JP7041825B2 - Optimized delivery system by analyzing transaction data - Google Patents

Description

The present invention relates to an optimized delivery system, and more particularly to a delivery system optimized based on analysis of transaction data extracted from messages such as e-mail.

In recent years, the purchase of products at online stores has been actively carried out. While the number of online stores continues to increase and the convenience of users increases, it is said that there will be a shortage of 240,000 delivery personnel in 2027 to deliver products purchased from online stores. In addition, the burden on delivery personnel due to redelivery has become a social problem.

Attempts have been made to address the problem of shortage of delivery personnel and the efficiency of delivery by analyzing the data that each delivery company has acquired. However, in a situation where one user uses a plurality of online stores, the delivery company to be used is often different for each online store to be used or for each transaction of product purchase.

Therefore, if only one company's usage status is analyzed for a certain user, sufficient data can be obtained in order to determine the optimum delivery date and time and delivery method for that user, and to prevent redelivery due to absence, etc. It may not be possible.

In addition, the specification of the delivery date and time and the delivery method is left to the user side, such as being selected by the user himself, but the delivery date and delivery method selected by the user is not always optimal in terms of delivery efficiency, and delivery is performed. There is also the problem that the convenience of the trader is not taken into consideration.

In addition, the user may be absent at the desired delivery date and time due to a sudden schedule change or the like. Furthermore, if there is no desired delivery date and time, or if a detailed date and time cannot be selected, the risk of redelivery increases.

In this way, in order to avoid the risk of redelivery and improve the efficiency of delivery, it is not enough to analyze the delivery company within one company and set the delivery date and time and delivery method depending on the user, and multiple delivery companies. There is a need for an optimized delivery system that can analyze transaction data from multiple online stores across the board.

Regarding the system for improving the efficiency of delivery, Patent Document 1 uses the information acquired for managing the transportation status of the freight vehicle to manage the physical distribution, and also delivers the current package for each shipper from the information. We are proposing a logistics cloud system that can create status information and notify shippers.

Further, Patent Document 2 collects home information by region of the delivery destination as a technology that enables efficiency improvement and cost reduction of home delivery work while appropriately handling information on the delivery destination home status as sensitive information. We are proposing a transportation business support system equipped with an arithmetic unit that calculates the ratio of delivery destinations scheduled to be at home in each region and outputs the transportation support information, which is the calculated information on the ratio of home delivery by region, to a predetermined device. ..

Japanese Unexamined Patent Publication No. 2014-160474 Japanese Unexamined Patent Publication No. 2017-33341

Patent Document 1 manages the transportation status and notifies the shipper of the delivery status information of the package to prevent the shipper from being absent at the delivery time. Further, Patent Document 2 makes it easy to avoid delivery when absent by using information on the home ratio, and aims to improve efficiency. However, neither Patent Document 1 or 2 focuses on cross-sectional analysis of transaction data in a plurality of delivery companies or a plurality of online stores, and the information is distributed to a plurality of delivery companies and a plurality of online stores. It does not give a concrete solution to the situation you are doing.

Therefore, a delivery system capable of cross-sectionally analyzing transaction data from a plurality of delivery companies and a plurality of online stores, reducing the risk of redelivery, and further improving the efficiency of delivery is desired.

Therefore, in order to solve the above problems, reduce the risk of redelivery, and improve the efficiency of delivery, the present invention can analyze transaction data at a plurality of delivery companies and a plurality of online stores in a cross-sectional manner. It provides an optimized delivery system. An object of the present invention is to reduce redelivery, which becomes a social problem, by providing such an optimized delivery system.

In order to solve the above problems, the present invention provides a delivery system that displays a recommendation regarding delivery to a user terminal based on the analysis result by analyzing transaction data acquired from an external service. The present invention is characterized in that, in particular, as transaction data, a message such as an e-mail exchanged in a transaction with a plurality of delivery companies or a plurality of online stores is analyzed, and a recommendation regarding delivery is generated.

