WO2020026359A1 - Computer system, marketing method, and program - Google Patents

Computer system, marketing method, and program Download PDF

Info

Publication number
WO2020026359A1
WO2020026359A1 PCT/JP2018/028747 JP2018028747W WO2020026359A1 WO 2020026359 A1 WO2020026359 A1 WO 2020026359A1 JP 2018028747 W JP2018028747 W JP 2018028747W WO 2020026359 A1 WO2020026359 A1 WO 2020026359A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
information
stocked
sales
age
Prior art date
Application number
PCT/JP2018/028747
Other languages
French (fr)
Japanese (ja)
Inventor
俊二 菅谷
Original Assignee
株式会社オプティム
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 株式会社オプティム filed Critical 株式会社オプティム
Priority to PCT/JP2018/028747 priority Critical patent/WO2020026359A1/en
Publication of WO2020026359A1 publication Critical patent/WO2020026359A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising

Definitions

  • the present invention relates to a computer system, a sales method, and a program for executing inventory management of commodities.
  • Patent Document 1 merely predicts demand during a predetermined period, and does not consider other factors. Therefore, the predicted demand may not always be accurate.
  • the present invention aims to provide a computer system, a sales method, and a program that make it easier to more accurately predict the demand for a product.
  • the present invention provides the following solutions.
  • the present invention provides an acquiring unit for acquiring regional information around a sales store, A prediction unit for predicting an item of a product to be inventoried in the sales store and a necessary inventory amount based on the regional information; A computer system is provided.
  • the computer system acquires regional information around the sales store, and predicts, based on the regional information, items of commodities to be stocked at the sales store and a necessary inventory amount.
  • the present invention is in the category of computer systems.
  • other categories such as methods and programs exhibit the same functions and effects according to the categories.
  • FIG. 1 is a diagram showing an outline of the sales system 1.
  • FIG. 2 is an overall configuration diagram of the sales system 1.
  • FIG. 3 is a flowchart illustrating a first sales process executed by the computer 10.
  • FIG. 4 is a flowchart illustrating a second sales process executed by the computer 10.
  • FIG. 5 is a flowchart illustrating a learning process performed by the computer 10.
  • FIG. 6 is a flowchart illustrating the suggestion processing executed by the computer 10.
  • FIG. 7 is a diagram illustrating an example in which the area information acquired by the computer 10 is schematically illustrated.
  • FIG. 8 is a diagram schematically showing the population distribution by age, the purchase probability, and the required inventory in the area 110 around the sales store 100 for the product A.
  • FIG. 1 is a diagram for explaining an outline of a sales system 1 according to a preferred embodiment of the present invention.
  • the sales system 1 is a computer system that includes a computer 10 and executes inventory management of merchandise in a sales store.
  • the sales system 1 may include, in addition to the computer 10, other terminal devices such as a dealer terminal owned by a dealer who sells commodities and an administrator terminal owned by an administrator of the sales store.
  • the computer 10 manages the item and the stock amount of the product in the sales store, and regional information in a region around the sales store (for example, population distribution by age in this region, SNS (Social Networking Service) in this region). Information, news of this area, medical information of this area, information of an event (concert, athletic meet, outdoor event, etc.) or weather information of this area) is obtained.
  • the computer 10 predicts the item of the product to be stocked at the sales store and the necessary stock amount of the product based on the acquired regional information.
  • the computer 10 notifies the seller of the product by notifying the predicted item of the product to be stocked and the necessary inventory amount of the product to the dealer terminal owned by the seller of the product. , The product item and the required inventory amount are notified.
  • the sales store managed by the computer 10 is a hospital.
  • the medical care information includes the number of patients who have reserved this hospital and their medical conditions, and the computer 10 calculates the items of the products to be inventoried and the necessary amount of the products based on the number and medical conditions of the patients. And predict.
  • the computer 10 manages the product handling status (actual sales) in other regions having characteristics similar to the region information around the sales store (for example, the number of people, the population structure by age, the climate, or illness that has become prevalent in the past). Of the product and the sales quantity of the product). The computer 10 predicts the item of the product to be stocked and the necessary stock amount of the product, taking into account the handling status of the obtained product.
  • sales stores include hospitals, shops, restaurants, and providers of various services (nursing care, cleaning, events, etc.), and products include pharmaceuticals, miscellaneous goods, articles, food and beverages, various services, and the like. It is.
  • the present invention is not limited to this example, and can be applied to various goods and services.
  • the computer 10 acquires regional information on a region around the sales store (step S01).
  • the computer 10 receives location information (location information acquired from a GPS (Global Positioning System) or the like, the address of the sales store, etc.) specifying the area of the sales store managed by the computer 10, and based on the location information, Identify the surrounding area.
  • the computer 10 acquires the area information in the specified area.
  • the regional information is, for example, population distribution by age in the region, SNS information in the region, news in the region, medical information in the region, event information, or weather information in the region.
  • the computer 10 uses at least one of the above-described area information in a process described below.
  • the computer 10 predicts, based on the acquired regional information, the item of the product to be stocked at the sales store and the necessary stock amount of the product (step S02).
  • the computer 10 stores the predetermined keyword, the item of the product, and the required inventory amount of the product in association with each other, and based on the keyword included in the acquired regional information and the stored predetermined keyword. Then, the item of the product associated with the keyword and the necessary inventory amount of the product are predicted.
  • the computer 10 notifies the predicted merchandise item and the required inventory amount of the merchandise to a trader terminal owned by a merchant who sells the merchandise.
  • the computer 10 notifies the trader of the item of the goods and the required stock by displaying the goods and the necessary stock on the trader terminal.
  • FIG. 2 is a diagram showing a system configuration of a sales system 1 according to a preferred embodiment of the present invention.
  • a sales system 1 is a computer system that includes a computer 10 and executes inventory management of merchandise in a sales store.
  • the sales system 1 may include a trader terminal, an administrator terminal, and other terminals.
  • the computer 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like as a control unit, and another device (a trader terminal or an administrator terminal not shown) as a communication unit. , And other terminals), for example, a device compatible with Wi-Fi (Wireless-Fidelity) compliant with IEEE 802.11. Further, the computer 10 includes, as a storage unit, a data storage unit such as a hard disk, a semiconductor memory, a recording medium, and a memory card. Further, the computer 10 includes, as a processing unit, various devices that execute various processes.
  • a CPU Central Processing Unit
  • RAM Random Access Memory
  • ROM Read Only Memory
  • the computer 10 includes, as a storage unit, a data storage unit such as a hard disk, a semiconductor memory, a recording medium, and a memory card.
  • the computer 10 includes, as a processing unit, various devices that execute various processes.
  • the control unit reads a predetermined program, and realizes the acquisition module 20, the notification module 21, the evaluation reception module 22, and the proposal module 23 in cooperation with the communication unit. Further, in the computer 10, the control unit reads a predetermined program, thereby realizing the storage module 30 in cooperation with the storage unit. Also, in the computer 10, the control unit reads a predetermined program, and in cooperation with the processing unit, the area designation module 40, the prediction module 41, the identification module 42, the learning module 43, the evaluation determination module 44, the substitute product module 45 is realized.
  • FIG. 3 is a diagram illustrating a flowchart of the first sales processing executed by the computer 10. The processing executed by each module described above will be described together with this processing.
  • the area specification module 40 receives specification of location information, which is information for specifying an area of a sales store managed by itself (step S10).
  • the area specifying module 40 receives the position information of the sales store (information that can uniquely specify a place such as a latitude / longitude or an address) as the position information.
  • the position information there are a latitude / longitude obtained from a GPS or the like, an address input from an administrator terminal, and the like.
  • the storage module 30 stores the received location information (Step S11).
  • the storage module 30 stores the location information in association with the sales store identifier (store name, management number, manager name, and the like). This is particularly effective when the computer 10 collectively manages a plurality of sales stores.
  • the acquisition module 20 acquires regional information (for example, population distribution by age, SNS information, news, medical information, event information, or weather information) around the sales store based on the location information (step S12).
  • the acquisition module 20 acquires area information corresponding to a predetermined range from the location information. For example, the acquisition module 20 acquires, from the addresses in the location information, the regional information in the same prefecture or the same ward, municipalities.
  • the area information acquired by the acquisition module 20 will be specifically described.
  • examples of the regional information include population distribution by age, SNS information, news, medical information, event information, and weather information.
  • the acquisition module 20 acquires at least one of these area information.
  • the area information acquired by the acquisition module 20 is not limited to the example described above, and may be other information.
  • the acquisition module 20 refers to various databases in which the population distribution by age is stored, using the prefecture or ward as a keyword, among the addresses included in the location information, and acquires the population distribution by age around the sales store. . At this time, the acquisition module 20 acquires the population distribution for each age around the sales store by referring to databases provided by various information agencies and public institutions.
  • the acquisition module 20 searches for posts of various SNSs by using the prefecture or the ward / municipality as a keyword among the addresses included in the location information.
  • the acquisition module 20 acquires a post having this keyword in SNS posts as SNS information around the sales store.
  • the acquisition module 20 searches for articles on various news providing sites by using, as keywords, prefectures or municipalities in the addresses included in the location information.
  • the acquisition module 20 acquires an article having this keyword from various news providing sites as news around the sales store.
  • the sales store is a hospital.
  • the acquisition module 20 acquires past medical records at the hospital serving as a sales store, the number of patients making a reservation, and medical conditions from a hospital database or the like.
  • the acquisition module 20 refers to a database or the like of another hospital that exists in this prefecture or ward, using the prefecture or ward as a keyword, among the addresses included in the location information, and refers to the past information in this other hospital. Get the number of medical records and the number of patients making reservations and medical conditions.
  • the acquisition module 20 searches various event introduction sites by using, as keywords, the prefecture or ward, municipalities, and various event names (concert, athletic meet, outdoor event, etc.) among the addresses included in the location information.
  • the acquisition module 20 acquires events having these keywords on various event introduction sites as event information around the sales store.
  • the acquisition module 20 compares the current date and time with the scheduled date and time of the acquired event information, and cancels the acquisition of the event that has already been completed.
  • the acquisition module 20 searches various weather information providing sites by using a prefecture or a ward, a municipal or the like as a keyword among the addresses included in the location information.
  • the acquisition module 20 acquires the weather information having this keyword from various types of weather information providing sites as weather information around the sales store.
  • the acquisition module 20 may use a keyword other than the prefecture or the ward, municipal, or the like as a keyword.
  • it may be a prefecture and a ward, a municipalities, a region name such as a Kyushu region or a Chugoku region, or a region capable of limiting other regions.
  • the acquisition module 20 may use a module that can limit an area other than the keyword. For example, regional information within a predetermined range (for example, a radius of 5 km and a radius of 10 km) from the address in the location information may be acquired.
  • FIG. 7 is a diagram schematically illustrating an example of the area information acquired by the acquisition module 20.
  • the acquisition module 20 acquires regional information in a region 110 around the sales store 100.
  • the regional information is a population distribution 120 for each age, SNS information 130, news 140, medical treatment information 150, event information 160, and weather information 170.
  • the computer 10 predicts the item of the product to be stocked and the necessary stock amount of the product by using such regional information in a process described later.
  • the acquisition module 20 specifies the area of the sales store based on the predetermined keyword included in the location information, and obtains at least one of the area information in the specified area.
  • the prediction module 41 predicts, based on the acquired area information, the items of the product to be stocked at the sales store and the necessary stock amount of the product (step S13). In step S13, the prediction module 41 predicts an item of a product to be stocked and a necessary stock amount based on a predetermined keyword included in the regional information.
  • the prediction module 41 compares, as a keyword, the previously calculated item of the product by age per unit number, the purchase probability of the product, and the population distribution by age acquired this time. For example, in the product A, the probability that a purchaser of a teenage age purchases the product A is 8%, the probability that a purchaser of a 20s age purchases the product A is 12%, and the purchaser is 30 years of age.
  • the population distribution by age acquired by the acquisition module 20 is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, and 900 people in their 60s.
  • the required inventory amount of the product A is the product of the probability of purchasing the product A in each age and the population distribution by age.
  • the required stock of this product A is 4 in the teens, 18 in the 20s, 30 in the 30s, 49 in the 40s, 40 in the 50s, 27 in the 60s, 70 or more Becomes zero.
  • the prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts that the required inventory amount of the product A is 178. At this time, the prediction module 41 performs the same prediction for all products handled by the sales store.
  • the purchase probability of a product is calculated by learning the approximate age of the purchaser and the purchased product when the product has been sold at this sales store or another sales store in the past. It is possible.
  • the prediction module 41 may execute prediction on some products instead of all products.
  • FIG. 8 is a diagram schematically showing the population distribution by age, the purchase probability, and the required inventory in the area 110 around the sales store 100 for the product A.
  • the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, and 900 people in their 60s. There are 400 people in their 70s and over.
  • the purchase probability of product A by age is 8% for teens, 12% for 20s, 15% for 30s, 7% for 40s, 5% for 50s, 3% for 60s, 70s
  • the above is 0.1%.
