sodium for elderly patients is P =1.1, the correction factor C for the number of chest CT examinations in a tertiary-level A hospital E =0.9. For ceftriaxone sodium, the initial difference was 0, so the revised target treatment dose difference data remained 0; for chest CT examination, the initial difference was 0, so the revised target treatment dose difference data was also 0.

[0069] In step 2054, if the target treatment dosage difference data is within the dosage difference threshold range, the medical insurance settlement entity is determined to be in compliance with treatment dosage rationality. Otherwise, it is not in compliance.

[0070] Furthermore, a dosage difference threshold range is set, and the medical insurance intelligent management system compares the target treatment dosage difference data with the threshold range. If the target treatment dosage difference data is within the dosage difference threshold range, the medical insurance intelligent management system determines that the medical insurance settlement entity meets the treatment dosage rationality. If the dosage difference data exceeds the dosage difference threshold range, the medical insurance intelligent management system determines that the treatment dosage rationality is not met.

[0071] Continuing with the above pneumonia treatment example, the dosage difference threshold range is [-0.2, 0.2]. Since the target treatment dosage difference data of ceftriaxone sodium and chest CT examination are both 0, which is within the set dosage difference threshold range, the medical insurance intelligent management system determines that the medical insurance settlement entity meets the rationality of treatment dosage.

[0072] Step 2055: If the medical insurance settlement entity meets the rationality of treatment dosage, the rationality of the reimbursement scope of the medical insurance settlement entity is verified based on the medical insurance knowledge graph to obtain the entity verification result.

[0073] Furthermore, if the medical insurance settlement entity meets the rationality of treatment dosage, the medical insurance intelligent management system verifies the rationality of the reimbursement scope of the medical insurance settlement entity based on the medical insurance knowledge graph to obtain the entity verification result, as described in steps 20551 to 20554.

[0074] The embodiment of the present invention can comprehensively and scientifically verify the rationality of the treatment dosage of the medical insurance settlement entity, and further verify the rationality of the reimbursement scope. Therefore, it can accurately verify the rationality of the business in the medical insurance settlement list data, thereby being able to quickly respond to changes in medical insurance settlement rules, improve the efficiency and accuracy of medical insurance settlement, and ensure the healthy and stable operation of the medical insurance system.

[0075] In one embodiment, steps 20551 to 20554 are described as follows:

[0076] Step 20551: Extract the reimbursement scope rules of the first target entity and the second target entity based on the local association network. The reimbursement scope rules include reimbursable items, reimbursement process, and reimbursement additional conditions.

[0077] Optionally, the medical insurance intelligent management system retrieves reimbursement scope rules related to the first target entity and the second target entity in the medical insurance knowledge graph based on the local association network. The reimbursement scope rules include three categories: reimbursable items, reimbursement processes and reimbursement additional conditions. Reimbursable items clarify which medicines, examination items, etc. can be included in medical insurance reimbursement; the reimbursement process stipulates the links and entities involved in reimbursement; and the reimbursement additional conditions set additional restrictions on reimbursement, such as specific diseases, treatment duration and other requirements.

[0078] In the medical insurance settlement entity for continued hospitalization for pneumonia, the first target entity is "cefotaxime sodium" and the second target entity is "chest CT examination." Reimbursement scope rules related to these two entities are extracted from the medical insurance knowledge graph based on the local association network. Reimbursable items show that ceftriaxone sodium is a reimbursable drug for the treatment of pneumonia, and chest CT examinations are reimbursable examination items for pneumonia diagnosis. The reimbursement process includes nodes and corresponding processes such as patient application submission, hospital review, and medical insurance department review. Reimbursement also requires that pneumonia be treated as a hospitalization and meet certain diagnostic criteria.

[0079] Step 20552: Determine based on the medical insurance knowledge graph whether the first target entity and the second target entity belong to entity nodes in the reimbursable items, determine based on the medical insurance knowledge graph whether the first target entity and the second target entity belong to entity nodes in the reimbursement process, and determine based on the medical insurance knowledge graph whether the first target entity and the second target entity belong to entity nodes in the reimbursement additional conditions.

[0080] Furthermore, the medical insurance intelligent management system determines whether the first and second target entities belong to entity nodes in the reimbursable items, reimbursement processes, and reimbursement additional conditions based on the medical insurance knowledge graph. This embodiment of the present invention determines whether the entities meet the requirements of the corresponding rules by searching the knowledge graph for the association between the entities and each rule node. For reimbursable items, the system checks whether the entity is in the specified reimbursable list; for reimbursement processes, the system confirms whether the entity participates in the specified process steps; and for reimbursement additional conditions, the system verifies whether the entity meets the set conditions.