The delivery system according to the present invention has a transaction data acquisition unit that acquires transaction data from an external service, a transaction data storage unit that stores transaction data acquired by the transaction data acquisition unit, and a transaction data stored in the transaction data storage unit. It includes an analysis unit that analyzes and generates recommendations related to delivery, and a display unit that displays recommendations related to delivery generated by the analysis unit on the user terminal.

The delivery system according to another example of the present invention has a transaction data acquisition unit that acquires transaction data and calendar schedules from an external service, a transaction data storage unit that stores transaction data acquired by the transaction data acquisition unit, and transaction data storage. It is provided with an analysis unit that analyzes transaction data stored in the unit and a schedule of a calendar and generates a recommendation regarding delivery, and a display unit that displays a recommendation regarding delivery generated by the analysis unit on a user terminal.

In the delivery system according to the present invention, the transaction data acquisition unit is characterized in that it filters messages exchanged in an external service and acquires a message related to a transaction of a product or service as transaction data.

In the delivery system according to the present invention, the message is an e-mail message, a message stored in the cloud, or a message exchanged by SNS.

In the delivery system according to the present invention, the analysis unit analyzes transaction data and detects whether or not redelivery has occurred.

In the delivery system according to the present invention, the analysis unit is characterized in that the analysis unit uses the past transaction data stored in the transaction data storage unit as at least a part of the learning data to generate a recommendation regarding delivery.

In the delivery system according to the present invention, the analysis unit is characterized in that a recommendation regarding delivery is generated by using the past transaction data stored in the transaction data storage unit and the schedule of the calendar as at least a part of the learning data. ..

In the delivery system according to the present invention, the analysis unit predicts whether the user's current behavior status is daily or extraordinary from the user's past behavior history stored in the transaction data storage unit, and is predicted. Delivery recommendations may be generated by using the user's current behavioral status as at least part of the training data.

In the delivery system according to the present invention, the analysis unit may generate recommendations regarding delivery by using environmental information as at least a part of learning data.

In the delivery system according to the invention, the recommendation is characterized by including at least one of a delivery date and time, a delivery destination or a delivery method.

The delivery system according to the present invention is characterized in that the analysis unit analyzes transaction data and calendar schedules and optimizes delivery time.

In the delivery system according to the present invention, the transaction data acquisition unit may perform name identification of transaction data related to delivery of the same product based on transaction data acquired from one or a plurality of external services.

In the delivery system according to the present invention, the transaction data acquisition unit may perform name identification of transaction data related to the same delivery case based on transaction data acquired from one or a plurality of external services.

According to the present invention, the risk of redelivery is reduced and delivery is performed by providing an optimized delivery system capable of cross-sectionally analyzing transaction data of multiple delivery companies and multiple online stores. Efficiency can be increased.

The present invention also provides an optimized delivery system that can cross-sectionally analyze calendar appointments as well as transaction data from multiple delivery companies and multiple online stores. The risk of delivery can be reduced and the efficiency of delivery can be increased.

Further, according to the present invention, by using transaction data from a plurality of delivery companies or a plurality of online stores as at least a part of learning data, there is a possibility that the user receives a package at the first delivery or the current delivery. Can be increased or the possibility of redelivery can be reduced. Other objects, features and advantages of the invention will become apparent from the following embodiments of the invention with respect to the accompanying drawings.

FIG. 1 is a conceptual diagram showing the entire delivery system according to the present invention. FIG. 2 is a diagram showing processing of a transaction data acquisition unit of the delivery system according to the present invention. FIG. 3 is a diagram showing the processing of the analysis unit of the delivery system according to the present invention. FIG. 4 is a diagram showing processing of a display unit of a delivery system according to the present invention.

FIG. 1 is a conceptual diagram showing the entire delivery system according to the present invention.
The delivery system 1 according to the present invention includes a transaction data acquisition unit 10 that acquires transaction data from an external service 2, a transaction data storage unit 20 that stores transaction data acquired by the transaction data acquisition unit 10, and a transaction data storage unit 20. It includes an analysis unit 30 that analyzes the stored transaction data, and a display unit 40 that displays a recommendation regarding delivery on the user terminal 50 based on the analysis result of the analysis unit 30.

