Information recommendation method and device, computer equipment and computer readable storage medium

Abstract

The invention discloses an information recommendation method and device, computer equipment and a computer readable storage medium, relates to the field of computer networks, and aims to determine hospitals with low suitability and high compensation and eliminate the hospitals so as to recommend the hospitals according to the popularity, so that the medical suitability requirement can be met, and the compensation amount and the compensation risk can be reduced. The method comprises the following steps: acquiring a disease name and a doctor-seeing province and city name uploaded by a user based on a terminal held by the user, and querying a plurality of hospitals associated with the doctor-seeing province and city name; determining an adaptation index, a popularity index and a compensation label of each hospital in the plurality of hospitals for the disease name; inputting the disease name, the adaptation index corresponding to each hospital, the popularity index and the compensation label into a pre-trained elimination model, and identifying a to-be-eliminated hospital in the plurality of hospitals based on the elimination model; and obtaining an information recommendation result which is output by the elimination model and is generated based on the to-be-eliminated hospital, and sending the information recommendation result to a terminal held by the user.

Description

Technical Field

[0001] The present application relates to the fields of computer networks and medical health, and in particular to an information recommendation method, apparatus, computer equipment, and computer-readable storage medium. Background Art

[0002] With the development of computer network technology, recommendation, as a technical means to solve information overload and tap users' potential needs, plays an important role in many fields.

[0003] In the related technology, target data is recommended by eliminating unreasonable data, which is applicable to many products. For example, some consultation-related software of current insurance companies will guide customers in the medical treatment stage and recommend hospitals for treatment. However, the applicant realizes that the currently recommended hospitals are only recommended and guided to customers based on the popularity of the hospitals. The basis for recommendation is relatively single, which often leads to large expenses for the insured to receive medical treatment in the recommended hospitals, causing a sharp increase in the amount of compensation, resulting in the problem of low accuracy of the information recommendation results. Summary of the invention

[0004] The present application provides an information recommendation method, device, computer equipment and medium to solve the technical problem that the recommendation basis is relatively single, resulting in the insured person incurring large expenses for medical treatment in the recommended hospital, causing a sharp increase in the amount of compensation, and resulting in low accuracy of the information recommendation results.

[0005] In a first aspect, an information recommendation method is provided, comprising:

[0006] Obtain the disease name and the name of the province and city where the patient is being treated uploaded by the user based on the terminal held by the user, and query multiple hospitals associated with the name of the province and city where the patient is being treated;

[0007] Determining the suitability index, popularity index and reimbursement label of each hospital among the plurality of hospitals for the disease name;

[0008] Input the disease name, the fitness index, popularity index and reimbursement label corresponding to each of the hospitals into a pre-trained elimination model, and identify hospitals to be eliminated from the multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding fitness index, popularity index and reimbursement label match the preset elimination criteria among the multiple hospitals;

[0009] The information recommendation result generated based on the hospital to be eliminated and output by the elimination model is obtained, and the information recommendation result is sent to the terminal held by the user.

[0010] In a second aspect, an information recommendation device is provided, comprising:

[0011] An acquisition module is used to acquire the disease name and the name of the province and city where the patient is being treated uploaded by the user based on the terminal held by the user, and query multiple hospitals associated with the name of the province and city where the patient is being treated;

[0012] A determination module, used to determine the adaptation index, popularity index and reimbursement label of each hospital among the plurality of hospitals for the disease name;

[0013] an identification module, for inputting the disease name, the fitness index, popularity index and reimbursement label corresponding to each of the hospitals into a pre-trained elimination model, and identifying hospitals to be eliminated from the multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding fitness index, popularity index and reimbursement label match the preset elimination criteria among the multiple hospitals;

[0014] The sending module is used to obtain the information recommendation result generated based on the hospital to be eliminated and output by the elimination model, and send the information recommendation result to the terminal held by the user.

[0015] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned information recommendation method when executing the computer program.

[0016] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned information recommendation method are implemented.

[0017] In the scheme implemented by the above-mentioned information recommendation method, device, computer equipment and computer-readable storage medium, it is possible to obtain the disease name and the name of the province and city where the patient is visiting uploaded by the user based on the terminal held by the user, and query multiple hospitals associated with the name of the province and city where the patient is visiting; determine the adaptation index, popularity index and reimbursement label of each hospital in multiple hospitals for the disease name; input the disease name, the adaptation index, popularity index and reimbursement label corresponding to each hospital into a pre-trained elimination model, and identify the hospitals to be eliminated from multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are the hospitals whose corresponding adaptation index, popularity index and reimbursement label are consistent with the hospital in multiple hospitals. Hospitals that match the preset elimination criteria; obtaining the information recommendation results generated by the elimination model output based on the hospitals to be eliminated, and sending the information recommendation results to the terminal held by the user. In this application, after receiving the disease name and the province and city where the user expects to visit the hospital filled in at the front end, the disease and the corresponding hospital data will be collected for aggregation, calculation and analysis to generate hospitals with lower hospital adaptability and higher compensation, and then these hospitals will be eliminated based on the recommended information. Recommendations are not only made based on the popularity of the hospital, which can not only meet the user's medical adaptability needs, but also reduce the insurance company's compensation amount and compensation risk, thereby improving the accuracy of recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only used for the purpose of illustrating the preferred embodiments and are not to be considered as limitations of the present application. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings.

