JP5269116B2 - Predictive wait time evaluation apparatus and predictive wait time evaluation method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To make a user who waits for a service less feel irritated. <P>SOLUTION: A predictive waiting time evaluation device 1 acquires a processing condition first (S601). Then a reference time is set for actual result data and a predictive medical examination waiting time is calculated as prediction data (S602). Processing data is extracted from the prediction data, and an actual medical examination waiting time is calculated (S603). Ranges (30 minutes or shorter, 60 minutes or shorter, 60 minutes or longer) of the predictive medical examination waiting time are specified for all patient IDs and all the predictive medical examination waiting time in the processing data (S605). A range of the actual medical examination waiting time is specified (S606), and 1 is added to numerals in fields, corresponding to the specified range, of frequency data (S607). Through S604-S608, frequencies of respective records in the processing data are counted by the ranges of the predictive medical examination waiting time and the actual medical examination waiting time. Numerals of the respective fields of probability data are calculated from the frequency data (S609), and the numerals are displayed on a display device 2 (S610). <P>COPYRIGHT: (C)2012,JPO&amp;INPIT

Description

  The present invention relates to an apparatus and a method for providing information relating to a predicted value being off when predicting a waiting time of a user in a service providing facility.

  Conventionally, a system for predicting and displaying a waiting time of a user, which occurs in a service providing facility such as a hospital, a beauty salon, or a restaurant, has been developed. For example, in Patent Document 1, when a consultation waiting time is received, the average consultation time of the patient who is currently being examined and the patient waiting to be examined before the inquiry patient is obtained from the examination time database, and the average of each patient is obtained. A “diagnosis waiting time prediction program, recording medium, apparatus and method” is disclosed in which the examination time is multiplied by a coefficient corresponding to the presence / absence of the examination result and the examination information, and the prediction waiting time is calculated based on the sum.

  Next, Patent Document 2 uses a neural network to predict the time required for service provision, multiply the service provision time by the number of scheduled users, and calculate a waiting time. A waiting time prediction system and program "are disclosed.

  Patent Document 3 uses a neural network to store past waiting times together with the date, day of the week, time zone, weather, etc., and specifies the date on which the prediction day of the week, weather, etc. match. A “waiting time prediction method, waiting time prediction system, and program” is disclosed in which the waiting time corresponding to the date and the prediction target time zone is read and averaged to calculate a predicted value of the waiting time.

JP 2008-217389 A Japanese Patent No. 4,217,689 Japanese Patent No. 4194573

  However, since the waiting time displayed by the system includes a prediction error, the actual waiting time may be different from the display waiting time (predicted value). In such a case, especially when the actual waiting time is longer than the predicted value, the user is frustrated.

  The present invention has been made in view of the above problems, and its main purpose is to reduce the irritation of users waiting for service.

  In order to solve the above-mentioned problem, the present invention provides the service waiting time data including a predicted value of the service waiting time, which is a time for the user to wait for the start of the service, and an actual value for the predicted value. A prediction waiting time evaluation device that calculates and outputs a probability that the waiting time is unpredictable, and sets a plurality of ranges in which the service waiting time is divided corresponding to the prediction value as a prediction waiting time range, and A plurality of ranges in which the service waiting time is divided corresponding to the actual value is set as the actual waiting time range, and the waiting time data included in the category specified by each predicted waiting time range and each actual waiting time range The actual value for the predicted value of the predicted waiting time range is calculated for each predicted waiting time range, based on the number of units and the number of each section. A means for calculating a ratio included in the actual waiting time range, and a ratio of the calculated ratio included in the actual waiting time range in which the actual value for the predicted value in the predicted waiting time range is different from the predicted waiting time range. And a means for outputting as a probability that the prediction is lost.

  According to this configuration, the number of waiting time data in the range of the predicted waiting time range and the actual waiting time (actual waiting time) range for the predicted waiting time is counted, and the actual waiting time is calculated from the predicted waiting time range. The ratio of transition to the waiting time range is calculated, and the ratio of transition to a different range is output as the probability that the waiting time is not predicted. According to this, since the ratio when the actual waiting time range is different from the predicted waiting time range, that is, the probability of deviating prediction based on the waiting time data is output, the user refers to the probability. Recognizing that this is possible, you can settle down without being frustrated even if the actual waiting time is longer than the expected waiting time.

