Information processing systems, methods, and programs

Abstract

The objective is to achieve efficient delivery of goods. [Solution] An information processing system in one aspect of the present invention includes an information acquisition unit that acquires location information and time information corresponding to the location information from a delivery terminal of a package delivery person, and a determination unit that determines the duration of stay corresponding to the delivery location where the delivery person delivered the package, based on the location information and the time information. Furthermore, a method in one aspect of the present invention is a method that acquires location information and time information corresponding to the location information from a delivery terminal of a package delivery person, and determines the duration of stay corresponding to the delivery location where the delivery person delivered the package, based on the location information and the time information.

Description

Technical Field

[0001] The present invention mainly relates to an information processing system, method, and program for managing package delivery.

Background Art

[0002] In logistics, as part of operational efficiency improvement, methods for managing package delivery are provided.

[0003] For example, Patent Document 1 discloses a method for detecting unentered delivery status by a delivery person based on the location information of the delivery person.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Although the technique disclosed in Patent Document 1 is premised on that the delivery location of a package is known in advance, on the other hand, especially in areas with little package delivery track record such as mountainous areas, there arises a problem that information on appropriate delivery locations and routes corresponding to the package delivery destinations is scarce.

[0006] Accordingly, the present invention aims to achieve improved delivery efficiency especially in areas with little package delivery track record.

Means for Solving the Problems

[0007] An information magazine processing system according to one aspect of the present invention includes an information acquisition unit that acquires location information and time information corresponding to the location information from a delivery terminal of a package delivery person, and a determination unit that determines the dwell time corresponding to the delivery location where the delivery person delivered the package, based on the location information and the time information. [Effects of the Invention]

[0008] According to the present invention, it is possible to improve delivery efficiency, especially in areas with a low volume of parcel deliveries. [Brief explanation of the drawing]

[0009] [Figure 1] This is a block diagram showing an information processing system according to the first embodiment of the present invention. [Figure 2] Figure 1 is a functional block diagram showing the server terminal 100. [Figure 3] Figure 1 is a functional block diagram showing the delivery terminal 200. [Figure 4] This figure shows an example of delivery data stored on the server terminal 100. [Figure 5] This figure shows an example of property data stored on the server terminal 100. [Figure 6] This figure shows an example of analysis data stored on the server terminal 100. [Figure 7] This flowchart shows an example of a process for determining the delivery person's dwell time according to the first embodiment of the present invention. [Figure 8] This flowchart shows an example of a process for calculating the average dwell time of a delivery person according to the first embodiment of the present invention. [Figure 9] This is a flowchart showing an example of a process for determining the delivery location of a package according to the first embodiment of the present invention. [Figure 10] This flowchart shows an example of a confirmation process based on the length of stay, according to the first embodiment of the present invention. [Figure 11]This is a schematic diagram showing an example of how the area map is displayed on the delivery terminal. [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described below with reference to the drawings. The embodiments described below are not intended to unduly limit the scope of the present invention as described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present invention.

[0011] <Structure> Figure 1 is a block diagram showing an information processing system according to a first embodiment of the present invention. This system 1 is managed, for example, by a delivery company or a delivery information platform operator, and consists of a server terminal 100 that manages delivery data, package data, etc. of delivery personnel and analyzes information for improving delivery efficiency, multiple delivery personnel terminals 200A, 200B of delivery personnel, and multiple user terminals 300A, 300B of users at delivery destinations. For the sake of explanation, each terminal is described as a single or specific number, but there is no limit to the number of each. Hereafter, for the sake of explanation, unless otherwise explained, delivery personnel terminals will be collectively referred to as delivery personnel terminals 200, and user terminals will be collectively referred to as user terminals 300, respectively.

[0012] The server terminal 100, the delivery terminal 200, and the user terminal 300 are each connected via the network NW1. The network NW consists of the Internet, intranet, wireless LAN (Local Area Network), WAN (Wide Area Network), etc.

[0013] The server terminal 100 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented through cloud computing.

[0014] The deliverer terminal 200 and the user terminal 300 are, for example, information processing apparatuses such as a personal computer and a tablet terminal, but may also be configured by a smartphone, a mobile phone, a PDA, or the like.

[0015] Figure 2 is a functional block configuration diagram of the server terminal 100 in Figure 1. The server terminal 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

[0016] The communication unit 110 is a communication interface for communicating with the deliverer terminal 200 and the user terminal 300 via the network NW1, and communication is performed according to a communication protocol such as TCP / IP (Transmission Control Protocol / Internet Protocol).

[0017] The storage unit 120 stores programs, input data and the like for executing various control processes and each function in the control unit 130, and is composed of a RAM (Random Access Memory), a ROM (Read Only Memory) and the like. Further, the storage unit 120 has a delivery data storage unit 121 that stores various data related to package delivery, a property data storage unit 122 that stores various data related to properties as delivery destinations, and an analysis data storage unit 123 that stores analysis data generated by analyzing delivery data, property data and the like. A database (not shown) storing various data may be constructed outside the storage unit 120 or the server terminal 100.

[0018] The control unit 130 controls the overall operation of the server terminal 100 by executing a program stored in the memory unit 120, and is composed of a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), etc. The functions of the control unit 130 include at least an information acquisition unit 131 that receives instructions and information from each terminal, a determination unit 132 that determines the delivery location of packages delivered by the delivery person based on the received information, a generation unit 133 that generates information such as the delivery location and screen information for displaying the information based on the result of the determination, and a display unit 134 that displays the generated information on each terminal. The information acquisition unit 131, determination unit 132, generation unit 133, and display unit 134 are started by a program stored in the memory unit 120 and executed by the server terminal 100, which is a computer (electronic calculator).

[0019] The information acquisition unit 131 receives predetermined information from the delivery terminal 200, etc., via the communication unit 110. For example, it receives the delivery person's location information and the time information corresponding to that location from the delivery terminal 200.

[0020] The information acquisition unit 131 can acquire location and time information from the delivery terminal 200 in various ways. For example, it can periodically poll the delivery terminal 200, receive information as a push notification from the delivery terminal 200, or acquire information based on pre-set conditions (for example, when the delivery person's travel distance exceeds a predetermined threshold, or when the delivery person enters a specific area).

