Data analysis apparatus, data analysis method, and program

Abstract

To provide a resident data analysis device, a data analysis method and a program for analyzing a database of a resident list in order to support a delivery person to immediately deliver articles.SOLUTION: A data analysis device 10 comprises: a setting unit 11 which sets a delivery route representing an order in which a first delivery person delivers articles by referring to a database of a resident list; a learning unit 12 which performs machine learning of an order of delivery in the past by a second delivery person by using data of a movement history of the second delivery person; and a correction unit 13 which corrects the delivery route on the basis of a result of performing the machine learning of the order of the delivery in the past by the second delivery person.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a data analysis apparatus, a data analysis method, and a program, and more particularly to a resident data analysis apparatus, a data analysis method, and a program for analyzing a database of resident lists.

Background Art

[0002] Due to the increase in deliveries accompanying the development of e-commerce and the increase in single-person households, the volume of goods has been rapidly increasing. On the other hand, since the working population is on a decreasing trend, a home delivery crisis has occurred. In the postal and home delivery industries, in order to make up for the shortage of labor, the employment of part-timers, the elderly, and unskilled workers such as new employees has been increasing more than before.

[0003] The delivery person creates a delivery route indicating the order in which articles (packages) are to be delivered, and then departs for delivery with the collected articles. Unskilled workers take more time to create a delivery route than skilled workers. Therefore, related technologies are used to simply set the delivery route.

[0004] In one example, Patent Document 1 describes a delivery management apparatus that generates a delivery route passing through a plurality of designated delivery routes when an operator performs an input operation of designating a plurality of delivery destinations, and displays a map showing the generated delivery route on a display.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0006] When an accident such as a traffic accident or a sudden change in weather occurs, an inexperienced person cannot freely modify the delivery route so as to shorten the time required for delivery. Therefore, inexperienced people tend to take more time to deliver items than experienced people.

[0007] The present invention has been made in view of the above problems, and an object thereof is to support a delivery person in delivering an item promptly.

Means for Solving the Problems

[0008] A data analysis apparatus according to an aspect of the present invention includes: a setting unit that sets a delivery route representing an order in which a first delivery person delivers an item by referring to a database of a resident list; a learning unit that machine-learns an order of past deliveries by the second delivery person using data of a movement history of the second delivery person; and a correction unit that corrects the delivery route of the first delivery person based on a result of machine-learning the order of the past deliveries by the second delivery person.

[0009] A data analysis method according to an aspect of the present invention includes: setting a delivery route representing an order in which a first delivery person delivers an item by referring to a database of a resident list; machine-learning an order of past deliveries by the second delivery person using data of a movement history of the second delivery person; and correcting the delivery route of the first delivery person based on a result of machine-learning the order of the past deliveries by the second delivery person.

[0010] A program according to an aspect of the present invention causes a computer to execute: setting a delivery route representing an order in which a first delivery person delivers an item by referring to a database of a resident list; machine-learning an order of past deliveries by the second delivery person using data of a movement history of the second delivery person; and correcting the delivery route of the first delivery person based on a result of machine-learning the order of the past deliveries by the second delivery person.

Effects of the Invention

[0011] According to one aspect of the present invention, it is possible to support a deliverer in quickly delivering an item.

Brief Description of the Drawings

[0012]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Modes for Carrying Out the Invention

[0013] With reference to the drawings, some embodiments of the present invention will be described.

[0014] 〔Embodiment 1〕 With reference to FIGS. 1 to 2, Embodiment 1 will be described.

[0015] (Data Analysis Device 10) With reference to FIG. 1, the data analysis device 10 according to the present Embodiment 1 will be described. FIG. 1 is a block diagram showing the configuration of the data analysis device 10. As shown in FIG. 1, the data analysis device 10 includes a setting unit 11, a learning unit 12, and a correction unit 13.

[0016] The setting unit 11 refers to the database of the resident list to set a delivery route representing the order in which the first deliverer delivers the articles. The setting unit 11 is an example of setting means.

[0017] The database of the resident list is used to set a delivery route when the deliverer delivers the articles. The order added to the resident list represents a predetermined basic delivery route. For example, when there is address A with number 1 added and address B with number 2 added, the basic delivery route is in the order from address A to address B. However, the deliverer is allowed to deliver the articles in an order different from the basic delivery route at his own discretion.