  In the predicted waiting time evaluation apparatus of the present invention, the predicted value and the actual value of the service waiting time in the same period, day, or time zone as the evaluation target may be used in the waiting time data.

  Even for the same service, if the number of users and the method of providing the service differ depending on the day of the week and the time zone, the service wait time will change, so the difference between the predicted wait time and the actual wait time will also change. It is possible to come. According to this configuration, by using the same waiting time data as the period, day of the week, and time period for which the predicted value is to be evaluated, the probability of the prediction being lost can be calculated along the actual results.

  Further, in the predicted waiting time evaluation apparatus of the present invention, the waiting time data includes information specific to the service provider and the user, and the same provider or user as the evaluation object is included in the waiting time data. It is good also as using the said predicted value and the said actual value of the said service waiting time concerning.

  Even if the service is the same, if the actual service status varies depending on the provider or user, the service wait time will change, and the way the predicted wait time will deviate from the actual wait time will also change. Can be considered. According to this configuration, by using the same waiting time data as the provider and the user whose predicted values are to be evaluated, the probability that the prediction is lost can be calculated according to the actual results.

  In the predicted waiting time evaluation apparatus of the present invention, the means for outputting the probability may simultaneously output the predicted waiting time range related to a predetermined user and the probability that the prediction is lost.

  According to this configuration, the range of the predicted waiting time at the present time and the probability that the range will actually change are output, so that the user grasps the approximate waiting time and sometimes deviates from it. Can be recognized.

  The present invention includes a predicted waiting time evaluation method. In addition, the problems disclosed by the present application and the solutions thereof will be clarified by the description of the mode for carrying out the invention and the drawings.

  According to the present invention, it is possible to reduce the irritation of a user waiting for service.

It is a figure which shows the hardware constitutions and peripheral structure of the prediction waiting time evaluation apparatus 1. It is a figure which shows the structure of the performance data 15A. It is a figure which shows the structure of the prediction data 15B. (A) shows the configuration of the initial setting data 15C, and (b) shows the configuration of the processing data 15D. (A) shows the configuration of the frequency data 15E, and (b) shows the configuration of the probability data 15F. It is a flowchart which shows the prediction waiting time calculation process and the calculation process of a prediction failure probability. It is a figure which shows the display content of the probability data 15F in the display apparatus 2. FIG.

Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. The predicted waiting time evaluation apparatus according to the embodiment of the present invention calculates the probability that the actual value of service waiting time by a user deviates from the predicted value from the past predicted value and actual value data, and notifies the user of the probability. Is. This can reduce the irritation of the user waiting for the service.
In the following, an explanation will be given by taking the patient's examination waiting time in a hospital as an example.

≪Device configuration and overview≫
FIG. 1 is a diagram illustrating a hardware configuration and a peripheral configuration of the predicted waiting time evaluation apparatus 1. The predicted waiting time evaluation apparatus 1 includes a communication unit 11, a display unit 12, an input unit 13, a processing unit 14, and a storage unit 15, and is configured so that each unit can transmit and receive data via a bus 16. The communication unit 11 is a part that performs IP (Internet Protocol) communication or the like with another device (for example, the display device 2 or a terminal installed in another place) via a network. For example, a NIC (Network Interface Card) ) Etc. The display unit 12 is a part that displays data according to an instruction from the processing unit 14, and is realized by, for example, a liquid crystal display (LCD). The input unit 13 is a part where an operator inputs data (for example, initial setting data), and is realized by, for example, a keyboard or a mouse.

  The processing unit 14 exchanges data between each unit via a predetermined memory and controls the prediction waiting time evaluation apparatus 1 as a whole. A CPU (Central Processing Unit) is stored in the predetermined memory. This is realized by executing the program. The storage unit 15 stores data from the processing unit 14 and reads the stored data, and is realized by a nonvolatile storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The The predicted waiting time evaluation device 1 is installed in a hospital office management center or the like, but may be a stand-alone device (PC (Personal Computer) or the like) or can communicate with a plurality of terminals via a network. A simple device (such as a server) may be used.

  The display device 2 is a device that receives data from the predicted waiting time evaluation device 1 and displays the data on a screen. For example, the display device 2 is realized by a large display device installed in a waiting room of a hospital.