  • the required inventory is the product of the population distribution for each age and the purchase probability. Therefore, four teenagers, 18 teenagers, 30 teenagers, 30 teenagers, 49 teenagers, and 50 teenagers take 40. The number is 27 for the 60s and zero for the 70s and above. As a result, the required inventory amount of the product A is 178 which is the total of the required inventory amount for each age.
  • the prediction module 41 compares the purchase probability of a product associated with a predetermined keyword set in advance with the SNS post acquired this time. When “asthma” is set as a predetermined keyword, the keyword of “asthma” is extracted by performing text recognition on the acquired SNS post. The prediction module 41 predicts “product B” associated with this “asthma” as an item of a product to be stocked.
  • the probability of purchase of this product B by a purchaser of age 10s is 8%
  • the probability of purchase of this product B by a purchaser of age 20s is 12%
  • purchasers of age 30s Has a 15% probability of purchasing this product B, a 7% probability that a buyer in their forties will purchase this product B, a 5% probability of a buyer in their 50s purchasing this product B
  • the probability that a buyer in his 60s will purchase this product B is 3%
  • the probability that a buyer in his 70s will purchase this product B is 0.1%, based on an example in which it is calculated in advance. Will be explained.
  • the required inventory amount of this product B is the probability that each age will purchase this product B at this sales store in response to the SNS post.
  • the population distribution by age The population distribution for each age is the same as that obtained as the above-mentioned area information.
  • the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, 900 people in their 60s, Assuming that there are 400 people in their 70s or more, the required inventory of this product B is 4 in their teens, 18 in their 20s, 30 in their 30s, 49 in their 40s, 40 in their 50s, There are 27 in 60s and 0 in 70s and above.
  • the prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts that the required inventory amount of the product B is 178. Also, at this time, the prediction module 41 performs the same prediction for all products associated with the predetermined keyword included in the acquired SNS post.
  • the purchase probability of a product in this sales store in response to an SNS post is calculated by learning the change in the number of sales with respect to the past SNS post when the product has been sold by this sales store or another sales store in the past. It is possible to For example, when the keyword “asthma” is extracted in the SNS post, the fluctuation of the sales of the product B in the sales store is learned.
  • the prediction module 41 performs the prediction in the SNS posting using the population distribution for each age, but may perform the prediction only in the SNS posting. In this case, the prediction module 41 changes the probability of purchasing this product at this sales store in response to the SNS post, and associates the number of items to be stocked at this sales store with this keyword in response to this SNS post. It is possible to deal with it by doing so.
  • the prediction module 41 compares the purchase probability of a product associated with a predetermined keyword set in advance with the news acquired this time. When “asthma” is set as the predetermined keyword, the keyword of “asthma” is extracted by performing text recognition on the acquired news. The prediction module 41 predicts “product C” associated with “asthma” as an item of a product to be stocked.
  • the probability of purchase of this product C by a purchaser of age 10s is 8%
  • the probability of purchase of this product C by a purchaser of age 20s is 12%
  • the purchaser of age 30s Has a 15% probability of purchasing this product C, a 7% probability that a buyer in their 40s will purchase this product C, a 5% probability of a buyer in their 50s purchasing this product C
  • the probability that a buyer in his 60s will purchase this product C is 3%
  • the probability that a buyer in his 70s will purchase this product C is 0.1% Will be explained.
  • the stock requirement of this product C is determined by the probability and age of purchasing this product C at this sales store in each age in response to the news. It is the product of each population distribution.
  • the population distribution for each age is the same as that obtained as the above-mentioned area information.
  • the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, 900 people in their 60s, Assuming that there are 400 people in their 70s or more, the required inventory of this product C is 4 in their 10s, 18 in their 20s, 30 in their 30s, 49 in their 40s, 40 in their 50s, There are 27 in 60s and 0 in 70s and above.
  • the prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts the required inventory amount of the product C to be 178. In addition, at this time, the prediction module 41 executes the same prediction for all products associated with a predetermined keyword included in the acquired news.
  • the probability of purchasing a product in this sales store in response to news should be calculated by learning the change in the number of sales for past news when selling at this sales store or another sales store in the past. Is possible. For example, when a keyword of “asthma” is extracted in news, the fluctuation of the sales of the product C in the sales store is learned.
  • the prediction module 41 uses the population distribution for each age to execute prediction in news, the prediction module 41 may execute prediction only in news. In this case, the prediction module 41 changes the probability of purchasing this product at this sales store in response to the news, and associates the number of items to be stocked at this sales store in response to this news with the keyword. And so on.
  • the prediction module 41 compares the prescription probability of a medicine associated with a predetermined keyword set in the past medical chart of the hospital with the medical condition and the number of patients acquired this time as medical treatment information.
  • “asthma” is set as the predetermined keyword
  • the acquired past medical record is recognized as a text to extract the keyword of “asthma”.
  • the prediction module 41 predicts “medicine D” associated with “asthma” as an item of a product to be stocked.
  • the probability that a patient in his teens is prescribed this medicine D is 8%
  • the probability that a patient in his 20s is prescribed this medicine D is 12%
  • the age of a patient in his thirties is 15% probability of prescribing this drug D
  • 7% probability of prescribing this drug D for patients in their 40s is 15% probability of prescribing this drug D
  • 5% probability of prescribing this drug D for patients in their 50s Based on an example in which the probability that a patient in his sixth generation is prescribed this drug D is 3%, and the probability that a patient in his 70s is prescribed this drug D is 0.1% in advance. Will be explained.
  • the stock requirement of this medicine D is the product of the probability of being prescribed this medicine D in each age and the number of patients for each age. Becomes The number of patients for each age is the number of patients who have reserved this hospital. The number of patients by age is 5 in their teens, 15 in their 20s, 20 in their 30s, 70 in their 40s, 80 in their 50s, 90 in their 60s, and 40 in their 70s and above Assuming that there is, the necessary inventory amount of this medicine D is 1 in 10s, 2 in 20s, 3 in 30s, 5 in 40s, 4 in 50s, 3 in 60s, 70 No more than generations.
  • the prediction module 41 predicts 18 pieces, which is the sum total of the calculated required inventory for each age, as the required inventory. That is, the prediction module 41 predicts that the necessary inventory amount of the medicine D is 18 pieces. In addition, at this time, the prediction module 41 performs the same prediction for all medicines associated with the predetermined keyword included in the acquired medical information.
  • the prescription probability of a medicine can be calculated by learning the change in the number of prescriptions with respect to past medical information when prescriptions have been made by this hospital or another hospital in the past. For example, when the keyword “asthma” is extracted from the medical care information, the fluctuation in the number of prescriptions of the medicine D in the hospital is learned.
  • the prediction module 41 compares the purchase probability of a product associated with a predetermined keyword set in advance with the event information acquired this time.
  • the keyword of the “athletic meet” is extracted by performing text recognition on the acquired event information.
  • the prediction module 41 predicts “product E” associated with this “athletic meet” as an item of a product to be stocked.
  • the probability that a purchaser of a teenage age purchases the product E is 8%
  • the probability of a purchaser of a twenties age purchasing this product E is 12%
  • a purchaser of an age 30s Has a 15% probability of purchasing this product E, a 7% probability that a buyer in their 40s will purchase this product E, a 5% probability that a buyer in their 50s will purchase this product E
  • Based on an example in which the probability that a buyer in his 60s will purchase this product E is 3%, and the probability that a buyer in his 70s will purchase this product E is 0.1%. Will be explained.
  • the stock requirement of this product E is the probability that each age will purchase this product E at this sales store in response to the event information.
  • the population distribution by age The population distribution for each age is the same as that obtained as the above-mentioned area information.
  • the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, 900 people in their 60s, Assuming that there are 400 people in their 70s or more, the required inventory of this product E is 4 in their teens, 18 in their 20s, 30 in their 30s, 49 in their 40s, 40 in their 50s, There are 27 in 60s and 0 in 70s and above.
  • the prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts that the required inventory amount of the product E is 178. At this time, the prediction module 41 performs the same prediction for all products associated with a predetermined keyword included in the acquired event information.
  • the purchase probability of the product in this sales store in response to the event information is calculated by learning the change in the number of sales with respect to the past event information when selling at this sales store or another sales store in the past. It is possible to For example, when the keyword of “athletic meet” is extracted from the event information, the fluctuation of the sales of the product E in the sales store is learned.
  • the prediction module 41 performs the prediction in the event information using the population distribution for each age, the prediction module 41 may perform the prediction using only the event information. In this case, the prediction module 41 changes the probability of purchasing this product at this sales store in response to the event information, and associates the number of items to be stocked at this sales store with this keyword in response to this event information. It is possible to deal with it by doing so.
  • the prediction module 41 compares the purchase probability of a product associated with a predetermined keyword set in advance with the weather information acquired this time. When “rain” is set as the predetermined keyword, the keyword of “rain” is extracted by performing text recognition on the acquired weather information. The prediction module 41 predicts “product F” associated with this “rain” as a product item to be stocked.
  • the probability of purchase of this product F by a purchaser of a teenage age is 8%
  • the probability of purchase of this product F by a purchaser of a age of 20 is 12%
  • the purchaser of age 30s Has a 15% probability of purchasing this product F, a 7% probability that a buyer in their forties will purchase this product F, a 5% probability of a buyer in their 50s purchasing this product F
  • the probability that a purchaser in his 60s will purchase this product F is 3%
  • the probability that a buyer in his 70s will purchase this product F is 0.1%, based on an example that is calculated in advance. Will be explained.
  • the necessary inventory amount of the product F is the probability that each age will purchase this product F at this sales store in response to the weather information.
  • the population distribution by age The population distribution for each age is the same as that obtained as the above-mentioned area information.
  • the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, 900 people in their 60s, Assuming that there are 400 people in their 70s or more, the required inventory of this product F is 4 in their teens, 18 in their 20s, 30 in their 30s, 49 in their 40s, 40 in their 50s, There are 27 in 60s and 0 in 70s and above.
  • the prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts the required inventory amount of the product F to be 178. At this time, the prediction module 41 performs the same prediction for all products associated with a predetermined keyword included in the acquired weather information.
  • the purchase probability of a product in this sales store in response to weather information is calculated by learning the change in the number of sales with respect to past weather information when selling from this sales store or another sales store in the past It is possible to For example, when the keyword “rain” is extracted from the weather information, the fluctuation of the sales of the product F in the sales store is learned.
  • the prediction module 41 executes the prediction in the weather information using the population distribution for each age, the prediction module 41 may execute the prediction only in the weather information. In this case, the prediction module 41 changes the probability of purchasing this product in this sales store in response to the weather information, and associates the number of items to be stocked in this sales store in response to this weather information with the keyword. It is possible to deal with it by doing so.
  • the notification module 21 notifies the predicted merchandise items to be stocked and the required inventory amount of the merchandise to the trader terminal owned by the trader who sells the merchandise (step S14). In step S14, the notification module 21 notifies the seller of the sale by displaying the item of the product and the necessary stock amount on the dealer terminal.
  • FIG. 4 is a diagram illustrating a flowchart of the second sales process executed by the computer 10. The processing executed by each module described above will be described together with this processing.
  • the region designation module 40 accepts designation of location information, which is information for specifying the region of the sales store managed by itself (step S20).
  • the processing in step S20 is the same as the processing in step S10 described above.
  • Step S21 The storage module 30 stores the received location information (Step S21).
  • the processing in step S21 is the same as the processing in step S11 described above.
  • the acquisition module 20 acquires regional information around the sales store based on the location information (Step S22).
  • the processing in step S22 is the same as the processing in step S12 described above.
  • the specifying module 42 specifies a region having a region characteristic (for example, population number, population structure by age, climate (weather information and weather conditions), or a disease that has become widespread in the past) similar to the obtained region information (step S23). ).
  • the specifying module 42 refers to various databases and various websites based on the acquired region information and specifies a region having a region characteristic similar to the region information around the sales store.
  • the identification module 42 identifies an area having an area characteristic similar to at least one of the acquired area information (having similar numerical values, close conditions, etc.) as an area having an area characteristic similar to the acquired area information.
  • the identification module 42 extracts a predetermined keyword included in the acquired area information, and identifies an area having an area characteristic including a keyword similar to the extracted keyword as an area having a similar area characteristic.
  • the identification module 42 may include a population distribution for each age in which the population distribution for each age falls within a predetermined range, or a population distribution for each age.
  • An area having the number of populations whose total sum of the population is within a predetermined range is specified as an area having similar area characteristics.
  • the acquired regional information is an SNS post, weather information, or news
  • a keyword related to climate included in the SNS post, a keyword related to climate in weather information, and a keyword related to climate included in news are extracted and extracted.
  • a region having a keyword related to climate similar to the keyword is specified as a region having similar region characteristics.
  • the acquired area information is medical information
  • a keyword relating to a medical condition or a disease name included in the medical information is extracted, and an area having a keyword relating to a disease similar to the extracted keyword is converted to an area having similar regional characteristics. To be specified.
  • the identification module 42 may identify an area having similar area characteristics by combining a plurality of the above-described examples. For example, an area that satisfies both the conditions of the age-specific population structure and the disease that has prevailed in the past may be specified as an area having similar area characteristics. Further, a region having a similar region characteristic may be specified by combining other region characteristics.
  • the acquisition module 20 acquires the handling status of the product in the specified area (Step S24).