[0018] In one example, the setting unit 11 accesses the database of the resident list stored in a storage device or server (not shown), and by ordering the order added to the resident list, sets a delivery route representing the order in which the first deliverer delivers the articles. Hereinafter, the delivery route set by the setting unit 11 is referred to as the "initial delivery route".

[0019] The setting unit 11 outputs information indicating the initial delivery route set as described above to a correction unit 13 described later.

[0020] The learning unit 12 uses the data of the movement history of the second deliverer to machine-learn the order of past deliveries by the second deliverer. The learning unit 12 is an example of learning means.

[0021] In one example, the learning unit 12 refers to the movement history of the second deliverer from the past delivery records by the second deliverer. Then, the learning unit 12 learns in what order the second deliverer delivered the articles. Note that the second deliverer may be a person different from the first deliverer. In particular, the second deliverer may be a skilled person with a longer delivery service history than the first deliverer.

[0022] For example, when there is address A with the number 1 added and address B with the number 2 added, the basic delivery route is in the order from address A to address B. However, it is assumed that the second deliverer delivered the goods in the order from address B to address A. In this case, the learning unit 12 learns that the second deliverer delivers the goods in the order from address B to address A instead of from address A to address B.

[0023] The learning unit 12 outputs the result of machine learning the past delivery order by the second deliverer (hereinafter referred to as the learning result) to the correction unit 13.

[0024] The correction unit 13 corrects the delivery route of the first deliverer based on the result of machine learning the past delivery order by the second deliverer. The correction unit 13 is an example of a correction means.

[0025] In one example, the correction unit 13 receives information indicating the initial delivery route from the setting unit 11. Also, the correction unit 13 receives the above-mentioned learning result from the learning unit 12. The correction unit 13 corrects the initial delivery route based on the past delivery order by the second deliverer.

[0026] In the previous example, the initial delivery route is in the order from address A to address B. However, it is assumed that the second deliverer delivered the goods in the order from address B to address A in the past. In this case, the correction unit 13 corrects the order from address A to address B to the order from address B to address A in the delivery route.

[0027] After that, the data analysis device 10 may display the information on the delivery route generated in this way on the terminal held by the first deliverer (Embodiment 2).

[0028] (Operation of the data analysis device 10) Referring to FIG. 2, the operation of the data analysis device 10 according to the first embodiment will be described. FIG. 2 is a flowchart showing the flow of processes executed by each part of the data analysis device 10.

[0029] As shown in FIG. 2, first, the setting unit 11 refers to the database of the resident list and sets an (initial) delivery route representing the order in which the first deliverer delivers the articles (S101). The setting unit 11 outputs information indicating the initial delivery route to the correction unit 13.

[0030] The learning unit 12 uses the data of the movement history of the second deliverer to perform machine learning on the order of past deliveries by the second deliverer (S102). The learning unit 12 outputs the result of machine learning (learning result) on the order of past deliveries by the second deliverer to the correction unit 13.

[0031] Note that steps S101 and S102 may be executed in the reverse order.

[0032] The correction unit 13 corrects the (initial) delivery route based on the result of machine learning on the order of past deliveries by the second deliverer (S103).

[0033] Thereafter, the data analysis device 10 may display the information on the delivery route thus generated on the terminal possessed by the first deliverer.

[0034] Thus, the operation of the data analysis device 10 according to the first embodiment ends.

[0035] (Modification example) In one modification example, the data analysis device 10 considers the conditions regarding the first deliverer. For example, the conditions regarding the first deliverer are the attributes of the first deliverer (age, gender, shift, personal circumstances), or the type of vehicle used by the first deliverer (bicycle, two-wheeler, automobile, loading capacity, etc.). Alternatively, from the viewpoint of business leveling (distribution of postal items to multiple deliverers), the data analysis device 10 may allocate the pick-up and delivery items to the first deliverer so that the delivery times of multiple deliverers are equal.

[0036] In another modification, the data analysis device 10 takes into account the conditions related to the collection and delivery. For example, the conditions related to the collection and delivery are the weight, size, quantity, or type of the article (ordinary mail, registered mail, collect on delivery). The data analysis device 10 may design a delivery route that uses a delivery box or a delivery station in order to reduce the delivery time, reduce the cost, or provide a service at a low price.