<< Data structure >>
2 to 5 are diagrams illustrating a configuration of data stored in the storage unit 15 of the predicted waiting time evaluation apparatus 1. FIG. 2 shows the configuration of the result data 15A. The record data 15A is record data related to the examinations conducted in the past in the hospital, and records including reservation, reception and examination time are stored for each patient who received the examination. , Department, doctor ID, ..., actual examination time is set. The necessary data items will be described in the description of the processing data 15D.

  FIG. 3 shows the configuration of the prediction data 15B. The prediction data 15B is a reception time (for example, 7 for each record of the actual data 15A (for example, a record indicated by a white arrow in FIG. 3 except for a predicted value, a predicted difference in examination time and a reference time)). : 42) is a data in which a reference time is set for each predetermined time interval, and a prediction value and a diagnosis time prediction difference at each reference time are set, and the patient is examined after receiving the patient at the hospital window. Records until the end are stored, and in each record, an examination date, a department, a doctor ID,..., A reference time are set as data items. The necessary data items will be described in the description of the processing data 15D.

  FIG. 4A shows the configuration of the initial setting data 15C. The initial setting data 15C is data of processing conditions used in the diagnosis waiting time prediction process that is always performed and the prediction probability calculation process that is performed as a batch, and includes a reference time interval 15C1, a number of days 15C2, and a doctor ID 15C3. The reference time interval 15C1 indicates the time interval of the reference time set in the diagnosis waiting time prediction process. For example, according to FIG. 3, “10 minutes” is set. The number of days 15C2 is the number of days of the examination date that is the target in the calculation process of the unpredicted probability. For example, if “1 day”, the prediction data 15B of the previous day is the target, and if “2 days”, 2 The prediction data 15B of the previous day and the previous day are targeted. The doctor ID 15C3 is an ID of a doctor who is a target in the calculation process of the predicted probability, and a plurality of doctor IDs may be set.

  FIG. 4B shows the configuration of the processing data 15D. The process data 15D is obtained by extracting records and data items necessary for the calculation process of the prediction failure probability from the prediction data 15B. The examination date 15D1, the medical department 15D2, the doctor ID 15D3, the patient ID 15D4, the predicted examination waiting time 15D5, the actual result. It consists of a record including a diagnosis start time 15D6, a reference time 15D7, and a result diagnosis waiting time 15D8. The examination date 15D1 indicates the day on which the examination is performed. The medical department 15D2 indicates the medical department where the medical examination is performed. The doctor ID 15D3 indicates an ID unique to the doctor who performed the examination. The patient ID 15D4 indicates an ID unique to the patient who has been examined.

  The predicted examination waiting time 15D5 is a predicted value of the patient's examination waiting time at the reference time 15D7, and changes every moment. In other words, when a new patient is accepted or when a patient's examination is completed, a predicted value of the diagnosis start time and waiting time of each patient is calculated. The predicted value of the waiting time is further matched with the reference time 15D7. Recalculated. For example, assuming that the time when a new patient is received is 7:59 and the waiting time predicted at that time is 170 minutes, the predicted diagnosis waiting time is 169 (= 170-1) when matched with the reference time 8:00. ) Minutes. The actual medical examination start time 15D6 is an actual time when the medical examination of the patient is started.

  The reference time 15D7 is a time in 10 minutes between 8:00 and 17:00, which is a hospital examination time, and the reception time (for example, when the patient ID in FIG. , 7:42) to the time (10:20) immediately before the actual examination start time (10:22) from the relevant time (8:00) immediately after the actual medical examination start time (10:22) is set. This is the base point. In the prediction data 15B of FIG. 3, the time until the time (10:50) immediately after the actual medical examination end time (10:48) is set. The time interval of the reference time 15D7 is defined by the reference time interval 15C1 of the initial setting data 15C. The actual medical examination waiting time 15D8 is a time when the patient actually waits for the medical examination from the reference time, and is an actual value obtained by subtracting the standard time 15D7 from the actual medical examination start time 15D6.

  The examination date 15D1 to the reference time 15D7 are extracted from the prediction data 15B, and the actual examination waiting time 15D8 is calculated and set from the extracted actual examination start time 15D6 and the reference time 15D7.

