Queuing and calling method and system

Abstract

The invention provides a queuing and calling method and system, and relates to the technical field of queuing and calling. The method comprises the following steps: inputting an interval duration from a current moment to a starting moment of a business handling time period and a pre-recorded reserved number of people in the business handling time period into a first number of people prediction model, and predicting a first reserved total number of people in the business handling time period; inputting the actual reservation number of people and the number of people change characteristics in the business handling time period in the latest N days into a second number of people prediction model, and predicting a second reservation number of people in the business handling time period; according to the first appointment total number of people and the second appointment total number of people in the business handling time period, predicting the final appointment total number of people in the business handling time period; and inputting the final reservation total number of people and the proportions of the businesses of the business types into a first waiting time length prediction model, and predicting the business handling waiting time length which needs to be waited after the user signs in the handling site of each sign-in time slice in the sign-in time period corresponding to the business handling time period.

Description

Technical Field

[0001] The present application relates to the technical field of queuing and calling numbers, and in particular to a queuing and calling number method and system. Background Art

[0002] In many situations, you need to queue up to handle business. For example, you need to queue up when you go to the bank, go to the government office, or see a doctor at a large hospital.

[0003] Currently, users can make an appointment for a business processing time in advance, and then arrive at the business processing site to sign in and queue before the end of the scheduled business processing time, and then rest at the candidate location and wait for their number to be called. This can help people get rid of the fatigue of standing in line and make business processing more reasonable and orderly.

[0004] However, in some cases, when users arrive at the service site, they have to wait for a long time due to the large number of people queuing, which may even cause them to give up on the service, resulting in a low user experience. Summary of the Invention

[0005] The present application provides a queuing and calling method and system for solving the problem in the prior art that in some cases, when users arrive at the business processing site, they have to wait for a long time due to the large number of people queuing, and even give up the business, resulting in a low user experience.

[0006] In a first aspect, the present application provides a queuing method, which is applied to a server. The method provided by the present application includes:

[0007] Receiving queue reservation information sent by a user terminal based on a target application, wherein the queue reservation information includes a reserved service processing time period, a service processing type, and user identity information;

[0008] When the user identity information belongs to a preset advanced user identity information set, the interval length between the current moment and the start moment of the service processing time period and the pre-recorded number of people who have made reservations for the service processing time period are input into a pre-trained first number prediction model to predict the total number of people who have made reservations for the first service processing time period, wherein the first number prediction model is obtained by inputting a plurality of first training samples into a first neural network for training, each first training sample including a historical interval length between the current moment and the start moment of a historical service processing time period, a historical number of people who have made reservations for a historical service processing time period pre-recorded in the past, and a historical total number of people who actually made reservations for the corresponding historical service processing time period;

[0009] Obtain the actual number of appointments made during the business processing time period in the past N days, and extract the number change characteristics of the actual number of appointments made during the business processing time period in the past N days;

[0010] Inputting the actual number of appointments and number change characteristics during the business processing time period in the past N days into a pre-trained second number prediction model to predict the second number of appointments during the business processing time period, wherein the second number prediction model is trained by inputting multiple second training samples into a long short-term memory network, each second training sample including the actual number of appointments during the business processing time period in the past N days, the corresponding historical number change characteristics, and the historical total number of actual appointments during the corresponding historical business processing time period;

[0011] Predict the final total number of appointments for the business processing time period based on the total number of first appointments and the total number of second appointments for the business processing time period;

[0012] According to the business processing time period, determine the proportion of each business type handled in the business processing time period;

[0013] The final total number of appointments and the proportion of each business type are input into the pre-trained first waiting time prediction model to predict the waiting time for business processing after the user signs in on-site at each sign-in time slot in the sign-in time slot corresponding to the business processing time slot. The first waiting time prediction model is obtained by inputting multiple third training samples into the second neural network for training, each third training sample including the total number of historical appointments, the proportion of each business type in history, and the corresponding historical actual waiting time for business processing after the user signs in on-site at each historical sign-in time slot in the historical sign-in time slot corresponding to the historical business processing time slot;

[0014] Recommending a target check-in time slice associated with the minimum service processing waiting time to the user terminal;

[0015] After receiving the check-in instruction based on the user identity information from the user terminal sent by the check-in machine at the business processing site during the target check-in time slice, the business queue number associated with the user identity information is generated according to the number of people who have checked in but have not processed the business, and the user identity information is queued and called according to the business queue number.

[0016] In some embodiments, after generating a service queue number associated with user identity information based on the number of people who have signed in but have not yet processed the service, the method provided by the present application further includes:

[0017] The number of people who have signed in but not yet processed their services and the type of pending services corresponding to each person are input into a pre-trained second waiting time prediction model to predict the waiting time that the user corresponding to the user identity information still needs to wait, wherein the second waiting time prediction model is trained by inputting multiple fourth training samples into the third neural network, each fourth training sample including the historical number of people who have signed in but not yet processed their services and the historical type of pending services corresponding to each person, as well as the historical actual waiting time of the user corresponding to the corresponding historical user identity information;

[0018] Sending the waiting time that the user corresponding to the user identity information needs to wait to the user terminal;

[0019] In response to a temporary leave instruction input by a user from a user terminal, determining in real time the remaining waiting time of the user, and receiving in real time user location information sent by the user terminal, wherein the temporary leave instruction carries a mode of transportation for leaving;

[0020] Determine in real time how long it will take for the user to return to the business processing site based on the user's location information, the location information of the business processing site, and the mode of transportation;

[0021] When the return time is equal to the remaining waiting time of the user, a prompt message indicating that the user should return to the service processing site as soon as possible is sent to the user terminal.

