Intelligent prescription payment system and method

Abstract

The present invention relates to the field of prescription payment technology, and in particular to an intelligent prescription payment system and method. The present invention first obtains the representative delivery time and time coefficient of each medicine to classify the medicines, and further obtains the time expansion coefficient and time contribution of each medicine in each medicine purchase record of the current user; then obtains the time weight of the current user at the time of current medicine purchase, and then combines the time coefficient of each medicine in the electronic prescription to determine the medicine purchase plan and make payment. The present invention classifies the medicines by analyzing the general time tendency of the user to purchase each medicine, and then analyzes the purchase interference effect between medicines with different time demand properties, corrects the time expansion deviation of each medicine in each purchase process, thereby accurately analyzing the user's medicine purchase tendency in the historical medicine purchase record, and then can determine a personalized medicine purchase plan for the user to balance timeliness and economy, and improve the user's payment efficiency and user experience in the prescription payment process.

Description

Technical Field

[0001] The present invention relates to the technical field of prescription payment, and in particular to an intelligent prescription payment system and method. Background Art

[0002] Smart prescription payment combines smart medical care and payment technology. After a doctor issues an electronic prescription during remote diagnosis and treatment, it can automatically generate drug purchase and payment processes. After the patient pays for the drug online, the system will provide users with drug delivery or self-pickup services. The smart prescription payment system simplifies the medical payment process through automation and intelligent means, improves the quality and efficiency of medical services, and provides users with a more convenient and transparent payment experience.

[0003] Existing prescription payment systems typically recommend purchase and payment methods for drugs in electronic prescriptions based on a single time-priority strategy or price-priority strategy. This means that the system recommends purchase and payment plans for users based on the shortest delivery time or lowest price of the drugs. However, the recommendation results based on a single strategy often fail to meet the comprehensive needs of users, causing users to adjust their purchase methods when purchasing drugs, increasing the time and decision-making costs of users when paying, and resulting in poor prescription payment results. Summary of the Invention

[0004] In order to solve the technical problem of poor prescription payment effect in the prior art, the purpose of the present invention is to provide an intelligent prescription payment system and method. The technical solutions adopted are as follows:

[0005] A smart prescription payment method, comprising:

[0006] Obtain the current user's electronic prescription and each user's purchase record for each historical prescription, wherein the purchase record includes at least the payment unit price and delivery time of each drug;

[0007] Obtaining a representative delivery time for each drug based on the delivery time of each drug in all drug purchase records; obtaining a time efficiency coefficient for each drug based on the payment unit price and the representative delivery time of each drug in each drug purchase record of the current user; classifying drugs based on the time efficiency coefficients, and obtaining a time efficiency expansion coefficient for each drug in each drug purchase record of the current user based on the time efficiency coefficient of each drug and the deviation of the delivery time from the representative delivery time of each drug category;

[0008] In each drug purchase record of the current user, the timeliness contribution of each drug is obtained based on the timeliness coefficient and the timeliness expansion coefficient of each drug, combined with the delivery time; based on the timeliness contribution of each drug in each drug purchase record of the current user, combined with the drug classification result, the timeliness weight of the current user at the time of current drug purchase is obtained; based on the timeliness weight and the timeliness coefficient of each drug in the electronic prescription, the drug purchase plan is determined and the prescription payment is made.

[0009] Furthermore, the method for obtaining the representative delivery time includes:

[0010] In all drug purchase records of all users, all the delivery times of each drug are clustered, and the delivery time corresponding to the cluster center of the largest cluster is used as the representative delivery time of the corresponding drug.

[0011] Furthermore, the method for obtaining the aging coefficient includes:

[0012] In each drug purchase record of the current user, the economic selectivity of each drug is obtained based on the deviation of the payment unit price of each drug relative to the selling unit price of the same drug in a nearby pharmacy, combined with the spatial distance between the current user and the nearby pharmacy;

[0013] The negative correlation mapping result of the mean value of the economic selectivity of each drug in all drug purchase records of the current user is used as the first timeliness parameter;

[0014] Obtaining a confidence weight of the representative delivery time for each drug based on the distance between the largest cluster corresponding to each drug and each of the remaining clusters, and weighting the negative correlation mapping results corresponding to the representative delivery time using the confidence weight to obtain a second timeliness parameter;

[0015] The first aging parameter and the second aging parameter are integrated to obtain the aging coefficient of the corresponding drug.

[0016] Furthermore, the method for obtaining the economic selectivity includes:

[0017] Take any drug in any purchase record of the current user as the target drug, select a preset number of pharmacies closest to the current user as reference pharmacies, and use the unit price of the target drug in each reference pharmacy as the comparison unit price;

[0018] The spatial distance between the current user and each reference pharmacy is used as the economic weight of the corresponding comparison unit price, the economic weight is used to weight the corresponding comparison unit price and the weighted average result is used as the reference unit price of the target drug;

[0019] According to the difference between the reference unit price and the payment unit price of the target drug, the economic selectivity of the target drug in the corresponding purchase record is obtained.

[0020] Furthermore, the method for classifying drugs according to the time-effect coefficient includes:

[0021] The time-effect coefficient is divided into two clusters based on a distance clustering algorithm, and all drugs corresponding to the cluster with the largest mean value of the time-effect coefficient within the cluster are regarded as acute drugs, and the remaining drugs are regarded as conventional drugs.