  FIG. 5A shows the configuration of the frequency data 15E. The frequency data 15E is data indicating a result of counting the frequency of the records for each division according to the time range by dividing the predicted medical check waiting time 15D5 and the actual medical check waiting time 15D8 of each record of the processing data 15D. This is matrix data (table data) having the predicted waiting time range 15E1 as a row item and the actual waiting time range 15E2 and the total 15E3 as column items. The predicted waiting time range 15E1 divides the predicted examination waiting time 15D5 into ranges of “within 30 minutes”, “within 60 minutes”, and “over 60 minutes”. The actual waiting time range 15E2 classifies the actual examination waiting time 15D8 into ranges of “within 30 minutes”, “within 60 minutes”, and “60 minutes or more”. “Within 60 minutes” means a range of 30 to 60 minutes. The total 15E3 indicates a value obtained by adding the frequencies for each range of the predicted waiting time range 15E1, and is used when calculating the probability data 15F.

  For example, “150” in the frequency data 15E indicates the frequency of records in which the predicted examination waiting time 15D5 is within 30 minutes, but the actual examination waiting time 15D8 has transitioned within 60 minutes among the records of the processing data 15D. . Further, “1000” in the frequency data 15E indicates the total value of the frequencies of the records of the processing data 15D whose predicted medical waiting time 15D5 is within 30 minutes.

  FIG. 5B shows the configuration of the probability data 15F. The probability data 15F is data indicating the probability of transition to each range of the actual medical examination waiting time 15D8 for each range of the predicted medical waiting time 15D5 of each record of the processing data 15D. And data of a matrix (table data) having the actual waiting time range 15F2 as a column item. The predicted waiting time range 15F1 divides the predicted examination waiting time 15D5 into ranges of “within 30 minutes”, “within 60 minutes”, and “over 60 minutes”. The actual waiting time range 15F2 divides the actual examination waiting time 15D8 into ranges of “within 30 minutes”, “within 60 minutes”, and “60 minutes or more”.

  For example, “15%” of the probability data 15F indicates a probability that the actual medical examination waiting time 15D8 extends within 60 minutes with respect to a record of the processing data 15D whose predicted medical waiting time 15D5 is within 30 minutes. Further, “5%” of the probability data 15F indicates a probability that the actual medical examination waiting time 15D8 is shortened within 30 minutes with respect to a record of the processing data 15D in which the predicted medical waiting time 15D5 is 60 minutes or more.

≪Device processing≫
FIG. 6 is a flowchart showing a diagnosis waiting time prediction process and an unforeseen probability calculation process. This process is performed mainly in the prediction waiting time evaluation apparatus 1, in which the processing unit 14 acquires initial setting data from the other by the communication unit 11 or the input unit 13, and refers to and updates the data in the storage unit 15, while waiting for the examination waiting time. Prediction, and the calculation and display of the probability of losing it. It is assumed that the result data 15A shown in FIG. 2 is set in the storage unit 15 before this processing.

  First, the prediction waiting time evaluation apparatus 1 acquires the reference time interval, the number of days, and the doctor ID as conditions for the calculation process of the prediction failure probability, and the storage unit 15 as the reference time interval 15C1, the number of days 15C2, and the doctor ID 15C3 of the initial setting data 15C. (S601). The acquisition of the processing conditions may be performed from the input unit 13 according to an operation by the operator of the predicted waiting time evaluation apparatus 1 or from the communication unit 11 according to transmission from a terminal capable of communicating with the predicted waiting time evaluation apparatus 1. You may go. At this time, the numerical value in each column of the frequency data 15E is initialized to zero.

  Next, the predicted waiting time evaluation apparatus 1 sets a reference time for each record of the record data 15A, calculates a predicted diagnosis waiting time at the reference time, and includes predicted data 15B including the predicted diagnosis waiting time for each reference time. Is stored in the storage unit 15 (S602). First, based on the reference time interval 15C1, the reference time is set between after the reception time and before the actual medical examination start time. Then, the predicted diagnosis start time and the predicted diagnosis waiting time at each reference time are calculated. For details, refer to the explanation of the predicted examination waiting time 15D5 and the reference time 15D7.

