An artificial intelligence service monitoring system

Abstract

The application discloses an artificial intelligence service monitoring system and relates to the technical field of service monitoring.The system monitors the user features, the environment features, the target service and the service function data of each medical self-service machine in real time, generates a comprehensive influence matrix according to the correlation of the user features, the environment features and the target service, generates a maximum relevant demand service sequence according to the comprehensive influence matrix and the current user features and the current environment features, adjusts the display interface of the medical self-service machine based on the maximum relevant demand service sequence, generates an event to be processed according to the service function data, gives different priorities, generates an event processing strategy in combination with the position and state of the management personnel, counts the number of medical self-service machines, the intervention times of the management personnel and the number of users of the service to calculate a medical self-service machine service index, and generates a report.The application monitors and optimizes the service of the medical self-service machine from multiple angles, and improves the service efficiency and user experience of the medical self-service machine.

Description

Technical Field

[0001] The present invention relates to the field of service monitoring technology, and in particular to an artificial intelligence service monitoring system. Background Art

[0002] In modern society, the rapid development of science and technology has profoundly changed our lifestyles. With the improvement of people's living standards, they are paying more attention to health care. This is especially true when they are sick or have any problem, no matter how big or small, they have to go to the hospital for a checkup. Hospitals are generally crowded during their opening hours, with long queues for registration, consultations, and even checkups. The waiting time can be several times longer than the time it takes to see a doctor or have an examination.

[0003] To address the challenges patients face when visiting hospitals, such as difficulty registering, paying fees, arranging hospitalization, and navigating the specific department, the widespread adoption of self-service medical devices is becoming a new trend. The introduction of self-service medical terminals represents a deep integration of hospital information technology and service process optimization. For patients, this approach saves both time and effort. For hospital management, it not only effectively eases traffic flow and reduces pressure on registration and billing windows, but also improves operational efficiency, ensuring efficient and orderly operation and enhancing patient satisfaction.

[0004] With the development of self-service medical kiosks, more and more hospital services are now available through these kiosks. However, existing technologies still have the following shortcomings: First, existing monitoring systems are primarily based on static rules and preset parameters, making them difficult to adapt to dynamically changing usage environments. Second, they are unable to analyze user behavior patterns and usage trends to predict potential problems. Third, monitoring data is isolated from device maintenance, lacking holistic analysis, making it difficult to use data insights to optimize resource allocation and service strategies. Fourth, as more and more services are available through self-service medical kiosks, how can users quickly find the medical services they need? In summary, current service monitoring systems suffer from relatively simple analysis, which makes it difficult to adapt to dynamically changing usage environments and lack holistic analysis, making it difficult to use data insights to optimize resource allocation and service strategies.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an artificial intelligence service monitoring system, which solves the problems raised in the above-mentioned background technology by analyzing user characteristics and environmental characteristics and finding the optimal strategy when manual intervention is required.

[0007] To achieve the above objectives, the present invention provides an artificial intelligence service monitoring system, which includes a data monitoring module, a data analysis module, a strategy module and a service evaluation module.

[0008] The data monitoring module includes a first monitoring unit and a second monitoring unit; the first monitoring unit is used to monitor and record user characteristics, environmental characteristics and target services;

[0009] The second monitoring unit is used to monitor service function data, including user operation time, number of remaining printed sheets, payment interface duration, number of user operation steps, number of people in queue, and location and status of management personnel;

[0010] The data analysis module generates a comprehensive impact matrix based on the correlation between user characteristics, environmental characteristics, and target services; generates a maximum correlation demand service sequence based on the comprehensive impact matrix and current user characteristics and current environmental characteristics; and adjusts the pre-built display interface of the medical self-service machine based on the maximum correlation demand service sequence; compares the service function data with the preset function threshold, generates pending events based on the comparison results, and assigns different priority weights to different pending events;

[0011] The policy module receives pending events and their weights in real time, generates event handling strategies based on different pending events and their weights, and combines the location and status of managers, handles pending events according to the event handling strategies, and records the number of managers' interventions;

[0012] The service evaluation module evaluates the service index corresponding to the medical self-service machine based on the number of medical self-service machines, the number of managers, the number of manager interventions, and the number of users served by the medical self-service machines, and generates a medical self-service machine service performance report.