[0022] In some embodiments, after queuing and calling the user identity information according to the service queue number, the method provided by the present application further includes:

[0023] Record the time when the user's identity information is called, and determine the actual service processing waiting time from the time the number is called to the time the check-in instruction is received;

[0024] When the difference between the actual waiting time for business processing and the predicted waiting time for business processing is greater than the set time difference threshold, the network parameters configured by the first number of people prediction model, the network parameters configured by the second number of people prediction model, and the network parameters configured by the first waiting time prediction model are updated according to the time difference.

[0025] In some embodiments, predicting the final total number of appointments for a business processing time period based on the first total number of appointments and the second total number of appointments for the business processing time period includes:

[0026] The total number of the first appointments and the total number of the second appointments in the business processing time period are input into the pre-trained third number prediction model to predict the final total number of appointments in the business processing time period, wherein the third number prediction model is obtained by inputting multiple fifth training samples into the fourth neural network for training, wherein each fifth training sample includes the historical total number of the first appointments, the historical total number of the second appointments, and the historical total number of the final appointments in the corresponding historical business processing time period.

[0027] In some embodiments, predicting the final total number of appointments for a business processing time period based on the first total number of appointments and the second total number of appointments for the business processing time period includes:

[0028] According to the formula N=k1N1+k2N2, the final total number of appointments for the business handling time period is predicted, where N is the final total number of appointments for the business handling time period, N1 is the total number of first appointments, N2 is the total number of second appointments, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 <k1<1,0<k2<1,k1+k2=1。

[0029] In a second aspect, the present application provides a queuing system configured on a server. The system provided by the present application includes:

[0030] An information receiving unit is configured to receive queue reservation information sent by a user terminal based on a target application, wherein the queue reservation information includes a reserved service processing time period, a service processing type, and user identity information;

[0031] A first number prediction unit is configured to, when the user identity information belongs to a preset advanced user identity information set, input the interval between the current moment and the start moment of the service processing time period and the number of people who have made reservations for the pre-recorded service processing time period into a pre-trained first number prediction model to predict the total number of people who have made reservations for the first service processing time period, wherein the first number prediction model is trained by inputting a plurality of first training samples into a first neural network, each first training sample including a historical interval between the current moment and the start moment of a historical service processing time period, a historical number of people who have made reservations for the historical service processing time period pre-recorded in the past, and a historical total number of people who actually made reservations for the corresponding historical service processing time period;

[0032] A feature extraction unit is used to obtain the actual number of appointments made during the business processing time period in the past N days, and to extract the number change characteristics of the actual number of appointments made during the business processing time period in the past N days;

[0033] A second number prediction unit is configured to input the actual number of appointments and number change characteristics during the business processing time period in the past N days into a pre-trained second number prediction model to predict the second number of appointments during the business processing time period, wherein the second number prediction model is trained by inputting multiple second training samples into a long short-term memory network, each second training sample including the actual number of appointments during the business processing time period in the past N days, the corresponding historical number change characteristics, and the total number of actual appointments during the corresponding historical business processing time period;

[0034] A third number prediction unit is used to predict the final total number of reservations for the business processing time period based on the first total number of reservations and the second total number of reservations for the business processing time period;

[0035] A business proportion determination unit is used to determine the proportion of each business type handled in the business handling time period according to the business handling time period;

[0036] A first waiting time prediction unit is used to input the final total number of appointments and the proportion of services of each business type into a pre-trained first waiting time prediction model, and predict the waiting time for business processing that a user needs to wait after signing in on-site at each sign-in time slice in the sign-in time period corresponding to the business processing time period, wherein the first waiting time prediction model is obtained by inputting multiple third training samples into the second neural network for training, each third training sample including the total number of historical appointments, the proportion of services of each business type in history, and the corresponding historical actual waiting time for business processing that a user needs to wait after signing in on-site at each historical sign-in time slice in the historical sign-in time period corresponding to the historical business processing time period;

[0037] A time slice recommendation unit, configured to recommend a target check-in time slice associated with a minimum service processing waiting time to a user terminal;

[0038] The queuing and calling unit is used to generate a business queue number associated with the user identity information based on the number of people who have signed in but have not processed the business, and to call the user identity information in the queue according to the business queue number after receiving the check-in instruction based on the user identity information sent by the check-in machine at the business processing site during the target check-in time slice.

[0039] In some embodiments, the system provided by the present application further includes:

[0040] a second waiting time prediction unit, configured to input the number of people who have signed in but not processed services and the type of pending services corresponding to each person into a pre-trained second waiting time prediction model, and predict the waiting time that a user corresponding to the user identity information still needs to wait, wherein the second waiting time prediction model is trained by inputting a plurality of fourth training samples into the third neural network, each fourth training sample including the historical number of people who have signed in but not processed services and the historical type of pending services corresponding to each person, as well as the historical actual waiting time of the user corresponding to the corresponding historical user identity information;

[0041] An information sending unit, configured to send the waiting time that the user needs to wait corresponding to the user identity information to the user terminal;

[0042] a remaining waiting time determining unit, configured to determine in real time the remaining waiting time of the user in response to a temporary leave instruction input by the user from the user terminal;

[0043] The information receiving unit is further configured to receive in real time user location information sent by the user terminal, wherein the temporary leave instruction carries the mode of transportation for leaving;

[0044] A return time determination unit, configured to determine in real time the time required for the user to return to the business processing site based on the user's location information, the location information of the business processing site, and the mode of transportation;

[0045] The return prompt unit is used to send a prompt message to the user terminal indicating that the user should return to the business processing site as soon as possible when the return time is equal to the remaining waiting time of the user.