[0081] Continuing with the above example, for "cefotaxime sodium" and "chest CT examination", a query is conducted in the medical insurance knowledge graph. In terms of reimbursable items, it is confirmed that "cefotaxime sodium" is in the list of reimbursable drugs for pneumonia treatment, and "chest CT examination" is in the list of reimbursable examination items for pneumonia diagnosis; in the reimbursement process, it is found that the treatment and examination behaviors corresponding to these two entities involve process nodes such as patient application submission and hospital review; in the reimbursement additional conditions, since the patient is hospitalized for pneumonia and the diagnosis meets the standards, "cefotaxime sodium" and "chest CT examination" meet the requirements of the reimbursement additional conditions.

[0082] In step 20553, if the first target entity and the second target entity are nodes in the reimbursable items, reimbursement process, and / or reimbursement additional conditions, then the medical insurance settlement entity is determined to meet the reimbursement scope rationality. Alternatively, if the first target entity or the second target entity is a node in the reimbursable items, reimbursement process, and / or reimbursement additional conditions, then the first target entity or the second target entity is determined to meet the reimbursement scope rationality.

[0083] Furthermore, the medical insurance intelligent management system makes a comprehensive judgment based on the judgment results of the reimbursement scope rules. If the first target entity and the second target entity simultaneously belong to nodes in the reimbursable items, reimbursement process, and / or reimbursement additional conditions, or if at least one of the first target entity or the second target entity belongs to these nodes, the medical insurance intelligent management system determines that the medical insurance settlement entity or the corresponding entity meets the reimbursement scope rationality.

[0084] Furthermore, if it is determined that neither the first target entity nor the second target entity satisfies the conditions, the medical insurance intelligent management system determines that the medical insurance settlement entity does not meet the rationality of the reimbursement scope.

[0085] Continuing with the above embodiment, since both "cefotaxime sodium" and "chest CT examination" meet the requirements of reimbursable items, reimbursement procedures and reimbursement additional conditions, the medical insurance intelligent management system determines that the medical insurance settlement entity meets the rationality of the reimbursement scope.

[0086] Step 20554: If the medical insurance settlement entity meets the rationality of the treatment method, or the first target entity or the second target entity meets the rationality of the reimbursement scope, the rationality of the treatment cost of the medical insurance settlement entity is verified based on the medical insurance knowledge graph to obtain the entity verification result.

[0087] Furthermore, if the medical insurance settlement entity meets the rationality of the treatment method, or the first target entity or the second target entity meets the rationality of the reimbursement scope, the medical insurance intelligent management system will verify the rationality of the treatment expenses of the medical insurance settlement entity based on the medical insurance knowledge graph to obtain the entity verification result, as described in steps 205541 to 205545.

[0088] The embodiment of the present invention has a complete verification chain from reimbursement rule review to expense verification, which can accurately determine whether the medical insurance settlement is compliant and reasonable. Therefore, it can accurately verify the rationality of the business in the medical insurance settlement list data, thereby quickly responding to changes in medical insurance settlement rules, improving the efficiency and accuracy of medical insurance settlement, and ensuring the healthy and stable operation of the medical insurance system.

[0089] In one embodiment, steps 205541 to 205545 are described as follows:

[0090] Step 205541: determine the entity path between the first target entity and the second target entity based on the medical insurance knowledge graph, and determine the path nodes related to treatment costs in the entity path.

[0091] Optionally, the medical insurance intelligent management system searches for all entity paths between the first target entity and the second target entity based on the medical insurance knowledge graph, where the entity path reflects the association relationship between the two entities in the medical insurance business logic, such as being connected through intermediate nodes such as diseases, treatment methods, and drug use.

[0092] Furthermore, for each entity path, the medical insurance intelligent management system filters out path nodes related to treatment costs, where path nodes usually contain information directly related to cost calculation, such as drug prices, examination item charging standards, treatment service costs, etc.

[0093] For the medical insurance settlement entity for continued pneumonia hospitalization, the first target entity is "cefotaxime sodium," and the second target entity is "chest CT examination." The medical insurance intelligent management system searches the medical insurance knowledge graph and obtains two entity paths: Path 1: "cefotaxime sodium - pneumonia treatment - chest CT examination," and Path 2: "cefotaxime sodium - antibiotic drug category - medical examination item category - chest CT examination." Within these two paths, nodes related to treatment costs are selected, such as the drug price node for "cefotaxime sodium," the examination item fee standard node for "chest CT examination," and nodes related to bed fees, nursing fees, and other expenses involved in "pneumonia treatment."

[0094] Step 205542, based on the cost standard range of the path nodes in each entity path in the medical insurance knowledge graph and the impact coefficient of the association relationship between the path nodes on the cost, determine the expected cost value of each entity path, and determine the expected cost range of the medical insurance settlement entity based on the expected cost value of each entity path.

[0095] Furthermore, for each entity path, the medical insurance intelligent management system obtains the cost standard interval corresponding to the path node from the medical insurance knowledge graph, and determines the impact coefficient of the association relationship between the path nodes on the cost, wherein the impact coefficient can be set according to the different business logic relationships recorded in the knowledge graph, such as the impact of different treatment methods on the cost of drug use. Calculate the expected cost of each entity path, where E p is the expected cost, C i is the median of the cost standard interval of the i-th path node, I i is the impact coefficient of the association relationship between the i-th path node and the next path node on the cost, and n is the number of path nodes.