[0019] Figure 1 A schematic diagram of an application environment for information recommendation provided by an embodiment of the present application is shown;

[0020] Figure 2 A schematic diagram of a method flow for information recommendation provided by an embodiment of the present application is shown;

[0021] Figure 3A A schematic diagram of another information recommendation method provided in an embodiment of the present application is shown;

[0022] Figure 3B A schematic diagram of a hospital recommendation architecture provided by an embodiment of the present application is shown;

[0023] Figure 4A A schematic diagram of the structure of information recommendation provided by an embodiment of the present application is shown;

[0024] Figure 4B A schematic diagram showing another structure of information recommendation provided by an embodiment of the present application is shown;

[0025] Figure 5 A schematic diagram of the device structure of a computer device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0027] The information recommendation method provided in the embodiment of the present application can be applied in Figure 1In the application environment, the executor of the present application is an information recommendation system, which relies on the computing power of the server to provide services to users and relies on the client to provide service programs for users corresponding to the server, and the client communicates with the server through the network. The server can receive the disease name and the name of the province and city where the patient is to be treated uploaded by the user through the client, and query multiple hospitals associated with the name of the province and city where the patient is to be treated; determine the adaptation index, popularity index and reimbursement label of each hospital in multiple hospitals for the disease name; input the disease name, the adaptation index, popularity index and reimbursement label corresponding to each hospital into a pre-trained elimination model, and identify the hospitals to be eliminated from multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding adaptation index, popularity index and reimbursement label in multiple hospitals match the preset elimination criteria; obtain the information recommendation results generated based on the hospitals to be eliminated output by the elimination model, and feed the information recommendation results back to the client. In this application, after receiving the disease name and the province and city where the patient is to be treated filled in by the user at the front end, the disease and the corresponding hospital data will be collected for aggregation, calculation and analysis to generate hospitals with lower hospital adaptability and higher reimbursement, and then these hospitals will be eliminated based on the recommended information. Recommendations are not only made based on the popularity of the hospital, which can not only meet the user's medical adaptability needs, but also reduce the insurance company's reimbursement amount and reimbursement risk, thereby improving the accuracy of recommendations. The client may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server may be an independent server, or it may provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and servers for basic cloud computing such as big data and artificial intelligence platforms. The present application is described in detail below through specific embodiments.

[0028] The present application embodiment provides an information recommendation method, such as Figure 2 As shown, the method includes:

[0029] 201. Obtain the disease name and the name of the province and city where the user is seeking medical treatment uploaded by the terminal held by the user, and query multiple hospitals associated with the name of the province and city where the user is seeking medical treatment.

[0030] In the embodiment of the present application, after the user enters the name of the disease and the name of the province and city where the hospital is expected to be treated on the front-end page, the information recommendation system obtains the name of the disease and the name of the province and city where the hospital is expected to be treated uploaded by the user based on the terminal held, and queries multiple hospitals associated with the province and city where the hospital is expected to be treated. For example, if the name of the disease uploaded by the user is diabetes and the province and city where the hospital is expected to be treated is Beijing, the information recommendation system will query multiple hospitals in Beijing after obtaining it, and eliminate hospitals with low adaptability and high compensation based on these hospitals.

[0031] 202. Determine the adaptation index, popularity index and reimbursement label for the disease name of each hospital among multiple hospitals.

[0032] In the embodiment of the present application, in order to improve the recommendation effect, it is necessary to filter out inappropriate hospitals before recommending them to users. Therefore, the information recommendation system determines the adaptation index, popularity index and compensation label of each hospital in multiple hospitals for the disease name, and filters according to the adaptation index, popularity index and compensation label, so that the recommendation results can not only meet the reasonable medical needs of the insured, but also reduce the insurance company's compensation costs. Among them, the adaptation index indicates the authority or diagnosis and treatment effect of the hospital in treating the disease. The higher the adaptation index, the better the hospital's treatment effect on the disease; the popularity index indicates the insurance company's compensation cost. The higher the popularity index, the larger the compensation amount; the compensation label includes a popular compensation label and a huge compensation label.

[0033] 203. Input the disease name, the adaptation index, popularity index and reimbursement label corresponding to each hospital into a pre-trained elimination model, and identify the hospitals to be eliminated from multiple hospitals based on the elimination model.

