Queuing reservation system based on dynamic pricing and scheduling method thereof

Abstract

The invention relates to a queuing reservation system based on dynamic pricing and a scheduling method thereof. The system comprises a user interaction module used for receiving a queuing reservation request of each user; wherein the queuing appointment request comprises user information and an appointment time period; the dynamic pricing engine is used for calculating real-time pricing data based on the spatio-temporal characteristic information; the resource management module is used for acquiring equipment state information of each terminal and maintaining a time resource pool and an equipment resource pool according to the equipment state information; performing resource allocation in a time resource pool and an equipment resource pool according to the reservation time period and the real-time pricing data of each user, and constructing a three-dimensional resource matrix comprising three dimensions of reservation time period-equipment resource-real-time pricing; the intelligent scheduling module is used for generating a queuing queue according to the three-dimensional resource matrix, performing closed-loop scheduling on the queuing queue, and allocating each terminal according to the queuing queue; according to the technical scheme, the queue circulation efficiency can be improved, and the user payment conversion rate is improved.

Description

Technical Field

[0001] This application relates to the field of computer processing technology, and in particular to a queuing reservation system and scheduling method based on dynamic pricing. Background Technology

[0002] In recent years, with the rapid development of the sharing economy, queuing and reservation systems have been required in many business scenarios, such as unmanned self-service KTVs, shared office spaces, and smart retail terminals. Common queuing and reservation systems handle queuing and reservations through queuing scheduling or price adjustments. However, these queuing and reservation systems mainly adopt separate strategies for handling queuing scheduling or price adjustments, which can easily lead to excessive concentration of resources during peak hours and vacancy during off-peak hours, resulting in low efficiency in resource scheduling and allocation. Summary of the Invention

[0003] To address one of the aforementioned shortcomings, this application provides a queuing reservation system and scheduling method based on dynamic pricing, which can improve the efficiency of pricing data processing and response, and improve queue flow efficiency.

[0004] A queuing and reservation system based on dynamic pricing includes: a user interaction module, a resource management module, an intelligent scheduling module, and a dynamic pricing engine; wherein, The user interaction module is used to receive queue reservation requests from each user; wherein, the queue reservation request includes user information and reservation time slot; The dynamic pricing engine is used to calculate real-time pricing data based on spatiotemporal feature information; wherein, the spatiotemporal features include time dimension information and spatial dimension; The resource management module is used to obtain the device status information of each terminal, maintain the time resource pool and the device resource pool according to the device status information, and allocate resources in the time resource pool and the device resource pool according to the reservation time period and real-time pricing data of each user, and construct a three-dimensional resource matrix including reservation time period - device resources - real-time pricing. The intelligent scheduling module is used to generate a queuing queue based on the three-dimensional resource matrix, perform closed-loop scheduling on the queuing queue, and allocate each terminal according to the queuing queue.

[0005] In some embodiments, the dynamic pricing engine is used to allocate resources in the time resource pool and the device resource pool based on each user's reservation time period and its real-time pricing data, satisfying the following requirements: T w ∩[ t c , t c +Δ t ] =∅and R s=Idle; where, T w Indicates the reservation time slot. t c For the current time period, Δ t ∩ represents the change over time, ∅ represents the intersection of two sets, and ∅ represents the empty set. R s This indicates the equipment resources to be allocated.

[0006] In some embodiments, the resource management module is further configured to allocate resources according to a preset priority order; wherein the priority order is: users with high willingness to pay > ordinary users > users queuing on-site.

[0007] In some embodiments, the elements of the queue include: user ID, appointment time slot, willingness to pay value, and number of postponements.

[0008] In some embodiments, the intelligent scheduling module is used to generate a queue based on the three-dimensional resource matrix, and when performing closed-loop scheduling on the queue, it is also used to generate differentiated queue priorities based on the real-time pricing data and willingness to pay of each user, and adjust the order of the queue based on the queue priorities; and insert users who purchase fast lanes into the front preset position of the queue.

[0009] In some embodiments, the intelligent scheduling module is further configured to start a countdown for the user at the head of the queuing queue when the device is released, and simultaneously push a real-time price reminder; when the user signs in on time, allocate the corresponding device resources and charge according to the real-time pricing; when the user does not sign in, trigger the dynamic extension rule to extend the queuing process for the user.

