Shared book putting management method and system based on user demand prediction

Abstract

The invention discloses a shared book putting management method and system based on user demand prediction, and aims to optimize book resource allocation and improve borrowing efficiency. The method comprises the following steps: acquiring user activeness information of each shared book putting point in a target area, and constructing a borrowing thermodynamic diagram; according to the thermodynamic diagram, optimizing a putting point position to form an optimization scheme; collecting user borrowing record change data of the optimized putting point in a preset time period, predicting a future user borrowing demand, and generating a demand prediction result; and allocating the shared book resources according to the prediction result to form an allocation scheme. According to the method, through borrowing demand prediction, the accuracy and efficiency of shared book putting management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shared book delivery, and in particular to a shared book delivery management method and system based on user demand prediction. Background Art

[0002] The shared book system arranges books at multiple distribution points in the city, and users can borrow and return books at each distribution point according to their own needs. However, there are some problems with the current shared book distribution management method, such as unreasonable distribution of distribution points and unbalanced allocation of book resources, which leads to unmet book demand in some areas, while other areas may have an oversupply of book resources. Therefore, how to reasonably plan the distribution points and quantity of shared books according to user needs has become a key issue in improving the efficiency of shared book management.

[0003] Most of the existing shared book delivery management methods are based on fixed delivery rules to configure books, lacking dynamic analysis and prediction of user needs. This method cannot flexibly respond to changes in user borrowing needs in different regions, and easily leads to waste or shortage of book resources. In addition, traditional book delivery management methods usually ignore the borrowing behavior patterns of users, making it difficult to accurately predict future borrowing needs and unable to provide effective decision support for managers.

[0004] In order to improve the management efficiency of the shared book system, it is necessary to introduce an intelligent book delivery management method and system based on user demand prediction. By analyzing and predicting user borrowing behavior, the book delivery location and quantity can be dynamically optimized, and book resources between different delivery points can be reasonably allocated to ensure the reasonable allocation of book resources, thereby improving the user's borrowing experience and reducing the waste of book resources. Summary of the invention

[0005] In order to solve at least one of the above technical problems, the present invention proposes a shared book delivery management method and system based on user demand prediction.

[0006] The first aspect of the present invention provides a shared book delivery management method based on user demand prediction, comprising:

[0007] Obtaining information on the number of active users at each shared book drop-off point in the target area, and constructing a borrowing heat map of the target area based on the information on the number of active users;

[0008] Optimizing the location of the shared book drop-off point according to the borrowing heat map to obtain an optimization plan for the shared book drop-off point;

[0009] Obtaining user borrowing record change data for each shared book delivery point optimized according to the shared book delivery point optimization plan in the target area within a preset time period, predicting user borrowing demand changes for each shared book delivery point within a future preset time period based on the user borrowing record change data, and obtaining a user borrowing demand change prediction result;

[0010] The shared books in the target area are allocated according to the prediction result of the change of the user's borrowing demand, so as to obtain a shared book allocation plan for the target area.

[0011] In this solution, the process of obtaining the user activity information of each shared book delivery point in the target area and constructing a borrowing heat map of the target area based on the user activity information is as follows:

[0012] Obtain historical user borrowing record data of each shared book distribution point in the target area, calculate the daily average number of active users of each shared book distribution point based on the historical user borrowing record data, and obtain user active number information;

[0013] Obtaining the location coordinate information of each shared book drop point, calculating the Euclidean distance between every two shared book drop points in the target area according to the location coordinate information, setting a grouping distance range, grouping the shared book drop point pairs according to the grouping distance range to obtain distance group data, and calculating the semi-variance of all shared book drop point pairs in each distance group according to the distance group data to obtain semi-variance data;

[0014] Using the Gaussian model as a variogram model, fitting the variogram model according to the semivariance data, constructing a Kriging equation based on the semivariance data and the fitted variogram model, converting the Kriging equation into a matrix form, and determining the interpolation weight of each shared book delivery point;

[0015] Divide the target area into grids according to a preset grid size, obtain the position coordinate information to be interpolated of the unknown user active quantity information grid, and perform an interpolation operation on each unknown user active quantity information grid according to the position coordinate information of each shared book delivery point, the user active quantity information of each shared book delivery point, the interpolation weight of each shared book delivery point, and the position coordinate information to be interpolated to obtain the user active quantity information of each grid in each target area;

[0016] A borrowing heat map of the target area is constructed according to the active user quantity information of each grid.