[0037] In another modification, the data analysis device 10 performs location, building type (high-rise / low-rise condominium, auto-lock, presence or absence of a delivery box), restrictions related to time designation, and cooperation with a smart grid or a smart home (for example, determination of presence or absence at home based on power consumption).

[0038] (Effect of this Embodiment) According to the configuration of this embodiment, the setting unit 11 refers to the database of the resident list and sets a delivery route representing the order in which the first delivery person delivers the articles. The learning unit 12 machine-learns the order of past deliveries by the second delivery person using the data of the movement history of the second delivery person. The correction unit 13 corrects the delivery route based on the result of machine-learning the order of past deliveries by the second delivery person. Thereby, the delivery route of the first delivery person can be determined by utilizing the experience of the second delivery person in making deliveries. In this way, it is possible to support the first delivery person in delivering the articles promptly.

[0039] 〔Embodiment 2〕 Referring to FIGS. 3 to 4, Embodiment 2 will be described. In this Embodiment 2, a configuration will be described in which information on a delivery route reflecting the result of machine-learning the order of past deliveries by the second delivery person is displayed on a terminal or the like held by the first delivery person.

[0040] (Data Analysis Device 20) FIG. 3 is a block diagram showing the configuration of the data analysis device 20 according to this Embodiment 2.

[0041] As shown in FIG. 3, the data analysis device 20 includes a setting unit 11, a learning unit 12, and a correction unit 13. In addition, the data analysis device 20 further includes a display unit 24.

[0042] The display unit 24 displays the corrected delivery route. The display unit 24 is an example of display means.

[0043] In one example, the display unit 24 receives, from the correction unit 13, information on the delivery route corrected based on the result of machine learning of the order of past deliveries by the second deliverer. Then, the display unit 24 displays the received delivery route information. For example, the display unit 24 may display the corrected delivery route on the screen of the mobile terminal possessed by the first deliverer. Alternatively, the display unit 24 may display the corrected delivery route on the screen of the terminal of the administrator who manages the deliverers. Or, the display unit 24 may distribute the data of the corrected delivery route to a plurality of terminals automatically or according to a request.

[0044] (Operation of Data Analysis Device 20) Referring to FIG. 4, the operation of the data analysis device 20 according to the second embodiment will be described. FIG. 4 is a flowchart showing the flow of processing executed by each part of the data analysis device 20.

[0045] As shown in FIG. 4, first, the setting unit 11 refers to the database of the resident list and sets an (initial) delivery route representing the order in which the first deliverer delivers the articles (S101). The setting unit 11 outputs information indicating the initial delivery route to the correction unit 13.

[0046] The learning unit 12 uses the data of the movement history of the second deliverer to machine-learn the order of past deliveries by the second deliverer (S102). The learning unit 12 outputs the (learning) result of machine-learning the order of past deliveries by the second deliverer to the correction unit 13.

[0047] Note that steps S101 and S102 may be executed in the reverse order.

[0048] The correction unit 13 corrects the delivery route based on the result of machine learning of the past delivery order by the second deliverer (S103). The correction unit 13 outputs the information on the corrected delivery route to the display unit 24.

[0049] The display unit 24 displays the information indicating the corrected delivery route on the screen of the terminal possessed by the first deliverer, etc. (S204).

[0050] Thus, the operation of the data analysis device 20 according to the second embodiment ends.

[0051] (Effects of the present embodiment) According to the configuration of the present embodiment, the setting unit 11 refers to the database of the resident list and sets a delivery route representing the order in which the first deliverer delivers the articles. The learning unit 12 machine-learns the past delivery order by the second deliverer using the data of the movement history of the second deliverer. The correction unit 13 corrects the delivery route based on the result of machine learning of the past delivery order by the second deliverer. Thereby, the delivery route of the first deliverer can be determined by making use of the delivery experience of the second deliverer. In that way, it is possible to support the first deliverer in delivering the articles promptly.

[0052] Furthermore, according to the configuration of the present embodiment, the display unit 24 displays the corrected delivery route. Thereby, it is possible to support the first deliverer in delivering the articles more efficiently.