  • the handling status is the item of the product that was actually sold and the handling amount of the product.
  • the acquisition module 20 acquires the handling status of the product in the specified area from the computer that manages the sales store in the specified area.
  • the acquisition module 20 may acquire the handling status of the product in the specified area by another method. For example, by referring to various databases and various websites, the handling status of the product in the specified area may be acquired.
  • the prediction module 41 in addition to the above-described area information, based on the obtained product handling status in a region having similar regional characteristics, the item of the product to be stocked at the sales store, the necessary inventory amount of this product, Is predicted (step S25).
  • step S25 the prediction module 41 predicts the item of the product to be stocked at the sales store and the necessary stock amount of the product in the process of step S13 described above, and further takes into account the handling status of the obtained product. Then, the item of the product to be stocked at the sales store and the necessary stock amount of this product are predicted.
  • the prediction module 41 specifies the medicine D as the item of the commodity to be stocked, and predicts 18 pieces of the necessary stock of the medicine D as the stock.
  • the prediction module 41 determines the prediction result based on the regional information and the product of the product in the region having the similar regional characteristics.
  • the average value with the handling status is predicted as the necessary inventory amount of the product to be inventoried. By using the average value, it can be expected that the required inventory amount can be more accurately predicted than a prediction result based on one information.
  • the handling status of the product for each age is obtained, and the required inventory amount of the product to be stocked for each age at the forecast time and the average value of the handling status of the product for each age are calculated. It is also possible to predict the sum of the values as the required inventory of the goods to be inventoried.
  • the prediction module 41 is not limited to the above-described average value, and may predict other numerical values. For example, if there is a difference equal to or greater than a predetermined threshold between the prediction result based on the regional information and the handling status of this product in a region having similar regional characteristics, the prediction result based on the regional information is prioritized. Then, based on the result of the prediction, it may be predicted that the required quantity of the product should be stored. Further, a configuration is adopted in which a predetermined coefficient is set according to the handling situation of this product in an area having similar area characteristics, not an average value, and a prediction result based on area information is corrected based on the coefficient. Is also good.
  • the prediction module 41 is similar to the prediction result of the item of the product to be stocked and the required inventory amount of this product, as in the case of the medical information described above, even if the regional information is the other example described above. By taking into account the handling status of this product in the region having the regional characteristics, the items of the product to be stocked and the necessary inventory amount of this product are predicted.
  • the prediction module 41 corrects the item of the product and the required inventory amount predicted based on the region information based on the handling status of the product in a region having similar region characteristics, thereby obtaining the item of the product to be stocked. And the inventory requirement for this product.
  • the computer 10 refers to the sales results in another sales store having a regional characteristic similar to the location of the sales store, and performs sales prediction in this sales store.
  • step S26 The notification module 21 notifies the trader terminal owned by the trader who sells the product of the predicted item of the product to be stocked and the required inventory amount of the product (step S26).
  • the process in step S26 is the same as the process in step S14 described above.
  • FIG. 5 is a diagram illustrating a flowchart of the learning process executed by the computer 10. The processing executed by each module described above will be described together with this processing.
  • the learning module 43 learns the predicted items to be stocked in the past predetermined period or the same day and the necessary stock amount of the products (step S30). In step S30, the learning module 43 determines, for example, in the past month, the past week, or the same day in the past, the item of the product predicted in the first sales process or the second sales process described above and the inventory of this product. Learn the amount.
  • Step S31 the storage module 30 stores the learned date and the learning result in association with each other.
  • the prediction module 41 predicts an item of a product to be stocked and a necessary stock amount of the product after taking the learning result into consideration (step S32). This processing will be described using the first sales processing as an example.
  • the prediction module 41 should stock the item in the sales store in consideration of the learning result, in addition to the item of the product to be stocked, which is predicted based on the acquired area information, and the necessary stock amount of the product. The item of the product and the required inventory of the product are predicted.
  • the prediction module 41 specifies the medicine D as the item of the commodity to be stocked, and predicts 18 pieces of the necessary stock of the medicine D as the stock.
  • the prediction module 41 stores the average value of the prediction result based on the regional information and the learning result in inventory. Predict the required inventory of goods. By using the average value, it can be expected that the required inventory amount can be more accurately predicted than a prediction result based on one information.
  • the prediction module 41 is not limited to the above-described average value, and may predict other numerical values. For example, if there is a difference equal to or greater than a predetermined threshold between the prediction result based on the region information and the learning result, the prediction result based on the region information is prioritized and the inventory is determined based on the prediction result. It may be estimated as the necessary inventory amount of the product to be manufactured. Further, a configuration may be adopted in which a predetermined coefficient is set according to the learning result instead of the average value, and the prediction result based on the area information is corrected based on the coefficient.
  • the prediction module 41 adds the learning result to the prediction result of the item of the product to be stocked and the necessary inventory amount of this product, similarly to the case of the medical information described above. Is added, the item of the commodity to be inventoried and the necessary inventory amount of this commodity are predicted.
  • the prediction module 41 corrects the item of the product and the required inventory amount predicted based on the regional information based on the learning result, thereby predicting the item of the product to be inventoried and the required inventory amount of the product.
  • the prediction module 41 specifies the medicine D as an item of the commodity to be inventoried, predicts 18 medicines as the necessary inventory amount of the medicine D, and predicts 18 medicines in an area having similar regional characteristics.
  • the handling status of this medicine D is 15.
  • the prediction module 41 determines that the prediction result based on the region information and the prediction result based on the region information indicate that this product in the region having similar region characteristics is obtained.
  • the average value of the handling status and the average value of the learning result are predicted as the required inventory amount of the product to be inventoried. By using the average value, it can be expected that the required inventory amount can be more accurately predicted than a prediction result based on the regional information and the handling status of products having similar regional characteristics.
  • the prediction module 41 is not limited to the above-described average value, and may predict other numerical values. For example, if there is a difference equal to or more than a predetermined threshold between the prediction result based on the regional information, the average value of the handling status of this product in a region having similar regional characteristics, and the learning result, A prediction result based on the handling situation of the product in a region having a region characteristic similar to the information may be prioritized, and the necessary inventory amount of the product to be stocked may be predicted based on the prediction result. Also, a predetermined coefficient is set according to the learning result instead of the average value, and based on the coefficient, the prediction result based on the area information and the handling situation of this product in a region having a similar regional characteristic is corrected. It may be a configuration.
  • the prediction module 41 determines the area similar to the prediction result of the item of the product to be stocked and the necessary inventory amount of this product, similarly to the case of the medical information described above. By adding the learning result to the handling situation of the product in the region having the characteristic, the items of the product to be stocked and the necessary stock amount of the product are predicted.
  • the prediction module 41 corrects, based on the learning result, the prediction based on the item of the product predicted based on the region information and the handling status of the product in a region having a region characteristic similar to the required inventory amount, based on the learning result.
  • the item of the product to be performed and the required inventory of the product are predicted.
  • step S33 The notification module 21 notifies the trader terminal owned by the trader who sells the product of the predicted item of the product to be stocked and the necessary inventory amount of the product (step S33).
  • the processing in step S33 is the same as the processing in step S14 described above.
  • FIG. 6 is a diagram illustrating a flowchart of the suggestion processing executed by the computer 10. The processing executed by each module described above will be described together with this processing.
  • the evaluation receiving module 22 obtains, from the user who has been provided with the product, the evaluation of the item of the product predicted in the first sales process, the second sales process, or the learning process (Step S40). In step S40, the evaluation module 22 evaluates the product (for example, texts such as good or bad, numbers, etc.) from a user terminal owned by the user via a dedicated application, a website, or the like. Symbol).
  • the evaluation determination module 44 determines whether the received evaluation is equal to or smaller than a predetermined threshold (Step S41). In step S41, the evaluation determination module 44 determines whether or not the received evaluations are equal to or more than a predetermined number and whether the evaluations are equal to or lower than a predetermined threshold (meaning that the evaluations are low). When the evaluation determination module 44 determines that the difference is not equal to or smaller than the predetermined threshold (step S41: NO), the present processing ends.
  • step S41 when the evaluation determination module 44 determines that the value is equal to or less than the predetermined threshold value (step S41 YES), the substitute product module 45 creates another product similar to this product as a substitute product plan. (Step S42).
  • the alternative product module 45 creates this alternative product plan based on the regional information acquired by the acquisition module 20 (for example, a test result of a newly released drug or a result of an actual prescription).
  • the proposal module 23 proposes the created alternative product plan to the manager terminal owned by the manager of the sales store (step S43).
  • the suggestion module 23 causes the manager terminal to display a notification for excluding items with low evaluations from the item of the item, and a notification for proposing an alternative item similar to the low evaluation.
  • the means and functions described above are implemented when a computer (including a CPU, an information processing device, and various terminals) reads and executes a predetermined program.
  • the program is provided, for example, in the form of being provided from a computer via a network (SaaS: Software as a Service).
  • the program is provided in a form recorded on a computer-readable recording medium such as a flexible disk, a CD (eg, a CD-ROM), and a DVD (eg, a DVD-ROM, a DVD-RAM).
  • the computer reads the program from the recording medium, transfers the program to an internal recording device or an external recording device, records the program, and executes the program.
  • the program may be recorded in advance on a recording device (recording medium) such as a magnetic disk, an optical disk, or a magneto-optical disk, and may be provided to the computer from the recording device via a communication line.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The purpose of the present invention is to provide a computer system, a marketing method, and a program which make it easy to more accurately predict demand for a product. This computer system acquires regional information relating to a region surrounding a sales store (including at least one from among the population distribution by age in the region surrounding the store, SNS information relating to this region, news about this region, clinical information relating to this region, and meteorological information about this region), and predicts product items to be stocked in the sales store, and the amount of each item required to be stocked, on the basis of the acquired regional information. The computer system also acquires turnovers of products in a region having regional characteristics (including at least one from among total population, population by age, climate, and past prevalent diseases) similar to said regional information, and predicts product items to be stocked in the sales store, and the amount of each item required to be stocked, on the basis of the acquired turnovers.

Description

コンピュータシステム、販売方法及びプログラムComputer system, sales method and program
　本発明は、商品の在庫管理を実行するコンピュータシステム、販売方法及びプログラムに関する。 The present invention relates to a computer system, a sales method, and a program for executing inventory management of commodities.
　近年、無人の販売ストアにより様々な商品を販売することが行われている。このような販売ストアにおいて、様々な方法により、販売ストアが販売する商品の需要を予測し、予測した結果に基づいて、商品の在庫管理を実行している。 In recent years, various products have been sold through unmanned sales stores. In such a sales store, demands for products sold by the sales store are predicted by various methods, and inventory management of the products is executed based on the predicted result.
　このような商品の需要を予測する構成として、所定期間における需要を予測し、予測した需要と、所定の係数とに基づいて、商品の需要を算出する構成が開示されている（特許文献１参照）。 As a configuration for predicting demand for such a product, a configuration is disclosed in which demand in a predetermined period is predicted, and demand for the product is calculated based on the predicted demand and a predetermined coefficient (see Patent Document 1). ).
特開２０１８－７３３３８号公報JP 2018-73338 A
　しかしながら、特許文献１の構成では、あくまでも所定期間における需要のみを予測するものに過ぎず、その他の要因を考慮するものではなかった。そのため、予測した需要が必ずしも正確でないおそれがあった。 However, the configuration of Patent Document 1 merely predicts demand during a predetermined period, and does not consider other factors. Therefore, the predicted demand may not always be accurate.
　本発明は、より正確に商品の需要を予測することを容易とするコンピュータシステム、販売方法及びプログラムを提供することを目的とする。 The present invention aims to provide a computer system, a sales method, and a program that make it easier to more accurately predict the demand for a product.
　本発明では、以下のような解決手段を提供する。 The present invention provides the following solutions.
　本発明は、販売ストア周辺の地域情報を取得する取得手段と、
　前記地域情報に基づいて、前記販売ストアにて在庫すべき商品の項目と、その在庫必要量とを予測する予測手段と、
　を備えることを特徴とするコンピュータシステムを提供する。 The present invention provides an acquiring unit for acquiring regional information around a sales store,
A prediction unit for predicting an item of a product to be inventoried in the sales store and a necessary inventory amount based on the regional information;
A computer system is provided.
　本発明によれば、コンピュータシステムは、販売ストア周辺の地域情報を取得し、前記地域情報に基づいて、前記販売ストアにて在庫すべき商品の項目と、その在庫必要量とを予測する。 According to the present invention, the computer system acquires regional information around the sales store, and predicts, based on the regional information, items of commodities to be stocked at the sales store and a necessary inventory amount.
　本発明は、コンピュータシステムのカテゴリであるが、方法及びプログラム等の他のカテゴリにおいても、そのカテゴリに応じた同様の作用・効果を発揮する。 The present invention is in the category of computer systems. However, other categories such as methods and programs exhibit the same functions and effects according to the categories.
　本発明によれば、より正確に商品の需要を予測することを容易とするコンピュータシステム、販売方法及びプログラムを提供することが可能となる。 According to the present invention, it is possible to provide a computer system, a sales method, and a program that facilitate more accurately predicting demand for a product.