[0034] In an embodiment of the present application, the information recommendation system inputs the disease name, the adaptation index, popularity index and reimbursement label corresponding to each hospital into a pre-trained elimination model, and identifies the hospitals to be eliminated from multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding adaptation index, popularity index and reimbursement label among multiple hospitals match the preset elimination criteria, and the hospitals to be eliminated are hospitals with lower adaptability and higher reimbursement. These hospitals often result in poor medical results and high costs for users, and will also cause a sharp increase in the amount of reimbursement, so eliminating these hospitals and recommending them to users can improve the accuracy of information recommendation.

[0035] 204. Obtain the information recommendation result generated based on the to-be-eliminated hospital output by the elimination model, and send the information recommendation result to the terminal held by the user.

[0036] In the embodiment of the present application, the information recommendation system obtains the information recommendation results generated by the elimination model based on the hospitals to be eliminated, and sends the information recommendation results to the terminal held by the user. In this way, the information recommendation system takes into account the hospital's applicability index and cost index, which can not only meet the user's medical adaptability needs, but also reduce the insurance company's compensation amount and compensation risk, achieving a win-win result.

[0037] The method provided in the embodiment of the present application obtains the disease name and the name of the province and city where the patient is treated uploaded by the user based on the terminal held by the user, and queries multiple hospitals associated with the name of the province and city where the patient is treated; determines the adaptation index, popularity index and reimbursement label of each hospital in multiple hospitals for the disease name; inputs the disease name, the adaptation index, popularity index and reimbursement label corresponding to each hospital into a pre-trained elimination model, and identifies hospitals to be eliminated from multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding adaptation index, popularity index and reimbursement label in multiple hospitals match the preset elimination criteria; obtains The information recommendation results generated based on the hospitals to be eliminated by the elimination model output are taken, and the information recommendation results are sent to the terminal held by the user. In this application, after the user fills in the disease name and the province and city where he expects to see a doctor at the front end, the disease and the corresponding hospital data will be collected for summary, calculation and analysis to generate hospitals with lower hospital adaptability and higher compensation, and then these hospitals will be eliminated based on the recommended information. Recommendations are not only made based on the popularity of the hospital, but can also meet the user's medical adaptability needs, and can also reduce the insurance company's compensation amount and compensation risk, thereby improving the accuracy of recommendations.

[0038] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the specific implementation process of this embodiment, the embodiment of the present application provides another strategy generation method, such as Figure 3A As shown, the method includes:

[0039] 301. Obtain the disease name and the name of the province and city where the user is seeking medical treatment uploaded by the terminal held by the user, and query multiple hospitals associated with the name of the province and city where the user is seeking medical treatment.

[0040] In the embodiment of the present application, the information recommendation system obtains the disease name and the name of the province and city where the patient is being treated uploaded by the user based on the terminal held, and queries multiple hospitals associated with the name of the province and city where the patient is being treated, wherein the name of the province and city where the patient is being treated is the name of the province and city where the user expects the hospital to be treated. For example, the disease name may be diabetes, asthma, rhinitis, hypertension, gastritis, etc. The information recommendation system uses the disease name to query the hospitals associated with the province and city where the patient is being treated, and obtains 100 hospitals. In this way, the insurance company's consultation-related software can recommend hospitals to users based on the disease name and the province and city where the patient is being treated during the medical consultation process.

[0041] 302. Perform fuzzy matching on the disease name in the database to obtain the disease code corresponding to the disease name.

[0042] In an embodiment of the present application, the information recommendation system uses fuzzy matching of disease names in the database to obtain the disease code (disease_code) corresponding to the disease name. Since the disease names uploaded by users are not necessarily standard terms, errors may occur in subsequent analysis. Therefore, the information recommendation system converts the disease names entered by users into disease codes.

[0043] 303. Collect hospital information of each hospital to obtain multiple hospital information, and use the multiple hospital information to calculate and determine the adaptation index of each hospital for the disease name.

[0044] In an embodiment of the present application, the information recommendation system collects hospital information of each hospital, obtains multiple hospital information, and uses multiple hospital information to calculate and determine the fitness index (is_fit) of each hospital for the disease name. The fitness index indicates whether the hospital is authoritative in the diagnosis and treatment of the disease, and whether it has an overwhelming advantage over other hospitals.