  Subsequently, the predicted waiting time evaluation apparatus 1 extracts a record including necessary data items from the predicted data 15B based on the number of days 15C2 and the doctor ID 15C3, and stores the record as processing data 15D in the storage unit 15 (S603). Specifically, in the prediction data 15B, the examination date is within a period corresponding to the number of days 15C2 (for example, if the number of days is 1, the previous day. If the number of days is 2, the previous day and the day before yesterday ...). Yes, a record whose doctor ID is doctor ID 15C3 is extracted. Then, from the data items of each record, the examination date 15D1 to the reference time 15D7 are extracted and set as processing data 15D excluding the actual examination waiting time 15D8.

  At this time, the predicted waiting time evaluation apparatus 1 calculates and sets the actual examination waiting time 15D8 for each reference time 15D7 of the processing data 15D. For example, as shown in FIG. 4B, when the reference time 15D7 is 8:00, 142 (minutes) obtained by subtracting 8:00 from 10:22 of the actual medical examination start time 15D6 is set as the actual medical examination waiting time 15D8. To do. When the reference time 15D7 is 10:20, 2 (minutes) obtained by subtracting 10:20 from 10:22 of the actual examination start time 15D6 is set as the actual examination waiting time 15D8.

  If there are a plurality of doctor IDs 15C3, the processes of S603 to S610 are performed for each doctor ID.

  And the prediction waiting time evaluation apparatus 1 performs the process of S605-S607 about all the patient ID15D4 and all prediction medical waiting time 15D5 in the process data 15D (S604-S608). First, it is specified whether the range of the predicted examination waiting time 15D5 is within 30 minutes, within 60 minutes, or over 60 minutes (S605). Next, it is specified whether the range of the actual examination waiting time 15D8 is within 30 minutes, within 60 minutes, or over 60 minutes (S606). Then, 1 is added to the numerical value of the column (section) corresponding to the range specified in S605 and S606 in the frequency data 15E (S607). By performing the processing of S604 to S608, the frequency of each record in the processing data 15D can be counted for each division (transition pattern) according to the range of the predicted examination waiting time 15D5 and the actual examination waiting time 15D8.

  Subsequently, the predicted waiting time evaluation apparatus 1 sums the frequencies for each range of the predicted waiting time range 15E1 in the frequency data 15E, sets the total value as a total 15E3, and sets the total number of frequencies from the frequency data 15E to the probability data 15F. The numerical value of each column is calculated and set (S609). For example, as shown in FIG. 5B, the probability data 15F is calculated by “830/1000 × 100” in the frequency data 15E as shown in FIG. 5% is calculated by “25/500 × 100” of the frequency data 15E.

  Further, the predicted waiting time evaluation apparatus 1 displays the numerical value of the probability data 15F (S610). Specifically, the probability data 15 </ b> F is transmitted to the display device 2 through the communication unit 11. Then, the display device 2 receives the probability data 15F and displays it.

  FIG. 7 is a diagram showing the display contents of the probability data 15F on the display device 2. As shown in FIG. In the “probability of prediction failure” at the bottom of FIG. 7, for example, “within 30 minutes → within 60 minutes... 15%” is displayed. This is because the waiting time of the patient whose number (patient ID) is displayed in “within 30 minutes” among the “waiting for examination” in the middle position in FIG. 7 is actually within “60 minutes”. This means that the probability of extension is 15%. Then, among the probability data 15F in FIG. 5B, “15%” in which the predicted waiting time range 15F1 is set within 30 minutes and the actual waiting time range 15F2 is set within 60 minutes is displayed. It is. 7 is displayed based on the range of the predicted examination waiting time of each patient at the current time calculated by the conventional waiting time prediction method.

  The predicted waiting time evaluation apparatus 1 may transmit the probability data 15F to a portable terminal owned by the patient. In that case, it is conceivable to simultaneously notify the examination waiting time and the time range of the patient at that time and the probability that the time range is actually different.

  In the above embodiment, the program executed by the processing unit 14 is recorded on a computer-readable recording medium so that each unit in the predicted waiting time evaluation apparatus 1 shown in FIG. It is assumed that the predicted waiting time evaluation apparatus 1 according to the embodiment of the present invention is realized by causing a computer to read and execute a program. In this case, the program may be provided to the computer via a network such as the Internet, or a semiconductor chip or the like in which the program is written may be incorporated in the computer.