図１は、販売システム１の概要を示す図である。FIG. 1 is a diagram showing an outline of the sales system 1. 図２は、販売システム１の全体構成図である。FIG. 2 is an overall configuration diagram of the sales system 1. 図３は、コンピュータ１０が実行する第一販売処理を示すフローチャートである。FIG. 3 is a flowchart illustrating a first sales process executed by the computer 10. 図４は、コンピュータ１０が実行する第二販売処理を示すフローチャートである。FIG. 4 is a flowchart illustrating a second sales process executed by the computer 10. 図５は、コンピュータ１０が実行する学習処理を示すフローチャートである。FIG. 5 is a flowchart illustrating a learning process performed by the computer 10. 図６は、コンピュータ１０が実行する提案処理を示すフローチャートである。FIG. 6 is a flowchart illustrating the suggestion processing executed by the computer 10. 図７は、コンピュータ１０が取得する地域情報を模式的に示した一例を示す図である。FIG. 7 is a diagram illustrating an example in which the area information acquired by the computer 10 is schematically illustrated. 図８は、商品Ａにおける販売ストア１００の周辺の地域１１０における年齢毎の人口分布、購入確率、在庫必要量を模式的に示した図である。FIG. 8 is a diagram schematically showing the population distribution by age, the purchase probability, and the required inventory in the area 110 around the sales store 100 for the product A.
　以下、本発明を実施するための最良の形態について図を参照しながら説明する。なお、これはあくまでも一例であって、本発明の技術的範囲はこれらに限られるものではない。 Hereinafter, the best mode for carrying out the present invention will be described with reference to the drawings. This is only an example, and the technical scope of the present invention is not limited to these.
　［販売システム１の概要］
　本発明の好適な実施形態の概要について、図１に基づいて説明する。図１は、本発明の好適な実施形態である販売システム１の概要を説明するための図である。販売システム１は、コンピュータ１０から構成され、販売ストアの商品の在庫管理を実行するコンピュータシステムである。 [Overview of Sales System 1]
An outline of a preferred embodiment of the present invention will be described with reference to FIG. FIG. 1 is a diagram for explaining an outline of a sales system 1 according to a preferred embodiment of the present invention. The sales system 1 is a computer system that includes a computer 10 and executes inventory management of merchandise in a sales store.
　なお、販売システム１は、コンピュータ１０に加え、商品を販売する業者が所有する業者端末や、販売ストアの管理者が所有する管理者端末等のその他の端末装置が含まれていてもよい。 Note that the sales system 1 may include, in addition to the computer 10, other terminal devices such as a dealer terminal owned by a dealer who sells commodities and an administrator terminal owned by an administrator of the sales store.
　コンピュータ１０は、販売ストアの商品の項目と在庫量とを管理しており、この販売ストア周辺の地域における地域情報（例えば、この地域の年齢毎の人口分布、この地域のＳＮＳ（Ｓｏｃｉａｌ　Ｎｅｔｗｏｒｋｉｎｇ　Ｓｅｒｖｉｃｅ）情報、この地域のニュース、この地域の診療情報、イベント（コンサート、運動会、野外イベント等）情報又はこの地域の気象情報）を取得する。コンピュータ１０は、この取得した地域情報に基づいて、販売ストアにて在庫すべき商品の項目とこの商品の在庫必要量とを予測する。 The computer 10 manages the item and the stock amount of the product in the sales store, and regional information in a region around the sales store (for example, population distribution by age in this region, SNS (Social Networking Service) in this region). Information, news of this area, medical information of this area, information of an event (concert, athletic meet, outdoor event, etc.) or weather information of this area) is obtained. The computer 10 predicts the item of the product to be stocked at the sales store and the necessary stock amount of the product based on the acquired regional information.
　また、コンピュータ１０は、予測した在庫すべき商品の項目とこの商品の在庫必要量とを、この商品を販売する業者が所有する業者端末に通知することにより、この商品を販売する業者に対して、商品の項目と在庫必要量とを通知する。 Also, the computer 10 notifies the seller of the product by notifying the predicted item of the product to be stocked and the necessary inventory amount of the product to the dealer terminal owned by the seller of the product. , The product item and the required inventory amount are notified.
　また、コンピュータ１０は、地域情報として、上述したもののうち、診療情報を取得する場合、コンピュータ１０が管理する販売ストアは病院である。このとき、診療情報としては、この病院を予約している患者の数やその病状であり、コンピュータ１０はこの患者の数や病状に基づいて、在庫すべき商品の項目とこの商品の在庫必要量とを予測する。 When the computer 10 acquires the medical information among the above-mentioned information as the regional information, the sales store managed by the computer 10 is a hospital. At this time, the medical care information includes the number of patients who have reserved this hospital and their medical conditions, and the computer 10 calculates the items of the products to be inventoried and the necessary amount of the products based on the number and medical conditions of the patients. And predict.
　また、コンピュータ１０は、販売ストア周辺の地域情報と類似した特性（例えば、人口数、年齢毎の人口構成、気候又は過去に流行った病気）を有する他の地域における商品の取扱状況（実際に販売が行われた商品の項目とこの商品の販売数量）を取得する。コンピュータ１０は、この取得した商品の取扱状況を加味したうえで、在庫すべき商品の項目とこの商品の在庫必要量とを予測する。 In addition, the computer 10 manages the product handling status (actual sales) in other regions having characteristics similar to the region information around the sales store (for example, the number of people, the population structure by age, the climate, or illness that has become prevalent in the past). Of the product and the sales quantity of the product). The computer 10 predicts the item of the product to be stocked and the necessary stock amount of the product, taking into account the handling status of the obtained product.
　販売システム１が実行する処理の概要について説明する。以下の説明において、販売ストアとしては、病院、商店、飲食店、各種サービス（介護、清掃、イベント等）提供事業者等であり、商品としては、医薬品、雑貨、物品、飲食物、各種サービス等である。 An outline of the processing executed by the sales system 1 will be described. In the following description, sales stores include hospitals, shops, restaurants, and providers of various services (nursing care, cleaning, events, etc.), and products include pharmaceuticals, miscellaneous goods, articles, food and beverages, various services, and the like. It is.
　なお、本発明は、この例に限らず、様々な物品やサービスに対しても適用可能である。 The present invention is not limited to this example, and can be applied to various goods and services.
　コンピュータ１０は、販売ストア周辺の地域における地域情報を取得する（ステップＳ０１）。コンピュータ１０は、自身が管理する販売ストアの地域を特定する所在地情報（ＧＰＳ（Ｇｌｏｂａｌ　Ｐｏｓｉｔｉｏｎｉｎｇ　Ｓｙｓｔｅｍ）等から取得した位置情報やこの販売ストアの住所等）を受け付け、この所在地情報に基づいて、販売ストア周辺の地域を特定する。コンピュータ１０は、この特定した地域における地域情報を取得する。この地域情報としては、例えば、この地域における年齢毎の人口分布、この地域のＳＮＳ情報、この地域のニュース、この地域の診療情報、イベント情報又はこの地域の気象情報である。コンピュータ１０は、後述する処理において、上述した地域情報のうち、少なくとも一つを用いる。 (4) The computer 10 acquires regional information on a region around the sales store (step S01). The computer 10 receives location information (location information acquired from a GPS (Global Positioning System) or the like, the address of the sales store, etc.) specifying the area of the sales store managed by the computer 10, and based on the location information, Identify the surrounding area. The computer 10 acquires the area information in the specified area. The regional information is, for example, population distribution by age in the region, SNS information in the region, news in the region, medical information in the region, event information, or weather information in the region. The computer 10 uses at least one of the above-described area information in a process described below.
　コンピュータ１０は、取得した地域情報に基づいて、販売ストアにて在庫すべき商品の項目と、この商品の在庫必要量とを予測する（ステップＳ０２）。コンピュータ１０は、所定のキーワードと、商品の項目と、この商品の在庫必要量とを対応付けて記憶しておき、取得した地域情報に含まれるこのキーワードと、記憶した所定のキーワードとに基づいて、このキーワードに対応付けられた商品の項目と、この商品の在庫必要量とを予測する。 The computer 10 predicts, based on the acquired regional information, the item of the product to be stocked at the sales store and the necessary stock amount of the product (step S02). The computer 10 stores the predetermined keyword, the item of the product, and the required inventory amount of the product in association with each other, and based on the keyword included in the acquired regional information and the stored predetermined keyword. Then, the item of the product associated with the keyword and the necessary inventory amount of the product are predicted.
　コンピュータ１０は、予測した商品の項目と、この商品の在庫必要量とを、この商品を販売する業者が所持する業者端末に通知する。コンピュータ１０は、この商品の項目と在庫必要量とを業者端末に表示させることにより、この商品の項目と、在庫必要量とを業者に通知する。 The computer 10 notifies the predicted merchandise item and the required inventory amount of the merchandise to a trader terminal owned by a merchant who sells the merchandise. The computer 10 notifies the trader of the item of the goods and the required stock by displaying the goods and the necessary stock on the trader terminal.
　以上が、販売システム１の概要である。 The above is an outline of the sales system 1.
　［販売システム１のシステム構成］
　図２に基づいて、本発明の好適な実施形態である販売システム１のシステム構成について説明する。図２は、本発明の好適な実施形態である販売システム１のシステム構成を示す図である。図２において、販売システム１は、コンピュータ１０から構成され、販売ストアの商品の在庫管理を実行するコンピュータシステムである。 [System Configuration of Sales System 1]
A system configuration of a sales system 1 according to a preferred embodiment of the present invention will be described with reference to FIG. FIG. 2 is a diagram showing a system configuration of a sales system 1 according to a preferred embodiment of the present invention. In FIG. 2, a sales system 1 is a computer system that includes a computer 10 and executes inventory management of merchandise in a sales store.
　なお、販売システム１は、上述した通り、業者端末や管理者端末やその他の端末が含まれていてもよい。 As described above, the sales system 1 may include a trader terminal, an administrator terminal, and other terminals.
　コンピュータ１０は、制御部として、ＣＰＵ（Ｃｅｎｔｒａｌ　Ｐｒｏｃｅｓｓｉｎｇ　Ｕｎｉｔ）、ＲＡＭ（Ｒａｎｄｏｍ　Ａｃｃｅｓｓ　Ｍｅｍｏｒｙ）、ＲＯＭ（Ｒｅａｄ　Ｏｎｌｙ　Ｍｅｍｏｒｙ）等を備え、通信部として、他の機器（図示していない業者端末や管理者端末やその他の端末等）と通信可能にするためのデバイス、例えば、ＩＥＥＥ８０２．１１に準拠したＷｉ―Ｆｉ（Ｗｉｒｅｌｅｓｓ―Ｆｉｄｅｌｉｔｙ）対応デバイス等を備える。また、コンピュータ１０は、記憶部として、ハードディスクや半導体メモリ、記録媒体、メモリカード等によるデータのストレージ部を備える。また、コンピュータ１０は、処理部として、各種処理を実行する各種デバイス等を備える。 The computer 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like as a control unit, and another device (a trader terminal or an administrator terminal not shown) as a communication unit. , And other terminals), for example, a device compatible with Wi-Fi (Wireless-Fidelity) compliant with IEEE 802.11. Further, the computer 10 includes, as a storage unit, a data storage unit such as a hard disk, a semiconductor memory, a recording medium, and a memory card. Further, the computer 10 includes, as a processing unit, various devices that execute various processes.
　コンピュータ１０において、制御部が所定のプログラムを読み込むことにより、通信部と協働して、取得モジュール２０、通知モジュール２１、評価受付モジュール２２、提案モジュール２３を実現する。また、コンピュータ１０において、制御部が所定のプログラムを読み込むことにより、記憶部と協働して、記憶モジュール３０を実現する。また、コンピュータ１０において、制御部が所定のプログラムを読み込むことにより、処理部と協働して、地域指定モジュール４０、予測モジュール４１、特定モジュール４２、学習モジュール４３、評価判定モジュール４４、代替商品モジュール４５を実現する。 (4) In the computer 10, the control unit reads a predetermined program, and realizes the acquisition module 20, the notification module 21, the evaluation reception module 22, and the proposal module 23 in cooperation with the communication unit. Further, in the computer 10, the control unit reads a predetermined program, thereby realizing the storage module 30 in cooperation with the storage unit. Also, in the computer 10, the control unit reads a predetermined program, and in cooperation with the processing unit, the area designation module 40, the prediction module 41, the identification module 42, the learning module 43, the evaluation determination module 44, the substitute product module 45 is realized.
　［第一販売処理］
　図３に基づいて、販売システム１が実行する第一販売処理について説明する。図３は、コンピュータ１０が実行する第一販売処理のフローチャートを示す図である。上述した各モジュールが実行する処理について、本処理に併せて説明する。 [First Sales Processing]
The first sales processing executed by the sales system 1 will be described with reference to FIG. FIG. 3 is a diagram illustrating a flowchart of the first sales processing executed by the computer 10. The processing executed by each module described above will be described together with this processing.