[0096] Furthermore, after obtaining the expected cost value of each entity path, the medical insurance intelligent management system takes the minimum and maximum values ​​of the expected cost values ​​of all paths to determine the expected cost range of the medical insurance settlement entity.

[0097] Continuing with the above example, for path 1 "cefotaxime sodium - pneumonia treatment - chest CT examination", for example, the unit price standard interval of "cefotaxime sodium" is [100, 150] yuan, the median C1 = 125 yuan, and the impact coefficient of its association with "pneumonia treatment" on the cost is I1 = 1.2; the cost standard interval of "pneumonia treatment" is [2000, 3000] yuan, the median C2 = 2500 yuan, and the impact coefficient of its association with "chest CT examination" on the cost is I2 = 1.1; the charging standard interval of "chest CT examination" is [500, 800] yuan, the median C3 = 360 yuan. Calculate the expected cost value E of this path according to the formula p1 =125×1.2×2500×1.1×650=25593750 yuan. For path 2, which is "cefotaxime sodium - antibiotic drug category - medical examination item category - chest CT examination", the expected cost value E is calculated in the same way. p2 =23,000,000 yuan. Take E p1 and E p2 The minimum and maximum values ​​in determine the expected cost range to be [23000000, 25593750] yuan.

[0098] In step 205543, if the actual treatment costs in the medical insurance settlement entity are within the expected cost range, the entity verification result is determined to be reasonable.

[0099] Furthermore, the medical insurance intelligent management system compares the actual treatment costs in the medical insurance settlement entity with the expected range of costs. If the actual treatment costs are within the expected range of costs, that is, the medical insurance settlement entity meets the reasonableness of treatment costs. Therefore, it can be understood that the medical insurance settlement entity at this time meets the reasonableness of treatment methods, reasonableness of treatment dosage, reasonableness of reimbursement scope, and reasonableness of treatment costs. Therefore, the medical insurance intelligent management system directly determines that the entity verification result is in compliance with reasonableness. Continuing with the above example, the actual treatment cost of the medical insurance settlement entity for hospitalization for pneumonia is 24,000,000 yuan, which is within the expected range of [23,000,000, 25,593,750] yuan. The medical insurance intelligent management system determines that the entity verification result is in compliance with reasonableness.

[0100] In step 205544, if the actual treatment cost is not within the expected cost range, a cost deviation path set is obtained. The expected cost value of the cost deviation path in the cost deviation path set intersects with an interval centered on the actual treatment cost and having a preset error cost as a radius.

[0101] Furthermore, if the actual treatment cost is not within the expected cost range, the medical insurance intelligent management system will obtain a set of cost deviation paths, wherein the cost deviation path in the cost deviation path set refers to an entity path whose expected cost value intersects with an interval centered on the actual treatment cost and with a preset error cost as a radius. Therefore, the medical insurance intelligent management system filters out qualified paths by traversing the expected cost values ​​of all entity paths to form a cost deviation path set. Continuing with the above embodiment, if the actual treatment cost is 26,000,000 yuan, which exceeds the expected cost range of [23,000,000, 25,593,750] yuan, and the preset error cost is 1,000,000 yuan, the interval centered on 26,000,000 yuan and with a radius of 1,000,000 yuan is [25,000,000, 27,000,000] yuan. After traversing all entity paths, it is found that there is a path with an expected cost value of 25,800,000 yuan. Within this interval, this path is included in the cost deviation path set.

[0102] In step 205545, if the number of cost deviation paths in the cost deviation path set is less than a preset number threshold, the entity verification result is determined to be reasonable.

[0103] Furthermore, the medical insurance intelligent management system compares the number of cost deviation paths in the cost deviation path set with a preset number threshold. If the number of cost deviation paths is less than the preset number threshold, the medical insurance intelligent management system determines that the entity verification result complies with rationality; otherwise, the entity verification result is determined to be inconsistent with rationality. In this embodiment of the present application, the preset number threshold is 1.

[0104] Therefore, it can be understood that as long as the medical insurance settlement entity does not comply with at least one of the rationality of treatment methods, rationality of treatment dosage, rationality of reimbursement scope and rationality of treatment costs, the medical insurance intelligent management system will judge the entity verification result of the medical insurance settlement entity as not meeting rationality.

[0105] The embodiment of the present invention analyzes the rationality of treatment costs through entity paths and cost-related nodes and multiple possible cost-related paths. Therefore, it can scientifically and comprehensively verify the rationality of treatment costs of medical insurance settlement entities, reduce misjudgments due to special circumstances or complex business logic, and thus accurately verify the rationality of the business in the medical insurance settlement list data, thereby being able to quickly respond to changes in medical insurance settlement rules, improve the efficiency and accuracy of medical insurance settlement, and ensure the healthy and stable operation of the medical insurance system.