[0022] Furthermore, the method for obtaining the aging expansion coefficient includes:

[0023] The average of the representative delivery times of all acute drugs is used as the acute delivery time, and the average of the representative delivery times of all conventional drugs is used as the conventional delivery time;

[0024] In each drug purchase record of the current user, the difference between the deviation of the delivery time relative to the regular delivery time and the deviation relative to the emergency delivery time is used as the inflation weight;

[0025] In each drug purchase record of the current user, an expansion parameter is obtained according to the difference between the time-efficiency coefficient of each drug and the maximum value of the time-efficiency coefficients of all drugs;

[0026] The expansion parameter is weighted using the expansion weight, and a normalized value of the weighted result is used as the time expansion coefficient of the corresponding drug.

[0027] Furthermore, the method for obtaining the timeliness contribution includes:

[0028] In each drug purchase record of the current user, a timeliness reference index of each drug is obtained based on the deviation of the delivery time of each drug relative to the representative delivery time, and the timeliness reference index is combined with the timeliness coefficient to obtain the timeliness selectivity of the corresponding drug;

[0029] In each drug purchase record of the current user, the difference between the constant 1 and the time expansion coefficient of each drug is used as the correction weight, the time selectivity is weighted using the correction weight, and the weighted result is used as the time contribution of the corresponding drug.

[0030] Furthermore, the method for obtaining the timeliness weight includes:

[0031] In each drug purchase record of the current user, the mean of the timeliness contribution of all conventional drugs is mapped to the range [-1, 1], and the mapping result is used as the timeliness bias coefficient; the timeliness bias coefficient in each drug purchase record of the current user is multiplied by a preset multiple and then added with a constant 1, and the sum is used as the adjustment weight of the corresponding timeliness weight of the adjacent previous drug purchase record;

[0032] The adjustment weight is used to weight the timeliness weight corresponding to the previous drug purchase record, and the weighted result is used as the timeliness weight of the current user after the drug purchase process corresponding to each drug purchase record; wherein, the timeliness weight when the current user purchases drugs for the first time is set to a preset value; and the timeliness weight after the drug purchase process corresponding to the current user's most recent drug purchase record is used as the timeliness weight for the current user's current drug purchase.

[0033] Furthermore, the method for determining the drug purchase plan includes:

[0034] In the current user's electronic prescription, all drugs are sorted in descending order according to the timeliness coefficient to construct a drug sorting sequence, and drugs with a preset proportion in the drug sorting sequence are used as timeliness priority drugs, and the remaining drugs are used as economic priority drugs; the preset proportion is the same as the timeliness weight when the current user currently purchases drugs;

[0035] Among the preset number of neighboring pharmacies of the current user, the pharmacy closest to the current user is selected as the preferred pharmacy for all time-priority priority drugs; among the remaining neighboring pharmacies except the preferred pharmacy for time-priority priority drugs, the pharmacy with the lowest payment unit price for each economically preferred drug is selected as the preferred pharmacy for each economically preferred drug;

[0036] Determine the purchase plan for the prescription based on the preferred pharmacy for all drugs in the electronic prescription.

[0037] An intelligent prescription payment system comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of an intelligent prescription payment method are implemented.

[0038] The present invention has the following beneficial effects:

[0039] The present invention obtains the electronic prescription of the current user and the drug purchase record of each historical prescription of each user, providing a data analysis basis for the subsequent analysis of the economic tendency or timeliness tendency of the user when purchasing drugs; then obtains a representative delivery time to help evaluate the universality of the user's timeliness demand for each drug, and further combines the payment unit price of each drug in each drug purchase record of the current user to obtain a timeliness coefficient that preliminarily reflects the degree of urgency of the current user's demand for the drug; classifies the drugs according to the timeliness coefficient, and further obtains a timeliness expansion coefficient that reflects the degree of deviation of the timeliness coefficient of each drug from the actual timeliness demand in each drug purchase record of the current user; and further obtains a timeliness expansion coefficient that reflects the degree of deviation of the timeliness coefficient of each drug from the actual timeliness demand in each drug purchase record of the current user. In each drug purchase record, the timeliness coefficient and timeliness expansion coefficient of each drug are combined with the delivery time to obtain the timeliness contribution of each drug. The timeliness contribution corrects the timeliness expansion deviation of each drug in each purchase process, helping to accurately evaluate the user's historical drug purchase tendency; based on the timeliness contribution of each drug in each drug purchase record of the current user, combined with the drug classification result, the timeliness weight of the current user at the time of current drug purchase is obtained. The timeliness weight is the habit and portrait of the timeliness tendency of the current user when purchasing drugs, preparing for the subsequent determination of the drug purchase plan for the electronic prescription; based on the timeliness weight and the timeliness coefficient of each drug in the electronic prescription, the drug purchase plan is determined and the prescription payment is made. The present invention classifies drugs by analyzing the user's general timeliness tendency when purchasing each drug, and then corrects the timeliness expansion deviation of each drug in each purchase process, accurately analyzing the user's drug purchase tendency in the historical drug purchase record, and then determining a personalized drug purchase plan for the user to balance timeliness and economy, and improve the user's payment efficiency and user experience during the prescription payment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A flow chart of a smart prescription payment method provided by one embodiment of the present invention;

[0042] Figure 2 A flow chart of a method for obtaining an aging coefficient provided by one embodiment of the present invention;

[0043] Figure 3 A flow chart of a method for obtaining an aging expansion coefficient provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0044] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a smart prescription payment system and method according to the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0045] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0046] The specific scheme of the intelligent prescription payment system and method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0047] See also Figure 1 , which shows a flow chart of a smart prescription payment method provided by one embodiment of the present invention, specifically including:

[0048] Step S1, obtaining the electronic prescription of the current user and the drug purchase record of each historical prescription of each user, wherein the drug purchase record at least includes the payment unit price and delivery time of each drug.