[0017] In this solution, the location of the shared book drop-off point is optimized according to the borrowing heat map to obtain the shared book drop-off point optimization solution, which is specifically:

[0018] Obtaining service restriction data for each shared book delivery point, wherein the service restriction data includes service radius restriction and user active number processing capacity restriction;

[0019] Introducing a particle swarm optimization algorithm, presetting an optimization distance limit for shared book delivery points, using the service restriction data and the optimization distance limit as optimization condition limits for the particle swarm optimization algorithm, and using the maximum number of active users that each shared book delivery point can serve as an optimization target for the particle swarm optimization algorithm;

[0020] Searching the borrowing heat map based on a particle swarm optimization algorithm to determine an optimal location of a shared book drop-off point in a target area, and optimizing the location of the shared book drop-off point according to the optimal location;

[0021] According to the service restriction data, the number of active user processing is counted for the shared book delivery point after the location optimization, and if the number of active user processing is greater than the active user processing capacity, the shared book delivery point is marked as a delivery point with overloaded processing capacity;

[0022] Additional shared book delivery points are added at preset distances from the delivery points with overloaded processing capacity until the number of active users processed by the shared book delivery points in the target area is no greater than the active user processing capacity, thereby obtaining an optimization plan for shared book delivery points.

[0023] In this solution, the user borrowing record change data of each shared book delivery point optimized according to the shared book delivery point optimization solution in the target area within a preset time period is obtained, and the user borrowing demand change of each shared book delivery point within the future preset time period is predicted according to the user borrowing record change data, and the user borrowing demand change prediction result is obtained, which is specifically:

[0024] Acquire historical user borrowing record change data of each shared book delivery point optimized according to the shared book delivery point optimization scheme in the target area, wherein the historical user borrowing record change data includes the change in the borrowing quantity of each type of book;

[0025] Based on the GRU algorithm, a user borrowing change prediction model is constructed for each shared book delivery point, the historical user borrowing record change data is divided into a training set and a test set according to a preset ratio, the training set is imported into the user borrowing change prediction model for model training, and the prediction performance of the trained user borrowing change prediction model is tested through the test set, and the model parameters are adjusted until the model prediction accuracy is greater than the preset accuracy;

[0026] The user borrowing record change data of each shared book delivery point within a preset time period is obtained, and the user borrowing record change data is imported into the user borrowing change prediction model to predict the user borrowing demand change of each shared book delivery point within a future preset time period to obtain the user borrowing demand change prediction result.

[0027] In this solution, the shared books in the target area are allocated according to the prediction result of the change of the user's borrowing demand, and the shared books allocation plan for the target area is obtained, which is specifically:

[0028] Acquire the shared book stock information of each shared book delivery point, determine the borrowing redundancy and borrowing shortage of each type of books at each shared book delivery point in a preset time period in the future according to the prediction result of the user borrowing demand change and the shared book stock information, and obtain the book borrowing supply and demand data of each shared book delivery point;

[0029] Acquire the location information of each shared book delivery point, and construct a location distribution map of the shared book delivery points in the target area according to the location information;

[0030] According to the book borrowing supply and demand data of each shared book delivery point, the shared book delivery point with borrowing shortage is marked as the delivery point to be transferred in;

[0031] According to the types of scarce books and the amount of scarce books borrowed at the drop-in point to be transferred in, a shared book drop-in point with redundant borrowing of the scarce books type is identified, and marked as the drop-in point to be transferred out;

[0032] Determine the distance between each to-be-called-out delivery point and the to-be-called-in delivery point according to the shared book delivery point location distribution map, and set a call-out priority for each to-be-called-out delivery point according to the distance;

[0033] The borrowing and shortage book types are allocated according to the borrowing redundancy of the borrowing and shortage book types in each to-be-allocated delivery point and the allocation priority. If the borrowing and shortage book types after allocation still cannot meet the borrowing and shortage quantity of the borrowing and shortage book types in the to-be-allocated delivery point, new books are placed for the borrowing and shortage book types to obtain a shared book allocation plan for the target area;

[0034] The shared books in the target area are allocated according to the shared book allocation plan.

[0035] In this solution, the shared books in the target area are allocated according to the shared book allocation scheme, specifically:

[0036] Acquire the resource information of the dispatched vehicles for the shared books in the target area, and determine the maximum dispatch quantity k of the dispatched vehicles according to the resource information of the dispatched vehicles;

[0037] According to the shared book allocation plan, the quantity information of the delivery points to be allocated is obtained, and according to the quantity information, the required dispatch quantity of vehicles for the shared book allocation in the target area is determined;

[0038] If the required dispatching amount of the vehicle is less than or equal to the maximum dispatching amount, a vehicle is arranged for each delivery point to be dispatched to dispatch shared books, each delivery point to be dispatched out and each delivery point to be dispatched to are marked in the shared book delivery point location distribution map, and a path search is performed on the delivery points marked in the shared book delivery point location distribution map based on the Dijkstra algorithm to determine the first dispatching path of each dispatching vehicle;

[0039] If the required dispatching quantity of the vehicle is greater than the maximum dispatching quantity, the priority of each waiting-to-be-dispatched delivery point is determined according to the total borrowing shortage quantity of each waiting-to-be-dispatched delivery point;

[0040] Performing a vehicle dispatch for the top k to-be-dispatched delivery points according to the dispatch priority, determining a second dispatch path for each dispatched vehicle in the vehicle dispatch, calculating a path length of the second dispatch path, and determining a dispatch pressure for each dispatched vehicle according to the path length;

[0041] Get the number i of waiting-for-dispatch points for vehicles that have not been scheduled in the first vehicle dispatch, sort the dispatched vehicles from small to large according to the dispatch pressure, select the first i vehicles for the second vehicle dispatch, and determine the third dispatch path for the second dispatched vehicles.