[0013] Optionally, the data monitoring module includes a first monitoring unit and a second monitoring unit; the first monitoring unit is used to monitor and record user characteristics , environmental characteristics and target services , and build a comprehensive user feature set (j);

[0014] The user characteristics include gender and age group;

[0015] The environmental characteristics include weather and temperature range;

[0016] The target service refers to the service category selected by the user when using the medical self-service machine, and the target services include registration, payment, department inquiry, personal inquiry, hospitalization, drug price inquiry, report printing, and voucher printing;

[0017] The user comprehensive feature set: (j)={ , , };

[0018] in, =1, 2, 3, 4, ... , indicating the A medical self-service machine, The total number of self-service medical machines in the hospital outpatient department; 、 、 Representing the The first medical self-service machine User characteristics, environment characteristics and target services of each user.

[0019] Optionally, the second monitoring unit is used to monitor service function data, including user operation time , Print remaining paper count , payment interface duration , Number of people in queue ( ), user operation step data ( ) and management personnel location and manager status .

[0020] in, 、 、 、 ( ), ( ) represent the The current user operation time, number of remaining printed sheets, payment interface duration, number of people in queue, and user operation step data of each medical self-service machine; Indicates the Managers relative to The location of the medical self-service machine, Indicates the The status of a manager.

[0021] Optionally, the data analysis module generates a comprehensive impact matrix by analyzing the correlation between user characteristics, environmental characteristics and target services, specifically:

[0022] The first demand impact matrix of user characteristics on the target service is set as [p][k], the second demand impact matrix of environmental characteristics on the target service is set as [q][k], specifically:

[0023] [p][k] = ;

[0024] [q][k] = ;

[0025] in, 1, 2, 3, 4, ... , Indicates the total number of target service types, Represents the user comprehensive feature set (j)={ , , }middle Total number of users, The user comprehensive feature set (j)={ , , }middle Total number of users, Represents the total number of all users in the user comprehensive feature set.

[0026] Calculate a comprehensive impact matrix based on the first demand impact matrix and the second demand impact matrix , specifically:

[0027] = ;

[0028] in, Indicates the User characteristics and The demand intensity of each target service, Indicates the Environmental characteristics and The intensity of demand for target services, Indicates the User characteristics and Environmental characteristics and The comprehensive demand intensity of each target service.

[0029] Optionally, the maximum related demand service sequence refers to the sequence in the comprehensive impact matrix In , find the number of rows that match the current user characteristics and the current environment characteristics, and sort them to generate the maximum relevant demand service sequence.

[0030] Optionally, the data analysis module compares the service function data with a preset function threshold, and generates pending events based on the comparison result. The pending events include: a user operation time that is too long, a printing paper out event, a payment anomaly event, a queue that is too long, and an event that involves too many user operation steps. Different priority weights are assigned to different pending events. Specifically:

[0031] Analyze user operation time:

[0032] when > When the user operation time is too long, an event and the corresponding first identifier are generated. , and assign the first initial standard weight corresponding to the event of user operation time being too long , and update the weight periodically in real time according to the user operation time. The updated weight is:

[0033] = (1+ ) * ;

[0034] Where, It is the maximum standard value of user operation time preset by the system. Indicates the Real-time user operation time of each medical self-service machine, Indicates The real-time weight of the event of excessive user operation time corresponding to each medical self-service machine;

[0035] Analyze the number of remaining pages for printing:

[0036] when At 10 o'clock, a printing paper exhaustion event and a corresponding second identifier are generated. , assign the corresponding second initial standard weight to the printing paper exhaustion event , and update the weight periodically in real time according to the number of remaining papers to be printed. The updated weight is:

[0037] = (1+ ) * ;

[0038] Where, Indicates the Each medical self-service machine prints the remaining paper quantity in real time. Indicates The real-time weight of the printing paper exhaustion event corresponding to each medical self-service machine;

[0039] Analysis of the payment interface duration:

[0040] Time spent on the payment interface Longer than the preset maximum standard payment time When a payment exception event and a corresponding third identifier are generated , and assign corresponding third initial standard weight to payment abnormal events , and update the weight periodically in real time based on the payment interface duration:

[0041] = (1+ ) * ;

[0042] Where, Indicates the The duration of the medical self-service machine payment interface, Indicates The real-time weight of abnormal payment events corresponding to each medical self-service machine;