Here, the external service 2 refers to various services such as an e-mail service, a cloud service, an SNS service, and a calendar service that can send and receive messages. The external service 2 may include not only a plurality of external services already deployed in the market but also a service capable of transmitting and receiving various messages to be added in the future.

These external services 2 are used between an online store, a user who uses the online store, and a delivery company. For example, the exchange of e-mails regarding the purchase, reservation, and delivery of products and the exchange of messages such as SNS are performed via the external service 2.

The transaction data acquisition unit 10 filters messages such as e-mails exchanged in the external service 2 and acquires a message related to a transaction of a product or service as transaction data. The e-mails and messages exchanged in the external service 2 include those not related to transactions such as purchase, reservation, and delivery of products, and the transaction data acquisition unit 10 filters the purchases and reservations of products. , Only those related to transactions such as delivery are extracted. The transaction data acquisition unit 10 stores transaction data acquired from a plurality of external services 2 in the transaction data storage unit 20.

Further, the transaction data acquisition unit 10 may perform name identification of transaction data related to the delivery of the same product based on the transaction data acquired from one or a plurality of external services 2. For example, the transaction data acquisition unit 10 has transaction data related to delivery of the same product based on identification numbers for identifying products such as order numbers and slip numbers included in transaction data acquired from a plurality of external services 2. You may try to identify the name. The transaction data acquisition unit 10 stores in the transaction data storage unit 20 the transaction data after name identification, which is named as transaction data related to the delivery of the same product. At that time, a plurality of transaction data before name identification may be associated with the transaction data after name identification and stored in the transaction data storage unit 20. Further, the newly acquired transaction data may be associated with the transaction data after name identification already stored in the transaction data storage unit 20 and stored in the transaction data storage unit 20. In this way, by performing name identification of transaction data related to delivery of the same product, the analysis unit 30 analyzes the transaction data or uses it as at least a part of learning data to generate a recommendation regarding delivery. It is possible to improve the accuracy of recommendations.

Further, the transaction data acquisition unit 10 may perform name identification of transaction data related to the same delivery case based on the transaction data acquired from one or a plurality of external services 2. For example, the transaction data acquisition unit 10 handles transactions related to the same delivery matter based on an identification number for identifying one delivery matter such as an order number or a slip number included in transaction data acquired from a plurality of external services 2. You may try to identify the data. For example, a message such as a notification email regarding the first delivery related to one delivery matter and a message such as a notification email regarding the second and subsequent redelivery are named as transaction data related to the same delivery matter. The transaction data acquisition unit 10 stores in the transaction data storage unit 20 the transaction data after name identification, which is named as transaction data related to the same delivery case. In this way, by performing name identification of transaction data related to the same delivery matter, the analysis unit 30 analyzes the transaction data or uses it as at least a part of learning data to generate a recommendation regarding delivery. It is possible to further improve the accuracy of.

When performing name identification of transaction data related to delivery of the same product or name identification of transaction data related to the same delivery matter, the transaction data acquisition unit 10 associates a plurality of transaction data before name identification with transaction data after name identification for transactions. It may be stored in the data storage unit 20. Further, the newly acquired transaction data may be associated with the transaction data after name identification already stored in the transaction data storage unit 20 and stored in the transaction data storage unit 20.

Here, the message is an e-mail message, a message stored in the cloud, or a message exchanged by SNS. For example, the e-mail messages exchanged in the plurality of e-mail services 3 are aggregated on the cloud service 4, and the aggregated e-mail messages are acquired by the transaction data acquisition unit 10. When collecting e-mail messages and the like on the cloud service 4, the consent of the user is obtained in advance. The e-mail message may be acquired directly from the e-mail service 3 by the transaction data acquisition unit 10.

The transaction data storage unit 20 stores the transaction data acquired by the transaction data acquisition unit 10. The acquired transaction data is stored in the form of a database or table. For example, the sender, recipient, transmission date / time, reception date / time, title, text, etc. of the e-mail are stored in the transaction data storage unit 20. The transaction data acquisition unit 10 and the transaction data storage unit 20 may be constructed on the cloud. Further, the transaction data acquisition unit 10 and the transaction data storage unit 20 may be combined to form one server. The transaction data may include an identification number for identifying a product or service such as an order number or a slip number, or an identification number for identifying one delivery matter.