  According to the embodiment of the present invention described above, it is possible to reduce the annoyance of a patient waiting for a medical examination in a hospital.

  Specifically, as shown in S601 and S603 of FIG. 6, since the record that matches the doctor ID 15C3 that is initially set is extracted as the processing data 15D from the prediction data 15B, the prediction wait is performed according to the examination results by the doctor. The probability that the time is out can be calculated.

  Next, as shown in S604 to S608, for each record of the extracted processing data 15D, the predicted waiting time range 15E1 and the actual waiting time range 15E2 are specified, and the frequency for each section according to each time range is counted, and in S609 As shown, since probability data 15F is set from frequency data 15E, the rate at which the time range has changed during the transition from predicted medical waiting time 15D5 to actual medical waiting time 15D8, that is, the probability that the time range is different is calculated. Can do.

  Then, as shown in S610, the probability data 15F is displayed for the patient in the waiting room, so that the patient knows that his / her waiting time currently displayed may actually change. Will be prepared to wait for a reasonable amount of time.

  According to the above, it is possible to provide a detailed service for the prediction display of the examination waiting time in the waiting room of the hospital.

<< Other embodiments >>
As mentioned above, although the form for implementing this invention was demonstrated, the said embodiment is for making an understanding of this invention easy, and is not for limiting and interpreting this invention. The present invention can be changed and improved without departing from the gist thereof, and equivalents thereof are also included in the present invention. For example, the following embodiments can be considered.

(1) Although the example which applied the prediction waiting time evaluation apparatus 1 about the patient's examination by the doctor of a hospital was demonstrated in the said embodiment, it is not restricted to this, Other service provision facilities, for example, a beauty salon, eating and drinking, etc. The service time prediction device 1 may be applied to a service in a store or the like. Also, it may be applied to the waiting time of transportation (predicted value is 0). For example, the waiting time at a bus stop (the time from the time in the timetable until the bus actually arrives) is the weather that causes the arrival delay. You may evaluate according to (it gets a lot of passengers at the time of rain) and time zone (the road is congested during commuting time zone).

(2) In the prediction data 15B in FIG. 3 and the processing data 15D in FIG. 4 (b), the reference time of the examination waiting time has been described as being in 10-minute increments. Since the base point only needs to be determined, the time is not necessarily limited to a fixed interval, and a time determined by another method may be used as the reference time. For example, the time when the predicted medical examination waiting time is actually recalculated, that is, the time when a new patient is accepted or the time when the medical examination of a patient is completed may be used as the reference time.

(3) In the above embodiment, the record in which the examination date is within the period corresponding to the number of days 15C2 is extracted from the prediction data 15B as the processing data 15D. However, based on the conditions of other examination dates You may make it extract. For example, when there is a day when the corresponding doctor does not come within the above period, it is conceivable to adjust the period so that the extraction target is 15 C2 minutes. In addition, when the number of patients to be examined changes greatly according to the specific day of the week or month, it is conceivable to extract the records for the same day of the week or specific day as the day on which the estimated waiting time is to be evaluated for 15C2. Further, it may not be the entire time zone of the examination date, and a record in the same time zone as the time zone for which the estimated waiting time should be evaluated may be selected.

(4) In the above embodiment, the estimated waiting time required by the patient is about 30 minutes, so the predicted and actual values of the waiting time for examination are divided into ranges of 30 minutes, 60 minutes, and 60 minutes or more. However, another division may be performed, or the predicted value and the actual value may be divided in different ranges. For example, in principle, a hospital that accepts only reserved patients will have a shorter waiting time and require a highly accurate guideline. Therefore, it may be divided into ranges of 15 minutes, 30 minutes, or 30 minutes or more. In addition, when a margin is provided for the predicted examination waiting time, since the actual value is often shorter than the predicted value, the predicted value is divided into ranges of 30 minutes, 60 minutes, or 60 minutes or more. On the other hand, the actual values may be divided into ranges of 15 minutes, 30 minutes, or 30 minutes or more.

(5) In the above embodiment, when the number of days 15C2 is two days or more, the prediction data 15B for the period is collectively described to obtain the transition probability. However, the transition probability for each day is calculated and averaged. May be.