[0045] Specifically, for each hospital, the information recommendation system performs field recognition processing on the hospital information of the hospital, and extracts the disease diagnosis and treatment information associated with the disease code from the hospital information, wherein the disease diagnosis and treatment information indicates the diagnosis and treatment effect of the hospital on the disease name, and the diagnosis and treatment effect and authority of the hospital can be determined through the disease diagnosis and treatment information, and then the adaptation index is determined. In this way, the information recommendation system performs field recognition processing on the hospital information of each hospital respectively, and obtains the disease diagnosis and treatment information of each hospital. Then, the information recommendation system sorts the multiple hospitals in the order of the diagnosis and treatment effect indicated by the disease diagnosis and treatment information of each hospital from high to low, and obtains the first sorting result. Subsequently, the information recommendation system obtains multiple adaptability parameters included in the adaptation rule of the adaptation index, and uses multiple adaptability parameters to generate and mark the adaptation index for each hospital in the first sorting result in turn, and obtains the adaptation index corresponding to each hospital, wherein the adaptability parameter is used to generate the adaptation index. In the first sorting result, the adaptation index of the hospital ranked first is the largest, and the adaptation index gradually decreases with the first sorting result. In this way, the information recommendation system can determine the hospital that meets the user's medical adaptability needs through the adaptation index, thereby improving the information recommendation effect.

[0046] 304. Read the claims data of each hospital in the database to obtain a plurality of claims data, and use the plurality of claims data to calculate and determine the popularity index of each hospital for the disease name.

[0047] In an embodiment of the present application, the information recommendation system reads the claims data of each hospital in the database, obtains a plurality of claims data, and uses the plurality of claims data to calculate and determine the popularity index of each hospital for the disease name.

[0048] Specifically, the information recommendation system reads the compensation amount corresponding to the disease name in the claims data of each hospital. Next, the information recommendation system sorts multiple hospitals in order of compensation amount from large to small to obtain a second sorting result. Then, the information recommendation system obtains the hot index adaptation rule, and refers to the hot index adaptation rule and the second sorting result to calculate the corresponding hot index for each hospital, where the hot index ranges from 0 to 1, and the larger the hot index, the larger the compensation amount. In this way, the information recommendation system can determine hospitals with lower compensation amounts through the hot index, thereby improving the information recommendation effect.

[0049] 305. Set up a compensation label for each hospital.

[0050] In an embodiment of the present application, the information recommendation system reads the number of compensations corresponding to the disease name in the claims data of each hospital to obtain the number of compensations of each hospital. Next, the information recommendation system obtains the preset compensation amount, extracts multiple target hospitals whose compensation amounts are greater than or equal to the preset compensation amount from multiple hospitals, and uses the huge compensation label (is_lager) as the compensation label of multiple target hospitals and marks them. Then, the information recommendation system obtains the preset number of compensations, extracts multiple designated hospitals whose compensation times are greater than or equal to the preset number of compensations from multiple hospitals, and uses the hot compensation label (is_hot) as the compensation label of multiple designated hospitals and marks them. By labeling multiple hospitals with compensation labels, the information recommendation system can reduce the insurance company's compensation amount and compensation risk when recommending hospitals.

[0051] 306. Obtain claim sample information and use the claim sample information to build a elimination model.

[0052] In an embodiment of the present application, the information recommendation system obtains claim sample information, which is data related to high-risk claim hospitals. These data may include the hospital's claim records, patient information, medical service types, etc. Next, multiple disease names, disease codes corresponding to each disease name, and major disease codes corresponding to each disease name are read in the claim sample information, and a disease information sample table is generated using multiple disease names, disease codes corresponding to each disease name, and major disease codes corresponding to each disease name. For example, the disease information table contains disease codes, disease names, and major disease codes. Because there are too many types of diseases, diseases need to be classified and processed. For example, coughs and sore throats can be classified as respiratory infections.

[0053] Subsequently, the information recommendation system reads the hospital names of multiple hospitals and the cities to which each hospital belongs in the claim sample information, determines the adaptation index, popularity index and compensation label of each hospital for each disease name, and uses the hospital names of multiple hospitals, the cities to which each hospital belongs, and the adaptation index, popularity index and compensation label of each hospital for each disease name to generate a hospital information sample table. For example, the hospital information table contains the name of the hospital, the city where it is located, the major disease category, whether it is a popular city, and whether it is a popular compensation. These data can be obtained from the claim amount data information. If a hospital in a certain city pays for a certain disease more frequently and the compensation amount is higher, it can be considered a popular city and popular compensation.

[0054] Then, the information recommendation system performs feature engineering calculations on the disease information sample table and the hospital information sample table to obtain the hospital score matrix. Then, the information recommendation system obtains a matrix decomposition algorithm, and uses the matrix decomposition algorithm to decompose the hospital score matrix into a hospital feature matrix and a disease feature matrix, and uses the product of the hospital feature matrix and the disease feature matrix as the compensation feature. For example, the extracted feature is that the compensation amount of a certain disease exceeds a certain proportion of the insured amount, such as more than 20%; the number of deduplicated data in units of patients for the same disease in the same hospital within a certain period of time, and the number of compensations is 2 or more. Then, the matrix decomposition algorithm is used to explore the potential connection between the disease compensation ratio, the number of compensations, and the hospital and city, and the hospital score matrix is ​​decomposed into a hospital feature matrix and a disease feature matrix. The popular compensation features are obtained by multiplying the hospital feature matrix and the disease feature matrix, where the compensation feature is represented by the letter r.