The analysis unit 30 analyzes the transaction data stored in the transaction data storage unit 20. The information obtained by analyzing the transaction data is used for determining the presence or absence of redelivery, generating recommendations for delivery, and the like. In addition, the information obtained by analyzing the transaction data is used for learning to increase the possibility that the user will receive the package in the first delivery or the current delivery, or to reduce the possibility of redelivery. obtain.

When a redelivery occurs, the external service 2 sends a message such as an e-mail regarding the redelivery from the delivery company to the user. Messages such as e-mails related to redelivery are filtered by the transaction data acquisition unit 10 and stored in the transaction data storage unit 20 as transaction data. The analysis unit 30 analyzes the transaction data stored in the transaction data storage unit 20 and detects whether or not redelivery has occurred. The analysis unit 30 determines whether or not the message is related to redelivery from the sender, recipient, transmission date / time, reception date / time, title, text, etc. of the message included in the transaction data, and redelivery has occurred. Detects whether or not. Further, the analysis unit 30 may detect whether or not redelivery has occurred by multiplying the delivery company, online store, product, delivery destination, delivery method, date and time, place, etc. extracted from the transaction data. good.

In addition, the analysis unit 30 analyzes the transaction data and generates a recommendation regarding delivery. Here, the recommendation refers to what is proposed to the user regarding delivery.

Recommendations include, for example, at least one of a delivery date, delivery destination or delivery method. The delivery method includes, for example, normal delivery to a delivery destination such as home or work, so-called "delivery" in which delivery is performed in a delivery box installed in the city, or delivery to a convenience store. It refers to a delivery method such as so-called "convenience store receipt". The delivery method is not limited to these, and may be any other type of delivery method. Further, the content of the recommendation is not limited to these, and may be any other type of proposal content. The recommendation also has the effect of informing the user that there are various delivery methods other than the normal delivery that delivers directly to the delivery destination, and encouraging the user to recognize and select a more appropriate delivery method.

The display unit 40 displays a recommendation regarding delivery on the user terminal 50 based on the analysis result of the analysis unit 30. The recommendations displayed by the display unit 40 are displayed in a unified design or display format on the same interface regardless of which online store or which delivery company the user is using, so that multiple online stores and deliveries can be made. The annoyance caused by the different formats of recommendation notifications among vendors is reduced.

The user terminal 50 is, for example, preferably a smartphone, but may be any terminal used by the user, such as a tablet, laptop or stand-alone computer.

Further, the delivery system 1 according to another example of the present invention has a transaction data acquisition unit 10 that acquires transaction data and a calendar schedule from an external service 2, and a transaction data storage unit that stores transaction data acquired by the transaction data acquisition unit 10. A display unit 40 that displays recommendations regarding delivery to the user terminal 50 based on the analysis results of the analysis unit 20, the analysis unit 30 that analyzes the transaction data stored in the transaction data storage unit 20 and the schedule of the calendar, and the analysis unit 30. And.

In the delivery system 1 according to another example of the present invention, the transaction data acquisition unit 10 acquires transaction data such as e-mail and a calendar schedule. The calendar schedule acquired by the transaction data acquisition unit 10 is analyzed together with the transaction data by the analysis unit 30, and is used for generating recommendations.

In the delivery system 1 according to another example of the present invention, the analysis unit 30 analyzes transaction data and calendar schedules and generates recommendations regarding delivery. For example, it is possible to analyze the schedule of the calendar used online, confirm that the user is not at home or work, optimize the delivery time, and recommend the optimum delivery time to the user. In addition, it is possible to confirm that the user is not at home or at work from the future schedule included in the message such as e-mail, optimize the delivery time, and recommend the optimum delivery time to the user. ..

Future appointments include, for example, travel and business trip appointments, use of transportation such as trains, planes and ships, restaurant reservations, movies, theatrical performances, concert appointments, event attendance, etc. Is done. Calendar appointments include all types of appointments, such as start and end times.