[0043] Analyze the number of people in the queue:

[0044] Monitor the user queue in real time through monitoring equipment, extract features and obtain the real-time queue number of each medical self-service machine ( ),when ( ) is greater than the preset number threshold Generate a queue too long event and the corresponding fourth identifier , and assign the corresponding fourth initial standard weight to the event of too long queues , and update the weight periodically in real time according to the real-time number of queues:

[0045] = (1+ ) * ;

[0046] Where, ( ) indicates the The real-time queue number of each medical self-service machine, Indicates The real-time weight of the long queue event corresponding to each medical self-service machine;

[0047] Analyze user operation step data:

[0048] The number of real-time operation steps of the user ( ) refers to the number of times a user clicks on the screen function button when using a medical self-service machine; ( ) is greater than the preset maximum number of user operation steps When the user operation steps too many events and the corresponding fifth identifier are generated , and assign the corresponding fifth initial standard weight to the event of excessive user operation steps , and periodically update the weight according to the number of real-time user operation steps:

[0049] = (1+ ) * ;

[0050] Where, ( ) indicates the The number of current user operation steps of a medical self-service machine, Indicates The real-time weight of the excessive user operation steps event corresponding to each medical self-service machine.

[0051] Optionally, the policy module receives pending events and their weights in real time, generates event handling strategies based on different pending events and their weights, and in combination with the location and status of the manager, handles the pending events according to the event handling strategies, and records the number of manual interventions by the manager; the specific steps are:

[0052] S1. Receive pending events and their weights from the data analysis module;

[0053] S2. Traverse all pending events and find the one with the largest weight.

[0054] S3. Check the location and status of the managers and select the managers whose status is available.

[0055] S4 find out the nearest manager from the medical self-service machine where the event is to be processed, and pass the event information corresponding to the event to be processed to the receiver in the hands of the manager;

[0056] S5 receives a confirmation signal from the receiver in the hands of the manager, and removes the pending event from all pending events;

[0057] S6. Update the counter of the number of manual interventions by the administrator.

[0058] Optionally, the location and status of the manager include:

[0059] The manager status is ,when =0, indicating the The status of a manager is idle; when =1, indicating the The status of a manager is busy;

[0060] The position of the manager refers to the position sensor installed in the receiver in the manager's hand. The medical self-service machine records the manager's position in real time through the position sensor. The position refers to the coordinate system with the medical self-service machine as the origin, the east-west direction as the x-axis, and the north-south direction as the y-axis, and the real-time x- and y-axis corresponding coordinates of the manager.

[0061] Optionally, the step of finding the manager closest to the medical self-service machine where the event to be processed is performed by calculating the straight-line distance between the manager and the medical self-service machine where the event to be processed is located using the manager's location information. The specific calculation formula is:

[0062] = ;

[0063] in, Indicates the Medical self-service machine and The straight-line distance between managers, 、 Respectively represent Managers in the The coordinate system with the medical self-service machine as the origin 、 Coordinate value.

[0064] Optionally, the service evaluation module counts the number of medical self-service machines, the number of management personnel, the number of manual interventions by management personnel, and the number of users served by the medical self-service machines to evaluate the medical self-service machine service index. , specifically:

[0065] = ;

[0066] in, Indicates the service hours of all medical self-service machines The total number of users of the service, is the maximum efficiency standard value based on manual service, 、 are the number of management personnel and medical self-service machines respectively; 、 is the preset weight, and , Indicates the number of interventions by managers.

[0067] The present invention provides an artificial intelligence service monitoring system, which has the following beneficial effects:

[0068] 1. This invention monitors the user characteristics and environmental features of medical self-service kiosks in real time, generates a service sequence that is most relevant to the user's characteristics, and adjusts the pre-built display interface of the medical self-service kiosk to make the system display interface more in line with user needs, reducing user selection time and improving the convenience of using the medical self-service kiosk.

[0069] 2. This invention monitors the service function data generated during the provision of services by the medical self-service kiosk, generates pending events, and promptly notifies management personnel to handle the events through the event processing strategy generated by the policy module. This effectively reduces the problems encountered by users during use and improves the efficiency of the use of the medical self-service kiosk. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a module diagram of an artificial intelligence service monitoring system of the present invention.