[0021] Furthermore, the information acquisition unit 131 may include a function to evaluate the accuracy and reliability of location information and correct or exclude low-accuracy location information. Indicators such as GPS signal strength, the number of satellites used for positioning, and the horizontal degradation rate (HDOP) can be used to evaluate the accuracy of location information. Additionally, an anomaly detection algorithm can be applied to exclude data points indicating physically impossible movement speeds.

[0022] The information acquisition unit 131 can perform preprocessing on the acquired position information as background processing. Preprocessing includes applying a noise reduction filter, quantizing the position information (for example, setting the smallest significant unit of movement), or smoothing consecutive position information. This makes it possible to improve the accuracy and optimize the computational efficiency in subsequent judgment processing.

[0023] Furthermore, the information acquisition unit 131 can acquire additional information not only from location information but also from various sensors on the delivery terminal 200. For example, it can acquire acceleration sensor data (useful for identifying the delivery person's movement status), barometer data (useful for detecting changes in altitude), or compass sensor data indicating the orientation of the terminal, and store them in the storage unit 120 in association with location information and time information. This additional data can be used for more accurate determination of dwell time and identification of delivery locations.

[0024] The determination unit 132 performs predetermined determination processes based on the received information. For example, it performs processes to determine the delivery location where the delivery person delivered the package, and to determine the duration of stay at the delivery location, based on the location information and time information.

[0025] Multiple determination methods can be applied to the determination of the stay time by the determination unit 132. The first determination method is a determination based on the length of time during which the same or nearby location information is received consecutively. Specifically, for multiple location information received from the delivery terminal 200, consecutive data points located within a predetermined distance threshold (e.g., 10 meters) are considered to be the same stay location, and the difference in time information between the first and last location information at that location is calculated as the stay time.

[0026] A second determination method is based on the delivery person's speed. Specifically, if the speed of movement between consecutive location information points falls below a predetermined threshold (for example, 1 km / h), it is considered to be in a dwelling state, and the duration of that state is calculated as the dwelling time. This method eliminates minute positional changes due to GPS errors, allowing for a more accurate determination of the dwelling time.

[0027] A third method of determination involves using a machine learning model. This model, trained on past delivery data, probabilistically determines whether a particular location is a delivery location based on multiple features such as location information, time information, surrounding environment information, and characteristics of the delivered item, and then estimates the corresponding dwell time. This model can be retrained each time new data is accumulated, thereby improving the accuracy of the determination.

[0028] The determination unit 132 can dynamically adjust the threshold setting for the length of stay according to various conditions. For example, different threshold values ​​can be set for each type of delivery area (urban, suburban, mountainous, etc.). Specifically, a relatively short threshold value (e.g., 3 minutes) can be applied in urban areas, a medium threshold value (e.g., 5 minutes) in suburban areas, and a longer threshold value (e.g., 7 minutes) in mountainous areas, applying values ​​according to regional characteristics. It is also possible to adjust the threshold by applying coefficients according to the time of day (daytime, evening, nighttime, etc.) and weather conditions (sunny, rainy, snowy, etc.).

[0029] Furthermore, the determination unit 132 can also use a method based on comparison with past delivery data when determining the delivery location. By referring to delivery location data for the same or similar delivery destinations from past delivery data stored in the storage unit 120, a probability density map of delivery locations can be generated, and the delivery location can be determined by comparing it with the current location information. This probability density map is generated based on the clustering results of past delivery location data, and a confidence score can be calculated according to the distance from the center of the cluster.

[0030] The determination unit 132 can integrally determine the delivery location and calculate the dwell time. Specifically, it first extracts locations where the dwell time exceeds a predetermined threshold as delivery location candidates, and then selects the most likely delivery location based on geographical factors (e.g., building location, distance from road, etc.) and past patterns. The dwell time corresponding to the selected delivery location can be recorded as the time required for the delivery process.

[0031] The generation unit 133 performs a process to generate predetermined information based on the determination result. For example, based on the delivery location obtained as a determination result, it performs a process to generate information indicating the delivery location and / or screen information. Here, when generating screen information, the generation unit 133 uses the image and text data stored in the storage unit 120 as material and generates screen information for the user interface by arranging various images and text in predetermined areas of the user interface according to predetermined layout rules. Furthermore, the processing related to the generation of screen information can also be performed by a GPU (Graphics Processing Unit).

[0032] The generation unit 133 can generate various analytical and visualization information based on the dwell time data determined by the determination unit 132. For example, by generating a heat map that overlays the dwell time data onto map information, geographical dwell patterns can be visualized. This heat map uses color representation according to the length of dwell time (for example, lighter colors for short periods and darker colors for longer periods), providing information in an intuitively easy-to-understand format.

[0033] Furthermore, the generation unit 133 can generate statistical analysis results of dwell time. It aggregates dwell time data from various perspectives, such as by property type, time of day, and day of the week, and calculates statistical indicators such as the mean, median, and standard deviation. This statistical information is expressed in table and graph format and can be used to optimize delivery plans and efficiently allocate delivery resources.

[0034] Furthermore, the generation unit 133 can also generate anomaly analysis results for dwell time. It detects values ​​that deviate significantly from past average dwell time patterns and generates information to identify potential problems or unusual events. For example, if the dwell time at a particular delivery location is more than twice the normal time, it can provide detailed information to analyze the cause (e.g., difficulty in access, redelivery due to recipient's absence).

[0035] The generation unit 133 can also generate route analysis information that combines the delivery person's movement trajectory and points of stay. By reconstructing the delivery person's movement route from continuous location information and analyzing its relationship with points of stay, it provides information that can be used to design efficient delivery routes. This analysis evaluates the balance between the length of stay and the distance and time traveled, and can be used to propose the optimal delivery order.

[0036] The display unit 134 performs the process of displaying the generated information via a user interface such as the delivery terminal 200. For example, the display unit 134 transmits screen information to the delivery terminal 200, and the delivery terminal 200 displays the screen via its user interface based on the received screen information.