[0046] In some embodiments, the system provided by the present application further includes:

[0047] The actual waiting time determination unit is used to record the time when the user's identity information is called and determine the actual service processing waiting time from the time of the number being called to the time of receiving the sign-in instruction;

[0048] The parameter updating unit is used to update the network parameters configured by the first number of people prediction model, the network parameters configured by the second number of people prediction model, and the network parameters configured by the first waiting time prediction model according to the time difference when the difference between the actual waiting time for business processing and the predicted waiting time for business processing is greater than the set time difference threshold.

[0049] In some embodiments, the third number of people prediction unit is specifically used to input the total number of first appointments and the total number of second appointments for the business processing time period into a pre-trained third number of people prediction model to predict the final total number of appointments for the business processing time period, wherein the third number of people prediction model is obtained by inputting multiple fifth training samples into the fourth neural network for training, wherein each fifth training sample includes the historical total number of first appointments, the historical total number of second appointments, and the historical total number of final appointments for the corresponding historical business processing time period.

[0050] In some embodiments, the third number prediction unit is specifically used to predict the final total number of reservations for the business processing time period according to the formula N=k1N1+k2N2, where N is the final total number of reservations for the business processing time period, N1 is the first total number of reservations, N2 is the second total number of reservations, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 <k1<1,0<k2<1,k1+k2=1。

[0051] The present application provides a queuing and calling method and system. When the user identity information belongs to a preset advanced user identity information set, the interval length between the current moment and the start moment of the business processing time period and the number of people who have made reservations in the pre-recorded business processing time period are input into a pre-trained first number prediction model to predict the total number of people who have made reservations for the first business processing time period. Since the first training sample for training the first number prediction model includes the historical interval length between the current moment and the start moment of the historical business processing time period, the historical number of people who have made reservations in the historical pre-recorded historical business processing time period, and the historical actual total number of people who have made reservations for the corresponding historical business processing time period, the accuracy of the predicted total number of people who have made reservations for the first business processing time period is high.

[0052] The actual number of appointments made during the business processing time period in the past N days is obtained, and the number of people changing features of the actual number of appointments made during the business processing time period in the past N days is extracted. It can be understood that the number of people changing features is used to characterize the evolution pattern of the actual number of appointments made during the business processing time period in the past N days.

[0053] The actual number of reservations and number change characteristics for the business processing time period over the past N days are input into a pre-trained second number prediction model to predict the second number of reservations for the business processing time period. Because the multiple second training samples used to train the second number prediction model include the actual number of reservations for the business processing time period over the past N days, the corresponding historical number change characteristics, and the total number of actual reservations for the corresponding historical business processing time period, the obtained second number of reservations for the business processing time period has a high degree of accuracy.

[0054] Since the accuracy of the first number of appointments for the business processing time period is high, and the accuracy of the second number of appointments for the business processing time period is also high, the accuracy of predicting the final total number of appointments for the business processing time period based on the first total number of appointments and the second total number of appointments for the business processing time period is higher.

[0055] Based on the business processing time period, determine the proportion of each business type handled during that time period. Understandably, based on historical patterns, different business processing time periods correspond to different business types. For example, for banking services, the proportion of senior citizens handling services such as pension collection and time deposit rollovers is higher between 9:00 AM and 10:00 AM. While office workers using their lunch breaks to handle services such as account transfers and credit card repayments is higher between 1:00 PM and 2:00 PM. For Housing Authority services, the proportion of services such as property transfers and mortgage registrations is higher between 9:00 AM and 10:00 AM. While office workers using their lunch breaks to handle services such as tax deduction consultation and tax payments is higher between 1:00 PM and 2:00 PM. Therefore, the proportion of each business type handled during that time period can be determined based on the business processing time period.

[0056] The final total number of appointments and the proportion of each business type are input into the pre-trained first waiting time prediction model to predict the waiting time for business processing after the user signs in on-site at each sign-in time slot in the sign-in time period corresponding to the business processing time period. Since the training of the first waiting time prediction model is a third training sample including the total number of historical appointments, the proportion of each business type in history, and the corresponding historical actual business processing waiting time that the user needs to wait after signing in on-site at each historical sign-in time slot in the historical sign-in time period corresponding to the historical business processing time period. Therefore, the accuracy of the waiting time for business processing that needs to be waited after signing in on-site at each sign-in time slot is high.

[0057] Recommend target check-in time slots associated with the minimum service processing wait time to the user terminal. Users can browse their target check-in time slots associated with the minimum service processing wait time and plan their time to arrive at the service processing site to check in during the target check-in time slot. This can minimize personal service processing time, reduce the proportion of abandoned services, and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0059] Figure 1 One of the flow charts of the queuing calling method provided in an embodiment of the present application;

[0060] Figure 2 This is a functional module block diagram of the queuing system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments made by ordinary technicians in this field based on the inspiration of these embodiments fall within the scope of protection of this application.

[0062] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the numbers used in this way are interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0063] See also Figure 1 , an embodiment of the present application provides a queuing calling method, which is applied to a server.

[0064] like Figure 1 As shown, the method provided in the embodiment of the present application includes:

[0065] S101: receiving queue reservation information sent by a user terminal based on a target application.

[0066] The queuing reservation information includes the scheduled service time period, service type, and user identity information.

[0067] For example, it can be the business processing time period for banking services (such as 13:00-14:00), business processing type (such as credit card repayment business), user identity information (such as name and ID number) sent by the bank APP

[0068] S102: When the user identity information belongs to a preset advanced user identity information set, the interval between the current moment and the start moment of the business processing time period and the number of people who have made reservations in the pre-recorded business processing time period are input into the pre-trained first number prediction model to predict the total number of first reservations in the business processing time period.

