Medical service pushing method and pushing system based on big data analysis

Abstract

The invention discloses a medical service pushing method and pushing system based on big data analysis, and relates to the technical field of medical service pushing, and the method comprises the steps: extracting subsequent examination items according to the diagnosis and treatment opinions of a doctor in a doctor seeing department of a user, automatically obtaining a plurality of destinations which the user needs to go subsequently, and carrying out the pushing of the medical service. Synchronizing the queuing number of the corresponding destination; a plurality of destinations are automatically combined into a plurality of inspection sequence groups, and then selected values are determined according to waiting inverse values and inspection length values in each inspection sequence group, so that a recommended inspection sequence group is formed, a user is helped to form a proper inspection sequence, and invalid or overlong waiting time is avoided; through analysis of the inspection report, preliminary analysis information is determined and recommended to the user, so that the user can preliminarily understand the report.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical service push, and specifically relates to a medical service push method and push system based on big data analysis. Background Art

[0002] The patent with publication number CN115238173A discloses a behavior analysis and medical service push method, device and medium based on big data, which is used to solve the technical problems of poor pertinence and low push efficiency of existing push methods. The method includes: receiving basic feature information of patients based on the patient's access request, crawling historical behavior feature information of patients based on the basic feature information of patients, analyzing historical behavior feature information based on a preset behavior analysis model and outputting a patient portrait; determining related medical service feature information from a medical service feature array and establishing a related medical service feature set according to the medical service feature information to be pushed corresponding to the patient portrait; determining the target medical service feature information of the patient based on the patient's response data to each related medical service feature information; updating the push strategy according to the target medical service feature information, and pushing the medical service feature information to the patient according to the updated push strategy, which is consistent with the actual situation of the patient, and improves the accuracy of medical service push.

[0003] Existing medical push services generally recommend medical projects based on the user's personal situation, or recommend nearby medical points for some people who need to buy medicine. They rarely take into account that when users seek medical treatment in hospitals, they are unfamiliar with hospitals, which leads to a lot of time spent waiting or looking for medical points. Then, when doing examinations, if there are multiple examination items, they are all randomly examined, and there is no reasonable examination order push service. Based on this, the present application provides a solution. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; To this end, the present invention proposes a medical service push method based on big data analysis, which specifically includes the following steps: Extract the subsequent examination items based on the doctor's diagnosis and treatment opinions of the user in the treatment department, automatically obtain several destinations that the user needs to go to later, and synchronize the number of people queuing at the corresponding destination; Automatically combine several destinations into several inspection sequence groups, and automatically obtain the inspection length value representing the length of the path required to be walked for each inspection sequence group; then determine the waiting inverse value of each inspection sequence group according to the waiting time of the inspection items ranked later in the inspection sequence group exceeding the waiting time of the inspection items ranked earlier; Then, the selected value is determined according to the waiting inverse value and the check length value, and the check sequence group corresponding to the minimum value of the selected value is marked as the recommended check sequence group.

[0005] Furthermore, when obtaining the inspection length value representing the path length required for each inspection sequence group, in addition to the path length of several destination combinations, the deemed distance must also be added. The deemed distance is obtained as follows: The distance from the last destination of the inspection sequence group to the hospital entrance is marked as the tail distance value; The distance from the last destination of the examination sequence group to the visiting department is added to the distance from the visiting department to the hospital entrance, and the sum of the distances is marked as the reverse distance; When the inspection reports for each destination in the inspection sequence group are issued on the same day, the reverse distance will be marked as the deemed distance, otherwise the tail distance value will be marked as the deemed distance.

[0006] Furthermore, when the tail distance value is marked as the considered distance, the user's examination report will be automatically monitored in real time, and the examination report will be marked as a real-time report after it comes out. For the real-time report, it will be matched from the examination records issued by the same doctor. The examination record includes the examination report and the evaluation information for the examination report; Mark the inspection report in the inspection record as a report to be matched, and mark any indicator in the report to be matched that is an abnormal indicator in both the report to be matched and the real-time report, and the ratio of the number of indicator differences exceeding the preset value X1 to the total number of abnormal indicators as the indicator difference ratio; Then, the anomaly number difference indicating the number of different anomaly indicators between the to-be-matched report and the real-time report is obtained; The report to be matched is selected according to the indicator difference ratio and the anomaly number difference, and the selected report to be matched is marked as an associated report.