[0037] The display unit 134 can provide various display modes for displaying information generated by the generation unit 133 on the delivery terminal 200, administrator terminals, etc. For example, in real-time mode, it processes and displays dwell time data for ongoing delivery operations almost instantly, supporting delivery personnel in understanding their situation and making immediate decisions. On the other hand, in analysis mode, it displays the results of aggregating and analyzing past delivery data in a detailed dashboard format, which can be used to formulate delivery strategies and identify areas for improvement. These modes may be configured to be selectively switched according to the user's selection.

[0038] The display unit 134 can also provide customized displays according to the user's role and permissions. For delivery drivers, it can focus on displaying practical information such as their own delivery efficiency and estimated arrival time at the next delivery destination, while for administrators, it can provide supervisory information such as team-wide performance indicators and anomaly detection results.

[0039] Furthermore, the display unit 134 also has an alert display function. If the dwell time exceeds a predetermined threshold or deviates significantly from the average value, it can provide visual and auditory warnings to the delivery terminal 200. This allows the delivery person to immediately notice potential problems and take appropriate action.

[0040] The display unit 134 can also provide a multi-layer display function for map display. It is possible to overlay multiple information layers, such as a dwell time heatmap, recommended routes, and parking location information, on top of the basic map information. Users can switch the display / hide of layers as needed, enabling information display optimized for the situation and purpose.

[0041] Figure 3 is a functional block diagram showing the delivery terminal 200 of Figure 1. The delivery terminal 200 includes a communication unit 210, a display and operation unit 220, a storage unit 230, a control unit 240, and a GPS 250.

[0042] The communication unit 210 is a communication interface for communicating with the server terminal 100 via the network NW, and communication is performed using a communication protocol such as TCP / IP.

[0043] The display operation unit 220 is a user interface used by the delivery person to input instructions and display text, images, etc., in accordance with the input data from the control unit 240. If the delivery person terminal 200 is a smartphone or tablet, the display operation unit 220 consists of a touch panel or the like. This display operation unit 220 is activated by a control program stored in the memory unit 230 and executed by the delivery person terminal 200, which is a computer (electronic calculator).

[0044] The memory unit 230 stores programs for executing various control processes and functions within the control unit 240, input data, etc., and is composed of RAM, ROM, etc. The memory unit 230 can also temporarily store the contents of communication with the server terminal 100.

[0045] The control unit 240 controls the overall operation of the delivery terminal 200 by executing a program stored in the memory unit 230, and is composed of a CPU, GPU, and the like.

[0046] GPS250 refers to the Global Positioning System, which uses artificial satellites to determine the current location and time (time information) of the delivery terminal 200.

[0047] In addition to its standard positioning capabilities, the GPS250 can also feature a high-precision mode as an extended function. This high-precision mode combines satellite positioning with auxiliary positioning technologies such as automated GPS (A-GPS), Wi-Fi positioning, and cell phone base station triangulation, improving positional accuracy, especially in urban areas and indoor environments. It also features a function to dynamically adjust the positioning frequency according to the situation, optimizing the balance between battery consumption and tracking accuracy by acquiring location information at a low frequency (e.g., every 30 seconds) while the delivery person is moving, and at a high frequency (e.g., every 5 seconds) when they reach a specific area.

[0048] Furthermore, the delivery terminal 200 can also be equipped with the ability to connect with external APIs. This function allows the delivery terminal 200 to connect with external data sources such as weather APIs, traffic information APIs, and map information APIs, and to acquire and utilize additional contextual information about the delivery environment. For example, by associating rainfall information obtained from the weather API with location information, it is possible to analyze the impact of bad weather on the length of stay. Similarly, by incorporating congestion data obtained from the traffic information API into route analysis, it becomes possible to make more realistic delivery time predictions.

[0049] Figure 4 shows an example of delivery data stored in the server terminal 100.

[0050] As shown in Figure 4, delivery data 1000 stores various data related to package delivery managed by the delivery company. As various data related to package delivery, first, a delivery ID (for example, a delivery event identified as "10001") is assigned as information to identify a single delivery event (delivery request, etc.), and associated with the delivery ID, package information (for example, information to identify the package (package ID, etc.), information about the sender (requester, shipper), information about the destination (recipient, recipient) (property ID, contact information, delivery location, etc.), other information such as date (reception date and time, specified delivery date and time, delivery completion date and time, etc.), package contents, package weight, fee, responsible delivery office, delivery vehicle, etc.), and delivery person information (information to identify the delivery person (delivery person ID, etc.), delivery person location information, time information corresponding to the location (time, etc.), delivery method (truck, motorcycle, UAV (drone), etc.), time spent at a specific location, delivery location where the package was delivered, parking location where the vehicle was parked, etc.) may be included, but is not limited to these.

[0051] Figure 5 shows an example of property data stored in the server terminal 100.

[0052] As shown in Figure 5, property data 2000 stores various data related to the property (house, facility, business premises, etc.) corresponding to the delivery destination of the package. As various data related to the property, a property ID (for example, a property identified as "20001") is assigned as information to identify the property, and associated with the property ID, property information (for example, location information to identify the location of the property, parking locations available for delivering packages to the property, information about the recipient (for example, name, gender, age, etc.), other information such as the type of property (detached house, apartment building, office, etc.)), and delivery information associated with that property (for example, delivery person's stay time, delivery location, drop-off location, number of deliveries, etc.) may be included, but is not limited to these.

[0053] Figure 6 shows an example of analysis data stored in the server terminal 100.

[0054] As shown in Figure 6, the analysis data 3000 stores information related to the analysis results obtained based on information received from the delivery person, and information referenced during the analysis. The analysis data 3000 may include, but is not limited to, map information obtained from external applications, etc., that the delivery person uses to identify the route and destination for delivery of the package, heat map information generated by superimposing on the map information based on the delivery person's location and time information, road information generated by superimposing on the map information to identify roads for the land transport of the package, route information that identifies the route to the delivery destination of the package, property information associated with the delivery destination of the package, and dwell time information related to the average dwell time of multiple delivery persons, etc.

[0055] <Making the most of your time during your stay> The system 1 of this embodiment can utilize the dwell time data determined by the determination unit 132 in a variety of ways. The main methods of utilizing the dwell time data will be described below.

[0056] First, dwell time data can be used to optimize delivery plans. By incorporating the average dwell time at specific properties or areas into delivery planning, more accurate delivery time predictions and efficient delivery route design become possible. For example, if it is found that dwell times are long in a particular area, the number of deliveries in that area can be adjusted, or more experienced delivery personnel can be assigned, thereby improving overall delivery efficiency.