[0069] Among them, since the first number prediction model is obtained by inputting multiple first training samples into the first neural network for training, each first training sample includes the historical interval length between the current historical moment and the start moment of the historical business processing time period, the historical number of people who have made reservations for the historical business processing time period pre-recorded in history, and the historical actual total number of reservations for the corresponding historical business processing time period, the accuracy of the predicted first total number of reservations for the business processing time period is high.

[0070] For example, when the user identity information belongs to a preset advanced user identity information set (such as a VIP user identity information set), the interval time (such as 3 hours) between the current time (such as 10:00) and the starting time (such as 13:00) of the business processing time period (such as 13:00-14:00) and the number of people who have made reservations in the pre-recorded business processing time period are input into the pre-trained first number prediction model to predict the total number of first reservations in the business processing time period (such as 13 people).

[0071] S103: Obtain the actual number of reservations during the business processing time period in the past N days, and extract the number change characteristics of the actual number of reservations during the business processing time period in the past N days. It can be understood that the number change characteristics are used to characterize the evolution pattern of the actual number of reservations during the business processing time period in the past N days.

[0072] For example, the time series dependency of the actual number of appointments made during the business processing time periods in the last N days can be extracted based on the deep confidence DBN network; based on the time series dependency of the actual number of appointments made during the business processing time periods in the last N days, the number change characteristics of the actual number of appointments made during the business processing time periods in the last N days can be extracted.

[0073] S104: Input the actual number of appointments and number change characteristics during the business processing time period in the past N days into the pre-trained second number prediction model to predict the second number of appointments during the business processing time period.

[0074] Among them, since the second number prediction model is obtained by training multiple second training samples in a long short-term memory network, each second training sample includes the actual appointment number in the business handling time period in the most recent N days in history, the corresponding historical number change characteristics, and the historical actual total appointment number in the corresponding historical business handling time period. Thus, the accuracy of the predicted second total appointment number in the business handling time period is also high.

[0075] S105: Predict the final total appointment number in the business handling time period according to the first total appointment number and the second total appointment number in the business handling time period.

[0076] Exemplarily, the specific implementation of S105 includes but is not limited to the following two:

[0077] The first: Input the first total appointment number and the second total appointment number in the business handling time period into a pre-trained third number prediction model to predict the final total appointment number in the business handling time period. Among them, the third number prediction model is obtained by training multiple fifth training samples in a fourth neural network. Among them, each fifth training sample includes the historical first total appointment number, the historical second total appointment number, and the historical final total appointment number in the corresponding historical business handling time period. [[ID=IO]]

[0078] The second: Predict the final total appointment number in the business handling time period according to the formula N = k1N1 + k2N2, where N is the final total appointment number in the business handling time period, N1 is the first total appointment number, N2 is the second total appointment number, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 < k1 < 1, 0 < k2 < 1, k1 + k2 = 1. For example, k1 = 0.5, k2 = O.5.

[0079] S106: Determine the proportion of the business of each business type handled in the business handling time period according to the business handling time period.

[0080] It can be understood that according to the summarized historical rules, the proportions of the business of each business type corresponding to different business handling time periods are different. For example, for banking services, from 9:00 to 10:00 in the morning, the proportion of the business handled by the elderly, such as pension collection and renewal of fixed-term deposits upon maturity, is relatively high. From 13:00 to 14:00 at noon, the proportion of the business handled by office workers during their breaks, such as transfer services and credit card repayment services, is relatively high. For the housing management bureau services, from 9:00 to 10:00 in the morning, the proportion of the business such as property transfer and mortgage registration is relatively high. From 13:00 to 14:00 at noon, the proportion of the business handled by office workers during their lunch breaks, such as tax deduction consultation and tax payment, is relatively high. Therefore, the proportion of the business of each business type handled in the business handling time period can be determined according to the business handling time period.

[0081] For example, the business handling time period can be input into a pre-trained business share prediction model to predict the proportion of business handled by each business type in the business handling time period. The business share prediction model is trained by inputting multiple historical business handling time periods and the proportion of business handled by each business type corresponding to each business handling time period into the to-be-trained network.

[0082] S107: The final total number of appointments and the proportion of each business type are input into the pre-trained first waiting time prediction model to predict the waiting time for business processing after the user signs in on-site in each sign-in time slice in the sign-in time period corresponding to the business processing time period.

[0083] Among them, the first waiting time prediction model is obtained by inputting multiple third training samples into the second neural network for training. Each third training sample includes the total number of historical appointments, the historical proportion of each business type of business, and the corresponding historical actual business processing waiting time that users need to wait after signing in on-site in each historical check-in time slice in the historical check-in time period corresponding to the historical business processing time period.

[0084] For example, when the business processing time period is 13:00-14:00, the corresponding check-in time period is 12:00-14:00. The check-in time slice can be any 5-minute or 10-minute sub-time period of the check-in time period 12:00-14:00. For example, the check-in time slice can be 12:00-12:05, 12:40-12:45, and 13:20-13:25, etc.; when the check-in time slice is 12:00-12:05, the predicted waiting time for waiting business processing can be 1 hour; when the check-in time slice is 12:40-12:45, the predicted waiting time for waiting business processing can be 25 minutes; when the check-in time slice is 13:00-13:05, the predicted waiting time for waiting business processing can be 40 minutes.

[0085] S108: Recommending a target check-in time slice associated with a minimum service processing waiting time to the user terminal.

[0086] Based on the above S106 , the check-in time slot 12:40-12:45, where the predicted waiting time for service processing is 25 minutes, may be recommended to the user terminal.

[0087] S109: After receiving the check-in instruction based on the user identity information from the user terminal sent by the check-in machine at the business processing site during the target check-in time slice, generate a business queue number associated with the user identity information according to the number of people who have checked in but have not processed the business, and queue and call the user identity information according to the business queue number.