[0007] Furthermore, the associated report and the corresponding evaluation information are integrated to form reference information, which is pushed to the user.

[0008] Furthermore, the specific method of selecting the report to be matched according to the index difference ratio and the anomaly number difference is as follows: The matching value of all reports to be matched is calculated using the formula: Matching value = 0.63*index difference ratio + 0.37*anomaly number difference; In the formula, 0.63 and 0.37 are preset weight values ​​used to highlight the different importance of different factors; The to-be-matched reports whose matching values ​​do not exceed the preset value X2 are marked as associated reports.

[0009] Furthermore, the specific method of determining the waiting inverse value of each check order group is as follows: Select an inspection order group, then obtain the first destination in the inspection order group and the number of people in the queue at the corresponding destination; After multiplying the number of people in line by the average waiting time, the resulting time is marked as the estimated waiting time, and the waiting time for each destination is obtained; Then, the first destination is selected, and the number of destinations whose waiting time after the first destination is obtained and is longer than the waiting time of the first destination is marked as the exceeded number; Automatically obtain the excess number of each destination, add up the excess numbers of all destinations, and mark the obtained value as the waiting inverse value of the corresponding inspection order group; The same process is performed on the remaining inspection order groups to obtain the waiting inverse values ​​of all inspection order groups.

[0010] Furthermore, the average waiting time is determined by the average time spent by users who have checked the project in the past month.

[0011] Furthermore, the specific method of determining the selected value according to the waiting inverse value and the check length value is as follows: Calculate the selected values ​​of all inspection order groups according to the formula. The specific formula is: Selected value = 0.57*check length value + 0.43*wait inverse value; In the formula, 0.57 and 0.43 are the preset weight values; The inspection order group with the smallest selected value is marked as the recommended inspection order group to obtain the recommended inspection order group.

[0012] A medical service push system based on big data analysis, which uses the aforementioned medical service push method to implement medical service push for users; Compared with the prior art, the present invention has the following beneficial effects: This application extracts subsequent examination items based on the diagnosis and treatment opinions of the doctor in the department where the user is visiting, automatically obtains several destinations that the user needs to go to later, and synchronizes the number of people in the queue at the corresponding destinations; then automatically combines several destinations into several examination sequence groups, and then determines the selected value based on the waiting inverse value and examination length value in each examination sequence group, thereby forming a recommended examination sequence group to help users form a suitable examination sequence and avoid invalid or excessive waiting time; By analyzing the inspection report, a preliminary analysis information is determined and recommended to the user, so that the user can have a preliminary understanding of the report; this application is simple, effective, and easy to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a flow chart of the push method of the present invention; Figure 2 Flow chart for determining the wait inverse value for each inspection order group for the present invention. DETAILED DESCRIPTION