[0071] Figure 2 This is a flow chart of an event processing strategy for processing pending events according to the present invention. DETAILED DESCRIPTION

[0072] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0073] Example 1

[0074] See also Figure 1 , an artificial intelligence service monitoring system, the system includes a data monitoring module, a data analysis module, a strategy module and a service evaluation module, specifically:

[0075] Data monitoring module: includes a first monitoring unit and a second monitoring unit. The first monitoring unit is used to monitor and record user characteristics, environmental characteristics and target services; the second monitoring unit is used to monitor service function data, including user operation time, number of remaining printed sheets, payment interface duration, number of user operation steps, number of people in queue, and location and status of managers.

[0076] Data analysis module: Generates a comprehensive impact matrix through the correlation between user characteristics, environmental characteristics and target services; generates a maximum relevant demand service sequence based on the comprehensive impact matrix and current user characteristics and current environmental characteristics, and adjusts the display interface of the pre-built medical self-service machine based on the maximum relevant demand service sequence; compares the service function data with the preset function threshold, generates pending events based on the comparison results, and assigns different priority weights to different pending events.

[0077] Strategy module: Receives pending events and their weights in real time, generates event handling strategies based on different pending events and their weights, and combines the location and status of managers, handles pending events according to the event handling strategies, and records the number of managers' interventions.

[0078] Service evaluation module: Based on the number of medical self-service kiosks, the number of management personnel, the number of management personnel's interventions and the number of users served by the medical self-service kiosks, the service index corresponding to the medical self-service kiosks is evaluated, and a medical self-service kiosk service performance report is generated.

[0079] Specifically, the first monitoring unit is used to monitor and record user characteristics. , environmental characteristics and target services , and build a comprehensive user feature set (j);

[0080] The user characteristics include gender and age group.

[0081] It should be noted that the gender and age range are obtained by extracting the user's gender and date of birth from the user's ID card or medical insurance card. The age range includes 'youth', 'middle-aged', 'middle-aged and elderly', and 'elderly'. The specific calculation method is:

[0082] Calculate the user's age user_age based on the user's date of birth and current time, and obtain the user's age group based on the user's age:

[0083] If user_age<25, then user_stage='youth';

[0084] If 45>user_age>=25, then user_stage='middle-aged';

[0085] If 45= <user_age<65,则user_stage=‘中老年’;

[0086] If user_age>=65, then user_stage='elderly';

[0087] It should be noted that the weather and temperature segments refer to the system obtaining the current weather and temperature through the Internet and dividing the temperature into temperature segments. Including 'ultra-high temperature', 'high temperature', 'normal temperature', 'low temperature', and 'ultra-low temperature'. The specific calculation method is:

[0088] If Wd>38℃, then ='Ultra high temperature';

[0089] If 38℃>Wd>=28℃, then ='high temperature';

[0090] If 28℃>Wd>=18℃, then ='normal temperature';

[0091] If 18℃>Wd>=8℃, then ='low temperature';

[0092] If Wd < 8℃, ='ultra-low temperature'.

[0093] It should be noted that the target service refers to the service category selected by the user when using the medical self-service machine. The target services include registration, payment, department inquiry, personal inquiry, hospitalization, medical insurance inquiry, drug price inquiry, report printing, and voucher printing;

[0094] The user comprehensive feature set: (j)={ , , };

[0095] in, =1, 2, 3, 4, ... , indicating the A medical self-service machine, The total number of self-service medical machines in the hospital outpatient department; 、 、 Representing the The first medical self-service machine User characteristics, environment characteristics and target services of each user.

[0096] The second monitoring unit is used to monitor service function data, including user operation time , Print remaining paper count , payment interface duration , Number of people in queue ( ), user operation step data ( ) and management personnel location and manager status .

[0097] In the embodiment of the present invention, basic data support is provided for subsequent analysis by monitoring and recording the user characteristics, the environment characteristics, the target service, and the service function data.