[0049] It should be noted that the implementation scenario targeted by the present invention is that the user determines the drug purchase plan in the prescription online and pays for the purchase, and then the medicine is automatically delivered to the user's location; each user can query his or her historical drug purchase records to analyze his or her drug purchase tendencies.

[0050] In order to intelligently recommend prescription payment plans that balance economy and timeliness to users based on their electronic prescriptions, one embodiment of the present invention first extracts each user's electronic prescription from the cloud diagnosis platform and obtains the drug name and corresponding dosage in the electronic prescription; at the same time, the user who currently needs a prescription to purchase medicine is regarded as the current user, in preparation for the subsequent determination of the medicine purchase plan and prescription payment; further, the medicine purchase record corresponding to each historical prescription of each non-current user is obtained in the prescription payment system, where the purchase record includes at least information such as the payment unit price of each medicine, delivery time, and purchase pharmacy, providing a data analysis basis for the subsequent analysis of the user's economic tendency or timeliness tendency when purchasing medicine.

[0051] It should be noted that electronic prescriptions and the names and dosages of the drugs therein, drug purchase records and the unit prices of the drugs therein, delivery times, and the acquisition of purchasing pharmacies are all existing technologies well known to those skilled in the art and will not be elaborated on here.

[0052] Step S2: Obtain the representative delivery time of each drug based on the delivery time of each drug in all drug purchase records; obtain the time efficiency coefficient of each drug based on the payment unit price and representative delivery time of each drug in each drug purchase record of the current user; classify the drugs according to the time efficiency coefficient, and obtain the time efficiency expansion coefficient of each drug in each drug purchase record of the current user based on the time efficiency coefficient of each drug and the deviation of the delivery time relative to the representative delivery time of similar drugs.

[0053] Considering that different users have different purchasing habits when purchasing medicine, their preferences for timeliness and affordability also vary. However, all users tend to have certain similarities in their timeliness requirements for different medicines. For example, for antipyretic or antidiarrheal medicines, users have higher timeliness requirements and expect to receive the medicine as soon as possible, so the delivery time is relatively short. On the other hand, for preventive or health-care medicines, the timeliness requirements are relatively low, so the delivery time may be relatively long.

[0054] Therefore, the embodiment of the present invention obtains the representative delivery time of each drug based on the aggregation of the delivery time of the same drug in all drug purchase records of all users; the representative delivery time can help evaluate the universality of users' timeliness requirements for each drug, and provide an analytical basis for the subsequent evaluation of the drug's timeliness coefficient and users' drug purchasing tendencies.

[0055] Preferably, in one embodiment of the present invention, considering that clustering can divide similar delivery times into a cluster, and the delivery time corresponding to the largest cluster can generally reflect the general demand for timeliness of different users; therefore, the method for obtaining the representative delivery time includes:

[0056] In all drug purchase records of all users, all delivery times of each drug are clustered, and the delivery time corresponding to the cluster center of the largest cluster is taken as the representative delivery time of the corresponding drug.

[0057] As an example, the affinity propagation (AP) clustering algorithm is used to cluster all delivery times of each drug, and the cluster with the largest total number of delivery times is taken as the largest cluster to obtain the corresponding representative delivery time.

[0058] It should be noted that in other examples, the implementer may also use the elbow method to determine the preset K value, perform clustering based on the preset K value and the K-means algorithm, or adopt other clustering algorithms. These and AP clustering are already existing technologies and will not be described in detail.

[0059] Considering that when users purchase medicines, the unit price they pay and the representative delivery time both reflect, to a certain extent, the user's preference for the timeliness of the medicines when purchasing them; based on this, the embodiment of the present invention can obtain the timeliness coefficient of each medicine; the timeliness coefficient preliminarily reflects the current user's degree of urgency in purchasing the medicine. The more they hope for the medicine to be delivered as soon as possible, the greater the timeliness coefficient.

[0060] Preferably, in one embodiment of the present invention, the method for obtaining the aging coefficient includes:

[0061] See also Figure 2 , which shows a flow chart of a method for obtaining an aging coefficient provided by an embodiment of the present invention, specifically comprising:

[0062] Step S201: In each drug purchase record of the current user, the economic selectivity of each drug is obtained based on the deviation of the payment unit price of each drug relative to the selling unit price of the same drug in the neighboring drugstores and the spatial distance between the current user and the neighboring drugstores.

[0063] Considering that in each drug purchase record of the current user, if the payment unit price of each drug is lower than the selling unit price of the neighboring drug store, it means that the current user is more inclined to economy when purchasing drugs; at the same time, considering that the spatial distance between the current user and the neighboring drug store is farther, it indirectly indicates that the user may abandon timeliness and be more inclined to economy; based on this, the embodiment of the present invention will obtain the economic selectivity of each drug in each drug purchase record of the current user; the economic selectivity reflects the user's tendency towards economy and abandonment of timeliness, preparing for the subsequent evaluation of the timeliness coefficient.