In another delivery system 1 according to the present invention, the analysis unit 30 analyzes the transaction data and the calendar schedule, and optimizes the delivery time.

FIG. 2 is a diagram showing processing of a transaction data acquisition unit of the delivery system according to the present invention.
The transaction data acquisition unit 10 acquires a message regarding a transaction of a product or service from the external service 2 as transaction data. The transaction data acquired by the transaction data acquisition unit 10 includes, for example, a purchase email of an online store, a delivery email of a delivery company, a calendar schedule, and the like. The transaction data includes, for example, information that the product B purchased at the online store A is delivered to Koto-ku, Tokyo at 14:00 by the delivery company C, and this information is from the external service 2. It is extracted from the contents of the acquired message such as e-mail.

Here, the online store purchase email is, for example, an email notifying the user who purchased the product that the purchase procedure has been completed when the purchase of the product is completed in the online store. The delivery mail of the delivery company is, for example, an mail notifying the user who purchased the product at the online store of the delivery date and time, the delivery destination, the delivery method, and other information regarding the delivery of the product. The purchase mail and the delivery mail are, for example, messages such as an e-mail and an SNS automatically delivered from the online store and the delivery company after purchasing the product in the online store. The calendar schedule is, for example, a schedule such as going out recorded in the calendar in the calendar service 6.

The transaction data acquisition unit 10 filters messages such as e-mails exchanged in the external service 2. The transaction data acquisition unit 10 extracts only those related to transactions such as purchase, reservation, and delivery of products from among them by filtering. The transaction data acquisition unit 10 stores a message related to a transaction of a product or service extracted by filtering in the transaction data storage unit 20 as transaction data.

FIG. 3 is a diagram showing the processing of the analysis unit of the delivery system according to the present invention.
The analysis unit 30 analyzes the transaction data stored in the transaction data storage unit 20. The analysis unit 30 preferably sends the analysis result as a recommendation or a report to the display unit 40 and stores it in the transaction data storage unit 20. The analysis result is stored in the transaction data storage unit 20 as past transaction data. The past transaction data stored in the transaction data storage unit 20 can also be used as a learning data or a part of the learning data for analysis in the analysis unit 30.

In addition, the analysis unit 30 analyzes the transaction data and detects whether or not redelivery has occurred. For example, the occurrence of redelivery determines whether or not the message is related to redelivery from the sender, recipient, transmission date and time, reception date and time, title, body, etc. of the message contained in the transaction data. Is detected by. In another example, the occurrence of redelivery may be detected by a product of a delivery company, an online store, a product, a delivery destination, a delivery method, a date and time, and a place.

In addition, the analysis unit 30 analyzes the transaction data and generates a recommendation regarding delivery. For example, suppose that a user has a business trip scheduled from Monday to Tuesday, has a meeting scheduled from 14:00 to 16:00 on Wednesday, and has made a restaurant reservation from 20:00. In this case, it is possible to recommend Wednesday from 17:00 to 19:00 as the delivery date and time while avoiding the scheduled time zone by the elimination method.

Further, the analysis unit 30 may use the past transaction data stored in the transaction data storage unit 20 as learning data or a part of the learning data, so that the user may receive the package in the first delivery or the current delivery. Can generate recommendations for deliveries that can increase or reduce the likelihood of redelivery. Further, the analysis unit 30 can generate a recommendation regarding delivery by using the calendar schedule as a learning data or a part of the learning data in addition to the past transaction data stored in the transaction data storage unit 20. .. Information such as receipt and return of luggage, calendar events, and the like is stored and stored in the transaction data storage unit 20. This information is stored and accumulated as the user's past behavior history or the user's current behavior status.

The user's current behavior status indicates the user's current situation, for example, whether the user's current situation is "daily" or "unusual". "Daily life" refers to a situation in which a user takes a daily routine behavior pattern at work, school, home, or the like. "Extraordinary" refers to a situation in which a user has an unusual behavior pattern, that is, a behavior pattern different from the daily routine behavior pattern, such as a travel destination or a business trip destination.