[0098] The data analysis module generates a comprehensive impact matrix by analyzing the relationship between user characteristics, environmental characteristics and target services. Specifically:

[0099] The first demand impact matrix of user characteristics on the target service is set as [p][k], the second demand impact matrix of environmental characteristics on the target service is set as [q][k], specifically:

[0100] = ;

[0101] = ;

[0102] in, 1, 2, 3, 4, ... , Indicates the total number of target service types, Represents the user comprehensive feature set (j)={ , , }middle Total number of users, The user comprehensive feature set (j)={ , , }middle Total number of users, Represents the total number of users in the user comprehensive feature set;

[0103] Calculate a comprehensive impact matrix based on the first demand impact matrix and the second demand impact matrix , specifically:

[0104] = ;

[0105] in, Indicates the User characteristics and The demand intensity of each target service, Indicates the Environmental characteristics and The demand intensity of each target service, Indicates the User characteristics and Environmental characteristics and The comprehensive demand intensity of each target service.

[0106] The maximum relevant demand service sequence refers to the maximum relevant demand service sequence in the comprehensive impact matrix In , find the number of rows that match the current user characteristics and the current environment characteristics, and sort them to generate the maximum relevant demand service sequence.

[0107] It should be noted that the maximum relevant demand service sequence The calculation formula is:

[0108] = sort( );

[0109] in, 、 Respectively The current user characteristics and environment characteristics of each self-service medical machine, It represents the row of the comprehensive influence matrix that matches the current user characteristics and the current environment characteristics. sort() is the sorting function.

[0110] The data analysis module compares the service function data with the preset function thresholds and generates pending events based on the comparison results. The pending events include: user operation time too long event, printing paper out event, payment anomaly event, queue too long event, and user operation step too many event. Different pending events are assigned different priority weights. Specifically:

[0111] Analyze user operation time:

[0112] when > When the user operation time is too long, an event and the corresponding first identifier are generated. , and assign the first initial standard weight corresponding to the event of user operation time being too long , and update the weight periodically in real time according to the user operation time. The updated weight is:

[0113] = (1+ ) * ;

[0114] Where, It is the maximum standard value of user operation time preset by the system. Indicates the Real-time user operation time of each medical self-service machine, Indicates The real-time weight of the event of excessive user operation time corresponding to each medical self-service machine;

[0115] Analyze the number of remaining pages for printing:

[0116] when At 10 o'clock, a printing paper exhaustion event and a corresponding second identifier are generated. , assign the corresponding second initial standard weight to the printing paper exhaustion event , and update the weight periodically in real time according to the number of remaining papers to be printed. The updated weight is:

[0117] = (1+ ) * ;

[0118] Where, Indicates the Each medical self-service machine prints the remaining paper quantity in real time. Indicates The real-time weight of the printing paper exhaustion event corresponding to each medical self-service machine;

[0119] Analysis of the payment interface duration:

[0120] Time spent on the payment interface Longer than the preset maximum standard payment time When a payment exception event and a corresponding third identifier are generated , and assign corresponding third initial standard weight to payment abnormal events , and update the weight periodically in real time based on the payment interface duration:

[0121] = (1+ ) * ;

[0122] Where, Indicates the The duration of the medical self-service machine payment interface, Indicates The real-time weight of abnormal payment events corresponding to each medical self-service machine;

[0123] Analyze the number of people in the queue:

[0124] Monitor the user queue screen in real time through monitoring equipment, extract features and obtain the real-time queue number of each medical self-service machine ( ),when ( ) is greater than the preset number threshold Generate a queue too long event and the corresponding fourth identifier , and assign the corresponding fourth initial standard weight to the event of too long queues , and update the weight periodically in real time according to the real-time number of queues:

[0125] = (1+ ) * ;

[0126] Where, ( ) indicates the The real-time queue number of each medical self-service machine, Indicates The real-time weight of the long queue event corresponding to each medical self-service machine;

[0127] Analyze user operation step data:

[0128] The number of real-time operation steps of the user ( ) refers to the number of times a user clicks on the screen function button when using a medical self-service machine; ( ) is greater than the preset maximum number of user operation steps When the user operation steps too many events and the corresponding fifth identifier are generated , and assign the corresponding fifth initial standard weight to the event of excessive user operation steps , and periodically update the weight according to the number of real-time user operation steps:

[0129] = (1+ ) * ;

[0130] Where, ( ) indicates the The number of current user operation steps of a medical self-service machine, Indicates The real-time weight of the excessive user operation steps event corresponding to each medical self-service machine.