[0064] In a preferred embodiment of the present invention, a target drug is first determined, and its unit price at the nearest pharmacy is used as the comparison unit price of the target drug. Considering that the higher the comparison unit price of the target drug at the nearest pharmacy and the greater the distance between the current user and the nearest pharmacy, if the current user has a higher timeliness requirement, the price paid for the target drug will also be higher, that is, the reference unit price is higher. Considering that in any drug purchase record of the current user, if the unit price paid by the current user for the target drug is lower than the reference unit price, it means that the current user may have chosen a pharmacy farther away to sacrifice timeliness, thereby purchasing at a lower price, and the economic selectivity is greater. Based on this, the method for obtaining the economic selectivity includes:

[0065] Take any drug in any purchase record of the current user as the target drug, select a preset number of pharmacies closest to the current user as reference pharmacies, and use the unit price of the target drug in each reference pharmacy as the comparison unit price;

[0066] The spatial distance between the current user and each reference pharmacy is used as the economic weight of the corresponding comparison unit price. The economic weight is used to weight the corresponding comparison unit price and the weighted average result is used as the reference unit price of the target drug.

[0067] According to the difference between the reference unit price and the payment unit price of the target drug, the economic selectivity of the target drug in the corresponding purchase records is obtained.

[0068] As an example, taking any purchase record of the current user as an example, the calculation formula for economic selectivity is:

[0069] ; Among them, r is the serial number of the current user's drug purchase record; m is the serial number of the drug; for Activation function; f is the serial number of the current user's neighboring pharmacies; F is the preset number, that is, the total number of the current user's neighboring pharmacies. In this example, it is 3, and the implementer can also customize it; is the economic weight of the comparative price of the mth drug in the fth neighboring pharmacy in the rth drug purchase record of the current user, and is also the spatial distance between the current user and the fth neighboring pharmacy; The comparative unit price of the mth drug in the fth neighboring pharmacy in the rth drug purchase record of the current user; The reference price of the mth drug in the rth drug purchase record of the current user; The unit price of the mth drug in the rth drug purchase record of the current user.

[0070] It should be noted that when hour, = ,when hour, =0, which is already an existing technology and will not be repeated here. In the above formula, the reference price of each drug is evaluated by weighted averaging if the current user has a high timeliness requirement. The greater the spatial distance, the greater the economic weight. At the same time, the higher the comparative price of the drug, the greater the reference price paid by the current user in pursuit of timeliness. When the actual payment price of each drug is less than the reference price, A positive value indicates that the actual payment price is relatively lower and the user's economic choice is greater; on the contrary, when the actual payment price of each drug is greater than or equal to the reference unit price, A value of 0 indicates that the actual payment price is relatively high. Users pursue higher efficiency and choose to pay higher drug purchase costs, and their economic choice is also smaller.

[0071] In other embodiments, the implementer may directly use the average of the comparative unit prices of each drug in all nearby pharmacies as the reference unit price; or normalize the difference between the reference unit price and the payment unit price. The larger the normalized value, the greater the economic choice of the current user.

[0072] Step S202: Using the negative correlation mapping result of the average economic selectivity of each drug in all drug purchase records of the current user as the first timeliness parameter.

[0073] As an example, the mean is added to a preset non-zero normal number 0.001 and then the inverse operation is performed to perform a negative correlation mapping adjustment logic, so that the smaller the mean is, the less economic concerns the current user has when purchasing this type of drug, and the larger the first time parameter is; in other examples, the implementer can also use the mean as an exponential function with the natural constant e as the base for negative correlation mapping, and can also use other negative correlation mapping methods, which will not be repeated here.

[0074] Step S203: Obtain the confidence weight representing the delivery time of each drug based on the distance between the largest cluster corresponding to each drug and each of the remaining clusters. Use the confidence weight to weight the negative correlation mapping result representing the delivery time to obtain the second timeliness parameter.

[0075] Considering that in the clustering results of the delivery time of each drug, the largest cluster corresponds to the delivery time, which can reflect the general timeliness demand of users for that drug; and considering that the distance between different clusters can reflect the clustering effect, the larger the distance between different clusters, the better the clustering effect, and the higher the credibility of the delivery time;

[0076] Therefore, as an example, the distance between the cluster center of the largest cluster and the cluster center of each other cluster is averaged, and the average is used as the confidence weight representing the delivery market. Then, the representative delivery time is reciprocally calculated to perform a negative correlation mapping adjustment logic, so that the shorter the representative delivery time, the stronger the tendency towards timeliness. Finally, the confidence weight is multiplied by the reciprocal to obtain the second timeliness parameter.

[0077] In other examples, implementers may also use other methods such as intra-cluster variance, or a fusion of intra-cluster variance and inter-cluster distance to evaluate clustering effects and obtain confidence weights, or use other negative correlation mapping methods, which are all existing technologies and will not be described in detail.

[0078] Step S204: The first aging parameter and the second aging parameter are integrated to obtain the aging coefficient of the corresponding drug.

[0079] As an example, the first time-effect parameter and the second time-effect parameter are multiplied and combined, and the product is linearly normalized to obtain the time-effect coefficient of the corresponding drug; in other examples, the implementer can also use basic mathematical operations such as addition or weighted summation to combine the two, which will not be repeated here.

[0080] Considering that a user's purchase history may contain both acute and non-acute medications, the presence of acute medications in the same purchase record may increase the timeliness coefficient of other non-acute medications. In other words, the user has a low demand for the timeliness of non-acute medications, but when they are ordered together with acute medications, the delivery time of the non-acute medications is shortened relative to the actual demand, thereby inflating the timeliness coefficient of non-acute medications.