[0055] Finally, the information recommendation system uses the compensation feature for model training to obtain a pre-trained elimination model. It should be noted that the value of the compensation feature is between -1 and +1, that is, -1≤r≤+1.

[0056] Its properties are as follows:

[0057] When r>0, it means the two variables are positively correlated, and when r<0, the two variables are negatively correlated.

[0058] When |r|=1, it means that the two variables are completely linearly correlated, that is, a functional relationship.

[0059] When r=0, it means there is no linear correlation between the two variables.

[0060] When 0<|r|<1, it means that there is a certain degree of linear correlation between the two variables. The closer |r| is to 1, the closer the linear relationship between the two variables is; the closer |r| is to 0, the weaker the linear correlation between the two variables is.

[0061] Based on the above process, the information recommendation system uses machine learning algorithms to explore the potential connection between diseases and popular hospitals and recommend hospitals for target users. In addition, during the algorithm training process, the algorithm model parameters are adjusted, such as hospital suitability and whether popular diseases with high reimbursement are included, to continuously optimize the performance of the elimination model.

[0062] 307. Input the disease name, the adaptation index, popularity index and reimbursement label corresponding to each hospital into a pre-trained elimination model, and identify the hospitals to be eliminated from multiple hospitals based on the elimination model.

[0063] In an embodiment of the present application, the information recommendation system inputs the disease name, the adaptation index, popularity index and compensation label corresponding to each hospital into a pre-trained elimination model, and identifies hospitals to be eliminated from multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding adaptation index, popularity index and compensation label match the preset elimination criteria among multiple hospitals. Next, the information recommendation system determines the preset adaptation index and preset popularity index indicated by the preset elimination criteria, such as the preset adaptation index is 0.25 and the preset popularity index is 0.75. Subsequently, based on the elimination model, the information recommendation system determines the hospitals whose adaptation index is less than or equal to the preset adaptation index and whose popularity index is greater than or equal to the preset popularity index and whose compensation label is a popular compensation label and / or a huge compensation label as hospitals to be eliminated from multiple hospitals, wherein the adaptation index is less than or equal to the preset adaptation index, indicating that the treatment effect of the hospital is not high, and the popularity index is greater than or equal to the preset popularity index, indicating that the compensation amount is too high. In this way, the information recommendation system can eliminate those hospitals with low adaptability and high compensation based on the original recommendation information. It will no longer make recommendations based solely on the popularity of the hospital, thereby avoiding the problem of insufficient adaptability of the hospital and excessive and large claims caused by compensation behavior.

[0064] 308. Obtain the information recommendation result generated based on the to-be-eliminated hospital output by the elimination model, and send the information recommendation result to the terminal held by the user.

[0065] In the embodiment of the present application, the information recommendation system obtains the information recommendation results generated by the elimination model based on the hospitals to be eliminated, and sends the information recommendation results to the terminal held by the user. In this way, the information recommendation system aims to control medical expenses, eliminates hospitals with a small applicability index and a large cost index, so that the recommendation results can not only meet the reasonable medical needs of the insured, but also reduce the compensation costs of the insurance company.

[0066] like Figure 3BA hospital recommendation process shown in the figure, first the user enters the name of the disease and the province and city where the patient is being treated at the front end, and then collects the disease and the corresponding hospital data and disease data. Then summarize, calculate and analyze, and use the model to calculate the popularity of the disease to obtain the disease with a high popularity. Then, match the disease name and the province and city name to obtain the hospital with low adaptability and high compensation and provincial and municipal data information. Finally, these hospitals and provincial and municipal data information can be eliminated on the basis of the original recommendation information, so that the recommendation is no longer based solely on the popularity of the hospital, avoiding the problem of insufficient adaptability of the hospital for treatment and excessive and large claims caused by the compensation behavior. It can not only meet the user's medical adaptability needs, but also reduce the insurance company's compensation amount and compensation risk, and achieve a win-win result.