[0042] The second aspect of the present invention further provides a shared book delivery management system based on user demand prediction, the system comprising: a memory, a processor, the memory comprising a shared book delivery management method program based on user demand prediction, the shared book delivery management method program based on user demand prediction when executed by the processor, implements the following steps:

[0043] Obtaining information on the number of active users at each shared book drop-off point in the target area, and constructing a borrowing heat map of the target area based on the information on the number of active users;

[0044] Optimizing the location of the shared book drop-off point according to the borrowing heat map to obtain an optimization plan for the shared book drop-off point;

[0045] Obtaining user borrowing record change data for each shared book delivery point optimized according to the shared book delivery point optimization plan in the target area within a preset time period, predicting user borrowing demand changes for each shared book delivery point within a future preset time period based on the user borrowing record change data, and obtaining a user borrowing demand change prediction result;

[0046] The shared books in the target area are allocated according to the prediction result of the change of the user's borrowing demand, so as to obtain a shared book allocation plan for the target area.

[0047] The present invention discloses a shared book delivery management method and system based on user demand prediction, aiming to optimize book resource allocation and improve borrowing efficiency. The method includes: obtaining user activity information of each shared book delivery point in the target area, constructing a borrowing heat map; optimizing the delivery point location according to the heat map, forming an optimization plan; collecting user borrowing record change data of the optimized delivery point within a preset time period, and predicting future user borrowing demand to generate demand prediction results; allocating shared book resources according to the prediction results to form an allocation plan. This method improves the accuracy and efficiency of shared book delivery management by predicting borrowing demand. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flow chart of a shared book delivery management method based on user demand prediction according to the present invention is shown;

[0049] Figure 2 A flow chart showing the optimization scheme for obtaining shared book delivery points according to the present invention is shown;

[0050] Figure 3 A flow chart showing the prediction result of the change of user borrowing demand obtained by the present invention;

[0051] Figure 4 A block diagram of a shared book delivery management system based on user demand prediction according to the present invention is shown. DETAILED DESCRIPTION

[0052] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0054] Figure 1 The flowchart of the shared book delivery management method based on user demand prediction of the present invention is shown.

[0055] like Figure 1 As shown, the first aspect of the present invention provides a shared book delivery management method based on user demand prediction, comprising:

[0056] S102, obtaining information on the number of active users at each shared book delivery point in the target area, and constructing a borrowing heat map of the target area according to the information on the number of active users;

[0057] S104, optimizing the locations of shared book drop-off points according to the borrowing heat map to obtain an optimization plan for shared book drop-off points;

[0058] S106, obtaining user borrowing record change data of each shared book delivery point optimized according to the shared book delivery point optimization scheme in the target area within a preset time period, predicting the user borrowing demand change of each shared book delivery point within the future preset time period according to the user borrowing record change data, and obtaining the user borrowing demand change prediction result;

[0059] S108, allocating shared books in the target area according to the prediction result of the change in user borrowing demand, and obtaining a shared book allocation plan for the target area.

[0060] It should be noted that by constructing a borrowing heat map, it is possible to intuitively reflect the borrowing preferences and activity distribution of users in different regions, which is convenient for optimizing the delivery strategy of book resources, reducing the phenomenon of over-concentration or dispersion of delivery, and improving resource utilization efficiency; based on the borrowing heat map, high-density areas with active users and areas with relatively high demand for book resources can be effectively identified. By optimizing the location of delivery points, it is possible to ensure that shared book delivery points are more reasonably distributed in areas with dense user demand, and avoid too many delivery points being concentrated in areas with low demand. By collecting and analyzing the change data of user borrowing records at the optimized delivery points, the user's borrowing behavior and demand trends can be captured more accurately. This process enables the shared book delivery system to have the ability to dynamically predict future demand, thereby avoiding the imbalance between supply and demand of book resources. Accurate demand prediction can ensure that book resources can respond to user needs in a timely manner and reduce the phenomenon of insufficient book supply during the peak borrowing period; allocating books according to the prediction results can effectively avoid resource waste and book shortages. The system can reasonably allocate book resources according to the demand change trend of different delivery points to ensure that the type and quantity of books at each delivery point meet actual needs, thereby improving user satisfaction with borrowing. At the same time, the allocation plan can reduce book redundancy, reduce operating costs, and ensure the dynamic optimization of book resources to form an efficient book management mechanism.