[0081] Considering that the proportion of acute and non-acute drugs in the same drug purchase record may be different, users usually make decisions based on the proportion when purchasing drugs, thus making decisions that prioritize timeliness or price. The representative delivery time of acute and non-acute drugs is based on the analysis and evaluation of a large number of drug purchase records, which can provide a certain inflation comparison reference to a certain extent. By comparing the delivery time of drugs with the deviation of the representative delivery time of similar drugs, it can help measure whether there is inflation deviation in the timeliness coefficient of such drugs. The timeliness coefficient of drugs can also provide a basis for analyzing and evaluating the degree of inflation deviation.

[0082] Therefore, after obtaining the timeliness coefficient of each drug, the embodiment of the present invention first classifies the drugs according to the timeliness coefficient. Furthermore, in each drug purchase record of the current user, the timeliness expansion coefficient of each drug is obtained based on the timeliness coefficient of each drug and the deviation of its delivery time relative to the representative delivery time of similar drugs. The timeliness expansion coefficient reflects the degree of deviation of the timeliness coefficient of each drug from the actual timeliness demand, and prepares for the subsequent accurate calculation of the timeliness contribution of each drug.

[0083] Preferably, in one embodiment of the present invention, the time-effect coefficient is divided into two clusters based on a distance clustering algorithm, and all drugs corresponding to the cluster with the largest mean time-effect coefficient within the cluster are used as acute drugs, and the remaining drugs are used as conventional drugs.

[0084] As an example, the timeliness coefficient is divided into two clusters based on the preset K value and the K-means clustering algorithm, where the preset K value is 2, that is, the drugs are divided into two categories. The cluster with the largest mean timeliness coefficient has a higher timeliness demand, and its corresponding drugs are acute drugs. The other cluster corresponds to conventional drugs, which are also non-acute drugs.

[0085] In other examples, implementers may also use other distance clustering algorithms, which are all existing technologies and will not be described in detail.

[0086] Preferably, in one embodiment of the present invention, the method for obtaining the aging expansion coefficient includes:

[0087] See also Figure 3 , which shows a flow chart of a method for obtaining an aging expansion coefficient provided by an embodiment of the present invention, specifically comprising:

[0088] In step S211 , the average of the representative delivery times of all acute drugs is used as the acute delivery time, and the average of the representative delivery times of all conventional drugs is used as the conventional delivery time.

[0089] As an example, the acute delivery time and the regular delivery time are first obtained, which are obtained based on the representative delivery time evaluation of a large number of drug purchase records, and can provide a certain expansion comparison reference; in other examples, implementers can also use the mode or median instead of the mean, which will not be repeated here.

[0090] Step S212: In each drug purchase record of the current user, the difference between the deviation of the delivery time relative to the regular delivery time and the deviation relative to the acute delivery time is used as an inflation weight.

[0091] Considering that in each drug purchase record of the current user, if the deviation of the delivery time relative to the acute delivery time is greater, it means that the proportion of acute drugs in the drug purchase record is relatively smaller, the current user is more inclined to economic decision-making, and the possibility and degree of inflation of the drug's timeliness coefficient are relatively smaller; similarly, the greater the deviation of the delivery time relative to the regular delivery time, it means that the proportion of regular drugs in the drug purchase record is relatively smaller, the current user is more inclined to timeliness decision-making, and the possibility and degree of inflation of the drug's timeliness coefficient are relatively greater;

[0092] Therefore, as an example, the deviation is measured in the form of the absolute value of the difference. When the absolute value of the difference between the delivery time and the regular delivery time, minus the absolute value of the difference between the delivery time and the acute delivery time, is greater than 0 and the larger the difference is, the greater the expansion weight of the timeliness coefficient of the drug in the current user's corresponding drug purchase record; conversely, the smaller the expansion weight is and less than 0.

[0093] Step S213, in each drug purchase record of the current user, obtaining an expansion parameter based on the difference between the time-efficiency coefficient of each drug and the maximum time-efficiency coefficient of all drugs;

[0094] As an example, in each drug purchase record of the current user, the maximum value of the time-effectiveness coefficients of all drugs is used as the numerator, the time-effectiveness coefficient of each drug is used as the denominator, and the fraction ratio is used as the expansion parameter; when the time-effectiveness coefficient of each drug is smaller, it means that the possibility that it is a conventional drug is greater, and the impact it will receive when purchased together with acute drugs is greater, and the corresponding expansion parameter is also larger.

[0095] In other examples, implementers may also use a difference instead of a ratio, that is, the difference between the maximum value of the time-efficiency coefficients of all drugs and the time-efficiency coefficient of each drug, as the expansion parameter.

[0096] Step S214: weighting the expansion parameter using the expansion weight, and taking the normalized value of the weighted result as the time expansion coefficient of the corresponding drug.

[0097] As an example, when the expansion weight is multiplied by the expansion parameter, the product may be a negative value, and the product is further normalized by a sigmoid function so that its value is between 0 and 1. In other examples, implementers may also use other normalization methods, which will not be described in detail.

[0098] Step S3: In each drug purchase record of the current user, the timeliness contribution of each drug is obtained based on the delivery time and the timeliness expansion coefficient of each drug, combined with the timeliness coefficient; based on the timeliness contribution of each drug in each drug purchase record of the current user, combined with the drug classification result, the timeliness weight of the current user at the time of current drug purchase is obtained; based on the timeliness weight and the timeliness coefficient of each drug in the electronic prescription, the drug purchase plan is determined and the prescription payment is made.