　はじめに、地域指定モジュール４０は、自身が管理する販売ストアの地域を特定する情報である所在地情報の指定を受け付ける（ステップＳ１０）。ステップＳ１０において、地域指定モジュール４０は、この販売ストアの位置情報（緯度・経度や住所等の場所を一意に特定可能な情報）を所在地情報として指定を受け付ける。位置情報としては、ＧＰＳ等から取得した緯度・経度や、管理者端末により入力された住所等である。 First, the area specification module 40 receives specification of location information, which is information for specifying an area of a sales store managed by itself (step S10). In step S10, the area specifying module 40 receives the position information of the sales store (information that can uniquely specify a place such as a latitude / longitude or an address) as the position information. As the position information, there are a latitude / longitude obtained from a GPS or the like, an address input from an administrator terminal, and the like.
　記憶モジュール３０は、受け付けた所在地情報を記憶する（ステップＳ１１）。ステップＳ１１において、記憶モジュール３０は、この所在地情報と、販売ストアの識別子（店舗名、管理番号、管理者名等）とを対応付けて記憶する。これは、コンピュータ１０が複数の販売ストアを一括して管理する場合に特に有効である。 (4) The storage module 30 stores the received location information (Step S11). In step S11, the storage module 30 stores the location information in association with the sales store identifier (store name, management number, manager name, and the like). This is particularly effective when the computer 10 collectively manages a plurality of sales stores.
　取得モジュール２０は、所在地情報に基づいて、販売ストア周辺の地域情報（例えば、年齢毎の人口分布、ＳＮＳ情報、ニュース、診療情報、イベント情報又は気象情報）を取得する（ステップＳ１２）。ステップＳ１２において、取得モジュール２０は、所在地情報から所定の範囲に該当する地域情報を取得する。例えば、取得モジュール２０は、所在地情報における住所のうち、同一の都道府県や同一の区市町村における地域情報を取得する。 The acquisition module 20 acquires regional information (for example, population distribution by age, SNS information, news, medical information, event information, or weather information) around the sales store based on the location information (step S12). In step S12, the acquisition module 20 acquires area information corresponding to a predetermined range from the location information. For example, the acquisition module 20 acquires, from the addresses in the location information, the regional information in the same prefecture or the same ward, municipalities.
　取得モジュール２０が取得する地域情報について、具体的に説明する。本実施形態において、地域情報の例として、年齢毎の人口分布、ＳＮＳ情報、ニュース、診療情報、イベント情報又は気象情報が挙げられる。取得モジュール２０は、これらの地域情報のうち、少なくとも一つを取得する。 (4) The area information acquired by the acquisition module 20 will be specifically described. In the present embodiment, examples of the regional information include population distribution by age, SNS information, news, medical information, event information, and weather information. The acquisition module 20 acquires at least one of these area information.
　なお、取得モジュール２０が取得する地域情報は、上述した例に限らず、その他のものであってもよい。 The area information acquired by the acquisition module 20 is not limited to the example described above, and may be other information.
　地域情報が、年齢毎の人口分布である場合について説明する。取得モジュール２０は、所在地情報に含まれる住所のうち、都道府県又は区市町村をキーワードとして、年齢毎の人口分布が格納された各種データベースを参照し、販売ストア周辺の年齢毎の人口分布を取得する。このとき、取得モジュール２０は、各種情報機関や公共機関等が提供するデータベースを参照することにより、販売ストア周辺の年齢毎の人口分布を取得する。 場合 The case where the regional information is the population distribution by age will be described. The acquisition module 20 refers to various databases in which the population distribution by age is stored, using the prefecture or ward as a keyword, among the addresses included in the location information, and acquires the population distribution by age around the sales store. . At this time, the acquisition module 20 acquires the population distribution for each age around the sales store by referring to databases provided by various information agencies and public institutions.
　地域情報が、ＳＮＳ情報である場合について説明する。取得モジュール２０は、所在地情報に含まれる住所のうち、都道府県又は区市町村をキーワードとして、各種ＳＮＳの投稿を検索する。取得モジュール２０は、ＳＮＳの投稿において、このキーワードを有する投稿を、販売ストア周辺のＳＮＳ情報として取得する。 場合 The case where the regional information is SNS information will be described. The acquisition module 20 searches for posts of various SNSs by using the prefecture or the ward / municipality as a keyword among the addresses included in the location information. The acquisition module 20 acquires a post having this keyword in SNS posts as SNS information around the sales store.
　地域情報が、ニュースである場合について説明する。取得モジュール２０は、所在地情報に含まれる住所のうち、都道府県又は区市町村をキーワードとして、各種ニュース提供サイトの記事を検索する。取得モジュール２０は、各種ニュース提供サイトにおいて、このキーワードを有する記事を、販売ストア周辺のニュースとして取得する。 場合 Explain the case where the regional information is news. The acquisition module 20 searches for articles on various news providing sites by using, as keywords, prefectures or municipalities in the addresses included in the location information. The acquisition module 20 acquires an article having this keyword from various news providing sites as news around the sales store.
　地域情報が、地域の診療情報である場合について説明する。この場合、特に、販売ストアは、病院である。取得モジュール２０は、販売ストアである病院における過去のカルテや予約している患者の人数や病状を、病院のデータベース等から取得する。また、取得モジュール２０は、所在地情報に含まれる住所のうち、都道府県又は区市町村をキーワードとして、この都道府県や区市町村に存在する他の病院のデータベース等を参照し、この他の病院における過去のカルテや予約している患者の人数や病状を取得する。 場合 The case where the regional information is regional medical information will be described. In this case, in particular, the sales store is a hospital. The acquisition module 20 acquires past medical records at the hospital serving as a sales store, the number of patients making a reservation, and medical conditions from a hospital database or the like. In addition, the acquisition module 20 refers to a database or the like of another hospital that exists in this prefecture or ward, using the prefecture or ward as a keyword, among the addresses included in the location information, and refers to the past information in this other hospital. Get the number of medical records and the number of patients making reservations and medical conditions.
　地域情報が、イベント情報である場合について説明する。取得モジュール２０は、所在地情報に含まれる住所のうち、都道府県又は区市町村と、各種イベント名（コンサート、運動会、野外イベント等）とをキーワードとして、各種イベント紹介サイトを検索する。取得モジュール２０は、各種イベント紹介サイトにおいて、これらのキーワードを有するイベントを、販売ストア周辺のイベント情報として取得する。このとき、取得モジュール２０は、現在の日時と、取得したイベント情報の開催予定日時とを比較し、既に終了したものについては、取得を取りやめる。 場合 The case where the regional information is event information will be described. The acquisition module 20 searches various event introduction sites by using, as keywords, the prefecture or ward, municipalities, and various event names (concert, athletic meet, outdoor event, etc.) among the addresses included in the location information. The acquisition module 20 acquires events having these keywords on various event introduction sites as event information around the sales store. At this time, the acquisition module 20 compares the current date and time with the scheduled date and time of the acquired event information, and cancels the acquisition of the event that has already been completed.
　地域情報が、気象情報である場合について説明する。取得モジュール２０は、所在地情報に含まれる住所のうち、都道府県又は区市町村をキーワードとして、各種気象情報提供サイトを検索する。取得モジュール２０は、各種気象情報提供サイトにおいて、このキーワードを有する気象情報を、販売ストア周辺の気象情報として取得する。 場合 The case where the regional information is weather information will be described. The acquisition module 20 searches various weather information providing sites by using a prefecture or a ward, a municipal or the like as a keyword among the addresses included in the location information. The acquisition module 20 acquires the weather information having this keyword from various types of weather information providing sites as weather information around the sales store.
　なお、取得モジュール２０は、キーワードとして、都道府県又は区市町村以外のものを用いてもよい。例えば、都道府県及び区市町村であってもよいし、九州地方や中国地方といった地域名であってもよいし、その他の地域を限定することが可能なものであってもよい。また、取得モジュール２０は、キーワード以外の地域を限定することが可能なものを利用してもよい。例えば、所在地情報における住所から所定の範囲（例えば、半径５ｋｍ、半径１０ｋｍ）内における地域情報を取得してもよい。 Note that the acquisition module 20 may use a keyword other than the prefecture or the ward, municipal, or the like as a keyword. For example, it may be a prefecture and a ward, a municipalities, a region name such as a Kyushu region or a Chugoku region, or a region capable of limiting other regions. The acquisition module 20 may use a module that can limit an area other than the keyword. For example, regional information within a predetermined range (for example, a radius of 5 km and a radius of 10 km) from the address in the location information may be acquired.
　図７に基づいて、取得モジュール２０が取得する地域情報について説明する。図７は、取得モジュール２０が取得する地域情報を模式的に示した一例を示す図である。図７において、取得モジュール２０は、販売ストア１００の周辺の地域１１０における地域情報を取得する。地域情報は、年齢毎の人口分布１２０、ＳＮＳ情報１３０、ニュース１４０、診療情報１５０、イベント情報１６０、気象情報１７０である。コンピュータ１０は、このような地域情報を、後述する処理に用いて、在庫すべき商品の項目とこの商品の在庫必要量とを予測する。 (5) The area information acquired by the acquisition module 20 will be described with reference to FIG. FIG. 7 is a diagram schematically illustrating an example of the area information acquired by the acquisition module 20. In FIG. 7, the acquisition module 20 acquires regional information in a region 110 around the sales store 100. The regional information is a population distribution 120 for each age, SNS information 130, news 140, medical treatment information 150, event information 160, and weather information 170. The computer 10 predicts the item of the product to be stocked and the necessary stock amount of the product by using such regional information in a process described later.
　このように、取得モジュール２０は、所在地情報に含まれる所定のキーワードに基づいて、販売ストアの地域を特定し、この特定した地域における地域情報の少なくとも一つを取得する。 As described above, the acquisition module 20 specifies the area of the sales store based on the predetermined keyword included in the location information, and obtains at least one of the area information in the specified area.
　予測モジュール４１は、取得した地域情報に基づいて、販売ストアにて在庫すべき商品の項目と、この商品の在庫必要量とを予測する（ステップＳ１３）。ステップＳ１３において、予測モジュール４１は、地域情報に含まれる所定のキーワードに基づいて、在庫すべき商品の項目と在庫必要量とを予測する。 The prediction module 41 predicts, based on the acquired area information, the items of the product to be stocked at the sales store and the necessary stock amount of the product (step S13). In step S13, the prediction module 41 predicts an item of a product to be stocked and a necessary stock amount based on a predetermined keyword included in the regional information.
　地域情報が、年齢毎の人口分布である場合について説明する。予測モジュール４１は、予め算出した単位人数当りの年齢別における商品の項目とこの商品の購入確率と、今回取得した年齢毎の人口分布をキーワードとして比較する。例えば、商品Ａにおいて、年齢が１０代の購入者がこの商品Ａを購入する確率が８％、年齢が２０代の購入者がこの商品Ａを購入する確率が１２％、年齢が３０代の購入者がこの商品Ａを購入する確率が１５％、年齢が４０代の購入者がこの商品Ａを購入する確率が７％、年齢が５０代の購入者がこの商品Ａを購入する確率が５％、年齢が６０代の購入者がこの商品Ａを購入する確率が３％、年齢が７０代の購入者がこの商品Ａを購入する確率が０．１％であると予め算出されている例に基づいて説明する。今回、取得モジュール２０が取得した年齢毎の人口分布が、１０代が５０人、２０代が１５０人、３０代が２００人、４０代が７００人、５０代が８００人、６０代が９００人、７０代以上が４００人であったとすると、この商品Ａの在庫必要量は、各年代が商品Ａを購入する確率と年齢毎の人口分布との積となる。すなわち、この商品Ａの在庫必要量は、１０代が４個、２０代が１８個、３０代が３０個、４０代が４９個、５０代が４０個、６０代が２７個、７０代以上が０個となる。予測モジュール４１は、算出した年齢毎における在庫必要量の総和である１７８個を在庫必要量として予測する。すなわち、予測モジュール４１は、この商品Ａの在庫必要量を１７８個と予測する。また、このとき、予測モジュール４１は、販売ストアが取り扱う全ての商品について同様の予測を実行する。 場合 The case where the regional information is the population distribution by age will be described. The prediction module 41 compares, as a keyword, the previously calculated item of the product by age per unit number, the purchase probability of the product, and the population distribution by age acquired this time. For example, in the product A, the probability that a purchaser of a teenage age purchases the product A is 8%, the probability that a purchaser of a 20s age purchases the product A is 12%, and the purchaser is 30 years of age. 15% probability that a purchaser will purchase this product A, 7% probability that a purchaser in his 40s will purchase this product A, 5% probability that a purchaser in his 50s will purchase this product A For example, it is calculated in advance that the probability that a buyer in his 60s will purchase this product A is 3% and the probability that a buyer in his 70s will purchase this product A is 0.1%. It will be described based on the following. This time, the population distribution by age acquired by the acquisition module 20 is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, and 900 people in their 60s. Assuming that there are 400 people in their 70s and above, the required inventory amount of the product A is the product of the probability of purchasing the product A in each age and the population distribution by age. In other words, the required stock of this product A is 4 in the teens, 18 in the 20s, 30 in the 30s, 49 in the 40s, 40 in the 50s, 27 in the 60s, 70 or more Becomes zero. The prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts that the required inventory amount of the product A is 178. At this time, the prediction module 41 performs the same prediction for all products handled by the sales store.