The analysis unit 30 predicts the user's current behavior status from the user's past behavior history stored and accumulated in the transaction data storage unit 20. For example, the analysis unit 30 predicts whether the user's current behavior status is "daily" or "unusual" from the past behavior history of the user stored and accumulated in the transaction data storage unit 20. The user's current behavioral status, such as the predicted "everyday" or "unusual", can be used as part of the learning data or learning data to generate recommendations for delivery.

In addition to the transaction data stored and stored in the transaction data storage unit 20, the user's past behavior history, the user's current behavior status, etc., the analysis unit 30 may, for example, time zone, day, weather information, national event, etc. , Environmental information such as an individual anniversary of the user and the holding of an event preferred by the user can be used as one of the learning data for generating a recommendation regarding delivery. This can generate recommendations for deliveries that can increase the likelihood that the user will receive the package in the first or current delivery, or reduce the likelihood of redelivery.

The time zone may be any time zone, for example, in the morning, afternoon, daytime, nighttime, during or after the user's working hours, during class hours or after school at school, etc., while the user is out or at home, etc. good. The day of the week may be any day of the week, for example, weekdays, weekends and holidays, and Fridays. The national event may be any date or period, such as New Year's holidays, Golden Week, Obon, Christmas, etc. The individual anniversary of the user may be, for example, the birthday of the user, family or friends, or any anniversary set by the user. The event preferred by the user may be any event such as a sports match or competition, a concert, a festival, a fireworks display, or the like.

As described above, the analysis unit 30 has at least one or at least two of the transaction data stored and stored in the transaction data storage unit 20, the user's past behavior history, the user's current behavior status, or the environmental information. By using the above combination as part of the training data or training data, it is possible to increase the possibility that the user will receive the package in the first delivery or the current delivery, or to reduce the possibility of redelivery. Can generate recommendations for various deliveries.

FIG. 4 is a diagram showing processing of a display unit of a delivery system according to the present invention.
The display unit 40 displays a recommendation regarding delivery on the user terminal 50 based on the analysis result of the analysis unit 30. Recommendations for delivery include, for example, delivery date and time, delivery destination, delivery method, and the like. As a recommendation regarding delivery, the display unit 40 displays, for example, a candidate for the date and time of receipt, a candidate for a delivery destination, a display of recommended delivery methods such as "delivery" and "convenience store receipt", and a plurality of packages collectively. Display messages that are recommended to be received, and display alerts that may not be received at the set date and time of receipt.

The display unit 40 displays a recommendation regarding delivery together with or incorporated in a list showing a future action list such as a schedule displayed on the screen of the user terminal 50 or a ToDo list. Further, the display unit 40 may notify the user terminal 50 of the recommendation regarding delivery as a message such as e-mail or SNS via the external service 2 or the external application. For example, when the analysis unit 30 detects information that causes the user to be absent on the scheduled delivery date or delivery time zone from the calendar information acquired from the external service 2, an alert is used as a message such as e-mail or SNS. The user terminal 50 may be notified.

As mentioned above, the delivery system according to the invention reduces the risk of redelivery and enhances delivery efficiency by cross-sectionally analyzing transaction data and calendar appointments at multiple delivery companies and multiple online stores. be able to. Further, the delivery system according to the present invention allows the user to receive a package at the first delivery or the current delivery by using transaction data from a plurality of delivery companies or a plurality of online stores as at least a part of learning data. It can increase the sex or reduce the possibility of redelivery.

The configurations of the parts described above can be arbitrarily combined. For example, (i) the analysis unit 30 uses the past transaction data stored in the transaction data storage unit 20 as at least a part of the learning data, and (ii) analyzes the past transaction data and the schedule of the calendar in addition to the past transaction data. Used as at least part of the learning data, (iii) predicts whether the user's current behavior status is daily or extraordinary from the user's past behavior history, and predicts the user's current behavior. Using status as at least part of the training data to generate recommendations for said delivery, and (iv) using environmental information as at least part of training data to generate recommendations for said delivery. Not only a single unit but also any one or more configurations can be used in combination.