[0067] The method provided in the embodiment of the present application obtains the disease name and the name of the province and city where the patient is treated uploaded by the user based on the terminal held by the user, and queries multiple hospitals associated with the name of the province and city where the patient is treated; determines the adaptation index, popularity index and reimbursement label of each hospital in multiple hospitals for the disease name; inputs the disease name, the adaptation index, popularity index and reimbursement label corresponding to each hospital into a pre-trained elimination model, and identifies hospitals to be eliminated from multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding adaptation index, popularity index and reimbursement label in multiple hospitals match the preset elimination criteria; obtains The information recommendation results generated based on the hospitals to be eliminated by the elimination model output are taken, and the information recommendation results are sent to the terminal held by the user. In this application, after the user fills in the disease name and the province and city where he expects to see a doctor at the front end, the disease and the corresponding hospital data will be collected for summary, calculation and analysis to generate hospitals with lower hospital adaptability and higher compensation, and then these hospitals will be eliminated based on the recommended information. Recommendations are not only made based on the popularity of the hospital, but can also meet the user's medical adaptability needs, and can also reduce the insurance company's compensation amount and compensation risk, thereby improving the accuracy of recommendations.

[0068] Further, as Figure 1 For the specific implementation of the method, the present application embodiment provides an information recommendation device, which corresponds one-to-one with the information recommendation method in the above embodiment. Figure 4A As shown, the device includes: an acquisition module 401, a determination module 402, an identification module 403 and a sending module 404.

[0069] The acquisition module 401 is used to acquire the disease name and the name of the province and city where the patient is being treated uploaded by the user based on the terminal held by the user, and query multiple hospitals associated with the name of the province and city where the patient is being treated;

[0070] A determination module 402 is used to determine the adaptation index, popularity index and reimbursement label of each hospital in the plurality of hospitals for the disease name;

[0071] The identification module 403 is used to input the disease name, the fitness index, popularity index and reimbursement label corresponding to each of the hospitals into a pre-trained elimination model, and identify hospitals to be eliminated from the multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding fitness index, popularity index and reimbursement label match the preset elimination criteria among the multiple hospitals;

[0072] The sending module 404 is used to obtain the information recommendation result generated based on the hospital to be eliminated and output by the elimination model, and send the information recommendation result to the terminal held by the user.

[0073] In a specific application scenario, the determination module 402 is used to perform fuzzy matching on the disease name in the database to obtain the disease code corresponding to the disease name; collect hospital information of each of the hospitals to obtain multiple hospital information, and use the multiple hospital information to calculate and determine the adaptation index of each of the hospitals for the disease name; read the claims data of each of the hospitals in the database to obtain multiple claims data, and use the multiple claims data to calculate and determine the popularity index of each of the hospitals for the disease name, and set a payment label for each of the hospitals.

[0074] In a specific application scenario, the determination module 402 is used to perform field recognition processing on the hospital information of each of the hospitals, and extract disease diagnosis and treatment information associated with the disease code from the hospital information, wherein the disease diagnosis and treatment information indicates the diagnosis and treatment effect of the hospital on the disease name; perform field recognition processing on the hospital information of each of the hospitals respectively to obtain the disease diagnosis and treatment information of each of the hospitals; sort the multiple hospitals in order from high to low according to the diagnosis and treatment effects indicated by the disease diagnosis and treatment information of each of the hospitals, to obtain a first sorting result; obtain multiple adaptability parameters included in the adaptation rule of the adaptation index, and use the multiple adaptability parameters to generate and label the adaptation index for each of the hospitals in the first sorting result in turn, to obtain the adaptation index corresponding to each of the hospitals, wherein in the first sorting result, the adaptation index of the hospital ranked first is the largest, and the adaptation index gradually decreases with the first sorting result.

[0075] In a specific application scenario, the determination module 402 is used to read the compensation amount corresponding to the disease name in the claims data of each of the hospitals; sort the multiple hospitals in order of the compensation amount from large to small to obtain a second sorting result; obtain the popularity index adaptation rule, and refer to the popularity index adaptation rule and the second sorting result to calculate the corresponding popularity index for each of the hospitals, wherein the larger the popularity index, the larger the compensation amount.

[0076] In a specific application scenario, the determination module 402 is used to read the number of compensations corresponding to the disease name in the claims data of each of the hospitals to obtain the number of compensations of each of the hospitals; obtain a preset compensation amount, extract multiple target hospitals whose compensation amounts are greater than or equal to the preset compensation amount from the multiple hospitals, and use a huge compensation label as the compensation label of the multiple target hospitals and mark them; obtain the preset number of compensations, extract multiple designated hospitals whose compensation numbers are greater than or equal to the preset number of compensations from the multiple hospitals, and use a popular compensation label as the compensation label of the multiple designated hospitals and mark them.

[0077] In a specific application scenario, the identification module 403 is used to determine the preset adaptation index and the preset popularity index indicated by the preset elimination criteria; based on the elimination model, the hospitals whose adaptation index is less than or equal to the preset adaptation index and whose popularity index is greater than or equal to the preset popularity index and whose payment labels are popular payment labels and / or huge payment labels are determined among the multiple hospitals as the hospitals to be eliminated.

[0078] In specific application scenarios, such as Figure 4B As shown, the device also includes: a construction module 405.