[0099] After obtaining the time expansion coefficient, we can further obtain the time contribution of each drug in each drug purchase record of the current user based on the delivery time and the time expansion coefficient of each drug, combined with the time coefficient; the time contribution accurately reflects the current user's actual time demand for each drug in each drug purchase record on the basis of time expansion, preparing for the subsequent accurate assessment of time tendency.

[0100] Preferably, in one embodiment of the present invention, considering that the timeliness coefficient reflects the general timeliness requirement of drugs when they are purchased, and that the timeliness requirements of the current user for the same drug may be different during different drug purchase processes, and that the deviation of the delivery time relative to the delivery time reflects the timeliness tendency to a certain extent; and considering that the timeliness coefficient of the drug in each drug purchase record may have a certain inflation deviation, it can be corrected based on the timeliness inflation coefficient, thereby accurately obtaining the contribution degree of each drug purchase record to the assessment of the timeliness tendency of the current user; therefore, the method for obtaining the timeliness contribution degree includes:

[0101] In each drug purchase record of the current user, the timeliness reference index of each drug is obtained based on the deviation of the delivery time of each drug relative to the representative delivery time. The timeliness reference index is combined with the timeliness coefficient to obtain the timeliness selectivity of the corresponding drug;

[0102] In each drug purchase record of the current user, the difference between the constant 1 and the time expansion coefficient of each drug is used as the correction weight, the time selectivity is weighted using the correction weight, and the weighted result is used as the time contribution of the corresponding drug.

[0103] As an example, in each drug purchase record of the current user, the delivery time of each drug is used as the denominator, the representative delivery time of each drug is used as the numerator, and the difference of the fraction ratio minus 1 is linearly normalized to serve as the timeliness reference index of each drug; the timeliness reference index is then multiplied and combined with the timeliness to obtain the timeliness selectivity; the larger the timeliness coefficient of a drug, the more likely it is an acute drug, and when the timeliness reference index is greater than 0 and the larger it is, the shorter the delivery time is relative to the representative delivery time, the more inclined the current user is to timeliness in the drug purchase record, and the greater the timeliness selectivity; then the correction weight is obtained, and the correction weight is multiplied by the timeliness selectivity, so as to reduce the impact of timeliness inflation and accurately obtain the contribution of each drug purchase record to the evaluation of the current user's timeliness tendency.

[0104] In other examples, implementers may also directly normalize the difference between the representative delivery time and the delivery time, and use the normalized value as the timeliness reference index of the corresponding drug.

[0105] Considering that acute drugs usually have a high timeliness, even if users tend to be more economical, they cannot sacrifice too much timeliness of acute drugs to achieve higher economy. Therefore, the timeliness contribution of acute drugs in each purchase record of the current user may not accurately reflect the user's personalized selection tendency.

[0106] Therefore, the embodiment of the present invention will combine the drug classification results to analyze the timeliness contribution of each drug in each drug purchase record of the current user to obtain the timeliness weight of the current user when purchasing drugs; the timeliness weight is based on the timeliness tendency of the current user in all historical drug purchase processes, reflecting the timeliness tendency of the current user when purchasing drugs, and is the habit and portrait of the current user when purchasing drugs, preparing for the subsequent determination of the drug purchase plan for the electronic prescription.

[0107] Preferably, in one embodiment of the present invention, the method for obtaining the timeliness weight includes:

[0108] In each drug purchase record of the current user, the mean of the timeliness contribution of all conventional drugs is mapped to the range [-1, 1], and the mapping result is used as the timeliness bias coefficient. The timeliness bias coefficient in each drug purchase record of the current user is multiplied by a preset multiple and then added with a constant 1. The sum is used as the adjustment weight of the corresponding timeliness weight of the adjacent previous drug purchase record.

[0109] The adjustment weight is used to weight the timeliness weight corresponding to the previous drug purchase record, and the weighted result is used as the timeliness weight of the current user after the drug purchase process corresponding to each drug purchase record; among which, the timeliness weight of the current user's first drug purchase is set to a preset value; the timeliness weight after the drug purchase process corresponding to the current user's most recent drug purchase record is used as the timeliness weight of the current user's current drug purchase.

[0110] As an example, the calculation formula for the timeliness weight of each drug purchase record corresponding to the drug purchase process of the current user is:

[0111] ; Among them, r is the serial number of the current user's drug purchase record; The timeliness weight of the current user's purchase process corresponding to the rth purchase record; It is a preset multiple. In this example, it is 0.1. The implementer can also set it to any value between 0 and 1 to control the adjustment range of the timeliness weight. is the timeliness bias coefficient of the current user’s r-th drug purchase record; To adjust the weight; The time-efficiency weight of the current user after the purchase process corresponding to the r-1th purchase record; in this example, the time-efficiency weight of the current user's first purchase of medicine Set to a preset value such as 0.5.

[0112] In the above formula, in the r-th drug purchase record, if the timeliness bias coefficient is greater than 0, it means that the greater the current user's tendency towards timeliness, the greater the adjustment weight obtained by multiplying it by a preset multiple, then the current user's timeliness tendency is relatively greater on the basis of the timeliness weight after the drug purchase process corresponding to the r-1-th drug purchase record, and the timeliness weight after the drug purchase process corresponding to the r-th drug purchase record is also greater; through continuous iteration, the timeliness weight after the drug purchase process corresponding to each drug purchase record can be obtained, and then the timeliness weight after the drug purchase process corresponding to the most recent drug purchase record of the current user can be obtained, and it can be used as the timeliness weight of the current user's current drug purchase.