[0057] Next, dwell time data can be used for evaluating and training delivery drivers. Analyzing each driver's dwell time pattern can help identify efficient work methods and areas for improvement. Furthermore, in the training process for new drivers, referencing the dwell time patterns of experienced drivers as a benchmark can facilitate the acquisition of efficient delivery techniques.

[0058] Furthermore, dwell time data can be used to improve the quality of delivery services. Extremely short dwell times may indicate poor delivery, while extremely long dwell times may indicate delivery difficulties, allowing for appropriate countermeasures to be taken in each case. For example, for properties where dwell times are consistently long, the delivery method can be optimized by recommending options such as leaving packages at the door or installing dedicated delivery boxes.

[0059] Furthermore, dwell time data can be used to optimize the selection of delivery methods. In particular, for areas such as mountainous regions where vehicle access is difficult and dwell times tend to be long, it can be used as a basis for considering the introduction of alternative delivery methods such as drones. By analyzing the correlation between dwell time and delivery efficiency, it is possible to optimize the scope of application for each delivery method, thereby achieving overall cost reduction and improved delivery efficiency.

[0060] From the perspective of improving customer service, it is also possible to improve the accuracy of delivery predictions by utilizing dwell time data. By combining past dwell time patterns with the current delivery status, it is possible to more accurately predict the arrival time at each delivery destination and notify recipients at the appropriate time. This makes it possible to minimize the waiting time for recipients and reduce redeliveries due to absence.

[0061] Furthermore, dwell time data can also be used in planning the development of logistics infrastructure. If there is a tendency for longer dwell times in specific areas or along certain routes, the causes can be analyzed and used to plan measures to improve logistics efficiency, such as road improvements and securing parking spaces. In particular, it serves as a valuable data source for building efficient delivery infrastructure in areas with low delivery volume.

[0062] As described above, System 1 of this embodiment determines the duration of stay based on the delivery person's location and time information, and can utilize this information in various ways. The specific processing flow of System 1 will be described in detail below with reference to Figure 7 and subsequent figures.

[0063] <Processing flow> Referring to Figures 7 and onward, the processing method for streamlining package delivery performed by System 1 of this embodiment will be described. First, Figure 7 is a flowchart showing an example of the process for determining the dwell time corresponding to the delivery location of a package, according to the first embodiment of the present invention.

[0064] First, as a premise, each delivery person (deliverer) of a delivery company carries a delivery terminal 200 and delivers packages requested by the consignor to designated destinations via delivery means such as trucks. In this case, especially in mountainous areas where roads are not well-developed or accessible, it is assumed that the delivery person will park their vehicle in a parking space near the destination, carry the packages on foot to the destination, and finally deliver them. Alternatively, it is also assumed that the packages will be delivered by leaving them at a designated delivery location specified by the user at the destination. Determining the time spent at the destination is an important indicator for analyzing and optimizing this entire delivery process.

[0065] Next, as part of step S101, the information acquisition unit 131 of the control unit 130 of the server terminal 100 receives the delivery person's location information from the delivery person's terminal 200. Here, the information acquisition unit 131 can receive the delivery person's current location information at predetermined time intervals or through batch processing, receiving location information corresponding to each of multiple time points. The information acquisition unit 121 stores the received location information as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120.

[0066] Next, as part of step S102, the information acquisition unit 131 of the control unit 130 of the server terminal 100 receives the location information along with time information (for example, date and time) corresponding to the location information. The information acquisition unit 131 associates the received time information with the location information and stores it as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120.

[0067] Next, as part of step S103, the determination unit 132 of the control unit 130 of the server terminal 100 determines the delivery location of the package by the delivery person based on the received location information and time information of the delivery person. Specifically, the determination unit 132 calculates the delivery person's stay time at a point identified by the location information based on multiple location information at different times obtained from the delivery person terminal 200, and determines the delivery location by inferring that the delivery person delivered the package at a point where the delivery person stayed for a predetermined time or longer.

[0068] Alternatively, the determination unit 132 can determine the delivery location by calculating the number of times a delivery person (whether the same delivery person or a different delivery person) has stayed at a location based on location and time information received from the delivery person terminal 200 for deliveries to the same destination corresponding to different delivery events (delivery IDs), and by inferring the location where the delivery person has stayed a predetermined number of times or more as the delivery location.

[0069] Furthermore, the determination unit 132 can also determine the delivery location by tracing the points that the delivery person (whether the same or different delivery person) has passed through, by plotting them on a map, based on the location and time information received from the delivery person terminal 200 for deliveries to the same destination corresponding to different delivery events (delivery IDs), and by inferring the end point of the route the delivery person has taken as the delivery location.

[0070] The determination unit 132 stores the determined delivery location as analysis data 3000 in the analysis data storage unit 123 of the memory unit 120, and can also store it as property data 2000 in the property data storage unit 122, associated with the property information of the delivery destination. This makes it possible to determine the delivery location based on location information, even in mountainous areas where it is difficult to determine the location where the package should be delivered using pre-registered property or map information.

[0071] Next, as part of step S104, the determination unit 132 stores the delivery person's dwell time corresponding to the determined delivery location as analysis data 3000 in the analysis data storage unit 123 of the memory unit 120, associating it with the delivery location. This makes it possible to manage the delivery person's dwell time corresponding to the delivery of the package, and to analyze the time required for unloading, handover (time required to deal with residents), etc., during package delivery for each property.

[0072] Figure 8 is a flowchart showing an example of a process for calculating the average dwell time of a delivery person according to the first embodiment of the present invention.

[0073] First, as part of step S201, the information acquisition unit 131 of the control unit 130 of the server terminal 100 receives the delivery person's location information from the delivery person's terminal 200. Here, the information acquisition unit 131 can receive the delivery person's current location information at predetermined time intervals or through batch processing, receiving location information corresponding to each of multiple time points. The information acquisition unit 121 stores the received location information as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120.

[0074] Next, as part of step S202, the information acquisition unit 131 of the control unit 130 of the server terminal 100 receives the location information along with time information (for example, date and time) corresponding to the location information. The information acquisition unit 131 associates the received time information with the location information and stores it as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120.