[0010] In some embodiments, triggering the dynamic postponement rule to perform queuing postponement processing for users includes: If a user fails to sign in for the first time, they will be placed in the next position in the queue, and their real-time price will be reduced. If a user fails to sign in twice, they will be moved to the end of the queue, their original reserved time slot will be released, and the time slot will be marked as "price-sensitive time slot". If a user fails to sign in at the end of the registration period, their eligibility is revoked, freeing up time and equipment resources and increasing the real-time pricing for the user to rebook within the set time. Here, "failed to sign in at the end of the registration period" means that the user has failed to sign in after multiple missed attempts and is called on their last available opportunity.

[0011] In some embodiments, the dynamic pricing engine is used to calculate real-time pricing data based on spatiotemporal feature information, including: Calculate the regional competitive price index; Collect spatiotemporal feature information and user behavior data, and use the spatiotemporal feature information, user behavior data and pre-trained neural network to predict the user's willingness to pay; The real-time pricing data is calculated based on the user's willingness to pay value and the regional competitive price index.

[0012] In some embodiments, the formula for calculating the regional competitive price index includes:

[0013] in, This is a regional competitive price index. For the first i Price data for competing products For the first i The straight-line distance of each competitor from the current service point; The calculation of the real-time pricing data based on the user's willingness to pay value and the regional competitive price index includes:

[0014]

[0015]

[0016]

[0017] in, For real-time pricing data, The user's willingness to pay. This is a regional competitive price index. These are parameters that are dynamically adjusted. The Sigmoid supply and demand regulation function. k This is the preset supply and demand adjustment coefficient. To meet the demand for order volume, This represents the amount of available resources.

[0018] A scheduling method for a queuing reservation system based on dynamic pricing includes: Receive queue reservation requests from each user; wherein, the queue reservation request includes user information and reservation time slot; Real-time pricing data is calculated based on spatiotemporal feature information; Obtain device status information for each terminal, maintain a time resource pool and a device resource pool based on the device status information; allocate resources in the time resource pool and device resource pool based on each user's reservation time period and real-time pricing data, and construct a three-dimensional resource matrix including reservation time period, device resources, and real-time pricing. A queuing queue is generated based on the three-dimensional resource matrix, the queuing queue is subjected to closed-loop scheduling, and each terminal is allocated according to the queuing queue.

[0019] As in the above embodiments, resource scheduling and real-time pricing work together, based on a spatiotemporal pricing and queuing linkage architecture: a dynamic pricing engine is embedded in the queuing reservation system, dynamically adjusting prices to influence user queuing decisions, and simultaneously managing user available time periods, device status, and dynamic prices; combined with the adjustment of sequential queuing rules and real-time pricing, queue flow efficiency is improved, and user payment conversion rate is increased.

[0020] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0021] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of a queuing reservation system based on dynamic pricing, as shown in one embodiment. Figure 2 This is a schematic diagram of an example queue structure; Figure 3 This is a flowchart of a scheduling method for a queuing reservation system based on dynamic pricing, as shown in one embodiment. Figure 4 This is a block diagram of an example computer device. Detailed Implementation

[0022] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0023] Those skilled in the art will understand that, unless otherwise stated, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the word “comprising” as used in this application’s specification means the presence of the stated feature, integer, step, or operation, but does not preclude the presence or addition of one or more other features, integers, steps, or operations.

[0024] This application addresses the technical shortcomings of queuing reservation systems, which are prone to excessive resource concentration during peak hours and idle resources during off-peak hours when processing pricing data, resulting in low efficiency in resource scheduling and allocation. It provides a queuing reservation system based on dynamic pricing and its scheduling method.

[0025] refer to Figure 1 As shown, Figure 1 This is a schematic diagram of a queuing reservation system based on dynamic pricing, as exemplified by one of the following modules: a user interaction module, a resource management module, an intelligent scheduling module, and a dynamic pricing engine; wherein: The user interaction module is used to receive queue reservation requests from various users. The queue reservation request includes user information and reservation time slot. For example, users can make queue reservations online or offline. When making a reservation online, users can also select a time slot and set price sensitivity.