[0106] In one embodiment, steps 301 to 304 are described as follows:

[0107] Step 301: Entity-associate the first entity attribute with the second entity attribute to determine a candidate reimbursement rule in the medical insurance reimbursement rule. The second entity attribute of the candidate reimbursement rule includes at least one entity attribute in the first entity attribute.

[0108] Optionally, the medical insurance intelligent management system performs an entity association operation on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph. It then traverses all medical insurance reimbursement rules and checks whether the second entity attribute of each rule contains at least one of the first entity attributes. If this condition is met, the medical insurance reimbursement rule is included in the candidate reimbursement rule set.

[0109] For the medical insurance settlement entity for continued hospitalization for pneumonia, the first entity attributes include the disease "pneumonia," the treatment method "hospitalization," and the medication "cefotaxime sodium." The medical insurance reimbursement rules in the medical insurance knowledge graph include: Rule A, "For hospitalization for pneumonia using antibiotics listed in the catalog, the reimbursement rate is 80%," whose second entity attributes include "pneumonia," "hospitalization," and "antibiotics listed in the catalog." Rule B, "For general hospitalization, the reimbursement rate is 70%," whose second entity attribute includes "hospitalization." Rule C, "For outpatient treatment of colds using specific medications, the reimbursement rate is 60%," whose second entity attributes include "colds," "outpatient treatment," and "specific medications." A comparison of the medical insurance intelligent management system revealed that the second entity attributes of Rules A and B contain at least one of the first entity attributes (such as "hospitalization"), while Rule C does not. Therefore, Rules A and B are identified as candidate reimbursement rules.

[0110] Step 302 : Entity mapping is performed based on the second entity attribute and the first entity attribute of each rule in the candidate reimbursement rules to obtain a target entity attribute that matches the first entity attribute in each rule.

[0111] Furthermore, for each candidate reimbursement rule, the medical insurance intelligent management system performs entity mapping on its second entity attribute and the first entity attribute of the medical insurance settlement entity, checks each attribute in the second entity attribute of the candidate reimbursement rule one by one, determines whether it matches the attribute in the first entity attribute, and determines the successfully matched attribute as the target entity attribute, wherein the target entity attribute reflects the degree of correlation between the candidate reimbursement rule and the actual situation of the current medical insurance settlement entity.

[0112] Continuing with the above embodiment, for candidate reimbursement rule A, its second entity attribute "pneumonia" matches "pneumonia" in the first entity attribute of the medical insurance settlement entity, "hospitalization" matches, and "antibiotics in the catalogue" matches "cefotaxime sodium (an antibiotic in the catalogue)", so the target entity attributes of rule A are "pneumonia", "hospitalization", and "antibiotics in the catalogue"; for candidate reimbursement rule B, its second entity attribute "hospitalization" matches "hospitalization" in the first entity attribute of the medical insurance settlement entity, and the other attributes do not match, so the target entity attribute of rule B is "hospitalization".

[0113] Step 303 : Based on the attribute inclusion relationship and attribute priority between the target entity attributes of each rule, the rule priority of each rule is determined, and the rule with a higher priority than the preset priority among the candidate reimbursement rules is determined as the target reimbursement rule.

[0114] Furthermore, the medical insurance intelligent management system analyzes the attribute inclusion relationship and preset attribute priority between the target entity attributes of each candidate reimbursement rule, wherein the attribute inclusion relationship refers to whether the target entity attribute of one rule completely includes the target entity attribute of another rule; the attribute priority is pre-set in the medical insurance knowledge graph, and different attributes have different priorities, for example, the disease type attribute has a higher priority than the treatment method attribute. Optionally, the embodiment of the present invention determines the rule priority according to the following logic: if the target entity attribute of one rule completely includes the target entity attribute of another rule, and there is no attribute with a higher priority in the included rule, the rule priority of the inclusion relationship is higher; if there is no inclusion relationship, the rule priority of the rule with the higher priority attribute is higher based on the comparison of the attribute with the highest priority in the target entity attributes. A preset priority is set, and the medical insurance intelligent management system determines the rule with a higher priority than the preset priority in the candidate reimbursement rules as the target reimbursement rule.

[0115] Continuing with the above example, for rules A and B, the target entity attributes "pneumonia", "hospitalization", and "antibiotics in the catalog" of rule A completely include the target entity attribute "hospitalization" of rule B, and there is no attribute with a higher priority in rule B (for example, the disease type attribute has a higher priority than the treatment method attribute), so rule A has a higher priority than rule B. The preset priority is set to medium, and the priority of rule A is higher than the preset priority, so rule A is determined as the target reimbursement rule.

[0116] Step 304: Determine settlement reimbursement rules based on the target reimbursement rules.

[0117] Furthermore, the medical insurance intelligent management system determines the settlement and reimbursement rules based on the target reimbursement rules, as specifically described in steps 3041 to 3044 .