[0053] 〔Embodiment 3〕 Referring to FIGS. 5 to 7, Embodiment 3 will be described. In the third embodiment, a configuration for notifying the first deliverer of an alert when an irregular event such as a traffic accident or a sudden change in weather (such as a thunderstorm) occurs on the corrected delivery route will be described.

[0054] (Data analysis device 30) FIG. 5 is a block diagram showing the configuration of a data analysis device 30 according to the third embodiment.

[0055] As shown in FIG. 5, the data analysis device 30 includes a setting unit 11, a learning unit 12, and a correction unit 13. In addition, the data analysis device 30 further includes a notification unit 34.

[0056] When an irregular event occurs on the corrected delivery route, the notification unit 34 notifies the first delivery person of an alert. The notification unit 34 is an example of a notification means.

[0057] In one example, the notification unit 34 receives information on the corrected delivery route from the correction unit 13. In addition, the notification unit 34 periodically collects information on the occurrence status of traffic accidents and weather forecasts from news sites and weather forecast sites. Then, when a traffic accident occurs on the corrected delivery route, or when the weather in the area including the delivery route suddenly changes, the notification unit 34 notifies the first delivery person of an alert. However, the trigger for the notification unit 34 to notify the first delivery person of an alert is not limited to the above example.

[0058] (Operation of the data analysis device 30) With reference to FIG. 6, the operation of the data analysis device 30 according to the third embodiment will be described. FIG. 6 is a flowchart showing the flow of processes executed by each part of the data analysis device 30.

[0059] As shown in FIG. 6, first, the setting unit 11 refers to the database of the resident list and sets an (initial) delivery route representing the order in which the first delivery person delivers the articles (S101). The setting unit 11 outputs information indicating the initial delivery route to the correction unit 13.

[0060] The learning unit 12 uses the movement history data of the second delivery person to perform machine learning on the order of past deliveries by the second delivery person (S102). The learning unit 12 outputs the (learning) result of performing machine learning on the order of past deliveries by the second delivery person to the correction unit 13.

[0061] Note that steps S101 and S102 may be executed in the reverse order.

[0062] Based on the result of machine learning of the past delivery order by the second deliverer, the correction unit 13 corrects the delivery route (S103). The correction unit 13 outputs the information of the corrected delivery route to the notification unit 34.

[0063] The notification unit 34 collects information from news sites on the web or the like, and analyzes the collected information to determine whether an irregular event has occurred on the corrected delivery route (S304).

[0064] If an irregular event has occurred on the corrected delivery route (YES in S304), the notification unit 34 notifies the first deliverer of an alert (S305). On the other hand, if no irregular event has occurred on the corrected delivery route (YES in S304), the flow returns to step S304.

[0065] Thus, the operation of the data analysis device 30 according to the third embodiment ends.

[0066] (Modification example) A modification example of the data analysis device 30 according to the third embodiment will be described.

[0067] FIG. 7 is a block diagram showing the configuration of a data analysis device 30a according to a modification example. As shown in FIG. 7, in addition to the setting unit 11, the learning unit 12, the correction unit 13, and the notification unit 34, the data analysis device 30a further includes the display unit 24 described in the second embodiment.

[0068] In this modification example, the correction unit 13 outputs the information of the delivery route corrected based on the learning result to the display unit 24 and the notification unit 34.

[0069] The display unit 24 displays the corrected delivery route. In one example, the display unit 24 receives information on the corrected delivery route from the correction unit 13 based on the result of machine learning the order of past deliveries by the second delivery person. For example, the display unit 24 may display the corrected delivery route on the mobile terminal possessed by the first delivery person. Alternatively, the display unit 24 may display the corrected delivery route on the terminal of the administrator who manages the delivery persons. Or, the display unit 24 may also distribute the data of the corrected delivery route to a plurality of terminals automatically or according to a request.

[0070] According to the configuration of this modification, when an alert is notified from the notification unit 34, the first delivery person can quickly take actions such as referring to the displayed delivery route to change the corrected delivery route or consulting with the administrator.