[0061] According to an embodiment of the present invention, the step of obtaining the user active quantity information of each shared book drop-off point in the target area and constructing a borrowing heat map of the target area according to the user active quantity information is specifically as follows:

[0062] Obtain historical user borrowing record data of each shared book distribution point in the target area, calculate the daily average number of active users of each shared book distribution point based on the historical user borrowing record data, and obtain user active number information;

[0063] Obtaining the location coordinate information of each shared book drop point, calculating the Euclidean distance between every two shared book drop points in the target area according to the location coordinate information, setting a grouping distance range, grouping the shared book drop point pairs according to the grouping distance range to obtain distance group data, and calculating the semi-variance of all shared book drop point pairs in each distance group according to the distance group data to obtain semi-variance data;

[0064] Using the Gaussian model as a variogram model, fitting the variogram model according to the semivariance data, constructing a Kriging equation based on the semivariance data and the fitted variogram model, converting the Kriging equation into a matrix form, and determining the interpolation weight of each shared book delivery point;

[0065] Divide the target area into grids according to a preset grid size, obtain the position coordinate information to be interpolated of the unknown user active quantity information grid, and perform an interpolation operation on each unknown user active quantity information grid according to the position coordinate information of each shared book delivery point, the user active quantity information of each shared book delivery point, the interpolation weight of each shared book delivery point, and the position coordinate information to be interpolated to obtain the user active quantity information of each grid in each target area;

[0066] A borrowing heat map of the target area is constructed according to the active user quantity information of each grid.

[0067] It should be noted that since the shared book drop-off points are sparse and incomplete, it is impossible to determine the borrowing heat in the target area. Therefore, the active number of users in each grid in the target area is interpolated by Kriging interpolation to construct an accurate borrowing heat map. Kriging interpolation is a geostatistical method that can analyze the correlation of spatial data and is particularly suitable for scenarios with spatial dependence. The active number of users at shared book drop-off points has obvious spatial distribution characteristics, that is, there is a spatial correlation between the user activity of drop-off points at different locations and their surrounding drop-off points. Through the Kriging interpolation method, this spatial correlation can be used to more accurately estimate the active number of users in unknown areas, thereby obtaining a more accurate borrowing heat map. The Kriging interpolation method can fit the semi-variance of spatial data through the variogram model and accurately describe the spatial variation trend of data. It analyzes the changes in the number of active users between known drop-off points, establishes a fitting model and calculates the interpolation weight to ensure that the interpolation operation has high accuracy. In the interpolation process, not only the distance factor is considered, but also the variance and covariance relationship between the data. By calculating the semi-variance, the impact of each delivery point on the adjacent area can be accurately evaluated; the grouping distance range is a preset distance range, for example, if the preset distance is 10m, the preset distance range includes distance ranges such as 0-10, 10-20, and 20-30, and grouping means that a pair of shared book delivery points within the same distance range are grouped together; the shared book delivery point pair is every two shared book delivery points; the calculation result of the semi-variance cannot be directly used for interpolation, so it is necessary to fit a variogram model to estimate the semi-variance value of any distance; the unknown user active number information grid means that the shared book delivery point is not in the grid, and the active number of users in the area described by the grid cannot be known.

[0068] Figure 2 The flowchart of the present invention for obtaining the optimization scheme of shared book delivery points is shown.

[0069] According to an embodiment of the present invention, the location of the shared book drop-off point is optimized according to the borrowing heat map to obtain an optimization plan for the shared book drop-off point, specifically:

[0070] S202, obtaining service restriction data of each shared book delivery point, wherein the service restriction data includes a service radius restriction and a user active number processing capacity restriction;

[0071] S204, introducing a particle swarm optimization algorithm, presetting an optimization distance limit for a shared book delivery point, using the service restriction data and the optimization distance limit as optimization condition limits for the particle swarm optimization algorithm, and using the maximum number of active users that each shared book delivery point can serve as an optimization target for the particle swarm optimization algorithm;

[0072] S206, searching the borrowing heat map based on a particle swarm optimization algorithm to determine an optimal location of a shared book drop-off point in a target area, and optimizing the location of the shared book drop-off point according to the optimal location;

[0073] S208, performing statistics on the number of active user processing for the shared book delivery point after the location optimization according to the service restriction data, and if the number of active user processing is greater than the active user processing capacity, marking the shared book delivery point as a delivery point with overloaded processing capacity;

[0074] S210, adding a shared book delivery point at a preset distance from the delivery point with overloaded processing capacity, until the number of active users processed by the shared book delivery points in the target area is not greater than the processing capacity of the active number of users, and obtaining an optimization plan for the shared book delivery points.

[0075] It should be noted that by introducing the particle swarm optimization algorithm (PSO) to optimize the location of shared book drop-off points, more users can easily borrow the required books, thereby improving user satisfaction. By analyzing the number of active users and the borrowing heat map, PSO can reasonably allocate resources among multiple drop-off points, avoid waste of book resources, ensure that the number of books at each drop-off point matches user needs, and improve resource utilization efficiency; PSO can find the best location of each drop-off point by global search in the borrowing heat map, ensure that the location distribution of the drop-off points is reasonable, and maximize the coverage of user demand areas; in the optimization of shared book drop-off points, particles can represent different possible locations of the drop-off points. Through the iterative process of the algorithm, the location of the drop-off points is continuously adjusted, thereby achieving the optimization of the location of the drop-off points. According to the data of the borrowing heat map, combined with the service radius and user active processing capacity and other constraints, PSO can flexibly adjust the distribution of each drop-off point to ensure that the user needs of each area are reasonably met; the user active number processing capacity is limited to the maximum number of borrowers that the shared book drop-off point can handle every day; the user active processing number is the number of borrowers that the shared book drop-off point needs to handle every day after the location is optimized.