　商品の購入確率は、過去にこの販売ストアや他の販売ストア等においてこの商品を販売した際に、購入者の凡その年齢と、購入した商品とを対応付けて学習させておくことにより算出することが可能である。 The purchase probability of a product is calculated by learning the approximate age of the purchaser and the purchased product when the product has been sold at this sales store or another sales store in the past. It is possible.
　なお、予測モジュール４１は、全ての商品ではなく、一部の商品についての予測を実行してもよい。 予 測 Note that the prediction module 41 may execute prediction on some products instead of all products.
　図８に基づいて、地域情報に基づいた販売ストアにて在庫すべき商品の項目と、この商品の在庫必要量との予測について説明する。図８は、商品Ａにおける販売ストア１００の周辺の地域１１０における年齢毎の人口分布、購入確率、在庫必要量を模式的に示した図である。図８において、上述した通り、年齢毎の人口分布は、１０代が５０人、２０代が１５０人、３０代が２００人、４０代が７００人、５０代が８００人、６０代が９００人、７０代以上が４００人である。また、年齢毎における商品Ａの購入確率が、１０代が８％、２０代が１２％、３０代が１５％、４０代が７％、５０代が５％、６０代が３％、７０代以上が０．１％である。在庫必要量は、この年齢毎の人口分布と購入確率との積であることから、１０代が４個、２０代が１８個、３０代が３０個、４０代が４９個、５０代が４０個、６０代が２７個、７０代以上が０個となる。この結果、商品Ａの在庫必要量は、年齢毎の在庫必要量の総和である１７８個となる。 Based on FIG. 8, a description will be given of the item of the product to be stocked at the sales store based on the regional information and the prediction of the necessary stock amount of the product. FIG. 8 is a diagram schematically showing the population distribution by age, the purchase probability, and the required inventory in the area 110 around the sales store 100 for the product A. In FIG. 8, as described above, the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, and 900 people in their 60s. There are 400 people in their 70s and over. Also, the purchase probability of product A by age is 8% for teens, 12% for 20s, 15% for 30s, 7% for 40s, 5% for 50s, 3% for 60s, 70s The above is 0.1%. The required inventory is the product of the population distribution for each age and the purchase probability. Therefore, four teenagers, 18 teenagers, 30 teenagers, 30 teenagers, 49 teenagers, and 50 teenagers take 40. The number is 27 for the 60s and zero for the 70s and above. As a result, the required inventory amount of the product A is 178 which is the total of the required inventory amount for each age.
　地域情報が、ＳＮＳ投稿である場合について説明する。予測モジュール４１は、予め設定した所定のキーワードに関連付けられた商品の購入確率と、今回取得したＳＮＳ投稿とを比較する。所定のキーワードとして、「喘息」が設定されている場合、取得したＳＮＳ投稿をテキスト認識することにより、この「喘息」のキーワードを抽出する。予測モジュール４１は、この「喘息」に関連付けられた「商品Ｂ」を在庫すべき商品の項目として予測する。この商品Ｂにおいて、年齢が１０代の購入者がこの商品Ｂを購入する確率が８％、年齢が２０代の購入者がこの商品Ｂを購入する確率が１２％、年齢が３０代の購入者がこの商品Ｂを購入する確率が１５％、年齢が４０代の購入者がこの商品Ｂを購入する確率が７％、年齢が５０代の購入者がこの商品Ｂを購入する確率が５％、年齢が６０代の購入者がこの商品Ｂを購入する確率が３％、年齢が７０代の購入者がこの商品Ｂを購入する確率が０．１％であると予め算出されている例に基づいて説明する。今回、取得モジュール２０が取得したＳＮＳ投稿におけるキーワードが「喘息」であることから、この商品Ｂの在庫必要量は、各年代がＳＮＳ投稿に反応してこの販売ストアでこの商品Ｂを購入する確率と年齢毎の人口分布との積となる。この年齢毎の人口分布は、上述した地域情報として取得したものと同様のものである。上述した例に従えば、年齢毎の人口分布が、１０代が５０人、２０代が１５０人、３０代が２００人、４０代が７００人、５０代が８００人、６０代が９００人、７０代以上が４００人であったとすると、この商品Ｂの在庫必要量は、１０代が４個、２０代が１８個、３０代が３０個、４０代が４９個、５０代が４０個、６０代が２７個、７０代以上が０個となる。予測モジュール４１は、算出した年齢毎における在庫必要量の総和である１７８個を在庫必要量として予測する。すなわち、予測モジュール４１は、この商品Ｂの在庫必要量を１７８個と予測する。また、このとき、予測モジュール４１は、取得したＳＮＳ投稿に含まれた所定のキーワードに関連付けられた全ての商品について同様の予測を実行する。 場合 The case where the regional information is an SNS post will be described. The prediction module 41 compares the purchase probability of a product associated with a predetermined keyword set in advance with the SNS post acquired this time. When “asthma” is set as a predetermined keyword, the keyword of “asthma” is extracted by performing text recognition on the acquired SNS post. The prediction module 41 predicts “product B” associated with this “asthma” as an item of a product to be stocked. In this product B, the probability of purchase of this product B by a purchaser of age 10s is 8%, the probability of purchase of this product B by a purchaser of age 20s is 12%, and purchasers of age 30s Has a 15% probability of purchasing this product B, a 7% probability that a buyer in their forties will purchase this product B, a 5% probability of a buyer in their 50s purchasing this product B, Based on an example in which the probability that a buyer in his 60s will purchase this product B is 3%, and the probability that a buyer in his 70s will purchase this product B is 0.1%, based on an example in which it is calculated in advance. Will be explained. Since the keyword in the SNS post acquired by the acquisition module 20 this time is “asthma”, the required inventory amount of this product B is the probability that each age will purchase this product B at this sales store in response to the SNS post. And the population distribution by age. The population distribution for each age is the same as that obtained as the above-mentioned area information. According to the example described above, the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, 900 people in their 60s, Assuming that there are 400 people in their 70s or more, the required inventory of this product B is 4 in their teens, 18 in their 20s, 30 in their 30s, 49 in their 40s, 40 in their 50s, There are 27 in 60s and 0 in 70s and above. The prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts that the required inventory amount of the product B is 178. Also, at this time, the prediction module 41 performs the same prediction for all products associated with the predetermined keyword included in the acquired SNS post.
　ＳＮＳ投稿に反応してこの販売ストアにおける商品の購入確率は、過去にこの販売ストアや他の販売ストア等により販売した際に、過去のＳＮＳ投稿に対する売上数の変動を学習させておくことにより算出することが可能である。例えば、ＳＮＳ投稿において、「喘息」のキーワードを抽出した際、販売ストアにおける商品Ｂの売り上げの変動を学習させておくである。 The purchase probability of a product in this sales store in response to an SNS post is calculated by learning the change in the number of sales with respect to the past SNS post when the product has been sold by this sales store or another sales store in the past. It is possible to For example, when the keyword “asthma” is extracted in the SNS post, the fluctuation of the sales of the product B in the sales store is learned.
　なお、予測モジュール４１は、年齢毎の人口分布を用いて、ＳＮＳ投稿における予測を実行しているが、ＳＮＳ投稿のみで予測を実行してもよい。この場合、予測モジュール４１は、ＳＮＳ投稿に反応してこの販売ストアでこの商品を購入する確率に変えて、このＳＮＳ投稿に反応してこの販売ストアでこの商品を在庫すべき数をキーワードに関連付けておく等することにより対応可能である。 Note that the prediction module 41 performs the prediction in the SNS posting using the population distribution for each age, but may perform the prediction only in the SNS posting. In this case, the prediction module 41 changes the probability of purchasing this product at this sales store in response to the SNS post, and associates the number of items to be stocked at this sales store with this keyword in response to this SNS post. It is possible to deal with it by doing so.
　地域情報が、ニュースである場合について説明する。予測モジュール４１は、予め設定した所定のキーワードに関連付けられた商品の購入確率と、今回取得したニュースとを比較する。所定のキーワードとして、「喘息」が設定されている場合、取得したニュースをテキスト認識することにより、この「喘息」のキーワードを抽出する。予測モジュール４１は、この「喘息」に関連付けられた「商品Ｃ」を在庫すべき商品の項目として予測する。この商品Ｃにおいて、年齢が１０代の購入者がこの商品Ｃを購入する確率が８％、年齢が２０代の購入者がこの商品Ｃを購入する確率が１２％、年齢が３０代の購入者がこの商品Ｃを購入する確率が１５％、年齢が４０代の購入者がこの商品Ｃを購入する確率が７％、年齢が５０代の購入者がこの商品Ｃを購入する確率が５％、年齢が６０代の購入者がこの商品Ｃを購入する確率が３％、年齢が７０代の購入者がこの商品Ｃを購入する確率が０．１％であると予め算出されている例に基づいて説明する。今回、取得モジュール２０が取得したニュースにおけるキーワードが「喘息」であることから、この商品Ｃの在庫必要量は、各年代がニュースに反応してこの販売ストアでこの商品Ｃを購入する確率と年齢毎の人口分布との積となる。この年齢毎の人口分布は、上述した地域情報として取得したものと同様のものである。上述した例に従えば、年齢毎の人口分布が、１０代が５０人、２０代が１５０人、３０代が２００人、４０代が７００人、５０代が８００人、６０代が９００人、７０代以上が４００人であったとすると、この商品Ｃの在庫必要量は、１０代が４個、２０代が１８個、３０代が３０個、４０代が４９個、５０代が４０個、６０代が２７個、７０代以上が０個となる。予測モジュール４１は、算出した年齢毎における在庫必要量の総和である１７８個を在庫必要量として予測する。すなわち、予測モジュール４１は、この商品Ｃの在庫必要量を１７８個と予測する。また、このとき、予測モジュール４１は、取得したニュースに含まれた所定のキーワードに関連付けられたすべての商品について同様の予測を実行する。 場合 Explain the case where the regional information is news. The prediction module 41 compares the purchase probability of a product associated with a predetermined keyword set in advance with the news acquired this time. When “asthma” is set as the predetermined keyword, the keyword of “asthma” is extracted by performing text recognition on the acquired news. The prediction module 41 predicts “product C” associated with “asthma” as an item of a product to be stocked. In this product C, the probability of purchase of this product C by a purchaser of age 10s is 8%, the probability of purchase of this product C by a purchaser of age 20s is 12%, and the purchaser of age 30s Has a 15% probability of purchasing this product C, a 7% probability that a buyer in their 40s will purchase this product C, a 5% probability of a buyer in their 50s purchasing this product C, Based on an example in which the probability that a buyer in his 60s will purchase this product C is 3%, and the probability that a buyer in his 70s will purchase this product C is 0.1% Will be explained. Since the keyword in the news acquired by the acquisition module 20 this time is “asthma”, the stock requirement of this product C is determined by the probability and age of purchasing this product C at this sales store in each age in response to the news. It is the product of each population distribution. The population distribution for each age is the same as that obtained as the above-mentioned area information. According to the example described above, the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, 900 people in their 60s, Assuming that there are 400 people in their 70s or more, the required inventory of this product C is 4 in their 10s, 18 in their 20s, 30 in their 30s, 49 in their 40s, 40 in their 50s, There are 27 in 60s and 0 in 70s and above. The prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts the required inventory amount of the product C to be 178. In addition, at this time, the prediction module 41 executes the same prediction for all products associated with a predetermined keyword included in the acquired news.
　ニュースに反応してこの販売ストアにおける商品の購入確率は、過去にこの販売ストアや他の販売ストア等により販売した際に、過去のニュースに対する売上数の変動を学習させておくことにより算出することが可能である。例えば、ニュースにおいて、「喘息」のキーワードを抽出した際、販売ストアにおける商品Ｃの売り上げの変動を学習させておくである。 The probability of purchasing a product in this sales store in response to news should be calculated by learning the change in the number of sales for past news when selling at this sales store or another sales store in the past. Is possible. For example, when a keyword of “asthma” is extracted in news, the fluctuation of the sales of the product C in the sales store is learned.
　なお、予測モジュール４１は、年齢毎の人口分布を用いて、ニュースにおける予測を実行しているが、ニュースのみで予測を実行してもよい。この場合、予測モジュール４１は、ニュースに反応してこの販売ストアでこの商品を購入する確率に変えて、このニュースに反応してこの販売ストアでこの商品を在庫すべき数をキーワードに関連付けておく等することにより対応可能である。 Although the prediction module 41 uses the population distribution for each age to execute prediction in news, the prediction module 41 may execute prediction only in news. In this case, the prediction module 41 changes the probability of purchasing this product at this sales store in response to the news, and associates the number of items to be stocked at this sales store in response to this news with the keyword. And so on.