[0026] The dynamic pricing engine is used to calculate real-time pricing data based on spatiotemporal feature information. Spatiotemporal features include both time and space dimensions. Specifically, it can collect user spatiotemporal feature information, such as geographical location and available time periods. It can also obtain users' historical consumption data through the system and then calculate real-time pricing data based on the spatiotemporal feature information. For example, the spatiotemporal feature information can be collected as follows: obtaining service point coordinates through GPS / BeiDou positioning on the terminal device, obtaining the user's location through the user's APP, calling the Gaode Map "Traffic Status" API to obtain pedestrian density within 3km, and collecting competitor prices from platforms such as Dianping or historical prices from the iResearch Consulting business database through web crawlers.

[0027] For example, the time dimension can include reservation time slots at 15-minute granularity, peak / off-peak time attributes (such as 19:00-21:00 on weekends being peak hours for KTV), holiday / weekday identifiers, etc.; the spatial dimension can include the latitude and longitude coordinates of the service point, the distribution of competitors within a 3km geofence, the straight-line distance between the user and the service point, the population density within a 3km area, etc.; based on the prices of competitors within the geofence, the user's willingness to pay, and supply and demand information, real-time prices are dynamically generated through reinforcement learning.

[0028] The resource management module is used to acquire device status information of each terminal, maintain a time resource pool and a device resource pool based on the device status information, and allocate resources in the time resource pool and device resource pool according to each user's reservation time period and real-time pricing data, constructing a three-dimensional resource matrix including reservation time period, device resources, and real-time pricing. Specifically, it can maintain a time resource pool, such as time periods with a 15-minute granularity, and maintain a device resource pool, which can include the terminal's device ID and device status. Terminals refer to devices such as unmanned self-service KTVs, shared office spaces, and smart retail terminals. These terminals can be connected to a queuing and reservation system based on dynamic pricing through the Internet of Things, and maintain a dynamic price list to record real-time pricing data. Thus, by allocating time resources and device resources, a three-dimensional resource matrix is ​​constructed, including information in the three dimensions of reservation time period, device resources, and real-time pricing.

[0029] The intelligent scheduling module is used to generate a queuing queue based on the three-dimensional resource matrix, perform closed-loop scheduling on the queuing queue, and allocate terminals according to the queuing queue. Specifically, it can perform closed-loop scheduling on the three-dimensional resource matrix according to the elastic queuing scheduling algorithm. By integrating the dynamic queuing algorithm with the real-time pricing strategy, it can realize closed-loop scheduling of pricing-guided queuing and queuing feedback pricing.

[0030] As in the above embodiments, resource scheduling and real-time pricing work together, based on a spatiotemporal pricing and queuing linkage architecture: a dynamic pricing engine is embedded in the queuing reservation system, dynamically adjusting prices to influence user queuing decisions, and simultaneously managing user available time periods, device status, and dynamic prices; combined with the adjustment of sequential queuing rules and real-time pricing, queue flow efficiency is improved, and user payment conversion rate is increased.

[0031] To make the technical solution of this application clearer, more embodiments are described below.

[0032] In some embodiments, the dynamic pricing engine is used to calculate real-time pricing data based on spatiotemporal feature information, including: (1) Calculate the regional competitive price index.

[0033] For example, a geofence with a radius of 3km can be constructed to obtain a more suitable scope for competitor data collection. Spatiotemporal characteristic information can include dimensions such as appointment time slots and store location attributes. User behavior data can include historical purchase frequency, repurchase intervals, browsing-to-appointment conversion rates, and appointment cancellation behavior. External event information can include weather information, surrounding events, and holiday attributes. Furthermore, multidimensional spatiotemporal data can also include user profile dimensions such as age stratification, consumer group types, and payment method preferences.

[0034] Taking KTV as an example, multidimensional spatiotemporal data can also include KTV room consumption information, such as room type selection, reservation duration, acceptance of time-slot premiums, beverage category preferences, beverage consumption correlation, and consumption amount stratification.