[0079] Construction module 405 is used to obtain claim sample information, read multiple disease names, disease codes corresponding to each disease name, and major disease codes corresponding to each disease name in the claim sample information, and use multiple disease names, disease codes corresponding to each disease name, and major disease codes corresponding to each disease name to generate a disease information sample table; read the hospital names of multiple hospitals and the city to which each hospital belongs in the claim sample information, determine the adaptation index, popularity index and compensation label of each hospital for each disease name, and use the hospital names of the multiple hospitals, the city to which each hospital belongs, and the adaptation index, popularity index and compensation label of each hospital for each disease name to generate a hospital information sample table; perform feature engineering calculations on the disease information sample table and the hospital information sample table to obtain a hospital scoring matrix; obtain a matrix decomposition algorithm, use the matrix decomposition algorithm to decompose the hospital scoring matrix into a hospital feature matrix and a disease feature matrix, use the product of the hospital feature matrix and the disease feature matrix as the compensation feature, use the compensation feature to perform model training, and obtain the pre-trained elimination model.

[0080] The device provided in the embodiment of the present application obtains the disease name and the name of the province and city where the patient is treated uploaded by the user based on the terminal held by the user, and queries multiple hospitals associated with the name of the province and city where the patient is treated; determines the adaptation index, popularity index and reimbursement label of each hospital in multiple hospitals for the disease name; inputs the disease name, the adaptation index, popularity index and reimbursement label corresponding to each hospital into a pre-trained elimination model, and identifies hospitals to be eliminated from multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding adaptation index, popularity index and reimbursement label in multiple hospitals match the preset elimination criteria; obtains The information recommendation results generated based on the hospitals to be eliminated by the elimination model output are taken, and the information recommendation results are sent to the terminal held by the user. In this application, after the user fills in the disease name and the province and city where he expects to see a doctor at the front end, the disease and the corresponding hospital data will be collected for summary, calculation and analysis to generate hospitals with lower hospital adaptability and higher compensation, and then these hospitals will be eliminated based on the recommended information. Recommendations are not only made based on the popularity of the hospital, but can also meet the user's medical adaptability needs, and can also reduce the insurance company's compensation amount and compensation risk, thereby improving the accuracy of recommendations.

[0081] It should be noted that for other corresponding descriptions of the functional units involved in the information recommendation device provided in the embodiment of the present application, reference can be made to Figure 1 , Figure 2 and FIG. 3A to FIG. 3B The corresponding description in the above information recommendation device will not be repeated here. Each module in the above information recommendation device can be implemented in whole or in part by software, hardware and their combination. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0082] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0083] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0084] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

[0085] In an exemplary embodiment, see Figure 5 , and also provides a computer device, which includes a bus, a processor, a memory and a communication interface, and may also include an input and output interface and a display device, wherein each functional unit can communicate with each other through the bus. The memory stores a computer program, and the processor is used to execute the program stored in the memory and execute the strategy generation method in the above embodiment.

[0086] A computer-readable storage medium stores a computer program, which implements the steps of the strategy generation method when executed by a processor.

[0087] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by hardware, or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including 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 implementation scenario of the present application.

[0088] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present application.

[0089] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0090] The above application serial numbers are for description only and do not represent the advantages or disadvantages of the implementation scenarios.

[0091] The above disclosure only discloses several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by technicians in this field should fall within the scope of protection of the present application.

Claims

1. An information recommendation method, characterized in that: include: Obtain the disease name and the name of the province and city where the patient is being treated uploaded by the user based on the terminal held by the user, and query multiple hospitals associated with the name of the province and city where the patient is being treated; Determining the suitability index, popularity index and reimbursement label of each hospital among the plurality of hospitals for the disease name; Input the disease name, the fitness index, popularity index and reimbursement label corresponding to each of the hospitals into a pre-trained elimination model, and identify hospitals to be eliminated from the multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding fitness index, popularity index and reimbursement label match the preset elimination criteria among the multiple hospitals; The information recommendation result generated based on the hospital to be eliminated and output by the elimination model is obtained, and the information recommendation result is sent to the terminal held by the user.

2. The information recommendation method according to claim 1, characterized in that: The determining of the adaptation index, popularity index and reimbursement label of each hospital among the plurality of hospitals for the disease name includes: Perform fuzzy matching on the disease name in the database to obtain a disease code corresponding to the disease name; Collecting hospital information of each of the hospitals to obtain multiple hospital information, and using the multiple hospital information to calculate and determine the adaptation index of each of the hospitals for the disease name; The claim data of each hospital is read in the database to obtain a plurality of claim data, and the plurality of claim data are used to calculate and determine the popularity index of each hospital for the disease name, and a claim label is set for each hospital.