[0113] After obtaining the timeliness weight of the current user when purchasing medicine, the medicine purchase plan can be determined and prescription payment can be made based on the timeliness weight and the timeliness coefficient of each medicine in the electronic prescription.

[0114] Preferably, in one embodiment of the present invention, the method for determining the drug purchase plan includes:

[0115] In the current user's electronic prescription, all drugs are sorted in descending order according to their timeliness coefficients to construct a drug sorting sequence. Drugs with a preset proportion in the drug sorting sequence are regarded as timeliness priority drugs, and the remaining drugs are regarded as cost-priority priority drugs. The preset proportion is the same as the timeliness weight of the current user's current drug purchase;

[0116] Among the preset number of neighboring pharmacies of the current user, the pharmacy closest to the current user is selected as the preferred pharmacy for all time-priority priority drugs; among the remaining neighboring pharmacies except the preferred pharmacy for time-priority priority drugs, the pharmacy with the lowest payment unit price for each economically preferred drug is selected as the preferred pharmacy for each economically preferred drug;

[0117] Determine the purchase plan for the prescription based on the preferred pharmacy for all drugs in the electronic prescription.

[0118] As an example, if the current user's electronic prescription contains a total of 10 drugs, and the timeliness weight for the current drug purchase is 0.3, then the drugs with the top 3 timeliness coefficients in the electronic prescription are time-priority drugs, and their timeliness should be paid extra attention to when determining the drug purchase plan. The other 7 drugs are economic priority drugs. The preset quantity is set to 3, that is, the drug purchase plan of the current user's electronic prescription is restricted to be purchased and delivered to 3 nearby pharmacies. Among these 3 nearby pharmacies, the pharmacy closest to the current user is the preferred pharmacy for all time-priority drugs. Among the other 2 nearby pharmacies, 2 delivery plans are determined for each economic priority drug, and the pharmacy corresponding to the plan with the lowest unit price is used as the preferred pharmacy for the corresponding economic priority drug. After determining the preferred pharmacy for all drugs in the electronic prescription, the drug purchase plan for the electronic prescription is determined.

[0119] In other examples, implementers can also set other drug purchase distribution rules on their own to determine a reasonable drug purchase plan while balancing timeliness and economy, which will not be elaborated here.

[0120] In one embodiment of the present invention, after determining the drug purchase plan, the current user can also adjust the specific drug purchase method for each drug by himself, such as canceling the online purchase of some conventional drugs and purchasing them offline by himself, etc., so as to determine the final drug purchase plan; after obtaining the final drug purchase plan, the purchase information of each drug is integrated, and orders are created separately in neighboring pharmacies. The drug purchase orders of different neighboring pharmacies are paid together, and the relevant medical platform interface is connected at the same time to automatically calculate the medical insurance reimbursement amount and the self-paid amount for the current user; after the user's combined payment is successful, a payment voucher is generated, and the real-time information of the cloud diagnosis platform and the pharmacy is synchronized, the progress of the cloud diagnosis platform is updated, the pharmacy is notified to prepare the medicine and the pharmacy inventory information is updated; the delivery progress of the user's order is updated in real time and the user is notified of the delivery time until the order is completed after the user receives the medicine.

[0121] Based on the same inventive concept, the present invention also proposes an intelligent prescription payment system, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned intelligent prescription payment method are implemented.

[0122] In summary, the present invention first obtains the representative delivery time of each drug, and then obtains the time efficiency coefficient of each drug to classify the drugs; then, in each drug purchase record of the current user, obtains the time efficiency expansion coefficient and time efficiency contribution of each drug; based on the time efficiency contribution of each drug in each drug purchase record of the current user, combined with the drug classification result, obtains the time efficiency weight of the current user at the time of current drug purchase, and then combines the time efficiency coefficient of each drug in the electronic prescription to determine the drug purchase plan and make payment. The present invention classifies drugs by analyzing the general time efficiency tendency of users to purchase each drug, and then analyzes the purchase interference effect between drugs with different time efficiency requirements, corrects the time efficiency expansion deviation of each drug in each purchase process, thereby accurately analyzing the user's drug purchase tendency in historical drug purchase records, and then can determine a personalized drug purchase plan for the user to balance time efficiency and economy, and improve the user's payment efficiency and user experience in the prescription payment process.