[0035] In some embodiments, the regional competition price index can be calculated as follows:

[0036] in, This is a regional competitive price index. For the first i Price data for competing products The distance between the i-th competitor and the current service point is the straight-line distance. The number of actual competitors within a 3km geofence is taken, with 3-5 competitors selected in the unmanned self-service KTV scenario. The regional competitive price index is calculated by weighting the prices of competitors within the geofence. The regional competitive price index is calculated using a specific algorithm to reflect the comprehensive impact of competitor pricing data within the geofence, thus providing an important reference for pricing decisions.

[0037] As described in the above embodiments, by using spatiotemporal perception and real-time collection of information such as competitor prices, user behavior data, and external events within the fence, multi-dimensional spatiotemporal data input is formed, thereby providing rich and accurate data support for subsequent real-time pricing calculations.

[0038] (2) Collect spatiotemporal feature information and user behavior data, and use the spatiotemporal feature information and user behavior data and a pre-trained neural network to predict the user's willingness to pay.

[0039] Specifically, information from multiple dimensions, such as spatiotemporal dimensions (e.g., time period encoding, geographic location coordinates) and user behavior dimensions (browsing trajectory, historical consumption amount, repurchase rate, etc.), can be collected to predict users' willingness to pay. Among these, the willingness to pay is a quantitative probability value that represents a user's willingness to pay.

[0040] For example, the neural network uses an LSTM (Long Short-Term Memory) neural network that integrates spatiotemporal features. It adopts a multi-layer LSTM network combined with a fully connected layer structure. The neural network uses a "3-layer LSTM + 2-layer fully connected" fusion architecture. The LSTM layer is used to capture spatiotemporal sequence features (128-dimensional input, 64 hidden neurons). The fully connected layer outputs the willingness to pay value with Sigmoid as the activation function. The training data can be 500,000 valid samples from the past 12 months (covering KTV and shared office scenarios). After normalization (distance normalized to the 0~1 interval) and one-hot encoding preprocessing, it is iterated for 500 rounds with mean squared error (MSE) as the loss function and Adam as the optimizer (learning rate 0.001). After training, the neural network outputs the payment probability in the 0~1 interval. After convergence, the actual accuracy on the test set reaches 89.7%, which can predict users' willingness to pay relatively accurately.

[0041] (3) Calculate the real-time pricing data based on the user's willingness to pay value and the regional competitive price index.

[0042] Specifically, real-time pricing data is calculated based on user willingness to pay, regional competitive price index, and dynamic pricing function.

[0043] The calculation process may include the following:

[0044]

[0045]

[0046]

[0047] in, For real-time pricing data, The user's willingness to pay. This is a regional competitive price index. For dynamically adjusted parameters, reinforcement learning optimizes the dynamic parameters through... To constrain The possible values ​​of ; The Sigmoid supply and demand regulation function. k The preset supply and demand adjustment coefficient is, under normal circumstances, k The rule is an example of a value range (0.5~2.0) + default value (1.0) + time period adjustment. k The time period adaptation rules can be as follows: peak hours k =1.5~2.0, low peak k =0.5~1.0, To meet the demand for order volume, This represents the amount of available resources.

[0048] Specifically, the Sigmoid supply and demand adjustment function is used. For example, the reward function is: resource utilization rate × user payment conversion rate; k The preset supply and demand adjustment coefficient controls the price's sensitivity to the supply-demand gap through a function. Based on real-time supply and demand difference (demand order volume) and available resources Dynamically adjust price elasticity to achieve reasonable price regulation when supply and demand are imbalanced; optimize weight parameters through reinforcement learning. This allows for a reasonable balance between the impact of competitors' pricing data, users' willingness to pay, and supply and demand on pricing data, based on different scenarios.

[0049] The solution described in the above embodiments integrates spatiotemporal feature information, which can effectively capture the dynamic patterns of changes in users' willingness to pay over time and geographical location, deeply explore the spatiotemporal correlation of user behavior, accurately predict users' willingness to pay, and achieve accurate real-time pricing.

[0050] In some embodiments, when the dynamic pricing engine allocates resources in the time resource pool and the device resource pool based on each user's reserved time period and its real-time pricing data, the following constraints are met: T w ∩[t c , t c +Δ t ]=∅and R s =Idle in, T w Indicates the reservation time slot. t c At the current moment, Δ t ∩ represents the change over time, and ∩ represents the intersection of two sets. The length is from the current time. The interval is given by ∅, where ∅ represents the empty set. R s This represents the device resources to be allocated; for example, when allocating resources, Δt = 15 minutes, corresponding to a 15-minute granularity in the time resource pool; the call countdown Δt = 3 minutes is used for check-in timeout determination.