[0118] The embodiments of the present invention can accurately match the most applicable reimbursement rules for medical insurance settlement entities based on complex entity attribute relationships and priority logic, effectively handle the diversity and complexity of medical insurance reimbursement rules, ensure that complex and changeable rules can be executed in an orderly manner in actual settlement, avoid rule conflicts, ensure that medical insurance funds are reimbursed according to reasonable and accurate rules, and improve the efficiency and accuracy of medical insurance settlement.

[0119] In one embodiment, steps 3041 to 3044 are described as follows:

[0120] Step 3041: If the number of rules in the target reimbursement rule is less than a preset number threshold, the target reimbursement rule is determined as a settlement reimbursement rule.

[0121] Optionally, the medical insurance intelligent management system counts the number of rules in the target reimbursement rules and compares it with a preset number threshold, where the preset number threshold in the embodiment of the present invention is 2. If the number of rules in the target reimbursement rules is less than the preset number threshold, it means that there is only one rule in the currently screened target reimbursement rules. Therefore, the medical insurance intelligent management system directly determines the target reimbursement rule as the settlement reimbursement rule.

[0122] Continuing with the case of hospitalization for pneumonia, for example, the target reimbursement rule only has Rule A, "For hospitalization for pneumonia and the use of antibiotics in the catalogue, the reimbursement rate is 80%." Therefore, the medical insurance intelligent management system directly determines Rule A as the settlement and reimbursement rule for the medical insurance settlement entity.

[0123] In step 3042, if the number of rules in the target reimbursement rules is greater than or equal to the preset number threshold, then for any first reimbursement rule and second reimbursement rule in the target reimbursement rules, if the entity attributes of the first reimbursement rule and the second reimbursement rule overlap, and the first reimbursement rule and the second reimbursement rule are different rules, then the first reimbursement rule and the second reimbursement rule are determined to be conflicting rules.

[0124] Furthermore, if the number of rules in the target reimbursement rules is greater than or equal to a preset number threshold, any two rules in the target reimbursement rules (the first reimbursement rule and the second reimbursement rule) are analyzed and the entity attributes of the two rules are compared. If there is an overlap in their entity attributes and the two rules belong to different rules (that is, the rule contents are not exactly the same), the two rules are determined to be conflicting rules.

[0125] Continuing with the above example, there are three target reimbursement rules: Rule A: "For hospitalization for pneumonia using antibiotics from the catalog, the reimbursement rate is 80%," Rule B: "For pneumonia treatment using drugs from the catalog, the reimbursement rate is 75%," and Rule C: "For hospitalization using antibiotics from the catalog, the reimbursement rate is 70%." The preset quantity threshold is 2. An analysis of Rules A and B reveals that they both contain overlapping entity attributes, such as "pneumonia" and "drugs from the catalog (antibiotics are included in the drug category)," and differ in their content. Therefore, Rules A and B are identified as conflicting rules. Similarly, Rules A and C, and Rules B and C, also have overlapping entity attributes and are different rules, and are therefore identified as conflicting rules.

[0126] In step 3043, the first target rule with the highest priority among the conflicting rules is retained in the target reimbursement rule, and the second target rule other than the first target rule is eliminated to obtain a resolved rule.

[0127] Furthermore, for the conflicting rule set, the medical insurance intelligent management system processes it according to the rule priority (determined in step 303), finds the rule with the highest rule priority among the conflicting rules, sets it as the first target rule, and retains the rule; at the same time, removes other rules except the first target rule (set as the second target rule), thereby obtaining the resolved rule. Continuing in the above-mentioned conflicting rule set containing rule A, rule B, and rule C, for example, the rule priority determined in step 303 is rule A>rule B>rule C. The medical insurance intelligent management system determines rule A as the first target rule and retains it, removes rules B and C as the second target rules, and obtains rule A as the resolved rule.

[0128] In step 3044, if the number of rules in the resolved rules is less than the preset threshold, the resolved rules are determined as settlement and reimbursement rules. If the number of rules in the resolved rules is greater than or equal to the preset threshold, the rule containing the most first entity attributes in the resolved rules is determined as the settlement and reimbursement rule.

[0129] Furthermore, the medical insurance intelligent management system counts the number of rules in the resolved rule set and compares it with a preset threshold. If the number of rules in the resolved rule set is less than the preset threshold, it indicates that the rules are relatively clear after conflict resolution, and the resolved rule is directly determined as the settlement and reimbursement rule.

[0130] Furthermore, if the number of rules in the resolved rules is greater than or equal to a preset threshold, the medical insurance intelligent management system further analyzes the resolved rules, finds out the rule containing the most first entity attributes of the medical insurance settlement entity, and determines it as the settlement and reimbursement rule.

[0131] Continuing with the above example, if the only resolved rule obtained after step 3043 is Rule A, the number of resolved rules is 1, and Rule A is determined as the settlement and reimbursement rule. If the resolved rules include Rule A, "For hospitalization for pneumonia and the use of antibiotics in the catalog, the reimbursement rate is 80%," and Rule D, "For hospitalization for pneumonia, the reimbursement rate is 70%," and the preset number threshold is 2, the number of resolved rules is 2, which is equal to the preset number threshold. The first entity attributes of the medical insurance settlement entity include "pneumonia," "hospitalization," and "cefotaxime sodium." Rule A contains 3 first entity attributes, and Rule D contains 2 first entity attributes. Rule A is determined as the settlement and reimbursement rule.