[0076] Figure 3 The flowchart of the present invention for obtaining the prediction result of the change of the user's borrowing demand is shown.

[0077] According to an embodiment of the present invention, the user borrowing record change data of each shared book delivery point optimized according to the shared book delivery point optimization scheme in the target area within a preset time period is obtained, and the user borrowing demand change of each shared book delivery point within the future preset time period is predicted according to the user borrowing record change data, and the user borrowing demand change prediction result is obtained, specifically:

[0078] S302, obtaining historical user borrowing record change data of each shared book delivery point optimized according to the shared book delivery point optimization scheme in the target area, wherein the historical user borrowing record change data includes a change in the borrowing quantity of each type of book;

[0079] S304, constructing a user borrowing change prediction model for each shared book delivery point based on the GRU algorithm, dividing the historical user borrowing record change data into a training set and a test set according to a preset ratio, importing the training set into the user borrowing change prediction model for model training, and performing a prediction performance test on the trained user borrowing change prediction model through the test set, and adjusting the model parameters until the model prediction accuracy is greater than the preset accuracy;

[0080] S306, obtaining the user borrowing record change data of each shared book distribution point within a preset time period, importing the user borrowing record change data into the user borrowing change prediction model to predict the user borrowing demand change of each shared book distribution point within the future preset time period, and obtaining the user borrowing demand change prediction result.

[0081] It should be noted that the GRU algorithm is a gated recurrent unit, which is an improved version of a recurrent neural network (RNN) for processing sequence data. It is specially designed to solve the long-term dependency problem in traditional RNN. GRU is a deep learning model specially designed to process sequence data, which can effectively capture the time dependency and trend in time series. In the management of shared book delivery, user borrowing records are essentially time series data. GRU can learn the pattern of borrowing behavior changing over time to help predict future borrowing demand; by predicting changes in user borrowing demand within a preset time period in the future, managers can increase the delivery of a certain type of books in advance, thereby avoiding borrowing shortages; accurate demand forecasting enables users to obtain the required books within the required time, improving the user's borrowing experience and satisfaction.

[0082] According to an embodiment of the present invention, the shared books in the target area are allocated according to the prediction result of the change of the user's borrowing demand to obtain a shared book allocation plan for the target area, specifically:

[0083] Acquire the shared book stock information of each shared book delivery point, determine the borrowing redundancy and borrowing shortage of each type of books at each shared book delivery point in a preset time period in the future according to the prediction result of the user borrowing demand change and the shared book stock information, and obtain the book borrowing supply and demand data of each shared book delivery point;

[0084] Acquire the location information of each shared book delivery point, and construct a location distribution map of the shared book delivery points in the target area according to the location information;

[0085] According to the book borrowing supply and demand data of each shared book delivery point, the shared book delivery point with borrowing shortage is marked as the delivery point to be transferred in;

[0086] According to the types of scarce books and the amount of scarce books borrowed at the drop-in point to be transferred in, a shared book drop-in point with redundant borrowing of the scarce books type is identified, and marked as the drop-in point to be transferred out;

[0087] Determine the distance between each to-be-called-out delivery point and the to-be-called-in delivery point according to the shared book delivery point location distribution map, and set a call-out priority for each to-be-called-out delivery point according to the distance;

[0088] The borrowing and shortage book types are allocated according to the borrowing redundancy of the borrowing and shortage book types in each to-be-allocated delivery point and the allocation priority. If the borrowing and shortage book types after allocation still cannot meet the borrowing and shortage quantity of the borrowing and shortage book types in the to-be-allocated delivery point, new books are placed for the borrowing and shortage book types to obtain a shared book allocation plan for the target area;

[0089] The shared books in the target area are allocated according to the shared book allocation plan.

[0090] It should be noted that by analyzing the prediction results of changes in user borrowing demand and book inventory information in real time, it can ensure that the book resources of each shared book delivery point are effectively allocated. This optimization can avoid resource waste or user loss caused by excess or shortage of inventory; based on the book borrowing supply and demand data, the system can accurately identify the borrowing shortage and redundancy of each delivery point, so as to implement targeted allocation; by evaluating the distance between the delivery points to be transferred in and out, it can select closer delivery points for book allocation, thereby reducing transportation costs and time; when the existing borrowing redundancy cannot meet the shortage, the system can quickly identify the type of new books that need to be delivered. This forward-looking management strategy helps to update book resources in a timely manner to attract more users to use shared book services. The entire allocation process is based on real-time data analysis of changes in user borrowing needs and inventory information to form a data-driven management system; the shared book storage information includes the current stock of each type of book; the allocation priority is that the closer to the shared book delivery point to be transferred in, the higher the priority, and books are allocated from the highest priority outgoing delivery point to the shared book delivery point to be transferred in. If the number of allocated books from a outgoing delivery point is not enough to fill the borrowing shortage of the shared book delivery point to be transferred in, the next priority outgoing delivery point will be selected in turn for book allocation until the borrowing shortage of the shared book delivery point to be transferred in is filled.