[0051] As in the above embodiment, the solution filters out idle device resources to be allocated. Then find the appointment time slot. and By finding the intersection of the two sets of resources and using constraint matching based on spatiotemporal characteristic information, Pareto optimality of resource allocation and revenue optimization can be achieved. This will lead to finding the minimum price combination of resources that satisfies the above constraints, thereby achieving higher resource utilization and business returns.

[0052] In some embodiments, the resource management module is further configured to allocate resources according to a preset priority order; wherein the priority order is: users with high willingness to pay > ordinary users > users queuing on-site.

[0053] Specifically, in the matching algorithm for time and equipment resources, a matching priority can be set. The priority order can be: users with high willingness to pay (combined with dynamic pricing data), ordinary users, and users queuing on-site (in order of arrival). Users with high willingness to pay generally refer to users whose willingness to pay is greater than a set threshold. For example, users with high willingness to pay refer to users whose willingness to pay V is predicted by a neural network. u Users with a score ≥0.8, V u The value range is 0~1, the actual accuracy rate is 89.7%, or it is a user with a historical single consumption amount of ≥200 yuan.

[0054] By prioritizing users with a high willingness to pay, dynamic pricing data can be used to determine their queuing priority, thereby ensuring resource utilization and improving business revenue.

[0055] In some embodiments, the intelligent scheduling module generates a queuing queue based on a three-dimensional resource matrix, and then performs closed-loop scheduling of the queuing queue according to an elastic queuing scheduling algorithm; wherein, reference Figure 2 As shown, Figure 2 This is a schematic diagram of an example queue structure. The elements of the queue include: User ID, Appointment Time Slot. Willingness to pay Number of postponements That is, all users in the queue have the above four elements recorded.

[0056] In some embodiments, the intelligent scheduling module is used to generate a queue based on the three-dimensional resource matrix, and when performing closed-loop scheduling on the queue, it is also used to generate differentiated queue priorities based on the real-time pricing data and willingness to pay of each user, and adjust the order of the queue based on the queue priorities; and insert users who purchase fast lanes into the front preset position of the queue.

[0057] Specifically, elastic queuing scheduling algorithms can guide queuing by price, for example, based on real-time pricing data P. t Generate differentiated queuing priorities; users with a high willingness to pay can purchase a "fast track" to insert themselves into the top 5% of the queue.

[0058] In some embodiments, the intelligent scheduling module is also used to start a countdown for the user at the head of the queuing queue when the device is released, and push a real-time price reminder simultaneously; when the user signs in on time, the corresponding device resources are allocated and billed according to the real-time pricing; when the user does not sign in, the dynamic extension rule is triggered to extend the queuing for the user.

[0059] For example, the call and check-in processing flow of the elastic queuing scheduling algorithm can be as follows: ① When the device is released, the user at the front of the queue will be called and a 3-minute countdown will be started, and a real-time price reminder will be pushed at the same time (such as a 5% discount if the waiting time is exceeded).

[0060] ②If the user signs in on time, resources will be allocated and billing will be based on real-time pricing data.

[0061] ③ If the user fails to check in on time, the dynamic postponement rule will be triggered, and the user will be queued and postponed.

[0062] In one embodiment, the dynamic continuation rule may include the following: a) If the user fails to sign in for the first time, insert the user into the next position in the queue, i.e., the second position, and reduce the user's real-time price; for example, temporarily reduce the user's subsequent time period pricing weight β by 10%. By reducing the real-time price, users can be encouraged to sign in as soon as possible.

[0063] b. If the user fails to check in twice, move the user to the end of the queue, release the original reserved time slot and mark it as a "price-sensitive time slot"; the user may be price-sensitive, so the real-time price can be further reduced, for example, the subsequent price can be reduced by 15% to attract the user.

[0064] c. If the user fails to sign in at the end of the session, their eligibility will be revoked, releasing time and equipment resources and increasing the real-time pricing for the user to make another reservation within the set time. Here, "failed to sign in at the end of the session" means that the user has failed to sign in after multiple missed attempts and is called on the last available time.