[0075] Next, as part of step S203, the determination unit 132 of the control unit 130 of the server terminal 100 determines the delivery location and dwell time for each delivery event (delivery ID) based on the received delivery person location information and time information. For each delivery event, the determination unit 132 obtains dwell time data corresponding to the delivery location stored for each of multiple delivery events by the same or different delivery persons, and calculates the average dwell time by arithmetic calculation of the average value.

[0076] The determination unit 132 stores the calculated average dwell time data as analysis data 3000 in the analysis data storage unit 123 of the storage unit 120. Specifically, it stores numerical data of the average dwell time associated with the ID of each delivery location. In addition to the average dwell time information, the determination unit 132 also stores the count value of the number of times packages have been delivered to each delivery location, and the delivery frequency (aggregated values ​​based on period divisions such as monthly, quarterly, semi-annually, and yearly). This makes it possible to numerically analyze the correlation between the dwell time data and the time of year (peak season or normal season) and season.

[0077] Furthermore, the determination unit 132 may also perform area-based analysis. Specifically, it aggregates average dwell time data stored in association with multiple properties for each predefined area code and calculates the average dwell time for each area. In this aggregation process, the dwell time data for all delivery locations within each area is used as a sample, the arithmetic mean is calculated, and the data is stored as analysis data 3000 in association with the area code.

[0078] The determination unit 132 may also perform a characteristic analysis of the length of stay on a property-by-property basis. It compares the average length of stay for each property and identifies properties that require a significantly longer stay than the overall average (for example, more than 1.5 times the average). For such properties, a flag data indicating "long stay" is associated with them and stored in the property data 2000. This flag data is referenced when planning delivery schedules and is used to set delivery schedules with sufficient time leeway.

[0079] Furthermore, the determination unit 132 can perform dwell time analysis on a user / resident basis, in addition to property-level analysis. Specifically, it associates recipient information (user ID) included in the delivery data 1000 with dwell time data and calculates the average dwell time during delivery for a specific user / resident. The determination unit 132 extracts delivery events related to the corresponding user ID from the delivery data 1000 and calculates the arithmetic mean from the dwell time data for each delivery event. Using this data, the determination unit 132 can quantify the time required for each user / resident and rank them according to their characteristics. For example, using the average dwell time of all users as a baseline, ranks such as "normal response" (0.8 to 1.2 times the average), "long response" (1.2 to 1.5 times the average), and "special response" (more than 1.5 times the average) are set and stored in the property data 2000 or analysis data 3000 in association with each user / resident's ID. This data is transmitted to the delivery terminal 200, enabling time allocation that takes user characteristics into account when planning delivery.

[0080] Furthermore, the determination unit 132 also provides a delivery optimization function based on the time required for user / resident response. The determination unit 132 performs delivery order optimization processing based on the aforementioned rank information. For example, users / residents with the "special response" rank are placed at the end of the delivery route to prevent delays in subsequent deliveries. Also, in areas where users / residents with the "long response" rank are concentrated, a delivery plan is generated with additional time buffers. These optimization parameters are stored in the storage unit 120 as part of the delivery data 1000 and are referenced by the generation unit 133 when generating route information and delivery schedules.

[0081] Furthermore, the determination unit 132 provides a delivery person assignment optimization function that correlates the experience level of delivery persons with the characteristics of users' dwell time. The determination unit 132 aggregates the delivery performance of each delivery person (number of deliveries, assigned area, average delivery time, etc.) from the delivery data 1000 and quantifies the experience level of the delivery persons. For example, it calculates an experience score by combining indicators such as the number of deliveries in a specific area, the total number of deliveries in the past three months, and the degree of variation in dwell time. The determination unit 132 performs a matching process that combines this experience score with the aforementioned dwell time rank of users / residents. Specifically, it applies a rule that prioritizes the assignment of delivery persons with high experience scores to areas with many users / residents in the "special service" or "long-duration service" rank. This matching rule is stored in the storage unit 120 as a delivery person assignment parameter in the delivery data 1000 and is referenced in the delivery plan generation process. This makes it possible to efficiently assign experienced delivery persons who can appropriately handle users who require long-duration service.

[0082] The determination unit 132 performs a characteristic analysis of the length of stay for each property and ranks each property. Specifically, it compares the average length of stay for each property and classifies them into several ranks based on the statistical distribution. The determination unit 132 retrieves the length of stay data for all properties from the storage unit 120 and calculates the mean and standard deviation. Using these statistical values, it classifies properties into ranks such as "standard length of stay," "long stay," and "requires special attention." The determination unit 132 stores this classification result in the property data 2000 as a numerical code (e.g., 1=standard, 2=long stay, 3=special attention) or a string identifier. Based on this rank information, the generation unit 133 can perform visualizations such as color-coding the properties on the map display of the delivery terminal 200.

[0083] Furthermore, the determination unit 132 also performs a factor analysis that influences the dwell time characteristics of properties. The determination unit 132 obtains physical characteristic data such as building type, number of floors, presence or absence of security systems, and distance from parking spaces from the property data 2000, and analyzes the correlation between these and the dwell time data. For example, by comparing the average dwell time for each building type, it quantifies the relationship between specific conditions such as "five floors or higher in apartment buildings" or "apartments with automatic locks" and dwell time. The determination unit 132 stores these analysis results as analysis data 3000 in the storage unit 120. This data is used to predict the dwell time of new properties and to propose delivery efficiency improvements for properties with long dwell times (e.g., recommending leaving packages at a designated location).

[0084] The generation unit 133 may perform visualization processing of the data calculated by the determination unit 132. As shown in Figure 11, numerical data of the average stay time is displayed on the map (area map) of each delivery area displayed on the delivery terminal 200, corresponding to marker icons indicating the location of each property. The generation unit 133 also provides a function to display information on the number of deliveries and delivery frequency to the delivery location of each property on the map, either together with the average stay time data or using a switching display function.

[0085] Furthermore, the determination unit 132 may perform an inter-area comparative analysis. For each designated area, it aggregates the dwell time data of multiple properties included in that area and performs a numerical comparison of the average dwell time across multiple areas. This analysis makes it possible to quantitatively understand which areas have longer dwell times.