[0071] (Effects of the present embodiment) According to the configuration of the present embodiment, the setting unit 11 refers to the database of the resident list and sets a delivery route representing the order in which the first delivery person delivers the articles. The learning unit 12 uses the data of the movement history of the second delivery person to machine learn the order of past deliveries by the second delivery person. The correction unit 13 corrects the delivery route based on the result of machine learning the order of past deliveries by the second delivery person. Thereby, it is possible to determine the delivery route of the first delivery person by utilizing the delivery experience of the second delivery person. In this way, it is possible to support the first delivery person in delivering the articles promptly.

[0072] Furthermore, according to the configuration of the present embodiment, when an irregular event occurs on the corrected delivery route, the notification unit 34 notifies the first delivery person of an alert. Thereby, the first delivery person can quickly judge the response.

[0073] (Modification example) In one modification example of the data analysis apparatuses 20, 20, 30, and 30a described in the first to third embodiments, a delivery route based on the order of the delivery ledger is displayed on the terminal, an operation on the displayed delivery route is received by the terminal, and the delivery route is reconstructed according to the received operation. In one modification example, the delivery route is reconstructed in the order traced on the map displayed on the screen of the terminal.

[0074] In another modification example, the display unit 24 (FIGS. 3 and 7) presents an optimal route according to the weather such as rain or snow in combination with the weather forecast (ex. generates a recommended route such as an arcade or an apartment).

[0075] (Regarding the hardware configuration) Each component of the data analysis apparatuses 10, 20, 30, and 30a described in the first to third embodiments indicates a block of a functional unit. Some or all of these components are realized by an information processing apparatus 900 as shown in FIG. 8, for example. FIG. 8 is a block diagram showing an example of the hardware configuration of the information processing apparatus 900.

[0076] As shown in FIG. 8, the information processing apparatus 900 includes, as an example, the following configuration.

[0077] ·CPU (Central Processing Unit) 901 ·ROM (Read Only Memory) 902 ·RAM (Random Access Memory) 903 ·Program 904 loaded into RAM 903 ·Storage device 905 that stores program 904 ·Drive device 907 that reads and writes recording medium 906 ·Communication interface 908 connected to communication network 909 ·Input / output interface 910 that performs input / output of data ·Bus 911 that connects each component Each component of the data analysis apparatuses 10, 20, 30, and 30a described in the first to third embodiments is realized by the CPU 901 reading and executing a program 904 that implements these functions. The program 904 for implementing the functions of each component is stored in advance in, for example, the storage device 905 or the ROM 902, and is loaded into the RAM 903 and executed by the CPU 901 as necessary. Note that the program 904 may be supplied to the CPU 901 via the communication network 909, or may be stored in advance in the recording medium 906, and the drive device 907 may read the program and supply it to the CPU 901.

[0078] According to the above configuration, the data analysis apparatuses 10, 20, 30, and 30a described in the first to third embodiments are realized as hardware. Therefore, the same effects as those described in the above embodiments can be achieved.

[0079] (Supplementary Note) One aspect of the present invention is also described as follows in the supplementary note, but is not limited thereto.

[0080] (Supplementary Note 1) Setting means for setting a delivery route representing the order in which a first deliverer delivers articles by referring to a database of resident lists; Learning means for machine learning the order of past deliveries by the second deliverer using data on the movement history of the second deliverer; Correction means for correcting the delivery route of the first deliverer based on the result of machine learning of the order of the past deliveries by the second deliverer A data analysis apparatus comprising:

[0081] (Supplementary Note 2) The setting means sets the delivery route based on the attributes of the first deliverer The data analysis apparatus according to Supplementary Note 1, characterized in that:

[0082] (Supplementary Note 3) Further comprising display means for displaying the corrected delivery route The data analysis device according to appendix 1 or 2, characterized in that

[0083] (Appendix 4) further comprising notification means for notifying the first deliverer of an alert when an irregular event occurs on the corrected delivery route The data analysis device according to any one of appendices 1 to 3, characterized in that

[0084] (Appendix 5) After the alert is notified, the correction means re-corrects the corrected delivery route so as to avoid the location where the irregular event occurred The data analysis device according to appendix 4, characterized in that

[0085] (Appendix 6) The correction means re-corrects the corrected delivery route based on an input operation by the first deliverer The data analysis device according to any one of appendices 1 to 5, characterized in that

[0086] (Appendix 7) Refer to the database of the resident list to set a delivery route representing the order in which the first deliverer delivers the goods, Use the data of the movement history of the second deliverer to machine-learn the order of past deliveries by the second deliverer, Based on the result of machine-learning the order of the past deliveries by the second deliverer, correct the delivery route of the first deliverer Data analysis method.