[0014] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] See also Figure 1-2 ,This application provides a medical service push method based on big data analysis; As an embodiment 1 of the present application, the method specifically includes the following steps: Step 1: First, you need to synchronize the internal map of the corresponding hospital. The internal map includes the specific locations of various departments and examination rooms in the hospital, as well as the specific road conditions of the hospital; Step 2: Then, the user is tracked. The specific method of tracking is as follows: First, the path from the gate to the registration room will be automatically planned and marked as the entry path. At this time, the user needs to enter the treatment department, and the shortest path from the registration room to the treatment department will be automatically obtained. During this process, the person will be automatically guided to the treatment department. Step 3: After arriving at the treatment department, the diagnosis and treatment opinions of the doctors in the corresponding treatment department will be automatically synchronized, and the examination items that the user needs to undergo in the future will be extracted from the diagnosis and treatment opinions. This extraction process can be based on keyword recognition, such as ultrasound examination and other keywords, and synchronized from the examination form issued by the doctor, and then automatically obtain several destinations that the user needs to go to, and synchronize the current number of people queuing at the corresponding destination; Step 4: Waiting planning for several destinations. The specific method of waiting planning is as follows: First, a number of destinations are obtained, and the destinations are randomly combined in order to obtain all the order combinations, which are marked as inspection order groups; Then, the total length of the inspection path constructed according to the inspection order group is obtained, and then the total length is added to the deemed distance of the last destination of the corresponding inspection order group, and the obtained mark is the inspection length value; The specific method of obtaining the considered distance is: First, obtain the distance from the last destination of the inspection sequence group to the hospital entrance and mark it as the tail distance value; Then, the distance from the last destination of the examination sequence group to the visiting department is obtained, and the distance from the visiting department to the hospital entrance is added, and the sum of the obtained distances is marked as the reverse distance; Afterwards, according to the inspection reports of several destinations, if there is no inspection item that needs several days to get the result, the reverse distance will be automatically marked as the deemed distance, otherwise the tail distance value will be marked as the deemed distance; Step 5: Then, according to the number of people queuing at each destination in the inspection sequence group, analyze the waiting inverse value of the inspection sequence group based on the number of people queuing. The specific analysis method is as follows: Select an inspection order group, then obtain the first destination in the inspection order group and the number of people in the queue at the corresponding destination; After multiplying the number of people in the queue by the average waiting time, the resulting time is marked as the expected waiting time, and the waiting time of each destination is obtained. Then the first destination is selected, and the number of destinations whose waiting time is longer than the first destination is obtained, and they are marked as the excess number; the excess number of each destination is automatically obtained, and the excess numbers of all destinations are added together, and the resulting value is marked as the inverse value of the waiting time of the corresponding inspection order group; the average waiting time here is determined by the average time spent by users who have done the inspection of this project in the past month; The same process is performed on the remaining inspection order groups to obtain the waiting inverse values ​​of all inspection order groups; Step 6: Perform selection analysis based on the inspection length value and waiting inverse value of the inspection sequence group. The specific method of selection analysis is as follows: Calculate the selected values ​​of all inspection order groups according to the formula. The specific formula is: Selected value = 0.57*check length value + 0.43*wait inverse value; In the formula, 0.57 and 0.43 are preset weight values, which are used to highlight the different importance of different factors; Mark the inspection sequence group with the smallest selected value as the recommended inspection sequence group, and obtain the recommended inspection sequence group; Step 7: Push the recommended inspection sequence group and its corresponding path to the user, and guide the user to perform corresponding inspections at each destination.

[0016] As the second embodiment of the present application, this embodiment is implemented on the basis of the first embodiment, and is different from the first embodiment in that, in this embodiment, if the tail distance value is marked as regarded as the distance in the first embodiment, when the user performs the inspection according to the recommended inspection sequence group, the inspection report of the user will be automatically obtained synchronously, and for non-imaging reports, it will be automatically marked as a real-time report; Obtain all the examination records of the same doctor in the department visited by the user. The examination records include examination reports and evaluation information. The examination report is the examination report issued by the doctor to the patient, and the evaluation information is the conclusion given by the doctor on the examination report; Afterwards, the user's real-time report is obtained, and all inspection reports of the same type as the real-time report are filtered out from the inspection reports according to the real-time report, and the filtered ones are marked as reports to be matched; Then, all the reports to be matched are obtained, each indicator in the reports to be matched is obtained, the difference between the values ​​of all abnormal indicators in the real-time report and the reports to be matched is obtained, and it is marked as the indicator difference corresponding to the report to be matched, and a number of indicator differences are obtained; the abnormal indicator here refers to any indicator that is abnormal in both the report to be matched and the real-time report; the number of indicator differences whose indicator differences exceed the preset value X1 is obtained, and the number is divided by the total value of the abnormal indicators, and the obtained value is marked as the indicator difference ratio of the report to be matched; Then, the difference in the number of anomalies between the to-be-matched report and the real-time report is obtained. The difference in the number of anomalies refers to the number of indicators that are different between the anomalies in the to-be-matched report and the anomalies in the real-time report. The matching value of all reports to be matched is calculated using the formula: Matching value = 0.63*index difference ratio + 0.37*anomaly number difference; In the formula, 0.63 and 0.37 are preset weight values ​​used to highlight the different importance of different factors; Mark the pending matching reports whose matching values ​​do not exceed the preset value X2 as associated reports; Obtaining evaluation information corresponding to the associated report, and integrating the evaluation information and its corresponding associated report to form reference information; Push reference information to users.

[0017] Of course, the present application also provides a medical service push system based on big data analysis, which adopts the medical service push method described in Example 1 and Example 2 to implement medical service push for users.