[0086] Furthermore, the determination unit 132 may also include a function to recommend delivery methods based on dwell time data. For properties or areas with particularly long dwell times, it generates information recommending the use of UAVs (unmanned aerial vehicles, drones) as an alternative delivery method to improve efficiency, taking into account their geographical characteristics (e.g., mountainous areas) and delivery conditions (e.g., time required for unloading). This recommendation information is transmitted to the delivery terminal 200 and the management terminal of the delivery company to support decision-making in the delivery plan.

[0087] In step S203 described above, the determination unit 132 can apply more advanced statistical processing to calculate the average stay time, rather than just a simple arithmetic mean. For example, to mitigate the influence of outliers, filtering based on the interquartile range (IQR) can be applied to exclude data points that deviate significantly from the mean (e.g., outside the range of mean ± 2 × standard deviation) before calculating the mean. Furthermore, as a time-series trend analysis, it is also possible to analyze the trend of changes in stay time from the past to the present and apply a weighted average method that gives higher weight to the latest data.

[0088] Furthermore, the determination unit 132 can also calculate the average dwell time based on complex classification criteria. For example, it can calculate the average dwell time for each multidimensional combination such as "property type x time of day x day of the week," enabling more precise delivery time predictions. This multidimensional analysis makes it possible to quantitatively understand that, for example, the optimal delivery plan differs between "delivery to an office building on a weekday morning" and "delivery to an apartment building on a weekend afternoon."

[0089] Figure 9 is a flowchart showing an example of a process for determining the delivery location of a package according to the first embodiment of the present invention.

[0090] First, as part of step S301, the information acquisition unit 131 of the control unit 130 of the server terminal 100 receives the delivery person's location information from the delivery person's terminal 200. Here, the information acquisition unit 131 can receive the delivery person's current location information at predetermined time intervals or through batch processing, receiving location information corresponding to each of multiple time points. The information acquisition unit 121 stores the received location information as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120.

[0091] Next, as part of step S302, the information acquisition unit 131 of the control unit 130 of the server terminal 100 receives the location information along with time information (for example, date and time) corresponding to the location information. The information acquisition unit 131 associates the received time information with the location information and stores it as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120.

[0092] Next, as part of step S303, the determination unit 132 of the control unit 130 of the server terminal 100 calculates the time spent at each location of the delivery person based on the received location and time information of the delivery person, and stores the calculated time spent as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120 as a delivery location for confirmation. The determination unit 132 then determines whether the time spent at the delivery location for confirmation exceeds a predetermined time. The determination unit 132 can refer to the calculated average time spent as the predetermined time.

[0093] If the determination unit 132 determines that the stay time exceeds a predetermined time as a result of the above determination, it determines the confirmation delivery location as the delivery location. The determination unit 132 stores the determined delivery location as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120 and / or as property data 2000 in the property data storage unit 122. This makes it possible to more accurately grasp and manage the delivery location.

[0094] In the delivery location determination process performed by the determination unit 132 described above, a complex determination algorithm that considers multiple factors in addition to the time spent at the location can be applied. For example, as a geographical context analysis, location information can be compared with building data on a map to verify whether the location at the location of stay matches the physical location of the building. Furthermore, as a delivery person movement pattern analysis, the accuracy of delivery location determination can be improved by detecting typical delivery behavior patterns (e.g., approaching the building from the road and returning) from the movement trajectory before and after the point of stay.

[0095] Furthermore, the determination unit 132 can also make determinations that take temporal context into consideration. For example, it can verify the consistency between the delivery time slot (morning delivery, afternoon delivery, etc.) and the time spent at the destination, and prioritize evaluating destinations that match the scheduled delivery time slot as potential delivery locations. It is also possible to apply a method that analyzes the relationship between the time interval and the time spent at the destination in multiple consecutive deliveries, and determines locations that show a reasonable time allocation on the delivery route as delivery locations.

[0096] Figure 10 is a flowchart showing an example of a verification process based on the length of stay, according to the first embodiment of the present invention.

[0097] First, as part of step S401, the information acquisition unit 131 of the control unit 130 of the server terminal 100 receives the delivery person's location information from the delivery person's terminal 200. Here, the information acquisition unit 131 can receive the delivery person's current location information at predetermined time intervals or through batch processing, receiving location information corresponding to each of multiple time points. The information acquisition unit 121 stores the received location information as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120.

[0098] Next, as part of step S402, the information acquisition unit 131 of the control unit 130 of the server terminal 100 receives the location information along with time information (for example, date and time) corresponding to the location information. The information acquisition unit 131 associates the received time information with the location information and stores it as delivery data 1000 in the delivery data storage unit 121 of the storage unit 120.

[0099] Next, as part of step S403, the determination unit 132 of the control unit 130 of the server terminal 100 calculates the delivery location and the delivery person's stay time at the delivery location based on the received delivery person location information and time information, and determines whether the calculated stay time exceeds a predetermined time. The determination unit 132 can refer to the calculated average stay time corresponding to the delivery location as the predetermined time.

[0100] If the determination unit 132 determines that the dwell time exceeds a predetermined time, it can send a notification to the delivery terminal 200 indicating that the dwell time exceeds the average dwell time, or a notification (alert) to check the delivery status. The delivery person can also input a memo in response to the alert, such as the reason for the delay, including unloading or dealing with residents, and send it to the server terminal 100. This allows the delivery status to be checked based on the dwell time at the delivery destination, thereby improving delivery efficiency.

[0101] In the verification process based on dwell time in step S403 described above, it is possible to apply more advanced anomaly detection algorithms than simply comparing with a predetermined time. For example, one method is to construct a statistical profile from past dwell time data for each property and determine that an anomaly occurs if the current dwell time falls outside the confidence interval (e.g., 95% confidence interval) of that profile. It is also possible to use time series analysis techniques to detect unexpected deviations while considering periodic patterns such as seasonal and time-of-day variations in dwell time.

[0102] Furthermore, the judgment unit 132 can perform context-aware anomaly detection. For example, considering that the overall dwell time tends to be longer during bad weather, it can set dynamic thresholds in conjunction with weather information. Similarly, it is possible to apply judgment criteria that take into account the impact of special delivery periods (such as the busy year-end and New Year period) or specific events (such as local festivals). This contextual information can be automatically acquired and applied through integration with external APIs.