[0091] According to an embodiment of the present invention, allocating shared books in a target area according to the shared book allocation scheme is specifically:

[0092] Acquire the resource information of the dispatched vehicles for the shared books in the target area, and determine the maximum dispatch quantity k of the dispatched vehicles according to the resource information of the dispatched vehicles;

[0093] According to the shared book allocation plan, the quantity information of the delivery points to be allocated is obtained, and according to the quantity information, the required dispatch quantity of vehicles for the shared book allocation in the target area is determined;

[0094] If the required dispatching amount of the vehicle is less than or equal to the maximum dispatching amount, a vehicle is arranged for each delivery point to be dispatched to dispatch shared books, each delivery point to be dispatched out and each delivery point to be dispatched to are marked in the shared book delivery point location distribution map, and a path search is performed on the delivery points marked in the shared book delivery point location distribution map based on the Dijkstra algorithm to determine the first dispatching path of each dispatching vehicle;

[0095] It should be noted that when allocating books, the number and dispatching capacity of the dispatching vehicles are often an important limiting factor. If the dispatching vehicles are insufficient, it will not be possible to respond to changes in user demand in a timely manner, which will further aggravate the problem of borrowing shortage. In addition, in the actual book allocation process, how to choose the best dispatching path is crucial. If the path selection is inappropriate, it will not only increase the transportation cost and time, but also lead to an increase in dispatching pressure; therefore, by determining the maximum dispatching amount of dispatching vehicles in the target area and determining the required dispatching amount of vehicles for the shared book allocation plan, when the required dispatching amount of the vehicle is less than or equal to the maximum dispatching amount, the vehicle dispatching can be dispatched in accordance with the shared book allocation plan. Since the delivery point to be transferred in may need to transfer multiple types of books from multiple delivery points to be transferred out, the dispatching vehicle needs to travel to multiple delivery points to be transferred out. At this time, the Dijkstra algorithm is used to search for paths and determine the first dispatching path of each dispatching vehicle. The Dijkstra algorithm can effectively calculate the shortest path from the starting point to each delivery point, ensuring that the shortest distance route is selected during the dispatching process, thereby reducing transportation time and cost; the dispatching vehicle resource information includes the number of vehicles and vehicle loading capacity.

[0096] If the required dispatching quantity of the vehicle is greater than the maximum dispatching quantity, the priority of each waiting-to-be-dispatched delivery point is determined according to the total borrowing shortage quantity of each waiting-to-be-dispatched delivery point;

[0097] Performing a vehicle dispatch for the top k to-be-dispatched delivery points according to the dispatch priority, determining a second dispatch path for each dispatched vehicle in the vehicle dispatch, calculating a path length of the second dispatch path, and determining a dispatch pressure for each dispatched vehicle according to the path length;

[0098] Get the number i of waiting-for-dispatch points for vehicles that have not been scheduled in the first vehicle dispatch, sort the dispatched vehicles from small to large according to the dispatch pressure, select the first i vehicles for the second vehicle dispatch, and determine the third dispatch path for the second dispatched vehicles.

[0099] It should be noted that when the required dispatching volume of vehicles exceeds the maximum dispatching volume of available vehicles, how to effectively allocate resources and plan routes becomes a key issue. At this time, relying solely on the first round of dispatching may not be able to meet the needs of all the delivery points to be transferred in, so it is necessary to introduce a priority dispatching strategy and a multi-round dispatching mechanism; by determining the priority of transfer-in according to the total borrowing shortage, the limited transportation resources can be effectively allocated to the delivery points that need them most; by evaluating and sorting the path lengths of dispatched vehicles, the burden on individual vehicles can be effectively reduced, ensuring that the dispatching pressure of each vehicle is within a reasonable range; in each round of dispatching, the optimal path can be recalculated according to new needs to ensure that transportation efficiency is improved and the overall dispatching time is shortened; the first, second, and third in the first dispatching path, the second dispatching path, and the third dispatching path are to distinguish the different paths obtained in the plan.

[0100] Figure 4 A block diagram of a shared book delivery management system based on user demand prediction according to the present invention is shown.

[0101] The second aspect of the present invention further provides a shared book delivery management system 4 based on user demand prediction, the system comprising: a memory 41, a processor 42, the memory comprising a shared book delivery management method program based on user demand prediction, the shared book delivery management method program based on user demand prediction when executed by the processor, implements the following steps:

[0102] Obtaining information on the number of active users at each shared book drop-off point in the target area, and constructing a borrowing heat map of the target area based on the information on the number of active users;

[0103] Optimizing the location of shared book drop-off points according to the borrowing heat map to obtain an optimization plan for shared book drop-off points;

[0104] Obtaining user borrowing record change data for each shared book delivery point optimized according to the shared book delivery point optimization plan in the target area within a preset time period, predicting user borrowing demand changes for each shared book delivery point within a future preset time period based on the user borrowing record change data, and obtaining a user borrowing demand change prediction result;

[0105] The shared books in the target area are allocated according to the prediction result of the change of the user's borrowing demand, so as to obtain a shared book allocation plan for the target area.