[0123] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0124] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A smart prescription payment method, characterized in that: The method comprises: Obtain the current user's electronic prescription and each user's purchase record for each historical prescription, wherein the purchase record includes at least the payment unit price and delivery time of each drug; Obtaining a representative delivery time for each drug based on the delivery time of each drug in all drug purchase records; obtaining a time efficiency coefficient for each drug based on the payment unit price and the representative delivery time of each drug in each drug purchase record of the current user; classifying drugs based on the time efficiency coefficients, and obtaining a time efficiency expansion coefficient for each drug in each drug purchase record of the current user based on the time efficiency coefficient of each drug and the deviation of the delivery time from the representative delivery time of each drug category; In each drug purchase record of the current user, the timeliness contribution of each drug is obtained based on the timeliness coefficient and the timeliness expansion coefficient of each drug, combined with the delivery time; based on the timeliness contribution of each drug in each drug purchase record of the current user, combined with the drug classification result, the timeliness weight of the current user at the time of the current drug purchase is obtained; based on the timeliness weight and the timeliness coefficient of each drug in the electronic prescription, the drug purchase plan is determined and the prescription payment is made; The method for obtaining the representative delivery time includes: Cluster all the delivery times of each drug in all drug purchase records of all users, and use the delivery time corresponding to the cluster center of the largest cluster as the representative delivery time of the corresponding drug; The method for obtaining the aging coefficient includes: In each drug purchase record of the current user, the economic selectivity of each drug is obtained based on the deviation of the payment unit price of each drug relative to the selling unit price of the same drug in a nearby pharmacy, combined with the spatial distance between the current user and the nearby pharmacy; The negative correlation mapping result of the mean value of the economic selectivity of each drug in all drug purchase records of the current user is used as the first timeliness parameter; Obtaining a confidence weight of the representative delivery time for each drug based on the distance between the largest cluster corresponding to each drug and each of the remaining clusters, and weighting the negative correlation mapping results corresponding to the representative delivery time using the confidence weight to obtain a second timeliness parameter; The first aging parameter and the second aging parameter are integrated to obtain the aging coefficient of the corresponding drug.

2. The smart prescription payment method according to claim 1, characterized in that: The method for obtaining the economic selectivity includes: Take any drug in any purchase record of the current user as the target drug, select a preset number of pharmacies closest to the current user as reference pharmacies, and use the unit price of the target drug in each reference pharmacy as the comparison unit price; The spatial distance between the current user and each reference pharmacy is used as the economic weight of the corresponding comparison unit price, the economic weight is used to weight the corresponding comparison unit price and the weighted average result is used as the reference unit price of the target drug; According to the difference between the reference unit price and the payment unit price of the target drug, the economic selectivity of the target drug in the corresponding purchase record is obtained.

3. The smart prescription payment method according to claim 1, characterized in that: The method for classifying drugs according to the time-effect coefficient includes: The time-effect coefficient is divided into two clusters based on a distance clustering algorithm, and all drugs corresponding to the cluster with the largest mean value of the time-effect coefficient within the cluster are regarded as acute drugs, and the remaining drugs are regarded as conventional drugs.

4. The smart prescription payment method according to claim 3, characterized in that: The method for obtaining the aging expansion coefficient includes: The average of the representative delivery times of all acute drugs is used as the acute delivery time, and the average of the representative delivery times of all conventional drugs is used as the conventional delivery time; In each drug purchase record of the current user, the difference between the deviation of the delivery time relative to the regular delivery time and the deviation relative to the emergency delivery time is used as the inflation weight; In each drug purchase record of the current user, an expansion parameter is obtained according to the difference between the time-efficiency coefficient of each drug and the maximum value of the time-efficiency coefficients of all drugs; The expansion parameter is weighted using the expansion weight, and a normalized value of the weighted result is used as the time expansion coefficient of the corresponding drug.

5. The smart prescription payment method according to claim 1, characterized in that: The method for obtaining the timeliness contribution includes: In each drug purchase record of the current user, a timeliness reference index of each drug is obtained based on the deviation of the delivery time of each drug relative to the representative delivery time, and the timeliness reference index is combined with the timeliness coefficient to obtain the timeliness selectivity of the corresponding drug; In each drug purchase record of the current user, the difference between the constant 1 and the time expansion coefficient of each drug is used as the correction weight, the time selectivity is weighted using the correction weight, and the weighted result is used as the time contribution of the corresponding drug.

6. The smart prescription payment method according to claim 3, characterized in that: The method for obtaining the timeliness weight includes: In each drug purchase record of the current user, the mean of the timeliness contribution of all conventional drugs is mapped to the range [-1, 1], and the mapping result is used as the timeliness bias coefficient; the timeliness bias coefficient in each drug purchase record of the current user is multiplied by a preset multiple and then added with a constant 1, and the sum is used as the adjustment weight of the corresponding timeliness weight of the adjacent previous drug purchase record; The adjustment weight is used to weight the timeliness weight corresponding to the previous drug purchase record, and the weighted result is used as the timeliness weight of the current user after the drug purchase process corresponding to each drug purchase record; wherein, the timeliness weight when the current user purchases drugs for the first time is set to a preset value; and the timeliness weight after the drug purchase process corresponding to the current user's most recent drug purchase record is used as the timeliness weight for the current user's current drug purchase.

7. The smart prescription payment method according to claim 1, characterized in that: The method for determining the drug purchasing plan includes: In the current user's electronic prescription, all drugs are sorted in descending order according to the timeliness coefficient to construct a drug sorting sequence, and drugs with a preset proportion in the drug sorting sequence are used as timeliness priority drugs, and the remaining drugs are used as economic priority drugs; the preset proportion is the same as the timeliness weight when the current user currently purchases drugs; Among the preset number of neighboring pharmacies of the current user, the pharmacy closest to the current user is selected as the preferred pharmacy for all time-priority priority drugs; among the remaining neighboring pharmacies except the preferred pharmacy for time-priority priority drugs, the pharmacy with the lowest payment unit price for each economically preferred drug is selected as the preferred pharmacy for each economically preferred drug; Determine the purchase plan for the prescription based on the preferred pharmacy for all drugs in the electronic prescription.

8. An intelligent prescription payment system, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the smart prescription payment method according to any one of claims 1 to 7 are implemented.

Images