[0088] In some embodiments, after S108, the method provided in the embodiment of the present application further includes:

[0089] Step 1: Input the number of people who have signed in but have not yet processed the business and the business type of each person's corresponding pending business into the pre-trained second waiting time prediction model to predict the waiting time that the user corresponding to the user identity information needs to wait.

[0090] Understandably, since the second wait time prediction model is trained by inputting multiple fourth training samples into the third neural network, each fourth training sample includes the historical number of people who have checked in but have not yet completed a transaction, the historical transaction type of each person's pending transaction, and the historical actual wait time of the user corresponding to the corresponding user identity information. This allows for a high degree of accuracy in predicting the remaining wait time for the user corresponding to the user identity information.

[0091] Step 2: Send the waiting time that the user needs to wait corresponding to the user identity information to the user terminal.

[0092] Step 3: In response to a temporary leave instruction input by the user from the user terminal, the remaining waiting time of the user is determined in real time, and the user location information sent by the user terminal is received in real time, wherein the temporary leave instruction carries the mode of transportation for leaving.

[0093] For example, when a user arrives at a business processing site and finds that the waiting time is long (e.g., 30 minutes), and needs to temporarily leave the business processing site, he or she can enter a temporary leave instruction on the user terminal based on the target application. When the user leaves the business processing site, the GPS module of the user terminal can record the user's location information in real time and send it to the server.

[0094] Step 4: Based on the user's location information, the location information of the business processing site, and the mode of transportation, the return time required for the user to return to the business processing site is determined in real time.

[0095] For example, when a user rides a shared bicycle to leave a business processing site for shopping or sightseeing, the return time of the user riding the shared bicycle from the user's location information to the business processing site can be determined.

[0096] Step 5: When the return time is equal to the remaining waiting time of the user, a prompt message is sent to the user terminal, indicating that the user should return to the service processing site as soon as possible.

[0097] Understandably, as time passes and the number of people who have signed in but haven't completed their business decreases, the remaining waiting time for users decreases. When the return time equals the remaining waiting time, a prompt message is sent to the user terminal, indicating that they should return to the business processing site as soon as possible. In this way, the user, upon receiving the prompt message, returns to the business processing site; and after returning to the business processing site, they can complete their business without waiting, thus meeting the diverse needs of users.

[0098] In some embodiments, after S108, the method provided in the embodiment of the present application further includes: recording the time when the user identity information is called, and determining the actual service waiting time from the time when the number is called to the time when the sign-in instruction is received; when the difference between the actual service waiting time and the predicted service waiting time is greater than a set time difference threshold, updating the network parameters configured by the first number of people prediction model, the network parameters configured by the second number of people prediction model, and the network parameters configured by the first waiting time prediction model according to the time difference. In this way, the subsequent predicted service waiting time that the user needs to wait after signing in on-site in each sign-in time slot in the sign-in time period corresponding to the service processing time period can be made with high accuracy.

[0099] In summary, the embodiment of the present application provides a queuing and calling method, in which, when the user identity information belongs to a preset advanced user identity information set, the interval length between the current moment and the start moment of the business processing time period and the number of people who have made reservations in the pre-recorded business processing time period are input into a pre-trained first number prediction model to predict the total number of people who have made reservations for the first business processing time period. Since the first training sample for training the first number prediction model includes the historical interval length between the historical current moment and the start moment of the historical business processing time period, the historical number of people who have made reservations in the historical pre-recorded historical business processing time period, and the historical actual total number of people who have made reservations for the corresponding historical business processing time period, the accuracy of the predicted total number of people who have made reservations for the first business processing time period is high.

[0100] The actual number of appointments made during the business processing time period in the past N days is obtained, and the number of people changing features of the actual number of appointments made during the business processing time period in the past N days is extracted. It can be understood that the number of people changing features is used to characterize the evolution pattern of the actual number of appointments made during the business processing time period in the past N days.

[0101] The actual number of reservations and number change characteristics for the business processing time period over the past N days are input into a pre-trained second number prediction model to predict the second number of reservations for the business processing time period. Because the multiple second training samples used to train the second number prediction model include the actual number of reservations for the business processing time period over the past N days, the corresponding historical number change characteristics, and the total number of actual reservations for the corresponding historical business processing time period, the obtained second number of reservations for the business processing time period has a high degree of accuracy.

[0102] Since the accuracy of the first number of appointments for the business processing time period is high, and the accuracy of the second number of appointments for the business processing time period is also high, the accuracy of predicting the final total number of appointments for the business processing time period based on the first total number of appointments and the second total number of appointments for the business processing time period is higher.

[0103] Based on the business processing time period, determine the proportion of each business type handled during that time period. Understandably, based on historical patterns, different business processing time periods correspond to different business types. For example, for banking services, the proportion of senior citizens handling services such as pension collection and time deposit rollovers is higher between 9:00 AM and 10:00 AM. While office workers using their lunch breaks to handle services such as account transfers and credit card repayments is higher between 1:00 PM and 2:00 PM. For Housing Authority services, the proportion of services such as property transfers and mortgage registrations is higher between 9:00 AM and 10:00 AM. While office workers using their lunch breaks to handle services such as tax deduction consultation and tax payments is higher between 1:00 PM and 2:00 PM. Therefore, the proportion of each business type handled during that time period can be determined based on the business processing time period.