　地域情報が、診療情報である場合について説明する。この場合、販売ストアは病院である。予測モジュール４１は、診療情報として、過去のこの病院のカルテにおいて予め設定した所定のキーワードに関連付けられた薬品の処方確率と、今回取得した患者の病状及び人数とを比較する。所定のキーワードとして「喘息」が設定されている場合、取得した過去のカルテをテキスト認識することにより、この「喘息」のキーワードを抽出する。予測モジュール４１は、この「喘息」に関連付けられた「薬品Ｄ」を在庫すべき商品の項目として予測する。この薬品Ｄにおいて、年齢が１０代の患者がこの薬品Ｄを処方される確率が８％、年齢が２０代の患者がこの薬品Ｄを処方される確率が１２％、年齢が３０代の患者がこの薬品Ｄを処方される確率が１５％、年齢が４０代の患者がこの薬品Ｄを処方される確率が７％、年齢が５０代の患者がこの薬品Ｄを処方される確率が５％、年齢が６代の患者がこの薬品Ｄを処方される確率が３％、年齢が７０代の患者がこの薬品Ｄを処方される確率が０．１％であると予め算出されている例に基づいて説明する。今回、取得モジュール２０が取得した診療情報におけるキーワードが「喘息」であることから、この薬品Ｄの在庫必要量は、各年代がこの薬品Ｄを処方される確率と年齢毎の患者数との積となる。この年齢毎の患者数は、この病院を予約した患者の人数である。年齢毎の患者数が、１０代が５人、２０代が１５人、３０代が２０人、４０代が７０人、５０代が８０人、６０代が９０人、７０代以上が４０人であったとすると、この薬品Ｄの在庫必要量は、１０代が１個、２０代が２個、３０代が３個、４０代が５個、５０代が４個、６０代が３個、７０代以上が０個となる。予測モジュール４１は、算出した年齢毎における在庫必要量の総和である１８個を在庫必要量として予測する。すなわち、予測モジュール４１は、この薬品Ｄの在庫必要量を１８個と予測する。また、このとき、予測モジュール４１は、取得した診療情報に含まれた所定のキーワードに関連付けられたすべての薬品について同様の予測を実行する。 場合 The case where the regional information is medical information will be described. In this case, the sales store is a hospital. The prediction module 41 compares the prescription probability of a medicine associated with a predetermined keyword set in the past medical chart of the hospital with the medical condition and the number of patients acquired this time as medical treatment information. When “asthma” is set as the predetermined keyword, the acquired past medical record is recognized as a text to extract the keyword of “asthma”. The prediction module 41 predicts “medicine D” associated with “asthma” as an item of a product to be stocked. In this medicine D, the probability that a patient in his teens is prescribed this medicine D is 8%, the probability that a patient in his 20s is prescribed this medicine D is 12%, and the age of a patient in his thirties is 15% probability of prescribing this drug D, 7% probability of prescribing this drug D for patients in their 40s, 5% probability of prescribing this drug D for patients in their 50s, Based on an example in which the probability that a patient in his sixth generation is prescribed this drug D is 3%, and the probability that a patient in his 70s is prescribed this drug D is 0.1% in advance. Will be explained. Since the keyword in the medical information acquired by the acquisition module 20 this time is “asthma”, the stock requirement of this medicine D is the product of the probability of being prescribed this medicine D in each age and the number of patients for each age. Becomes The number of patients for each age is the number of patients who have reserved this hospital. The number of patients by age is 5 in their teens, 15 in their 20s, 20 in their 30s, 70 in their 40s, 80 in their 50s, 90 in their 60s, and 40 in their 70s and above Assuming that there is, the necessary inventory amount of this medicine D is 1 in 10s, 2 in 20s, 3 in 30s, 5 in 40s, 4 in 50s, 3 in 60s, 70 No more than generations. The prediction module 41 predicts 18 pieces, which is the sum total of the calculated required inventory for each age, as the required inventory. That is, the prediction module 41 predicts that the necessary inventory amount of the medicine D is 18 pieces. In addition, at this time, the prediction module 41 performs the same prediction for all medicines associated with the predetermined keyword included in the acquired medical information.
　薬品の処方確率は、過去にこの病院や他の病院等により処方した際に、過去の診療情報に対する処方数の変動を学習させておくことにより算出することが可能である。例えば、診療情報において、「喘息」のキーワードを抽出した際、病院における薬品Ｄの処方数の変動を学習させておくである。 処方 The prescription probability of a medicine can be calculated by learning the change in the number of prescriptions with respect to past medical information when prescriptions have been made by this hospital or another hospital in the past. For example, when the keyword “asthma” is extracted from the medical care information, the fluctuation in the number of prescriptions of the medicine D in the hospital is learned.
　地域情報が、イベント情報である場合について説明する。予測モジュール４１は、予め設定した所定のキーワードに関連付けられた商品の購入確率と、今回取得したイベント情報とを比較する。所定のキーワードとして「運動会」が設定されている場合、取得したイベント情報をテキスト認識することにより、この「運動会」のキーワードを抽出する。予測モジュール４１は、この「運動会」に関連付けられた「商品Ｅ」を在庫すべき商品の項目として予測する。この商品Ｅにおいて、年齢が１０代の購入者がこの商品Ｅを購入する確率が８％、年齢が２０代の購入者がこの商品Ｅを購入する確率が１２％、年齢が３０代の購入者がこの商品Ｅを購入する確率が１５％、年齢が４０代の購入者がこの商品Ｅを購入する確率が７％、年齢が５０代の購入者がこの商品Ｅを購入する確率が５％、年齢が６０代の購入者がこの商品Ｅを購入する確率が３％、年齢が７０代の購入者がこの商品Ｅを購入する確率が０．１％であると予め算出されている例に基づいて説明する。今回、取得モジュール２０が取得したイベント情報におけるキーワードが「運動会」であることから、この商品Ｅの在庫必要量は、各年代がイベント情報に反応してこの販売ストアでこの商品Ｅを購入する確率と年齢毎の人口分布との積となる。この年齢毎の人口分布は、上述した地域情報として取得したものと同様のものである。上述した例に従えば、年齢毎の人口分布が、１０代が５０人、２０代が１５０人、３０代が２００人、４０代が７００人、５０代が８００人、６０代が９００人、７０代以上が４００人であったとすると、この商品Ｅの在庫必要量は、１０代が４個、２０代が１８個、３０代が３０個、４０代が４９個、５０代が４０個、６０代が２７個、７０代以上が０個となる。予測モジュール４１は、算出した年齢毎における在庫必要量の総和である１７８個を在庫必要量として予測する。すなわち、予測モジュール４１は、この商品Ｅの在庫必要量を１７８個と予測する。また、このとき、予測モジュール４１は、取得したイベント情報に含まれた所定のキーワードに関連付けられたすべての商品について同様の予測を実行する。 場合 The case where the regional information is event information will be described. The prediction module 41 compares the purchase probability of a product associated with a predetermined keyword set in advance with the event information acquired this time. When “athletic meet” is set as a predetermined keyword, the keyword of the “athletic meet” is extracted by performing text recognition on the acquired event information. The prediction module 41 predicts “product E” associated with this “athletic meet” as an item of a product to be stocked. In this product E, the probability that a purchaser of a teenage age purchases the product E is 8%, the probability of a purchaser of a twenties age purchasing this product E is 12%, and a purchaser of an age 30s Has a 15% probability of purchasing this product E, a 7% probability that a buyer in their 40s will purchase this product E, a 5% probability that a buyer in their 50s will purchase this product E, Based on an example in which the probability that a buyer in his 60s will purchase this product E is 3%, and the probability that a buyer in his 70s will purchase this product E is 0.1%. Will be explained. Since the keyword in the event information acquired by the acquisition module 20 this time is “athletic meeting”, the stock requirement of this product E is the probability that each age will purchase this product E at this sales store in response to the event information. And the population distribution by age. The population distribution for each age is the same as that obtained as the above-mentioned area information. According to the example described above, the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, 900 people in their 60s, Assuming that there are 400 people in their 70s or more, the required inventory of this product E is 4 in their teens, 18 in their 20s, 30 in their 30s, 49 in their 40s, 40 in their 50s, There are 27 in 60s and 0 in 70s and above. The prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts that the required inventory amount of the product E is 178. At this time, the prediction module 41 performs the same prediction for all products associated with a predetermined keyword included in the acquired event information.
　イベント情報に反応してこの販売ストアにおける商品の購入確率は、過去にこの販売ストアや他の販売ストア等により販売した際に、過去のイベント情報に対する売上数の変動を学習させておくことにより算出することが可能である。例えば、イベント情報において、「運動会」のキーワードを抽出した際、販売ストアにおける商品Ｅの売り上げの変動を学習させておくである。 The purchase probability of the product in this sales store in response to the event information is calculated by learning the change in the number of sales with respect to the past event information when selling at this sales store or another sales store in the past. It is possible to For example, when the keyword of “athletic meet” is extracted from the event information, the fluctuation of the sales of the product E in the sales store is learned.
　なお、予測モジュール４１は、年齢毎の人口分布を用いて、イベント情報における予測を実行しているが、イベント情報のみで予測を実行してもよい。この場合、予測モジュール４１は、イベント情報に反応してこの販売ストアでこの商品を購入する確率に変えて、このイベント情報に反応してこの販売ストアでこの商品を在庫すべき数をキーワードに関連付けておく等することにより対応可能である。 Although the prediction module 41 performs the prediction in the event information using the population distribution for each age, the prediction module 41 may perform the prediction using only the event information. In this case, the prediction module 41 changes the probability of purchasing this product at this sales store in response to the event information, and associates the number of items to be stocked at this sales store with this keyword in response to this event information. It is possible to deal with it by doing so.
　地域情報が、気象情報である場合について説明する。予測モジュール４１は、予め設定した所定のキーワードに関連付けられた商品の購入確率と、今回取得した気象情報とを比較する。所定のキーワードとして「雨」が設定されている場合、取得した気象情報をテキスト認識することにより、この「雨」のキーワードを抽出する。予測モジュール４１は、この「雨」に関連付けられた「商品Ｆ」を在庫すべき商品の項目として予測する。この商品Ｆにおいて、年齢が１０代の購入者がこの商品Ｆを購入する確率が８％、年齢が２０代の購入者がこの商品Ｆを購入する確率が１２％、年齢が３０代の購入者がこの商品Ｆを購入する確率が１５％、年齢が４０代の購入者がこの商品Ｆを購入する確率が７％、年齢が５０代の購入者がこの商品Ｆを購入する確率が５％、年齢が６０代の購入者がこの商品Ｆを購入する確率が３％、年齢が７０代の購入者がこの商品Ｆを購入する確率が０．１％であると予め算出されている例に基づいて説明する。今回、取得モジュール２０が取得したイベント情報におけるキーワードが「雨」であることから、この商品Ｆの在庫必要量は、各年代が気象情報に反応してこの販売ストアでこの商品Ｆを購入する確率と年齢毎の人口分布との積となる。この年齢毎の人口分布は、上述した地域情報として取得したものと同様のものである。上述した例に従えば、年齢毎の人口分布が、１０代が５０人、２０代が１５０人、３０代が２００人、４０代が７００人、５０代が８００人、６０代が９００人、７０代以上が４００人であったとすると、この商品Ｆの在庫必要量は、１０代が４個、２０代が１８個、３０代が３０個、４０代が４９個、５０代が４０個、６０代が２７個、７０代以上が０個となる。予測モジュール４１は、算出した年齢毎における在庫必要量の総和である１７８個を在庫必要量として予測する。すなわち、予測モジュール４１は、この商品Ｆの在庫必要量を１７８個と予測する。また、このとき、予測モジュール４１は、取得した気象情報に含まれた所定のキーワードに関連付けられたすべての商品について同様の予測を実行する。 場合 The case where the regional information is weather information will be described. The prediction module 41 compares the purchase probability of a product associated with a predetermined keyword set in advance with the weather information acquired this time. When “rain” is set as the predetermined keyword, the keyword of “rain” is extracted by performing text recognition on the acquired weather information. The prediction module 41 predicts “product F” associated with this “rain” as a product item to be stocked. In this product F, the probability of purchase of this product F by a purchaser of a teenage age is 8%, the probability of purchase of this product F by a purchaser of a age of 20 is 12%, and the purchaser of age 30s Has a 15% probability of purchasing this product F, a 7% probability that a buyer in their forties will purchase this product F, a 5% probability of a buyer in their 50s purchasing this product F, Based on an example in which the probability that a purchaser in his 60s will purchase this product F is 3%, and the probability that a buyer in his 70s will purchase this product F is 0.1%, based on an example that is calculated in advance. Will be explained. This time, since the keyword in the event information acquired by the acquisition module 20 is “rain”, the necessary inventory amount of the product F is the probability that each age will purchase this product F at this sales store in response to the weather information. And the population distribution by age. The population distribution for each age is the same as that obtained as the above-mentioned area information. According to the example described above, the population distribution by age is 50 people in their teens, 150 people in their 20s, 200 people in their 30s, 700 people in their 40s, 800 people in their 50s, 900 people in their 60s, Assuming that there are 400 people in their 70s or more, the required inventory of this product F is 4 in their teens, 18 in their 20s, 30 in their 30s, 49 in their 40s, 40 in their 50s, There are 27 in 60s and 0 in 70s and above. The prediction module 41 predicts 178 pieces, which is the sum total of the calculated required inventory amount for each age, as the required inventory amount. That is, the prediction module 41 predicts the required inventory amount of the product F to be 178. At this time, the prediction module 41 performs the same prediction for all products associated with a predetermined keyword included in the acquired weather information.