[0132] The embodiments of the present invention can effectively handle complex situations such as excessive numbers and rule conflicts that may exist in the target reimbursement rules, ensure that the final settlement and reimbursement rules are unique and reasonable, avoid reimbursement confusion caused by unclear or conflicting rules, and thus adapt to the diversity and complexity of medical insurance reimbursement rules, quickly respond to changes in medical insurance settlement rules, and improve the efficiency and accuracy of medical insurance settlement.

[0133] Furthermore, the medical insurance settlement list intelligent management system based on knowledge graph provided by the present invention is described below. The medical insurance settlement list intelligent management system based on knowledge graph described below and the medical insurance settlement list intelligent management method based on knowledge graph described above can be referenced to each other.

[0134] Optional, see Figure 2 , Figure 2 This is a schematic diagram of the structure of the medical insurance settlement list intelligent management system based on the knowledge graph provided by the present invention. The medical insurance settlement list intelligent management system based on the knowledge graph includes:

[0135] The settlement entity matching module 210 is used to parse the acquired medical insurance settlement list data to obtain business keywords, and associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity;

[0136] Entity verification module 220 is used to verify the medical insurance settlement entity based on the medical insurance knowledge graph and obtain the entity verification result; the verification includes the rationality verification of the treatment method, the rationality verification of the treatment dosage and the rationality verification of the reimbursement scope;

[0137] The reimbursement rule matching module 230 is configured to perform a priority logic match based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rule of the medical insurance settlement entity if the entity verification result meets the rationality requirement;

[0138] The medical insurance list settlement module 240 is used to determine the medical insurance settlement reimbursement ratio based on the settlement and reimbursement rules, and to determine the medical insurance settlement reimbursement amount based on the medical insurance settlement reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

[0139] The embodiment of the present invention performs entity matching and verification of the rationality of treatment methods, treatment dosage, reimbursement scope and treatment costs through the medical insurance knowledge graph and the medical insurance settlement list data, so that the rationality of the business in the medical insurance settlement list data can be accurately verified, and then priority logic judgment is performed through entity attributes and the medical insurance knowledge graph to ensure that complex and changeable rules can be executed in an orderly manner in actual settlement to avoid rule conflicts, and then medical insurance reimbursement is performed according to the medical insurance settlement reimbursement ratio determined by the settlement and reimbursement rules. Therefore, no matter how the medical insurance settlement rules change, the medical insurance settlement list can be verified for rationality, reimbursement rules can be matched, reimbursement ratios can be determined and reimbursement amounts can be settled through the medical insurance knowledge graph. The entire process does not require a large amount of manual intervention, can quickly respond to changes in medical insurance settlement rules, and improves the efficiency and accuracy of medical insurance settlement.

[0140] See also Figure 3 , Figure 3 This is a diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0141] Parse the acquired medical insurance settlement list data to obtain business keywords, and then associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity;

[0142] Verify the medical insurance settlement entity based on the medical insurance knowledge graph and obtain the entity verification result; the verification includes the treatment method, treatment dosage, reimbursement scope and the rationality of treatment costs;

[0143] If the entity verification result is reasonable, priority logic matching is performed based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rules of the medical insurance settlement entity;

[0144] The medical insurance settlement reimbursement ratio is determined based on the settlement and reimbursement rules, and the medical insurance settlement reimbursement amount is determined based on the medical insurance settlement reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

[0145] See also Figure 4 , Figure 4 Detailed description of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, the following steps are implemented:

[0146] Parse the acquired medical insurance settlement list data to obtain business keywords, and then associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity;

[0147] Verify the medical insurance settlement entity based on the medical insurance knowledge graph and obtain the entity verification result; the verification includes the treatment method, treatment dosage, reimbursement scope and the rationality of treatment costs;

[0148] If the entity verification result is reasonable, priority logic matching is performed based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rules of the medical insurance settlement entity;

[0149] The medical insurance settlement reimbursement ratio is determined based on the settlement and reimbursement rules, and the medical insurance settlement reimbursement amount is determined based on the medical insurance settlement reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

[0150] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the medical insurance settlement list intelligent management method based on the knowledge graph provided by the above methods, which includes:

[0151] Parse the acquired medical insurance settlement list data to obtain business keywords, and then associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity;

[0152] Verify the medical insurance settlement entity based on the medical insurance knowledge graph and obtain the entity verification result; the verification includes the treatment method, treatment dosage, reimbursement scope and the rationality of treatment costs;

[0153] If the entity verification result is reasonable, priority logic matching is performed based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rules of the medical insurance settlement entity;