[0104] The final total number of appointments and the proportion of each business type are input into the pre-trained first waiting time prediction model to predict the waiting time for business processing after the user signs in on-site at each sign-in time slot in the sign-in time period corresponding to the business processing time period. Since the training of the first waiting time prediction model is a third training sample including the total number of historical appointments, the proportion of each business type in history, and the corresponding historical actual business processing waiting time that the user needs to wait after signing in on-site at each historical sign-in time slot in the historical sign-in time period corresponding to the historical business processing time period. Therefore, the accuracy of the waiting time for business processing that needs to be waited after signing in on-site at each sign-in time slot is high.

[0105] Recommend target check-in time slots associated with the minimum service processing wait time to the user terminal. Users can browse their target check-in time slots associated with the minimum service processing wait time and plan their time to arrive at the service processing site to check in during the target check-in time slot. This can minimize personal service processing time, reduce the proportion of abandoned services, and improve the user experience.

[0106] See also Figure 2 , the embodiment of the present application provides a queuing and calling system, which is configured on a server. It should be noted that the basic principles and technical effects of the queuing and calling system provided by the embodiment of the present application are the same as those of the above-mentioned embodiment. For the sake of brief description, for parts not mentioned in the embodiment of the present application, please refer to the corresponding content in the above-mentioned embodiment. The system provided by the embodiment of the present application includes an information receiving unit, a first number of people prediction unit, a feature extraction unit, a second number of people prediction unit, a third number of people prediction unit, a business proportion determination unit, a first waiting time prediction unit, a time slice recommendation unit, and a queuing and calling unit, wherein,

[0107] An information receiving unit is configured to receive queue reservation information sent by a user terminal based on a target application, wherein the queue reservation information includes a reserved service processing time period, a service processing type, and user identity information;

[0108] A first number prediction unit is configured to, when the user identity information belongs to a preset advanced user identity information set, input the interval between the current moment and the start moment of the service processing time period and the number of people who have made reservations for the pre-recorded service processing time period into a pre-trained first number prediction model to predict the total number of people who have made reservations for the first service processing time period, wherein the first number prediction model is trained by inputting a plurality of first training samples into a first neural network, each first training sample including a historical interval between the current moment and the start moment of a historical service processing time period, a historical number of people who have made reservations for the historical service processing time period pre-recorded in the past, and a historical total number of people who actually made reservations for the corresponding historical service processing time period;

[0109] A feature extraction unit is used to obtain the actual number of appointments made during the business processing time period in the past N days, and to extract the number change characteristics of the actual number of appointments made during the business processing time period in the past N days;

[0110] A second number prediction unit is configured to input the actual number of appointments and number change characteristics during the business processing time period in the past N days into a pre-trained second number prediction model to predict the second number of appointments during the business processing time period, wherein the second number prediction model is trained by inputting multiple second training samples into a long short-term memory network, each second training sample including the actual number of appointments during the business processing time period in the past N days, the corresponding historical number change characteristics, and the total number of actual appointments during the corresponding historical business processing time period;

[0111] A third number prediction unit is used to predict the final total number of reservations for the business processing time period based on the first total number of reservations and the second total number of reservations for the business processing time period;

[0112] A business proportion determination unit is used to determine the proportion of each business type handled in the business handling time period according to the business handling time period;

[0113] A first waiting time prediction unit is used to input the final total number of appointments and the proportion of services of each business type into a pre-trained first waiting time prediction model, and predict the waiting time for business processing that a user needs to wait after signing in on-site at each sign-in time slice in the sign-in time period corresponding to the business processing time period, wherein the first waiting time prediction model is obtained by inputting multiple third training samples into the second neural network for training, each third training sample including the total number of historical appointments, the proportion of services of each business type in history, and the corresponding historical actual waiting time for business processing that a user needs to wait after signing in on-site at each historical sign-in time slice in the historical sign-in time period corresponding to the historical business processing time period;

[0114] A time slice recommendation unit, configured to recommend a target check-in time slice associated with a minimum service processing waiting time to a user terminal;

[0115] The queuing and calling unit is used to generate a business queue number associated with the user identity information based on the number of people who have signed in but have not processed the business, and to call the user identity information in the queue according to the business queue number after receiving the check-in instruction based on the user identity information sent by the check-in machine at the business processing site during the target check-in time slice.

[0116] In some embodiments, the system provided by the embodiments of the present application further includes: a second waiting time prediction unit, configured to input the number of people who have signed in but have not processed the business and the business type of the pending business corresponding to each person into a pre-trained second waiting time prediction model, and predict the waiting time that the user corresponding to the user identity information still needs to wait, wherein the second waiting time prediction model is trained by inputting multiple fourth training samples into the third neural network, each fourth training sample including the historical number of people who have signed in but have not processed the business and the historical business type of the pending business corresponding to each person, as well as the historical actual waiting time of the user corresponding to the corresponding historical user identity information;

[0117] An information sending unit, configured to send the waiting time that the user needs to wait corresponding to the user identity information to the user terminal;

[0118] a remaining waiting time determining unit, configured to determine in real time the remaining waiting time of the user in response to a temporary leave instruction input by the user from the user terminal;

[0119] The information receiving unit is further configured to receive in real time user location information sent by the user terminal, wherein the temporary leave instruction carries the mode of transportation for leaving;

[0120] A return time determination unit, configured to determine in real time the time required for the user to return to the business processing site based on the user's location information, the location information of the business processing site, and the mode of transportation;

[0121] The return prompt unit is used to send a prompt message to the user terminal indicating that the user should return to the business processing site as soon as possible when the return time is equal to the remaining waiting time of the user.

[0122] In some embodiments, the system provided by the present application further includes: an actual waiting time determination unit, configured to record the time when the user identity information is called and determine the actual service processing waiting time from the time when the number is called to the time when the sign-in instruction is received;

[0123] The parameter updating unit is used to update the network parameters configured by the first number of people prediction model, the network parameters configured by the second number of people prediction model, and the network parameters configured by the first waiting time prediction model according to the time difference when the difference between the actual waiting time for business processing and the predicted waiting time for business processing is greater than the set time difference threshold.