[0065] For example, if a user fails to sign in twice consecutively, and still fails to sign in on the third (last) chance, the number of attempts will be deferred. f =3, release all resources, and set the user to have a 20% price increase for reservations within 30 minutes (credit penalty mechanism).

[0066] As described in the above embodiments, the technical solutions link real-time pricing and queuing based on spatiotemporal feature information. A dynamic pricing engine is embedded in the queuing reservation system, dynamically adjusting pricing based on real-time queue length and user willingness to pay predictions. This, in turn, influences user queuing decisions. By constructing a three-dimensional matrix of reservation time slots, equipment resources, and real-time pricing, the system simultaneously manages user available time slots, equipment status, and dynamic prices, achieving Pareto optimality in resource allocation and revenue optimization. The elastic queuing algorithm combines sequential queuing rules with price-sensitive priority adjustments, supporting automatic postponement, last-place reset, and dynamic cancellation of eligibility based on pricing when users fail to arrive on time. Dynamic pricing adjusts user waiting willingness, while real-time price strategy optimization based on the queue improves abnormal scenario handling efficiency to a second-level response time.

[0067] The following describes an application example of the technical solution of this application in a shared KTV.

[0068] A certain unmanned KTV has 10 private rooms, which can be booked online (1-3 hours) or on-site.

[0069] During peak hours (7:00 PM - 9:00 PM on weekends), the queue reached 20 people, and the average price of competing products in the surrounding area increased by 20%. User A made a reservation for 7:00 PM - 8:00 PM, but failed to check in at 7:05 PM (first time not showing up); User B is a user with a high willingness to pay (historical consumption > 500 yuan).

[0070] The scheduling process is as follows: The pricing engine generates a real-time price (base price + 15%) based on the number of people in the queue and the prices of competing products. User B purchases the fast lane, and the queue becomes [B, A, C, ...].

[0071] At 19:00, user A, who had not checked in, was placed in the second position in the queue. The actual price for user A's subsequent time period was reduced by 10% (19:30-20:30 price was 10% off).

[0072] At 19:10, Room 1 was released again. User B was called to check in, and Room 1 was assigned to User B, with billing based on real-time pricing (including fast-track premium).

[0073] Room 1 was released at 19:30. User A, whose number was called, failed to check in (missed twice). He was moved to the end of the queue and marked as a price-sensitive user. The price for subsequent time slots will be reduced by 15%.

[0074] If user A fails to check in at the end, their qualification will be cancelled, all resources will be released, and the price for user A to make a reservation within 30 minutes will be increased by 20% (credit penalty mechanism).

[0075] As shown in the example above, based on the technical solution of this application, the total revenue during the 19:00-19:30 period increased by 45%, the vacancy time of KTV rooms decreased by 60%, and the satisfaction of high-value users increased by 70%.

[0076] Based on the application data across all time periods and the technical solution of this application, the revenue of shared spaces is increased by 60% and the utilization rate of equipment resources is increased from 65% to 92% through the linkage of real-time pricing and queuing. Resource usage during off-peak hours is increased by 40%. Waiting time for high-paying users is reduced by 50%, the automatic processing delay for unreached users is less than 10 seconds, and the queue flow efficiency is improved by 35%, resulting in a significant optimization of queuing efficiency. Through flexible pricing algorithm scheduling, the system can respond to supply and demand fluctuations at the millisecond level and achieve real-time pricing adjustment delay of less than 100ms in extreme scenarios (such as events or heavy rain), thereby increasing user payment conversion rate by 50%.

[0077] The following describes an embodiment of the scheduling method for a queuing reservation system based on dynamic pricing.

[0078] like Figure 3 As shown, Figure 3 This is a flowchart of a scheduling method for a dynamic pricing-based queuing reservation system, as shown in one embodiment, including: S10, Receive queue reservation requests from each user; wherein, the queue reservation request includes user information and reservation time slot; S20, calculate real-time pricing data based on spatiotemporal feature information; wherein, the spatiotemporal features include time dimension information and spatial dimension; S30: Obtain device status information of each terminal, maintain time resource pool and device resource pool according to the device status information; allocate resources in time resource pool and device resource pool according to the reservation time period and real-time pricing data of each user, and construct a three-dimensional resource matrix including reservation time period - device resources - real-time pricing. S40, generate a queuing queue based on the three-dimensional resource matrix, perform closed-loop scheduling on the queuing queue, and allocate each terminal according to the queuing queue.