[0106] The present invention discloses a shared book delivery management method and system based on user demand prediction, aiming to optimize book resource allocation and improve borrowing efficiency. The method includes: obtaining user activity information of each shared book delivery point in the target area, constructing a borrowing heat map; optimizing the delivery point location according to the heat map, forming an optimization plan; collecting user borrowing record change data of the optimized delivery point within a preset time period, and predicting future user borrowing demand to generate demand prediction results; allocating shared book resources according to the prediction results to form an allocation plan. This method improves the accuracy and efficiency of shared book delivery management by predicting borrowing demand.

[0107] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0108] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0109] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0110] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.

[0111] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0112] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A shared book delivery management method based on user demand prediction, characterized in that: The following steps are involved: Obtaining information on the number of active users at each shared book drop-off point in the target area, and constructing a borrowing heat map of the target area based on the information on the number of active users; Optimizing the location of shared book drop-off points according to the borrowing heat map to obtain an optimization plan for shared book drop-off points; Obtaining user borrowing record change data for each shared book delivery point optimized according to the shared book delivery point optimization plan in the target area within a preset time period, predicting user borrowing demand changes for each shared book delivery point within a future preset time period based on the user borrowing record change data, and obtaining a user borrowing demand change prediction result; The shared books in the target area are allocated according to the prediction result of the change of the user's borrowing demand, so as to obtain a shared book allocation plan for the target area.

2. A shared book delivery management method based on user demand prediction according to claim 1, characterized in that: The step of obtaining the user activity number information of each shared book delivery point in the target area and constructing a borrowing heat map of the target area according to the user activity number information is as follows: Obtain historical user borrowing record data of each shared book distribution point in the target area, calculate the daily average number of active users of each shared book distribution point based on the historical user borrowing record data, and obtain user active number information; Obtaining the location coordinate information of each shared book drop point, calculating the Euclidean distance between every two shared book drop points in the target area according to the location coordinate information, setting a grouping distance range, grouping the shared book drop point pairs according to the grouping distance range to obtain distance group data, and calculating the semi-variance of all shared book drop point pairs in each distance group according to the distance group data to obtain semi-variance data; Using the Gaussian model as a variogram model, fitting the variogram model according to the semivariance data, constructing a Kriging equation based on the semivariance data and the fitted variogram model, converting the Kriging equation into a matrix form, and determining the interpolation weight of each shared book delivery point; Divide the target area into grids according to a preset grid size, obtain the position coordinate information to be interpolated of the unknown user active quantity information grid, and perform an interpolation operation on each unknown user active quantity information grid according to the position coordinate information of each shared book delivery point, the user active quantity information of each shared book delivery point, the interpolation weight of each shared book delivery point, and the position coordinate information to be interpolated to obtain the user active quantity information of each grid in each target area; A borrowing heat map of the target area is constructed according to the active user quantity information of each grid.

3. A shared book delivery management method based on user demand prediction according to claim 1, characterized in that: The location of the shared book placement point is optimized according to the borrowing heat map to obtain an optimization plan for the shared book placement point, which is specifically: Obtaining service restriction data for each shared book delivery point, wherein the service restriction data includes service radius restriction and user active number processing capacity restriction; Introducing a particle swarm optimization algorithm, presetting an optimization distance limit for shared book delivery points, using the service restriction data and the optimization distance limit as optimization condition limits for the particle swarm optimization algorithm, and using the maximum number of active users that each shared book delivery point can serve as an optimization target for the particle swarm optimization algorithm; Searching the borrowing heat map based on a particle swarm optimization algorithm to determine an optimal location of a shared book drop-off point in a target area, and optimizing the location of the shared book drop-off point according to the optimal location; According to the service restriction data, the number of active user processing is counted for the shared book delivery point after the location optimization, and if the number of active user processing is greater than the active user processing capacity, the shared book delivery point is marked as a delivery point with overloaded processing capacity; Additional shared book delivery points are added at preset distances from the delivery points with overloaded processing capacity until the number of active users processed by the shared book delivery points in the target area is no greater than the active user processing capacity, thereby obtaining an optimization plan for shared book delivery points.