[0124] In some embodiments, the third number of people prediction unit is specifically used to input the total number of first appointments and the total number of second appointments for the business processing time period into a pre-trained third number of people prediction model to predict the final total number of appointments for the business processing time period, wherein the third number of people prediction model is obtained by inputting multiple fifth training samples into the fourth neural network for training, wherein each fifth training sample includes the historical total number of first appointments, the historical total number of second appointments, and the historical total number of final appointments for the corresponding historical business processing time period.

[0125] In some embodiments, the third number prediction unit is specifically used to predict the final total number of reservations for the business processing time period according to the formula N=k1N1+k2N2, where N is the final total number of reservations for the business processing time period, N1 is the first total number of reservations, N2 is the second total number of reservations, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 <k1<1,0<k2<1,k1+k2=1。

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A queuing method, characterized in that: Applied to a server, the method includes: Receiving queue reservation information sent by a user terminal based on a target application, wherein the queue reservation information includes a reserved service processing time period, a service processing type, and user identity information; In a case where the user identity information belongs to a preset advanced user identity information set, the interval length between the current moment and the start moment of the service processing time period and the pre-recorded number of people who have made reservations for the service processing time period are input into a pre-trained first number prediction model to predict the first total number of people who have made reservations for the service processing time period, wherein the first number prediction model is obtained by inputting a plurality of first training samples into a first neural network for training, each of the first training samples including the historical interval length between the current moment and the start moment of a historical service processing time period, the historical number of people who have made reservations for the historical service processing time period pre-recorded in history, and the historical total number of people who actually made reservations for the corresponding historical service processing time period; Obtain the actual number of people who made reservations during the business processing time period in the past N days, and extract the number change characteristics of the actual number of people who made reservations during the business processing time period in the past N days; Inputting the actual number of appointments for the business processing time period in the last N days and the number change characteristics into a pre-trained second number prediction model to predict the second number of appointments for the business processing time period, wherein the second number prediction model is trained by inputting multiple second training samples into a long short-term memory network, each second training sample including the actual number of appointments for the business processing time period in the last N days in history, the corresponding historical number change characteristics, and the total number of actual appointments for the corresponding historical business processing time period; Predicting the final total number of appointments for the business processing time period based on the first total number of appointments and the second total number of appointments for the business processing time period; Determine, based on the business processing time period, the proportion of each business type processed in the business processing time period; The final total number of appointments and the proportion of services of each business type are input into a pre-trained first waiting time prediction model to predict the waiting time for service processing that the user needs to wait after signing in on-site at each sign-in time slot in the sign-in time slot corresponding to the service processing time slot, wherein the first waiting time prediction model is obtained by inputting multiple third training samples into the second neural network for training, each of the third training samples including the total number of historical appointments, the historical proportion of services of each business type, and the corresponding historical actual waiting time for service processing that the user needs to wait after signing in on-site at each historical sign-in time slot in the historical sign-in time slot corresponding to the historical service processing time slot; recommending a target check-in time slice associated with a minimum service processing waiting time to the user terminal; After the user terminal receives the check-in instruction based on the user identity information sent by the check-in machine at the business processing site during the target check-in time slice, a business queue number associated with the user identity information is generated according to the number of people who have checked in but have not processed the business, and the user identity information is queued and called according to the business queue number.

2. The method according to claim 1, characterized in that After generating the service queue number associated with the user identity information based on the number of people who have signed in but have not processed the service, the method further includes: The number of people who have signed in but not processed their services and the type of pending services corresponding to each person are input into a pre-trained second waiting time prediction model to predict the waiting time that the user corresponding to the user identity information still needs to wait, wherein the second waiting time prediction model is trained by inputting multiple fourth training samples into a third neural network, each of the fourth training samples including the historical number of people who have signed in but not processed their services and the historical type of pending services corresponding to each person, as well as the historical actual waiting time of the user corresponding to the corresponding historical user identity information; Sending the waiting time that the user corresponding to the user identity information needs to wait to the user terminal; In response to a temporary leave instruction input by the user from the user terminal, determining in real time the remaining waiting time of the user, and receiving in real time user location information sent by the user terminal, wherein the temporary leave instruction carries a mode of transportation for departure; Determine in real time the time required for the user to return to the business processing site based on the user location information, the location information of the business processing site, and the transportation method; In the case that the return time is equal to the remaining waiting time of the user, a prompt message indicating that the user should return to the service processing site as soon as possible is sent to the user terminal.

3. The method according to claim 1, characterized in that After calling the user identity information in a queue according to the service queue number, the method further includes: Record the time when the user identity information is called, and determine the actual service processing waiting time from the time when the number is called to the time when the sign-in instruction is received; When the difference between the actual waiting time for business processing and the predicted waiting time for business processing is greater than the set time difference threshold, the network parameters configured by the first number of people prediction model, the network parameters configured by the second number of people prediction model, and the network parameters configured by the first waiting time prediction model are updated according to the time difference.

4. The method according to claim 1, wherein The predicting of the final total number of appointments for the business processing time period based on the first total number of appointments and the second total number of appointments for the business processing time period includes: The first total number of appointments and the second total number of appointments for the business processing time period are input into a pre-trained third number prediction model to predict the final total number of appointments for the business processing time period, wherein the third number prediction model is obtained by inputting multiple fifth training samples into a fourth neural network for training, wherein each of the fifth training samples includes the historical first total number of appointments, the historical second total number of appointments, and the historical final total number of appointments for the corresponding historical business processing time period.