(6) Although only “probability of prediction failure” is displayed in FIG. 7, it may be displayed including “probability of prediction”. For example, “within 30 minutes → within 30 minutes... 83%” may be displayed.

DESCRIPTION OF SYMBOLS 1 Predictive waiting time evaluation apparatus 14 Processing part 15 Storage part 15A Performance data 15B Predictive data (waiting time data)
15D treatment data 15D1 Examination date (period, day or time)
15D3 Doctor ID (provider)
15D4 Patient ID (user)
15D5 Predictive medical waiting time (predicted service waiting time)
15D8 Actual medical examination waiting time (actual value of service waiting time)
15E Frequency data (number)
15E1 Expected waiting time range 15E2 Actual waiting time range 15F Probability data (probability)
15F1 Expected waiting time range 15F2 Actual waiting time range

Claims (8)

Calculate the probability that the service waiting time will be unpredicted from the waiting time data including the predicted value in the past and the actual value for the predicted value of the service waiting time, which is the time for the user to wait for the start of the service. A predictive waiting time evaluation device,
A plurality of ranges in which the service waiting time is divided corresponding to the predicted value is set as a predicted waiting time range, and a plurality of ranges in which the service waiting time is divided in correspondence with the actual value is set as an actual waiting time range. Means for setting and counting the number of the waiting time data included in the category specified by each predicted waiting time range and each actual waiting time range;
Based on the number of each section, for each predicted waiting time range, a means for calculating a ratio that the actual value for the predicted value of the predicted waiting time range is included in each actual waiting time range;
Means for outputting, as a probability that the prediction is lost, a ratio in which the actual value with respect to the predicted value of the predicted waiting time range is included in the actual waiting time range, which is different from the predicted waiting time range, of the calculated ratio;
The waiting time evaluation apparatus characterized by comprising. It is the prediction waiting time evaluation apparatus of Claim 1, Comprising:
Of the waiting time data, the predicted waiting time evaluation device using the predicted value and the actual value of the service waiting time in the same period, day, or time zone as the evaluation target. The prediction waiting time evaluation apparatus according to claim 1 or 2,
The waiting time data includes information specific to the provider and user of the service,
Among the waiting time data, the predicted waiting time evaluation apparatus using the predicted value and the actual value of the service waiting time related to the same provider or user as the evaluation target. The prediction waiting time evaluation apparatus according to any one of claims 1 to 3,
The means for outputting the probability is:
The predicted waiting time evaluation apparatus characterized by simultaneously outputting the predicted waiting time range relating to a predetermined user and the probability that the prediction is lost. The computer calculates the probability that the service waiting time will be unpredicted from the waiting time data including the past predicted value of the service waiting time, which is the time for the user to wait for the start of the service, and the actual value for the predicted value. And a predicted waiting time evaluation method to output,
The computer
A plurality of ranges in which the service waiting time is divided corresponding to the predicted value is set as a predicted waiting time range, and a plurality of ranges in which the service waiting time is divided in correspondence with the actual value is set as an actual waiting time range. Setting and counting the number of the waiting time data included in the category specified by each predicted waiting time range and each actual waiting time range;
Based on the number of each division, for each predicted waiting time range, calculating a ratio that the actual value for the predicted value of the predicted waiting time range is included in each actual waiting time range;
Out of the calculated ratios, the actual value for the predicted value of the predicted waiting time range is included in the actual waiting time range different from the predicted waiting time range, and the step of outputting as a probability that the prediction is off;
A method for evaluating a predicted waiting time, comprising: It is the prediction waiting time evaluation method of Claim 5, Comprising:
The computer
Of the waiting time data, the predicted waiting time evaluation method using the predicted value and the actual value of the service waiting time in the same period, day, or time zone as the evaluation target. The prediction waiting time evaluation method according to claim 5 or 6,
The waiting time data includes information specific to the provider and user of the service,
The computer
Of the waiting time data, the predicted waiting time evaluation method using the predicted value and the actual value of the service waiting time relating to the same provider or user as the evaluation target. A prediction waiting time evaluation method according to any one of claims 5 to 7,
The computer
In the step of outputting the probability,
The predicted waiting time evaluation method, wherein the predicted waiting time range relating to a predetermined user and the probability that the prediction is lost are simultaneously output.