[0079] As in the above embodiments, resource scheduling and real-time pricing work together, based on a spatiotemporal pricing and queuing linkage architecture: a dynamic pricing engine is embedded in the queuing reservation system, dynamically adjusting prices to influence user queuing decisions, and simultaneously managing user available time periods, device status, and dynamic prices; combined with the adjustment of sequential queuing rules and real-time pricing, queue flow efficiency is improved, and user payment conversion rate is increased.

[0080] The scheduling method of the dynamic pricing-based queuing reservation system in this application is mainly applied to the dynamic pricing-based queuing reservation system of any of the foregoing embodiments. Therefore, the schemes in the dynamic pricing-based queuing reservation system embodiments can also be applied to the scheduling method, which will not be elaborated here.

[0081] In some embodiments, the scheduling method of the dynamic pricing-based queuing reservation system of this application can be applied to a computing device.

[0082] Based on this, this application provides a technical solution for a computer device to implement the scheduling method related to a dynamic pricing-based queuing reservation system. The computer device of this embodiment includes one or more processors, a memory, and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs are configured for the steps of the scheduling method of the dynamic pricing-based queuing reservation system in any embodiment.

[0083] like Figure 4 As shown, Figure 4 This is a block diagram of an example computer device; the computer device 100 may include one or more of the following components: a processing component 102, a memory 104, a power supply component 106, a multimedia component 108, an audio component 110, an input / output (I / O) interface 112, a sensor component 114, and a communication component 116.

[0084] Processing component 102 typically controls the overall operation of computer device 100, such as operations associated with display, telephone calls, data communication, camera operation, and recording operation.

[0085] The memory 104 is configured to store various types of data to support the operation of the computer device 100. Such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0086] The power supply unit 106 provides power to the various components of the computer device 100.

[0087] Multimedia component 108 includes a screen that provides an output interface between computer device 100 and user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). In some embodiments, multimedia component 108 includes a front-facing camera and / or a rear-facing camera.

[0088] The audio component 110 is configured to output and / or input audio signals.

[0089] I / O interface 112 provides an interface between processing component 102 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0090] Sensor assembly 114 includes one or more sensors for providing various aspects of state assessment for computer device 100. Sensor assembly 114 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact.

[0091] The communication component 116 is configured to facilitate wired or wireless communication between the computer device 100 and other devices. The computer device 100 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof.

[0092] This application provides a computer-readable storage medium to implement the scheduling method related to a dynamic pricing-based queuing reservation system. The computer-readable storage medium stores at least one instruction, at least one program, code set, or instruction set. The at least one instruction, at least one program, code set, or instruction set is loaded by a processor and executes the scheduling method of the dynamic pricing-based queuing reservation system according to any embodiment.

[0093] In an exemplary embodiment, the computer-readable storage medium may be a non-transitory computer-readable storage medium that includes instructions, such as a memory that includes instructions. For example, a non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0094] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A queuing and reservation system based on dynamic pricing, characterized in that, include: The system includes a user interaction module, a resource management module, an intelligent scheduling module, and a dynamic pricing engine; among them, The user interaction module is used to receive queue reservation requests from each user; wherein, the queue reservation request includes user information and reservation time slot; The dynamic pricing engine is used to calculate real-time pricing data based on spatiotemporal feature information; wherein, the spatiotemporal features include time dimension information and spatial dimension; The resource management module is used to obtain the device status information of each terminal, maintain the time resource pool and the device resource pool according to the device status information, and allocate resources in the time resource pool and the device resource pool according to the reservation time period and real-time pricing data of each user, and construct a three-dimensional resource matrix including reservation time period - device resources - real-time pricing. The intelligent scheduling module is used to generate a queuing queue based on the three-dimensional resource matrix, perform closed-loop scheduling on the queuing queue, and allocate each terminal according to the queuing queue.