4. A shared book delivery management method based on user demand prediction according to claim 1, characterized in that: The step of obtaining the user borrowing record change data of each shared book delivery point optimized according to the shared book delivery point optimization scheme in the target area within a preset time period, and predicting the user borrowing demand change of each shared book delivery point within a future preset time period according to the user borrowing record change data, and obtaining the user borrowing demand change prediction result is specifically as follows: Acquire historical user borrowing record change data of each shared book delivery point optimized according to the shared book delivery point optimization scheme in the target area, wherein the historical user borrowing record change data includes the change in the borrowing quantity of each type of book; Based on the GRU algorithm, a user borrowing change prediction model is constructed for each shared book delivery point, the historical user borrowing record change data is divided into a training set and a test set according to a preset ratio, the training set is imported into the user borrowing change prediction model for model training, and the prediction performance of the trained user borrowing change prediction model is tested through the test set, and the model parameters are adjusted until the model prediction accuracy is greater than the preset accuracy; The user borrowing record change data of each shared book delivery point within a preset time period is obtained, and the user borrowing record change data is imported into the user borrowing change prediction model to predict the user borrowing demand change of each shared book delivery point within a future preset time period to obtain the user borrowing demand change prediction result.

5. A shared book delivery management method based on user demand prediction according to claim 1, characterized in that: The shared books in the target area are allocated according to the prediction result of the change of the user's borrowing demand to obtain a shared book allocation plan for the target area, specifically: Acquire the shared book stock information of each shared book delivery point, determine the borrowing redundancy and borrowing shortage of each type of books at each shared book delivery point in a preset time period in the future according to the prediction result of the user borrowing demand change and the shared book stock information, and obtain the book borrowing supply and demand data of each shared book delivery point; Acquire the location information of each shared book delivery point, and construct a location distribution map of the shared book delivery points in the target area according to the location information; According to the book borrowing supply and demand data of each shared book delivery point, the shared book delivery point with borrowing shortage is marked as the delivery point to be transferred in; According to the types of scarce books and the amount of scarce books borrowed at the drop-in point to be transferred in, a shared book drop-in point with redundant borrowing of the scarce books type is identified, and marked as the drop-in point to be transferred out; Determine the distance between each to-be-called-out delivery point and the to-be-called-in delivery point according to the shared book delivery point location distribution map, and set a call-out priority for each to-be-called-out delivery point according to the distance; The borrowing and shortage book types are allocated according to the borrowing redundancy of the borrowing and shortage book types in each to-be-allocated delivery point and the allocation priority. If the borrowing and shortage book types after allocation still cannot meet the borrowing and shortage quantity of the borrowing and shortage book types in the to-be-allocated delivery point, new books are placed for the borrowing and shortage book types to obtain a shared book allocation plan for the target area; The shared books in the target area are allocated according to the shared book allocation plan.

6. A shared book delivery management method based on user demand prediction according to claim 5, characterized in that: The allocation of shared books in the target area according to the shared book allocation plan is specifically as follows: Acquire the resource information of the dispatched vehicles for the shared books in the target area, and determine the maximum dispatch quantity k of the dispatched vehicles according to the resource information of the dispatched vehicles; According to the shared book allocation plan, the quantity information of the delivery points to be allocated is obtained, and according to the quantity information, the required dispatch quantity of vehicles for the shared book allocation in the target area is determined; If the required dispatching amount of the vehicle is less than or equal to the maximum dispatching amount, a vehicle is arranged for each delivery point to be dispatched to carry out the shared book dispatching, each delivery point to be dispatched out and each delivery point to be dispatched to are marked in the shared book delivery point location distribution map, and a path search is performed on the delivery points marked in the shared book delivery point location distribution map based on the Dijkstra algorithm to determine the first dispatching path of each dispatching vehicle; If the required dispatching quantity of the vehicle is greater than the maximum dispatching quantity, the priority of each waiting-to-be-dispatched delivery point is determined according to the total borrowing shortage quantity of each waiting-to-be-dispatched delivery point; Performing a vehicle dispatch for the top k to-be-dispatched delivery points according to the dispatch priority, determining a second dispatch path for each dispatched vehicle in the vehicle dispatch, calculating a path length of the second dispatch path, and determining a dispatch pressure for each dispatched vehicle according to the path length; Get the number i of waiting-for-dispatch points for vehicles that have not been scheduled in the first vehicle dispatch, sort the dispatched vehicles from small to large according to the dispatch pressure, select the first i vehicles for the second vehicle dispatch, and determine the third dispatch path for the second dispatched vehicles.

7. A shared book delivery management system based on user demand prediction, characterized in that: The shared book delivery management system based on user demand prediction includes a storage device and a processor. The storage device includes a shared book delivery management method program based on user demand prediction. When the shared book delivery management method program based on user demand prediction is executed by the processor, the following steps are implemented: Obtaining information on the number of active users at each shared book drop-off point in the target area, and constructing a borrowing heat map of the target area based on the information on the number of active users; Optimizing the location of shared book drop-off points according to the borrowing heat map to obtain an optimization plan for shared book drop-off points; Obtaining user borrowing record change data for each shared book delivery point optimized according to the shared book delivery point optimization plan in the target area within a preset time period, predicting user borrowing demand changes for each shared book delivery point within a future preset time period based on the user borrowing record change data, and obtaining a user borrowing demand change prediction result; The shared books in the target area are allocated according to the prediction result of the change of the user's borrowing demand, so as to obtain a shared book allocation plan for the target area.

Images