[0131] It should be noted that for each pending event, the initial standard weight should be set according to the importance of the event. For example, the event of running out of printing paper is relatively more important, the events of long user operation time, abnormal payment events, and too many user operation steps are relatively moderate in importance, and the event of too many people in the queue is relatively unimportant.

[0132] In an embodiment of the present invention, by real-time monitoring of user characteristics and environmental characteristics of medical self-service kiosks, and generating a service sequence with the greatest correlation to the user characteristics, the pre-built display interface of the medical self-service kiosk is adjusted to make the system display interface more in line with user needs, thereby reducing user selection time and improving user convenience in using the medical self-service kiosk.

[0133] The strategy module receives pending events and their weights in real time, generates event processing strategies based on different pending events and their weights, and combines the location and status of managers, processes pending events according to the event processing strategies, and records the number of manual interventions by managers.

[0134] The embodiment of the present invention analyzes the service function data generated during the service provision of the medical self-service machine, generates pending events, and generates an event processing strategy to promptly notify management personnel for processing, thereby effectively reducing the problems encountered by users during use and improving the efficiency of using the medical self-service machine.

[0135] The service evaluation module counts the number of medical self-service machines, the number of management personnel, the number of manual interventions by management personnel, and the number of users served by the medical self-service machines to evaluate the medical self-service machine service index. , specifically:

[0136] = ;

[0137] in, Indicates the service hours of all medical self-service machines The total number of users of the service, is the maximum efficiency standard value based on manual service, 、 are the number of management personnel and medical self-service machines respectively; 、 is the preset weight, Indicates the number of interventions by managers.

[0138] It should be noted that 、 They can be set to 0.98 and 0.02 respectively. Medical self-service machine service index The preset weight can be adjusted appropriately by the operator, indicating that the fewer times the manager intervenes, the better the medical self-service machine service.

[0139] Furthermore, the formula shows that the fewer the number of managers, the less manual intervention, the more people served, and the higher the efficiency of the medical self-service machine service.

[0140] In the embodiment of the present invention, the accuracy of evaluating the efficiency of the medical self-service machine is improved by calculating the ratio of the service efficiency of the medical self-service machine to the maximum efficiency standard value of manual service per unit time.

[0141] Example 2

[0142] See also Figure 2 The event handling strategy for handling pending events is as follows:

[0143] S1. Receive the pending events, corresponding identifiers, and their weights from the data analysis module;

[0144] S2. Traverse all pending events and find the one with the largest weight.

[0145] S3. Check the location and status of the managers and select the managers whose status is available.

[0146] S4 find out the nearest manager from the medical self-service machine where the event is to be processed, and pass the event information corresponding to the event to be processed to the receiver in the hands of the manager;

[0147] S5 receives a confirmation signal from the receiver in the hands of the manager, and removes the pending event from all pending events;

[0148] S6. Update the counter of the number of manual interventions by the administrator.

[0149] It should be noted that the status of the manager is ,when =0, indicating the The status of a manager is idle; when =1, indicating the The status of the manager is busy.

[0150] It should be noted that the position of the manager refers to the position sensor installed in the receiver in the manager's hand. The medical self-service machine records the manager's position in real time through the position sensor. The position refers to the coordinate system with the medical self-service machine as the origin, the east-west direction as the x-axis, and the north-south direction as the y-axis, and the real-time x- and y-axis corresponding coordinates of the manager.

[0151] The method of finding the manager closest to the medical self-service machine where the pending event is located is to calculate the straight-line distance between the manager and the medical self-service machine where the pending event is located using the manager's location information. The specific calculation formula is:

[0152] = ;

[0153] in, Indicates the Medical self-service machine and The straight-line distance between managers, 、 Respectively represent Managers in the The coordinate system with the medical self-service machine as the origin 、 Coordinate value.

[0154] This embodiment can improve the efficiency of managers in handling pending events, and process pending events with higher priorities first, thereby improving the utilization efficiency of medical self-service machines.

[0155] It should be noted that the above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0156] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0157] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0158] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0159] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0160] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, some or all of the units can be selected to achieve the purpose of the embodiment.

[0161] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit.