[0103] Thus, according to the present invention, it is possible to improve delivery efficiency, especially in areas with a low volume of parcel deliveries.

[0104] In addition to this embodiment, the determination unit 132 can implement multiple derivative analysis and prediction functions utilizing the dwell time data. In one embodiment, the determination unit 132 can perform dwell time pattern analysis by property type. Specifically, the determination unit 132 acquires property data 2000 and delivery data 1000 from the storage unit 120, associates property ID and delivery ID, and constructs a dwell time dataset for each property type. Next, statistical processing is applied to this dataset to calculate distribution characteristics such as the mean, median, and standard deviation for each property type. Furthermore, the significance of the difference in dwell time between property types is evaluated, and characteristic dwell time models are generated for each type, such as "apartment buildings," "single-family homes," and "office buildings." This makes it possible to predict dwell time based on property type even for new delivery destinations, improving the accuracy of delivery planning.

[0105] In another embodiment, the determination unit 132 can perform analysis of dwell time variations by time of day and day of the week. The determination unit 132 processes time information obtained from delivery data 1000 into time category (morning, afternoon, evening, etc.) and day of the week (weekday, holiday), and associates this with dwell time data. Next, it calculates the average dwell time and variation range for each combination of "time of day × day of the week" to identify temporal patterns. Furthermore, by evaluating the main effects and interaction effects of time of day and day of the week, it quantifies temporal characteristics such as "shortest dwell time on weekday mornings" and "longest dwell time on holiday evenings." By integrating this model into delivery route optimization, it can contribute to the creation of efficient delivery plans that take temporal factors into consideration.

[0106] In yet another embodiment, the determination unit 132 can perform a dwell time analysis based on the proficiency level of the delivery person. The determination unit 132 extracts delivery person ID, area code, delivery date and time, and dwell time data from the delivery data storage unit 121 and calculates the cumulative number of deliveries for each delivery person in a specific area. It analyzes the relationship between this cumulative number and the dwell time and expresses the trend of changes in dwell time due to the accumulation of experience as a mathematical model. For example, by quantifying the difference in dwell time between the first delivery in a new area and after experiencing multiple deliveries, the proficiency effect due to experience can be measured. The results of this analysis are stored in the storage unit 120 in a format that can be used in delivery management systems and human resource management systems, and can be used for training support for new delivery people, evaluating the suitability of delivery people, or optimizing delivery person assignments.

[0107] Furthermore, the determination unit 132 can perform an analysis of the efficiency of dwell time in consolidated deliveries to multiple destinations. Based on the location information of the delivery destinations, the determination unit 132 performs a clustering process that groups geographically close delivery destinations together. Next, it analyzes the relationship between the number of delivery destinations and the total dwell time within each cluster and constructs a model to evaluate the time efficiency of consolidated deliveries. Using this model, it is possible to predict the dwell time efficiency for different cluster sizes and determine the optimal grouping scale. The analysis results can be used as parameters for the delivery planning algorithm, which can be used to formulate delivery destination grouping strategies for improving delivery efficiency and to identify areas suitable for consolidated deliveries.

[0108] As a further embodiment of the present invention, a system configuration that utilizes dwell time data in real time is also possible. In this embodiment, the determination unit 132 analyzes dwell time data in ongoing delivery operations in real time and performs processing to detect abnormal values. Specifically, after receiving location information and time information from the delivery terminal 200, it immediately performs a determination process of the dwell status and generates an alert if the dwell time exceeds the normal range for each property. This alert includes information such as delivery ID, delivery ID, location information, dwell time, and the difference from the expected dwell time, and is notified to the delivery terminal 200 and the management system. The alert threshold can be adjusted according to the delivery area, time of day, weather conditions, etc., enabling early detection and response to potential delivery problems (difficulty in delivery, unknown address, recipient absent, etc.).

[0109] Alternatively, the determination unit 132 can employ a distributed processing architecture. To efficiently process large amounts of location and time information, a hierarchical processing structure is implemented where primary processing is performed on the delivery terminal 200 and secondary processing is performed on the server terminal 100. The local processing module on the delivery terminal 200 performs basic processing such as evaluating the accuracy of location information acquired from GPS, determining the movement state, and detecting the stay state, and saves the stay event data locally. Depending on the network connection status, it also controls transmission to be immediate when online and to be transmitted all at once after the connection is restored when offline. On the other hand, the server terminal 100 integrates stay data from multiple delivery terminals and performs advanced processing such as statistical analysis and updating the prediction model. This architecture achieves both reduced network load and improved real-time performance, making it possible to maintain basic functions even in areas with unstable communication environments.

[0110] As another implementation method, the determination unit 132 can provide a dwell time analysis function that takes privacy protection into consideration. This function processes data in an anonymized and aggregated format, rather than using the detailed location information of the delivery person. Specifically, instead of individual location information points, dwell time data is aggregated in units of a certain area (for example, a 500m square grid) and processed in a way that does not identify individuals. Anonymization processing is also applied, such as replacing the delivery person ID with a temporary identifier and reassigning it after a certain period of time. Through these processes, it is possible to extract insights necessary for improving the efficiency of delivery operations while protecting the privacy of delivery persons.

[0111] As a further embodiment of the present invention, functional enhancements are possible to accommodate international delivery environments. In this embodiment, the determination unit 132 performs dwell time analysis that takes into account differences in delivery practices and housing types for each country and region. Specifically, it associates country / region identifiers with delivery data and property data, and applies analysis parameters according to regional characteristics. For example, it constructs an analysis model that takes into account differences between urban areas with a high proportion of apartment buildings and suburbs with many detached houses, or differences in address systems and architectural styles by country. It also provides data conversion functions that support multilingualism and region-specific address notation, enabling consistent dwell time analysis even in global logistics operations.

[0112] Furthermore, the determination unit 132 can provide an interface that supports multiple languages ​​and region-specific address systems. This enables consistent dwell time analysis and delivery location determination even in global logistics operations, contributing to the efficiency of international delivery networks.