Further, when the transaction data acquisition unit 10 performs name identification, the transaction data related to the delivery of the same product may be identified and the transaction data related to the same delivery item may be identified.

The delivery system according to the present invention can be used as a system provided to a delivery company. It can also be used to provide a delivery company with a report such as delivery status. Further, a part of the delivery system according to the present invention can be used as an anonymized data linkage engine or recommendation engine. In this way, it is also possible to cut out and use a part of the functions of the delivery system according to the present invention.
Although the above description has been made for Examples, it will be apparent to those skilled in the art that the present invention is not limited thereto and various modifications and modifications can be made within the scope of the principles of the present invention and the appended claims.

1 Delivery system 2 External service 10 Transaction data acquisition unit 20 Transaction data storage unit 30 Analysis unit 40 Display unit 50 User terminal

Claims (10)

It ’s a delivery system,
The transaction data acquisition department that acquires transaction data from external services,
A transaction data storage unit that stores transaction data acquired by the transaction data acquisition unit, and a transaction data storage unit.
The transaction data stored in the transaction data storage unit is analyzed , at least one of the delivery date and time, the delivery destination, and the delivery method is extracted, and whether or not redelivery has occurred is detected, and from the past transaction data. The extracted delivery date and time, the delivery destination, or at least one of the delivery methods is used as at least a part of the training data so as to reduce the possibility that the redelivery will occur in the first delivery or the current delivery. An analysis unit that generates recommendations for delivery , including at least one of the delivery date and time, the delivery destination, or the delivery method .
A display unit that displays a delivery recommendation generated by the analysis unit on the user terminal, and a display unit.
The delivery system comprising . It ’s a delivery system,
Transaction data acquisition department that acquires transaction data and calendar schedules from external services,
A transaction data storage unit that stores transaction data acquired by the transaction data acquisition unit, and a transaction data storage unit.
The transaction data stored in the transaction data storage unit and the schedule of the calendar are analyzed , at least one of the delivery date and time, the delivery destination or the delivery method is extracted, and whether or not redelivery has occurred is detected, and the past Using at least one of the delivery date and time, the delivery destination, or the delivery method extracted from the transaction data as at least a part of the training data, the possibility that the redelivery may occur in the first delivery or the current delivery. An analysis unit that generates recommendations for delivery , including at least one of the delivery date and time, the delivery destination, or the delivery method, so as to be low.
A display unit that displays a delivery recommendation generated by the analysis unit on the user terminal, and a display unit.
The delivery system comprising . The transaction data acquisition unit is characterized in that it filters messages exchanged in the external service to extract only messages related to transactions of goods or services, and acquires messages related to transactions of goods or services as transaction data. , The delivery system according to claim 1 or 2. The delivery system according to claim 3, wherein the message is an e-mail message, a message stored in the cloud, or a message exchanged by SNS. The analysis unit is characterized in that it generates a recommendation regarding delivery by using a calendar schedule as at least a part of learning data in addition to the past transaction data stored in the transaction data storage unit. The delivery system according to any one of 1 to 4 . The analysis unit predicts whether the user's current behavior status is daily or extraordinary from the user's past behavior history stored in the transaction data storage unit, and the predicted current behavior of the user. The delivery system according to any one of claims 1 to 5 , wherein the status is used as at least a part of the training data to generate a recommendation regarding the delivery. The delivery system according to any one of claims 1 to 6, wherein the analysis unit generates a recommendation regarding the delivery by using the environmental information as at least a part of the learning data. The analysis unit analyzes the transaction data and the schedule of the calendar, and optimizes the delivery time. Either claim 2 or claims 3 to 7 in the case of being subordinate to claim 2. The delivery system described in paragraph 1. Any of claims 1 to 8 , wherein the transaction data acquisition unit performs name identification of transaction data related to delivery of the same product based on the transaction data acquired from one or more of the external services. The delivery system described in item 1. One of claims 1 to 9 , wherein the transaction data acquisition unit performs name identification of transaction data related to the same delivery case based on the transaction data acquired from one or more of the external services. The delivery system described in paragraph 1.

Images