[0162] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0163] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An artificial intelligence service monitoring system, characterized in that: The system includes a data monitoring module, a data analysis module, a strategy module and a service evaluation module; The data monitoring module includes a first monitoring unit and a second monitoring unit; the first monitoring unit is used to monitor and record user characteristics, environmental characteristics and target services; The second monitoring unit is used to monitor service function data, including user operation time, number of remaining printed sheets, payment interface duration, number of user operation steps, number of people in queue, and location and status of management personnel; The data analysis module generates a comprehensive impact matrix based on the correlation between user characteristics, environmental characteristics, and target services; generates a maximum correlation demand service sequence based on the comprehensive impact matrix and current user characteristics and current environmental characteristics; and adjusts the pre-built display interface of the medical self-service machine based on the maximum correlation demand service sequence; compares the service function data with the preset function threshold, generates pending events based on the comparison results, and assigns different priority weights to different pending events; The policy module receives pending events and their weights in real time, generates event handling strategies based on different pending events and their weights, and combines the location and status of managers, handles pending events according to the event handling strategies, and records the number of managers' interventions; The service evaluation module evaluates the service index corresponding to the medical self-service kiosk based on the number of medical self-service kiosks, the number of management personnel, the number of management personnel's interventions, and the number of users served by the medical self-service kiosks, and generates a medical self-service kiosk service performance report; The data analysis module generates a comprehensive impact matrix by analyzing the relationship between user characteristics, environmental characteristics and target services. Specifically: The first demand impact matrix of user characteristics on the target service is set as [p][k], the second demand impact matrix of environmental characteristics on the target service is set as [q][k], specifically: = ； = ； in, 1, 2, 3, 4, ... , Indicates the total number of target service types, Represents the user comprehensive feature set (j)={ , , }middle Total number of users, The user comprehensive feature set (j)={ , , }middle Total number of users, Represents the total number of users in the user comprehensive feature set; Calculate a comprehensive impact matrix based on the first demand impact matrix and the second demand impact matrix , specifically: = ； in, Indicates the User characteristics and The demand intensity of each target service, Indicates the Environmental characteristics and The intensity of demand for target services, Indicates the User characteristics and Environmental characteristics and The comprehensive demand intensity of each target service; The service evaluation module counts the number of medical self-service machines, the number of management personnel, the number of manual interventions by management personnel, and the number of users served by the medical self-service machines to evaluate the medical self-service machine service index. , specifically: = ； in, Indicates the service hours of all medical self-service machines The total number of users of the service, is the maximum efficiency standard value based on manual service, 、 are the number of management personnel and medical self-service machines respectively; 、 is the preset weight, Indicates the number of interventions by managers.

2. An artificial intelligence service monitoring system according to claim 1, characterized in that: The data monitoring module includes a first monitoring unit and a second monitoring unit; the first monitoring unit is used to monitor and record user characteristics , environmental characteristics and target services , and build a comprehensive user feature set (j); The user characteristics include gender and age group; The environmental characteristics include weather and temperature range; The target service refers to the service category selected by the user when using the medical self-service machine. The target services include registration, payment, department inquiry, personal inquiry, medical insurance inquiry, hospitalization, drug price inquiry, report printing, and voucher printing; The user comprehensive feature set: (j)={ , , }; in, =1, 2, 3, 4, ... , indicating the A medical self-service machine, The total number of self-service medical machines in the hospital outpatient department; 、 、 Representing the The first medical self-service machine User characteristics, environment characteristics and target services of each user.

3. An artificial intelligence service monitoring system according to claim 2, characterized in that The second monitoring unit is used to monitor service function data, including user operation time , Print remaining paper count , payment interface duration , Number of people in queue ( ), user operation step data ( ) and management personnel location and manager status ; in, 、 、 、 ( ), ( ) represent the The current user operation time, number of remaining printed sheets, payment interface duration, number of people in queue, and user operation step data of each medical self-service machine; Indicates the Managers relative to The location of the medical self-service machine, Indicates the The status of a manager.

4. An artificial intelligence service monitoring system according to claim 3, characterized in that: The maximum relevant demand service sequence refers to the maximum relevant demand service sequence in the comprehensive impact matrix In , find the number of rows that match the current user characteristics and the current environment characteristics, and sort them to generate the maximum relevant demand service sequence.