[0154] The medical insurance settlement reimbursement ratio is determined based on the settlement and reimbursement rules, and the medical insurance settlement reimbursement amount is determined based on the medical insurance settlement reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

[0155] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0156] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0157] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for intelligent management of medical insurance settlement lists based on knowledge graph, characterized in that: include: Parse the acquired medical insurance settlement list data to obtain business keywords, and associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity; Verify the medical insurance settlement entity based on the medical insurance knowledge graph to obtain an entity verification result; the verification includes verification of treatment methods, treatment dosage, reimbursement scope and rationality of treatment costs; If the entity verification result is reasonable, priority logic matching is performed based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rule of the medical insurance settlement entity; The medical insurance settlement and reimbursement ratio is determined based on the settlement and reimbursement rules, and the medical insurance settlement and reimbursement amount is determined based on the medical insurance settlement and reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

2. The medical insurance settlement list intelligent management method based on knowledge graph according to claim 1 is characterized in that: The verifying the medical insurance settlement entity based on the medical insurance knowledge graph to obtain an entity verification result includes: If there is no direct relationship between any first target entity and any second target entity in the medical insurance settlement entity in the medical insurance knowledge graph, then the path traversal is performed in the medical insurance knowledge graph with a preset step length with the first target entity and the second target entity as endpoints to obtain an initial indirect path, and the indirect association mode of the medical insurance business logic of each initial indirect path is determined to determine the target indirect path; Common associated entities whose occurrence frequency of each entity in the target indirect path is greater than a preset frequency threshold; Determining a first scene matching strength and a second scene matching strength based on matching relationships between the entity type of the common associated entity and the entity scenes of the first target entity and the second target entity, and determining a first entity association strength and a second entity association strength based on entity distances between the common associated entity and the first target entity and the second target entity, respectively; If the first scenario matching strength and the second scenario matching strength are both greater than a preset matching strength threshold, and the first entity association strength and the second entity association strength are both less than or equal to a preset association strength threshold, then it is determined that the medical insurance settlement entity meets the rationality of the treatment method; otherwise, it does not meet the requirements; If the medical insurance settlement entity meets the rationality of the treatment method, the rationality of the treatment dosage of the medical insurance settlement entity is verified based on the medical insurance knowledge graph to obtain the entity verification result.

3. The medical insurance settlement list intelligent management method based on knowledge graph according to claim 2 is characterized in that: The rationality verification of treatment dosage of the medical insurance settlement entity based on the medical insurance knowledge graph is performed to obtain the entity verification result, including: Constructing a local association network based on the nodes and node edges related to the first target entity and the second target entity in the medical insurance knowledge graph, and filtering the nodes and node edges related to the treatment dosage in the local association network to obtain actual treatment dosage data; Determine, based on the medical insurance knowledge graph, a standard treatment dosage range in the treatment scenario where the first target entity and the second target entity are located, and determine initial treatment dosage difference data based on the actual treatment dosage data and the standard treatment dosage range; Based on the initial treatment dosage difference data, influencing factors are traversed in the medical insurance knowledge graph to obtain dosage difference correlation factors, and the initial treatment dosage difference data is corrected based on the dosage difference correlation factors to obtain target treatment dosage difference data; the dosage difference correlation factors include patient characteristic factors and treatment environment factors; If the target treatment dosage difference data is within the dosage difference threshold range, it is determined that the medical insurance settlement entity meets the treatment dosage rationality; otherwise, it does not meet the requirements; If the medical insurance settlement entity meets the rationality of treatment dosage, the rationality of the reimbursement scope of the medical insurance settlement entity is verified based on the medical insurance knowledge graph to obtain the entity verification result.

4. The medical insurance settlement list intelligent management method based on knowledge graph according to claim 3 is characterized in that: The rationality verification of the reimbursement scope of the medical insurance settlement entity based on the medical insurance knowledge graph is performed to obtain the entity verification result, including: Extracting reimbursement scope rules of the first target entity and the second target entity according to the local association network; the reimbursement scope rules include reimbursable items, reimbursement process and reimbursement additional conditions; Determining, based on the medical insurance knowledge graph, whether the first target entity and the second target entity belong to entity nodes in the reimbursable item, and determining, based on the medical insurance knowledge graph, whether the first target entity and the second target entity belong to entity nodes in the reimbursement process, and determining, based on the medical insurance knowledge graph, whether the first target entity and the second target entity belong to entity nodes in the reimbursement additional conditions; If the first target entity and the second target entity belong to the nodes in the reimbursable items, the reimbursement process and / or the additional reimbursement conditions, then the medical insurance settlement entity is determined to meet the rationality of the reimbursement scope; or if the first target entity or the second target entity belongs to the nodes in the reimbursable items, the reimbursement process and / or the additional reimbursement conditions, then the first target entity or the second target entity is determined to meet the rationality of the reimbursement scope; otherwise, it does not meet the requirements; If the medical insurance settlement entity meets the rationality of the treatment method, or the first target entity or the second target entity meets the rationality of the reimbursement scope, the rationality of the treatment cost of the medical insurance settlement entity is verified based on the medical insurance knowledge graph to obtain the entity verification result.