[0018] Some of the data in the above formula are calculated by removing the dimensions and taking their numerical values. The formula is a formula that is closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0019] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A medical service push method based on big data analysis, characterized in that: The steps include: Extract the subsequent examination items based on the doctor's diagnosis and treatment opinions of the user in the treatment department, automatically obtain several destinations required for the subsequent examination items, and simultaneously obtain the number of people queuing at the corresponding destinations; Automatically combine several destinations into several inspection sequence groups, and obtain the inspection length value representing the length of the path required to be walked for each inspection sequence group; Determine a waiting inverse value for each inspection order group according to the waiting time of the inspection item ranked later in the inspection order group exceeding the waiting time of the inspection item ranked earlier; The selected value is determined according to the waiting inverse value and the check length value, and the check sequence group corresponding to the minimum value of the selected value is marked as the recommended check sequence group.

2. The method for pushing medical services based on big data analysis according to claim 1, characterized in that: When obtaining the inspection length value representing the path length required for each inspection sequence group, in addition to the path length of several destination combinations, the deemed distance must also be added. The deemed distance is obtained as follows: The distance from the last destination of the inspection sequence group to the hospital entrance is marked as the tail distance value; The distance from the last destination of the examination sequence group to the visiting department is added to the distance from the visiting department to the hospital entrance, and the sum of the distances is marked as the reverse distance; When the inspection reports for each destination in the inspection sequence group are issued on the same day, the reverse distance is marked as the deemed distance, otherwise the tail distance value is marked as the deemed distance.

3. The method for pushing medical services based on big data analysis according to claim 2, characterized in that: When the tail distance value is marked as considered as distance, the user's examination report will be automatically monitored in real time, and the obtained examination report will be marked as a real-time report, and the real-time report will be matched with the examination record issued by the same doctor. The examination record includes the examination report form and evaluation information for the examination report form; Mark the inspection report in the inspection record as a report to be matched, and mark any indicator in the report to be matched that is an abnormal indicator in both the report to be matched and the real-time report, and the ratio of the number of indicator differences exceeding X1 to the total number of abnormal indicators as the indicator difference ratio, where X1 is a preset value; Then obtain the anomaly number difference, which indicates the number of different anomaly indicators between the to-be-matched report and the real-time report; The report to be matched is selected according to the indicator difference ratio and the anomaly number difference, and the selected report to be matched is marked as an associated report.

4. The method for pushing medical services based on big data analysis according to claim 3, characterized in that: The related reports and corresponding evaluation information are integrated to form reference information and pushed to users.

5. The method for pushing medical services based on big data analysis according to claim 3, characterized in that: The specific method of selecting the report to be matched based on the index difference ratio and the anomaly number difference is: The matching value of all reports to be matched is calculated using the formula: Matching value = 0.63*index difference ratio + 0.37*anomaly number difference; In the formula, 0.63 and 0.37 are the preset weight values; The to-be-matched reports whose matching values ​​do not exceed the preset value X2 are marked as associated reports.

6. The method for pushing medical services based on big data analysis according to claim 1, characterized in that: The specific method for determining the wait inverse value of each check order group is: Select an inspection order group, then obtain the first destination in the inspection order group and the number of people in the queue at the corresponding destination; After multiplying the number of people in line by the average waiting time, the resulting time is marked as the estimated waiting time, and the waiting time for each destination is obtained; Then, the first destination is selected, and the number of destinations whose waiting time after the first destination is obtained and is longer than the waiting time of the first destination is marked as the exceeded number; Automatically obtain the excess number of each destination, add up the excess numbers of all destinations, and mark the obtained value as the waiting inverse value of the corresponding inspection order group; The same process is performed on the remaining inspection order groups to obtain the waiting inverse values ​​of all inspection order groups.

7. The method for pushing medical services based on big data analysis according to claim 6, characterized in that: The average waiting time is the average time spent by users who checked the corresponding project in the past month.

8. The method for pushing medical services based on big data analysis according to claim 1, characterized in that: The specific method of determining the selected value based on the waiting inverse value and the check length value is: Calculate the selected values ​​of all inspection order groups according to the formula. The specific formula is: Selected value = 0.57*check length value + 0.43*wait inverse value; In the formula, 0.57 and 0.43 are the preset weight values; The inspection order group with the smallest selected value is marked as the recommended inspection order group to obtain the recommended inspection order group.

9. A medical service push system based on big data analysis, characterized in that: The system adopts the medical service push method as described in any one of claims 1-8 to implement medical service push for users.

Images