[0113] Furthermore, the judgment unit 132 can be equipped with an automatic learning function. This function automatically adjusts and optimizes the dwell time judgment algorithm based on accumulated delivery data. Specifically, it continuously evaluates the accuracy of the judgment results and readjusts the model parameters if the accuracy decreases. For example, it adaptively updates the dwell time threshold and judgment logic in response to environmental changes such as seasonal variations and changes in traffic patterns. It also utilizes feedback from delivery personnel (such as delivery completion operations) as training data to improve the accuracy of the model. This makes it possible to realize a self-improving judgment system in which the accuracy and efficiency of the system continuously improve without human intervention.

[0114] This automated learning function can be achieved through a combination of supervised learning and reinforcement learning. In supervised learning, explicit feedback from delivery personnel (e.g., delivery completion markings) is used as training data, while in reinforcement learning, improvements in delivery efficiency (e.g., reduction in total delivery time) are designed as rewards. This makes it possible to continuously improve the accuracy and efficiency of the system without explicit human intervention.

[0115] As a further embodiment of the present invention, it is also possible to provide a function for linking with external systems. The server terminal 100 shares dwell time data with delivery management systems, warehouse management systems, customer relationship management systems, etc., through a standardized interface. This enables, for example, optimization of shipping schedules based on dwell time predictions and accurate delivery time notifications to customers. Furthermore, by integrating contextual data such as weather information and traffic information acquired from external sources into dwell time analysis, it is possible to build a more situation-adapted predictive model. Such inter-system linkage can optimize the entire logistics process and improve customer satisfaction.

[0116] Furthermore, the determination unit 132 can also be equipped with advanced geospatial analysis capabilities. This function integrates dwell time data with geographic information system (GIS) data to analyze the correlation between geographic factors such as topography, road networks, and building density and dwell time. For example, it can quantify the impact of specific road patterns (e.g., cul-de-sacs and complex intersections) or building styles (e.g., high-density apartment buildings) on dwell time, and optimize delivery plans by taking these factors into consideration.

[0117] Furthermore, the determination unit 132 can also be equipped with a geospatial analysis function. This function integrates dwell time data with geographic information and analyzes the correlation between geographical factors such as topography, road networks, and building density and dwell time. For example, it can quantify the impact of specific road patterns or building styles on dwell time and formulate delivery plans that take geographical characteristics into account. It also provides a heat map generation function that visualizes the geographical distribution of dwell time, making it possible to intuitively grasp regional differences in delivery efficiency. These analysis results can be used for strategic decision-making, such as planning the establishment of new delivery bases or optimizing delivery area divisions.

[0118] Furthermore, the judgment unit 132 can also implement seasonal variation and special event management functions. It analyzes the periodic fluctuation patterns of dwell time throughout the year and reflects seasonal factors (such as congestion at tourist destinations in summer and snowfall in winter) in the dwell time forecast. It also provides a function to link local event calendar information with dwell time data to predict and respond to unique patterns when events occur. This makes it possible to plan delivery schedules that are adapted to the delivery environment that changes throughout the year, and to maintain efficient delivery even under seasonal variations and temporary congestion caused by events.

[0119] Finally, the present invention can also be integrated with autonomous delivery systems. The dwell time patterns and delivery location information analyzed by the determination unit 132 are provided as control parameters for autonomous delivery systems such as delivery robots and drones. By applying optimal delivery procedures (such as approaches to specific buildings and efficient delivery sequences) learned from the behavior of human delivery personnel to the autonomous system, human experiential knowledge can be transferred to the autonomous system through machine learning, improving delivery efficiency and success rates. Furthermore, in cooperative delivery between human delivery personnel and autonomous delivery systems, it is possible to determine the optimal division of labor based on dwell time data.

[0120] Although embodiments of the invention have been described above, these can be implemented in various other forms, and can be carried out by various omissions, substitutions, and modifications. These embodiments and variations, as well as those with omissions, substitutions, and modifications, are included within the technical scope of the claims and their equivalents. [Explanation of Symbols]

[0121] 1 System: 100 Server terminal, 110 Communication unit, 120 Storage unit, 130 Control unit, 200 Delivery terminal, 300 User terminal, NW1 Network

Claims

1. An information acquisition unit that acquires location information and time information corresponding to the location information from the delivery terminal of the package delivery person, An information processing system including a determination unit that determines the duration of stay corresponding to the delivery location where the delivery person delivered the package, based on the location information and the time information.

2. The information processing system according to claim 1, wherein the determination unit calculates the average stay time based on location information and time information corresponding to a plurality of delivery locations where the delivery person delivered the package.

3. The information processing system according to claim 1, wherein the determination unit stores the delivery location as a confirmed delivery location in the recording unit of the information processing system if the stay time exceeds a predetermined standard.

4. The information processing system according to claim 2, wherein the predetermined standard is the average stay time.

5. The information processing system according to claim 1, comprising a display unit that displays the delivery location for confirmation on a predetermined map, associated with information identifying the object to be delivered, for the delivery person's terminal.

6. The information processing system according to claim 1, wherein the determination unit recommends to the delivery person terminal, among a plurality of delivery means, a drone delivery means as a means of delivering the package to the delivery location requiring confirmation.

7. The information processing system according to claim 2, wherein the determination unit sends an alert to the delivery person's terminal when the time spent at the delivery location exceeds the average time spent.

8. The determination unit calculates the time spent at each of the multiple delivery locations based on the location information and time information corresponding to the multiple delivery locations where the delivery person delivered the package. The information processing system according to claim 1, further comprising a display unit that displays the time spent at each of the plurality of delivery locations on a predetermined map for the delivery terminal.

9. The information processing system according to claim 1, wherein the determination unit compares the time spent at the delivery location at predetermined intervals.

10. The information processing system according to claim 1, wherein the determination unit stores the time spent at the delivery location in the recording unit of the information processing system, in association with the delivery frequency for the delivery location.

11. Location information and time information corresponding to the location information are obtained from the delivery terminal of the package delivery person. A method for determining the duration of stay at a delivery location where the delivery person delivered the package, based on the location information and time information.

12. The computer is instructed to obtain location information and time information corresponding to the location information from the delivery terminal of the package delivery person. A program that determines the duration of stay at the delivery location where the delivery person delivered the package, based on the location information and time information.

Images