5. The medical insurance settlement list intelligent management method based on knowledge graph according to claim 4 is characterized in that: The rationality of treatment expenses of the medical insurance settlement entity is verified based on the medical insurance knowledge graph to obtain the entity verification result, including: Determine an entity path between the first target entity and the second target entity based on the medical insurance knowledge graph, and determine a path node related to treatment costs in the entity path; Determine the expected cost value of each entity path based on the cost standard range of the path nodes in the medical insurance knowledge graph and the impact coefficient of the association relationship between the path nodes on the cost, and determine the expected cost range of the medical insurance settlement entity based on the expected cost value of each entity path; If the actual treatment costs in the medical insurance settlement entity are within the expected cost range, the entity verification result is determined to be reasonable; or, If the actual treatment cost is not within the expected cost range, a cost deviation path set is obtained; the expected cost value of the cost deviation path in the cost deviation path set intersects with an interval centered on the actual treatment cost and with a preset error cost as a radius; If the number of cost deviation paths in the cost deviation path set is less than a preset number threshold, the entity verification result is determined to be reasonable.

6. The method for intelligent management of medical insurance settlement lists based on knowledge graph according to any one of claims 1 to 5, characterized in that: The determining the settlement and reimbursement rules of the medical insurance settlement entity by performing priority logic matching based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rules in the medical insurance knowledge graph includes: Performing entity association on the first entity attribute and the second entity attribute to determine a candidate reimbursement rule in the medical insurance reimbursement rule; the second entity attribute of the candidate reimbursement rule includes at least one entity attribute of the first entity attribute; Performing entity mapping based on the second entity attribute of each rule in the candidate reimbursement rules and the first entity attribute to obtain a target entity attribute in each rule that matches the first entity attribute; Determine the rule priority of each rule based on the attribute inclusion relationship and attribute priority between the target entity attributes of each rule, and determine the rule with a rule priority higher than the preset priority among the candidate reimbursement rules as the target reimbursement rule; The settlement reimbursement rule is determined based on the target reimbursement rule.

7. The method for intelligent management of medical insurance settlement list based on knowledge graph according to claim 6 is characterized in that: The determining the settlement reimbursement rule based on the target reimbursement rule includes: If the number of rules in the target reimbursement rule is less than a preset number threshold, the target reimbursement rule is determined as the settlement reimbursement rule; or, If the number of rules in the target reimbursement rules is greater than or equal to the preset number threshold, then for any first reimbursement rule and second reimbursement rule in the target reimbursement rules, if the entity attributes of the first reimbursement rule and the second reimbursement rule overlap, and the first reimbursement rule and the second reimbursement rule are different rules, then the first reimbursement rule and the second reimbursement rule are determined to be conflicting rules; retaining a first target rule with the highest rule priority among the conflicting rules in the target reimbursement rule, and eliminating a second target rule other than the first target rule to obtain a resolved rule; If the number of rules in the resolved rules is less than the preset number threshold, the resolved rules are determined as the settlement and reimbursement rules; if the number of rules in the resolved rules is greater than or equal to the preset number threshold, the rule in the resolved rules that includes the most first entity attributes is determined as the settlement and reimbursement rules.

8. An intelligent management system for medical insurance settlement list based on knowledge graph, characterized by: Applicable to the medical insurance settlement list intelligent management method based on knowledge graph as described in any one of claims 1 to 7; The medical insurance settlement list intelligent management system based on knowledge graph includes: The settlement entity matching module is used to parse the acquired medical insurance settlement list data to obtain business keywords, and then associate and match the business keywords in the pre-built medical insurance knowledge graph to obtain the medical insurance settlement entity; An entity verification module is used to verify the medical insurance settlement entity based on the medical insurance knowledge graph to obtain an entity verification result; the verification includes the rationality verification of the treatment method, the rationality verification of the treatment dosage, and the rationality verification of the reimbursement scope; A reimbursement rule matching module is configured to, if the entity verification result conforms to rationality, perform priority logic matching based on the first entity attribute of the medical insurance settlement entity and the second entity attribute of the medical insurance reimbursement rule in the medical insurance knowledge graph to determine the settlement and reimbursement rule of the medical insurance settlement entity; The medical insurance list settlement module is used to determine the medical insurance settlement reimbursement ratio based on the settlement and reimbursement rules, and to determine the medical insurance settlement reimbursement amount based on the medical insurance settlement and reimbursement ratio and the actual settlement amount of the medical insurance settlement entity.

9. An electronic device comprising: Memory for storing computer software programs; A processor, used to read and execute the computer software program, characterized in that when the processor executes the computer software program, it implements the medical insurance settlement list intelligent management method based on the knowledge graph as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing a computer software program, wherein: When the computer software program is executed by the processor, the intelligent management method for medical insurance settlement list based on knowledge graph as described in any one of claims 1 to 7 is implemented.

Images