5. The method according to claim 1, wherein The predicting of the final total number of appointments for the business processing time period based on the first total number of appointments and the second total number of appointments for the business processing time period includes: According to the formula N=k1N1+k2N2, the final total number of appointments for the business processing time period is predicted, where N is the final total number of appointments for the business processing time period, N1 is the total number of the first appointments, N2 is the total number of the second appointments, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 <k1<1,0<k2<1,k1+k2=1。 6. A queuing system, characterized in that: Configured on a server, the system includes: An information receiving unit, configured to receive queue reservation information sent by a user terminal based on a target application, wherein the queue reservation information includes a reserved service processing time period, a service processing type, and user identity information; A first number prediction unit is configured to, when the user identity information belongs to a preset advanced user identity information set, input the interval between the current moment and the start moment of the business processing time period and the pre-recorded number of people who have made reservations for the business processing time period into a pre-trained first number prediction model, and predict the total number of people who have made reservations for the first business processing time period, wherein the first number prediction model is obtained by inputting a plurality of first training samples into a first neural network for training, each of the first training samples including the historical interval between the current moment and the start moment of a historical business processing time period, the historical number of people who have made reservations for the historical business processing time period pre-recorded in history, and the historical total number of people who actually made reservations for the corresponding historical business processing time period; A feature extraction unit is used to obtain the actual number of people who have made reservations during the business processing time period in the past N days, and to extract a number change feature of the actual number of people who have made reservations during the business processing time period in the past N days; a second number prediction unit, configured to input the actual number of appointments for the business processing time period in the last N days and the number change characteristics into a pre-trained second number prediction model, and predict the second number of appointments for the business processing time period, wherein the second number prediction model is trained by inputting a plurality of second training samples into a long short-term memory network, each second training sample including the actual number of appointments for the business processing time period in the last N days in history, the corresponding historical number change characteristics, and the total number of actual appointments for the corresponding historical business processing time period; a third number prediction unit, configured to predict the final total number of reservations for the business handling time period based on the first total number of reservations and the second total number of reservations for the business handling time period; A business proportion determining unit, configured to determine, based on the business handling time period, the proportion of each business type handled in the business handling time period; A first waiting time prediction unit is used to input the total number of final appointments and the proportion of services of each business type into a pre-trained first waiting time prediction model, and predict the waiting time that users need to wait for business processing after signing in on-site at each check-in time slice in the check-in time period corresponding to the business processing time period, wherein the first waiting time prediction model is obtained by inputting multiple third training samples into the second neural network for training, each of the third training samples including the total number of historical appointments, the proportion of services of each business type in history, and the corresponding historical actual waiting time for business processing that users need to wait after signing in on-site at each historical check-in time slice in the historical check-in time period corresponding to the historical business processing time period; A time slice recommendation unit, configured to recommend a target check-in time slice associated with a minimum service processing waiting time to the user terminal; The queuing and calling unit is used to generate a business queue number associated with the user identity information according to the number of people who have signed in but have not processed the business, after receiving the check-in instruction based on the user identity information sent by the check-in machine at the business processing site during the target check-in time slice, and to queue and call the user identity information according to the business queue number.

7. The system according to claim 6, characterized in that The system further comprises: a second waiting time prediction unit, configured to input the number of people who have signed in but have not processed services and the type of pending services corresponding to each person into a pre-trained second waiting time prediction model, and predict the waiting time that the user corresponding to the user identity information still needs to wait, wherein the second waiting time prediction model is trained by inputting a plurality of fourth training samples into a third neural network, each of the fourth training samples including the historical number of people who have signed in but have not processed services and the historical type of pending services corresponding to each person, as well as the historical actual waiting time of the user corresponding to the corresponding historical user identity information; An information sending unit, configured to send the waiting time that the user corresponding to the user identity information needs to wait to the user terminal; a remaining waiting time determining unit, configured to determine in real time the remaining waiting time of the user in response to a temporary leave instruction input by the user from the user terminal; The information receiving unit is further configured to receive in real time the user location information sent by the user terminal, wherein the temporary leave instruction carries the mode of transportation for leaving; a return time determination unit, configured to determine in real time the return time required for the user to return to the business processing site based on the user location information, the location information of the business processing site, and the mode of transportation; The return prompting unit is used to send a prompting message to the user terminal indicating that the user should return to the business processing site as soon as possible when the return time is equal to the remaining waiting time of the user.

8. The system according to claim 6, wherein: The system further comprises: An actual waiting time determination unit is used to record the time when the user identity information is called and determine the actual service processing waiting time from the time when the number is called to the time when the sign-in instruction is received; A parameter updating unit is used to update the network parameters configured by the first number of people prediction model, the network parameters configured by the second number of people prediction model, and the network parameters configured by the first waiting time prediction model according to the time difference when the difference between the actual waiting time for business processing and the predicted waiting time for business processing is greater than a set time difference threshold.

9. The system according to claim 6, wherein: The third number prediction unit is specifically used to input the total number of first appointments and the total number of second appointments for the business processing time period into a pre-trained third number prediction model to predict the final total number of appointments for the business processing time period, wherein the third number prediction model is obtained by inputting multiple fifth training samples into the fourth neural network for training, wherein each of the fifth training samples includes the historical total number of first appointments, the historical total number of second appointments, and the historical total number of final appointments for the corresponding historical business processing time period.

10. The system according to claim 6, wherein: The third number prediction unit is specifically used to predict the final total number of reservations for the business processing time period according to the formula N=k1N1+k2N2, wherein N is the final total number of reservations for the business processing time period, N1 is the first total number of reservations, N2 is the second total number of reservations, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 <k1<1,0<k2<1,k1+k2=1。

Images