2. The queuing and reservation system based on dynamic pricing according to claim 1, characterized in that, The dynamic pricing engine is used to allocate resources in the time resource pool and device resource pool based on each user's reservation time slot and its real-time pricing data, satisfying the following requirements: T w ∩[ t c , t c +Δ t ] =∅and R s =Idle; where, T w Indicates the reservation time slot. t c For the current time period, Δ t ∩ represents the change over time, ∅ represents the intersection of two sets, and ∅ represents the empty set. R s This indicates the equipment resources to be allocated.

3. The queuing and reservation system based on dynamic pricing according to claim 2, characterized in that, The resource management module is also used to allocate resources according to a preset priority order; wherein the priority order is: users with high willingness to pay > ordinary users > users queuing on-site.

4. The queuing reservation system based on dynamic pricing according to any one of claims 1-3, characterized in that, The elements of the queue include: user ID, appointment time slot, payment willingness value, and number of postponements.

5. The queuing and reservation system based on dynamic pricing according to claim 4, characterized in that, The intelligent scheduling module is used to generate a queuing queue based on the three-dimensional resource matrix. When performing closed-loop scheduling on the queuing queue, it is also used to generate differentiated queuing priorities based on the real-time pricing data and payment willingness values ​​of each user, and adjust the order of the queuing queues according to the queuing priorities. And a pre-defined position at the front of the queue for users who purchase fast lane access.

6. The queuing and reservation system based on dynamic pricing according to claim 5, characterized in that, The intelligent scheduling module is also used to start a countdown for the first user in the queuing queue when the equipment is released, and to push a real-time price reminder simultaneously; when the user signs in on time, the corresponding equipment resources are allocated and billed according to the real-time pricing. When a user fails to sign in, a dynamic postponement rule is triggered, and the user is placed in a queue for postponement.

7. The queuing and reservation system based on dynamic pricing according to claim 6, characterized in that, The dynamic delay rule is used to process user queue delays, including: If a user fails to sign in for the first time, they will be placed in the next position in the queue, and their real-time price will be reduced. If a user fails to sign in twice, they will be moved to the end of the queue, their original reserved time slot will be released, and the time slot will be marked as "price-sensitive time slot". If a user fails to sign in at the end of the registration period, their eligibility is revoked, freeing up time and equipment resources and increasing the real-time pricing for the user to rebook within the set time. Here, "failed to sign in at the end of the registration period" means that the user has failed to sign in after multiple missed attempts and is called on their last available opportunity.

8. The queuing and reservation system based on dynamic pricing according to claim 1, characterized in that, The dynamic pricing engine is used to calculate real-time pricing data based on spatiotemporal feature information, including: Calculate the regional competitive price index; Collect spatiotemporal feature information and user behavior data, and use the spatiotemporal feature information, user behavior data and pre-trained neural network to predict the user's willingness to pay; The real-time pricing data is calculated based on the user's willingness to pay value and the regional competitive price index.

9. The queuing and reservation system based on dynamic pricing according to claim 8, characterized in that, The formula for calculating the regional competitive price index includes: ; in, This is a regional competitive price index. For the first i Price data for competing products For the first i The straight-line distance of each competitor from the current service point; The calculation of the real-time pricing data based on the user's willingness to pay value and the regional competitive price index includes: ; ; ; ; in, For real-time pricing data, The user's willingness to pay value This is a regional competitive price index. These are parameters that are dynamically adjusted. The Sigmoid supply and demand regulation function. k This is the preset supply and demand adjustment coefficient. To meet the demand for order volume, This represents the amount of available resources.

10. A scheduling method for a queuing reservation system based on dynamic pricing, characterized in that, include: Receive queue reservation requests from each user; wherein, the queue reservation request includes user information and reservation time slot; Real-time pricing data is calculated based on spatiotemporal feature information; wherein, the spatiotemporal features include time dimension information and spatial dimension; Obtain device status information for each terminal, maintain a time resource pool and a device resource pool based on the device status information; allocate resources in the time resource pool and device resource pool based on each user's reservation time period and real-time pricing data, and construct a three-dimensional resource matrix including reservation time period, device resources, and real-time pricing. A queuing queue is generated based on the three-dimensional resource matrix, the queuing queue is subjected to closed-loop scheduling, and each terminal is allocated according to the queuing queue.

Images