5. The artificial intelligence service monitoring system according to claim 3, characterized in that: The data analysis module compares the service function data with the preset function thresholds and generates pending events based on the comparison results. The pending events include: user operation time too long event, printing paper out event, payment anomaly event, queue too long event, and user operation step too many event. Different pending events are assigned different priority weights. Specifically: Analyze user operation time: when > When the user operation time is too long, an event and the corresponding first identifier are generated. , and assign the first initial standard weight corresponding to the event of user operation time being too long , and update the weight periodically in real time according to the user operation time. The updated weight is: = (1+ ) * ； Where, It is the maximum standard value of user operation time preset by the system. Indicates the Real-time user operation time of each medical self-service machine, Indicates The real-time weight of the event of excessive user operation time corresponding to each medical self-service machine; Analyze the number of remaining pages for printing: when At 10 o'clock, a printing paper exhaustion event and a corresponding second identifier are generated. , assign the corresponding second initial standard weight to the printing paper exhaustion event , and update the weight periodically in real time according to the number of remaining papers to be printed. The updated weight is: = (1+ ) * ； Where, Indicates the Each medical self-service machine prints the remaining paper quantity in real time. Indicates The real-time weight of the printing paper exhaustion event corresponding to each medical self-service machine; Analysis of the payment interface duration: Time spent on the payment interface Longer than the preset maximum standard payment time When a payment exception event and a corresponding third identifier are generated , and assign corresponding third initial standard weight to payment abnormal events , and update the weight periodically in real time based on the payment interface duration: = (1+ ) * ； Where, Indicates the The duration of the medical self-service machine payment interface, Indicates The real-time weight of abnormal payment events corresponding to each medical self-service machine; Analyze the number of people in the queue: Monitor the user queue in real time through monitoring equipment, extract features and obtain the real-time queue number of each medical self-service machine ( ),when ( ) is greater than the preset number threshold Generate a queue too long event and the corresponding fourth identifier , and assign the corresponding fourth initial standard weight to the event of too long queues , and update the weight periodically in real time according to the real-time number of queues: = (1+ ) * ； Where, ( ) indicates the The real-time queue number of each medical self-service machine, Indicates The real-time weight of the long queue event corresponding to each medical self-service machine; Analyze user operation step data: The number of real-time operation steps of the user ( ) refers to the number of times a user clicks on the screen function button when using a medical self-service machine; ( ) is greater than the preset maximum number of user operation steps When the user operation steps too many events and the corresponding fifth identifier are generated , and assign the corresponding fifth initial standard weight to the event of excessive user operation steps , and periodically update the weight according to the number of real-time user operation steps: = (1+ ) * ； Where, ( ) indicates the The number of current user operation steps of a medical self-service machine, Indicates The real-time weight of the excessive user operation steps event corresponding to each medical self-service machine.

6. The artificial intelligence service monitoring system according to claim 1, characterized in that: The policy module receives pending events and their weights in real time, generates event handling strategies based on different pending events and their weights, and combines the location and status of managers, handles pending events according to the event handling strategies, and records the number of manual interventions by managers. The specific steps are as follows: S1. Receive pending events and their weights from the data analysis module; S2. Traverse all pending events and find the one with the largest weight. S3. Check the location and status of the managers and select the managers whose status is available. S4 find out the nearest manager from the medical self-service machine where the event is to be processed, and pass the event information corresponding to the event to be processed to the receiver in the hands of the manager; S5 receives a confirmation signal from the receiver in the hands of the manager, and removes the pending event from all pending events; S6. Update the counter of the number of manual interventions by the administrator.

7. An artificial intelligence service monitoring system according to claim 6, characterized in that: The positions and status of managers include: The administrator status is ,when =0, indicating the The status of a manager is idle; when =1, indicating the The status of a manager is busy; The position of the manager refers to the position sensor installed in the receiver in the manager's hand. The medical self-service machine records the manager's position in real time through the position sensor. The position refers to the coordinates corresponding to the real-time x and y axes of the manager in a coordinate system with the medical self-service machine as the origin, the east-west direction as the x-axis, and the north-south direction as the y-axis.

8. An artificial intelligence service monitoring system according to claim 7, characterized in that: The method of finding the manager closest to the medical self-service machine where the pending event is located is to calculate the straight-line distance between the manager and the medical self-service machine where the pending event is located using the manager's location information. The specific calculation formula is: = ； in, Indicates the Medical self-service machine and The straight-line distance between managers, 、 Respectively represent Managers in the The coordinate system with the medical self-service machine as the origin 、 Coordinate value.

Images