3. The information recommendation method according to claim 2, characterized in that: The step of using the information of the plurality of hospitals to calculate and determine the adaptation index of each hospital for the disease name includes: For each of the hospitals, field identification processing is performed on the hospital information of the hospital, and disease diagnosis and treatment information associated with the disease code is extracted from the hospital information, wherein the disease diagnosis and treatment information indicates the diagnosis and treatment effect of the hospital on the disease name; Performing field recognition processing on the hospital information of each of the hospitals respectively to obtain the disease diagnosis and treatment information of each of the hospitals; Sorting the multiple hospitals in descending order of the diagnosis and treatment effect indicated by the disease diagnosis and treatment information of each hospital to obtain a first sorting result; Obtain multiple adaptability parameters included in the adaptation rules of the adaptation index, and use the multiple adaptability parameters to generate and label the adaptation index for each of the hospitals in the first sorting result in turn to obtain the adaptation index corresponding to each of the hospitals, wherein the adaptation index of the hospital ranked first in the first sorting result is the largest, and the adaptation index gradually decreases with the first sorting result.

4. The information recommendation method according to claim 2, characterized in that: The method of using the plurality of claim data to calculate and determine the popularity index of each hospital for the disease name includes: Reading the compensation amount corresponding to the disease name in the claim data of each hospital; Sorting the multiple hospitals in descending order of compensation amount to obtain a second sorting result; Obtain a hot index adaptation rule, refer to the hot index adaptation rule and the second sorting result, and calculate a corresponding hot index for each of the hospitals, wherein a larger hot index indicates a larger compensation amount.

5. The information recommendation method according to claim 3, characterized in that: The step of setting a compensation label for each hospital includes: Reading the number of compensations corresponding to the disease name in the claim settlement data of each hospital to obtain the number of compensations of each hospital; Obtaining a preset compensation amount, extracting multiple target hospitals whose compensation amounts are greater than or equal to the preset compensation amount from the multiple hospitals, and marking the multiple target hospitals with huge compensation tags as compensation tags; Obtain a preset number of compensations, extract a plurality of designated hospitals whose number of compensations is greater than or equal to the preset number of compensations from the plurality of hospitals, and use popular compensation tags as compensation tags for the plurality of designated hospitals and mark them.

6. The information recommendation method according to claim 1, characterized in that: The step of identifying a hospital to be eliminated from the plurality of hospitals based on the elimination model comprises: Determining a preset adaptation index and a preset popularity index indicated by the preset rejection criterion; Based on the elimination model, hospitals whose adaptation index is less than or equal to the preset adaptation index, whose popularity index is greater than or equal to the preset popularity index, and whose payment tags are popular payment tags and / or huge payment tags are determined among the multiple hospitals as the hospitals to be eliminated.

7. The information recommendation method according to claim 1, characterized in that: Before inputting the disease name, the adaptation index, popularity index and compensation label corresponding to each hospital into the pre-trained elimination model, the method further includes: Obtaining claim sample information, reading multiple disease names, disease codes corresponding to each of the disease names, and major disease categories corresponding to each of the disease names in the claim sample information, and generating a disease information sample table using multiple disease names, disease codes corresponding to each of the disease names, and major disease categories corresponding to each of the disease names; Read the names of multiple hospitals and the cities to which each hospital belongs in the claim sample information, determine the adaptation index, popularity index and compensation label of each hospital for each disease name, and generate a hospital information sample table using the names of multiple hospitals, the cities to which each hospital belongs, and the adaptation index, popularity index and compensation label of each hospital for each disease name; Performing feature engineering calculations on the disease information sample table and the hospital information sample table to obtain a hospital scoring matrix; Obtain a matrix decomposition algorithm, use the matrix decomposition algorithm to decompose the hospital rating matrix into a hospital feature matrix and a disease feature matrix, use the product of the hospital feature matrix and the disease feature matrix as compensation features, use the compensation features to perform model training, and obtain the pre-trained elimination model.

8. An information recommendation device, characterized in that: include: An acquisition module is used to acquire the disease name and the name of the province and city where the patient is being treated uploaded by the user based on the terminal held by the user, and query multiple hospitals associated with the name of the province and city where the patient is being treated; A determination module, used to determine the adaptation index, popularity index and reimbursement label of each hospital among the plurality of hospitals for the disease name; an identification module, for inputting the disease name, the fitness index, popularity index and reimbursement label corresponding to each of the hospitals into a pre-trained elimination model, and identifying hospitals to be eliminated from the multiple hospitals based on the elimination model, wherein the hospitals to be eliminated are hospitals whose corresponding fitness index, popularity index and reimbursement label match the preset elimination criteria among the multiple hospitals; The sending module is used to obtain the information recommendation result generated based on the hospital to be eliminated and output by the elimination model, and send the information recommendation result to the terminal held by the user.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the information recommendation method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the information recommendation method according to any one of claims 1 to 7 are implemented.

Images