[0087] (Appendix 8) Refer to the database of the resident list to set a delivery route representing the order in which the first deliverer delivers the goods; and Use the data of the movement history of the second deliverer to machine-learn the order of past deliveries by the second deliverer; and Based on the result of machine learning the order of the past deliveries by the second deliverer, modifying the delivery route of the first deliverer A program for causing a computer to execute.

[0088] (Appendix 9) The modifying means modifies the delivery route of the first deliverer based on conditions regarding the delivery destination of the article. The data analysis device according to any one of Appendices 1 to 6, characterized in that.

[0089] (Appendix 10) The modifying means modifies the delivery route of the first deliverer based on conditions regarding the article. The data analysis device according to any one of Appendices 1 to 6, characterized in that.

[0090] (Appendix 11) The modifying means modifies the delivery route of the first deliverer based on conditions regarding the first deliverer. The data analysis device according to any one of Appendices 1 to 6, characterized in that.

Industrial Applicability

[0091] The present invention can be used, for example, in a data analysis device that proposes a preferable delivery route for a business operator providing resident services such as delivery of articles.

Explanation of Signs

[0092] 10 Data analysis device 11 Setting unit 12 Learning unit 13 Modifying unit 20 Data analysis device 24 Display unit 30 Data analysis device 30a Data analysis device 34 Notification unit

Claims

Setting means for setting a delivery route representing the order in which a first deliverer delivers articles by referring to a database of a resident list with an added order representing a predetermined basic delivery route; Learning means for machine learning the order of past deliveries by the second deliverer using data on the movement history of the second deliverer; Modifying means for modifying the delivery route of the first deliverer based on the result of machine learning the order of the past deliveries by the second deliverer; Notification means for notifying the first deliverer of an alert when information on an irregular event occurring on the modified delivery route is acquired; Comprising; The notification means periodically collects information on weather forecasts and presents an optimal route according to the weather in combination with the weather forecasts; After the alert is notified, the modifying means re-modifies the modified delivery route so as to avoid the location where the irregular event occurred; The modifying means re-modifies the modified delivery route based on an input operation by the first deliverer; Data analysis device.

2. The setting means sets the delivery route based on the attributes of the first deliverer. The data analysis device according to claim 1, characterized in that.

3. Further comprising display means for displaying the modified delivery route. The data analysis device according to claim 1 or 2, characterized in that.

4. A computer, Sets a delivery route representing the order in which a first deliverer delivers articles by referring to a database of a resident list with an added order representing a predetermined basic delivery route; Machine learns the order of past deliveries by the second deliverer using data on the movement history of the second deliverer; Modifies the delivery route of the first deliverer based on the result of machine learning the order of the past deliveries by the second deliverer; A data analysis method for notifying the first deliverer of an alert when information on an irregular event occurring on the modified delivery route is acquired, wherein The computer periodically collects information on weather forecasts and presents an optimal route according to the weather in combination with the weather forecasts; After the alert is notified, the computer re-modifies the modified delivery route so as to avoid the location where the irregular event occurred; The computer re-revises the revised delivery route based on an input operation by the first deliverer. Data analysis method.

5. Setting a delivery route representing the order in which a first deliverer delivers articles by referring to a database of a resident list with an added order representing a predetermined basic delivery route; Using data on the movement history of a second deliverer to machine-learn the order of past deliveries by the second deliverer; Modifying the delivery route of the first deliverer based on the result of machine-learning the order of the past deliveries by the second deliverer; A program for causing a computer to perform: when information on an irregular event occurring on the modified delivery route is acquired, notifying the first deliverer of an alert. Causing the computer to periodically collect information on weather forecasts and, in combination with the weather forecasts, present an optimal route according to the weather. After the alert is notified, causing the computer to re-revise the modified delivery route so as to avoid the location where the irregular event occurred. Causing the computer to re-revise the modified delivery route based on an input operation by the first deliverer. Program for.

Images