　気象情報に反応してこの販売ストアにおける商品の購入確率は、過去にこの販売ストアや他の販売ストア等により販売した際に、過去の気象情報に対する売上数の変動を学習させておくことにより算出することが可能である。例えば、気象情報において、「雨」のキーワードを抽出した際、販売ストアにおける商品Ｆの売り上げの変動を学習させておくである。 The purchase probability of a product in this sales store in response to weather information is calculated by learning the change in the number of sales with respect to past weather information when selling from this sales store or another sales store in the past It is possible to For example, when the keyword “rain” is extracted from the weather information, the fluctuation of the sales of the product F in the sales store is learned.
　なお、予測モジュール４１は、年齢毎の人口分布を用いて、気象情報における予測を実行しているが、気象情報のみで予測を実行してもよい。この場合、予測モジュール４１は、気象情報に反応してこの販売ストアでこの商品を購入する確率に変えて、この気象情報に反応してこの販売ストアでこの商品を在庫すべき数をキーワードに関連付けておく等することにより対応可能である。 Although the prediction module 41 executes the prediction in the weather information using the population distribution for each age, the prediction module 41 may execute the prediction only in the weather information. In this case, the prediction module 41 changes the probability of purchasing this product in this sales store in response to the weather information, and associates the number of items to be stocked in this sales store in response to this weather information with the keyword. It is possible to deal with it by doing so.
　通知モジュール２１は、予測した在庫すべき商品の項目と、この商品の在庫必要量とを、この商品を販売する業者が所持する業者端末に通知する（ステップＳ１４）。ステップＳ１４において、通知モジュール２１は、この商品の項目と、在庫必要量とを業者端末に表示させることにより、販売する業者に通知する。 The notification module 21 notifies the predicted merchandise items to be stocked and the required inventory amount of the merchandise to the trader terminal owned by the trader who sells the merchandise (step S14). In step S14, the notification module 21 notifies the seller of the sale by displaying the item of the product and the necessary stock amount on the dealer terminal.
　以上が、第一販売処理である。 The above is the first sales process.
　［第二販売処理］
　図４に基づいて、販売システム１が実行する第二販売処理について説明する。図４は、コンピュータ１０が実行する第二販売処理のフローチャートを示す図である。上述した各モジュールが実行する処理について、本処理に併せて説明する。 [Second sales process]
The second sales processing executed by the sales system 1 will be described with reference to FIG. FIG. 4 is a diagram illustrating a flowchart of the second sales process executed by the computer 10. The processing executed by each module described above will be described together with this processing.
　なお、上述した第一販売処理と同様の処理については、その詳細な説明は省略する。 A detailed description of the same processing as the first sales processing described above is omitted.
　地域指定モジュール４０は、自身が管理する販売ストアの地域を特定する情報である所在地情報の指定を受け付ける（ステップＳ２０）。ステップＳ２０の処理は、上述したステップＳ１０の処理と同様である。 The region designation module 40 accepts designation of location information, which is information for specifying the region of the sales store managed by itself (step S20). The processing in step S20 is the same as the processing in step S10 described above.
　記憶モジュール３０は、受け付けた所在地情報を記憶する（ステップＳ２１）。ステップＳ２１の処理は、上述したステップＳ１１の処理と同様である。 (4) The storage module 30 stores the received location information (Step S21). The processing in step S21 is the same as the processing in step S11 described above.
　取得モジュール２０は、所在地情報に基づいて、販売ストア周辺の地域情報を取得する（ステップＳ２２）。ステップＳ２２の処理は、上述したステップＳ１２の処理と同様である。 The acquisition module 20 acquires regional information around the sales store based on the location information (Step S22). The processing in step S22 is the same as the processing in step S12 described above.
　特定モジュール４２は、取得した地域情報と類似する地域特性（例えば、人口数、年齢別の人口構成、気候（気象情報や気象条件）又は過去に流行った病気）を有する地域を特定する（ステップＳ２３）。ステップＳ２３において、特定モジュール４２は、取得した地域情報に基づいて、各種データベースや各種ウェブサイトを参照し、販売ストア周辺の地域情報と類似する地域特性を有する地域を特定する。特定モジュール４２は、取得した地域情報の少なくとも一つと類似（数値が近い、条件が近い等）する地域特性を有する地域を、取得した地域情報と類似する地域特性を有する地域として特定する。特定モジュール４２は、取得した地域情報に含まれる所定のキーワードを抽出し、この抽出したキーワードと類似したキーワードを含んだ地域特性を有する地域を、類似する地域特性を有する地域として特定する。 The specifying module 42 specifies a region having a region characteristic (for example, population number, population structure by age, climate (weather information and weather conditions), or a disease that has become widespread in the past) similar to the obtained region information (step S23). ). In step S23, the specifying module 42 refers to various databases and various websites based on the acquired region information and specifies a region having a region characteristic similar to the region information around the sales store. The identification module 42 identifies an area having an area characteristic similar to at least one of the acquired area information (having similar numerical values, close conditions, etc.) as an area having an area characteristic similar to the acquired area information. The identification module 42 extracts a predetermined keyword included in the acquired area information, and identifies an area having an area characteristic including a keyword similar to the extracted keyword as an area having a similar area characteristic.
　例えば、特定モジュール４２は、取得した地域情報が、年齢毎の人口分布であるとき、年齢毎における人口分布が所定の範囲内に収まる年齢別の人口構成を有する地域や、年齢毎の人口分布に基づいた人口の総和が所定の範囲内に収まる人口数を有する地域を、類似する地域特性を有する地域として特定する。また、取得した地域情報が、ＳＮＳ投稿、気象情報やニュースであるとき、このＳＮＳ投稿に含まれる気候に関するキーワード、気象情報における気候に関するキーワード、ニュースに含まれる気候に関するキーワードを抽出し、この抽出したキーワードと類似した気候に関するキーワードを有する地域を、類似する地域特性を有する地域として特定する。また、取得した地域情報が診療情報であるとき、この診療情報に含まれる病状や病名に関するキーワードを抽出し、この抽出したキーワードと類似した病気に関するキーワードを有する地域を、類似する地域特性を有する地域として特定する。 For example, when the acquired area information is a population distribution for each age, the identification module 42 may include a population distribution for each age in which the population distribution for each age falls within a predetermined range, or a population distribution for each age. An area having the number of populations whose total sum of the population is within a predetermined range is specified as an area having similar area characteristics. When the acquired regional information is an SNS post, weather information, or news, a keyword related to climate included in the SNS post, a keyword related to climate in weather information, and a keyword related to climate included in news are extracted and extracted. A region having a keyword related to climate similar to the keyword is specified as a region having similar region characteristics. Further, when the acquired area information is medical information, a keyword relating to a medical condition or a disease name included in the medical information is extracted, and an area having a keyword relating to a disease similar to the extracted keyword is converted to an area having similar regional characteristics. To be specified.
　なお、特定モジュール４２は、上述した例を複数組み合わせて類似する地域特性を有する地域を特定してもよい。例えば、年齢別の人口構成と、過去に流行った病気との両者の条件を満たす地域を、類似する地域特性を有する地域として特定してもよい。また、その他の地域特性を組み合わせて、類似する地域特性を有する地域を特定してもよい。 The identification module 42 may identify an area having similar area characteristics by combining a plurality of the above-described examples. For example, an area that satisfies both the conditions of the age-specific population structure and the disease that has prevailed in the past may be specified as an area having similar area characteristics. Further, a region having a similar region characteristic may be specified by combining other region characteristics.
　取得モジュール２０は、この特定した地域における商品の取扱状況を取得する（ステップＳ２４）。ステップＳ２４において、取扱状況とは、実際に販売が行われた商品の項目とこの商品の取扱数量である。取得モジュール２０は、この特定した地域における商品の取扱状況を、この特定した地域における販売ストアを管理するコンピュータから取得する。 The acquisition module 20 acquires the handling status of the product in the specified area (Step S24). In step S <b> 24, the handling status is the item of the product that was actually sold and the handling amount of the product. The acquisition module 20 acquires the handling status of the product in the specified area from the computer that manages the sales store in the specified area.
　なお、取得モジュール２０は、この特定した地域における商品の取扱状況をその他の方法により取得してもよい。例えば、各種データベースや各種ウェブサイトを参照し、この特定した地域における商品の取扱状況を取得してもよい。 The acquisition module 20 may acquire the handling status of the product in the specified area by another method. For example, by referring to various databases and various websites, the handling status of the product in the specified area may be acquired.
　予測モジュール４１は、上述した地域情報に加えて、取得した類似する地域特性を有する地域における商品の取扱状況に基づいて、販売ストアにて在庫すべき商品の項目と、この商品の在庫必要量とを予測する（ステップＳ２５）。ステップＳ２５において、予測モジュール４１は、上述したステップＳ１３の処理による販売ストアにて在庫すべき商品の項目と、この商品の在庫必要量とを予測に際して、さらに、この取得した商品の取扱状況を加味して、販売ストアにて在庫すべき商品の項目と、この商品の在庫必要量とを予測する。 The prediction module 41, in addition to the above-described area information, based on the obtained product handling status in a region having similar regional characteristics, the item of the product to be stocked at the sales store, the necessary inventory amount of this product, Is predicted (step S25). In step S25, the prediction module 41 predicts the item of the product to be stocked at the sales store and the necessary stock amount of the product in the process of step S13 described above, and further takes into account the handling status of the obtained product. Then, the item of the product to be stocked at the sales store and the necessary stock amount of this product are predicted.
　一例として、地域情報が、診療情報である場合について説明する。予測モジュール４１は、上述したステップＳ１３の処理において、在庫すべき商品の項目として、薬品Ｄを特定し、この薬品Ｄの在庫必要量として、１８個を予測している。ここで、予測モジュール４１は、類似する地域特性を有する地域におけるこの薬品Ｄの取扱状況が、１５個である場合、地域情報に基づいた予測結果と、類似する地域特性を有する地域におけるこの商品の取扱状況との平均値を、在庫すべき商品の在庫必要量と予測する。平均値とすることにより、一方の情報に基づいた予測結果とするよりもより正確な在庫必要量を予測できることが期待可能である。このとき、年齢毎における商品の取扱状況を取得し、予測時点における年齢毎における在庫すべき商品の在庫必要量と、年齢毎における商品の取扱状況との其々の平均値を算出し、この平均値の総和を、在庫すべき商品の在庫必要量と予測することも可能である。 場合 As an example, a case where the regional information is medical treatment information will be described. In the processing of step S13 described above, the prediction module 41 specifies the medicine D as the item of the commodity to be stocked, and predicts 18 pieces of the necessary stock of the medicine D as the stock. Here, when the handling status of the medicine D in the region having the similar regional characteristics is 15, the prediction module 41 determines the prediction result based on the regional information and the product of the product in the region having the similar regional characteristics. The average value with the handling status is predicted as the necessary inventory amount of the product to be inventoried. By using the average value, it can be expected that the required inventory amount can be more accurately predicted than a prediction result based on one information. At this time, the handling status of the product for each age is obtained, and the required inventory amount of the product to be stocked for each age at the forecast time and the average value of the handling status of the product for each age are calculated. It is also possible to predict the sum of the values as the required inventory of the goods to be inventoried.
　なお、予測モジュール４１は、上述した平均値に限らず、その他の数値を予測してもよい。例えば、地域情報に基づいた予測結果と、類似する地域特性を有する地域におけるこの商品の取扱状況との間に所定の閾値以上のずれが存在していた場合、地域情報に基づいた予測結果を優先し、この予測結果に基づいて、在庫すべき商品の在庫必要量と予測してもよい。また、平均値ではなく、類似する地域特性を有する地域におけるこの商品の取扱状況に応じて所定の係数を設定し、この係数に基づいて、地域情報に基づいた予測結果を補正する構成であってもよい。 予 測 Note that the prediction module 41 is not limited to the above-described average value, and may predict other numerical values. For example, if there is a difference equal to or greater than a predetermined threshold between the prediction result based on the regional information and the handling status of this product in a region having similar regional characteristics, the prediction result based on the regional information is prioritized. Then, based on the result of the prediction, it may be predicted that the required quantity of the product should be stored. Further, a configuration is adopted in which a predetermined coefficient is set according to the handling situation of this product in an area having similar area characteristics, not an average value, and a prediction result based on area information is corrected based on the coefficient. Is also good.
　予測モジュール４１は、地域情報が、上述した他の例であっても、上述した診療情報の場合と同様に、在庫すべき商品の項目とこの商品の在庫必要量との予測結果に、類似する地域特性を有する地域におけるこの商品の取扱状況を加味することにより、在庫すべき商品の項目とこの商品の在庫必要量と予測する。 The prediction module 41 is similar to the prediction result of the item of the product to be stocked and the required inventory amount of this product, as in the case of the medical information described above, even if the regional information is the other example described above. By taking into account the handling status of this product in the region having the regional characteristics, the items of the product to be stocked and the necessary inventory amount of this product are predicted.
　すなわち、予測モジュール４１は、地域情報に基づいて予測した商品の項目と在庫必要量とを、類似する地域特性を有する地域における商品の取扱状況に基づいて補正することにより、在庫すべき商品の項目とこの商品の在庫必要量とを予測する。加えて、コンピュータ１０は、販売ストアの所在地と類似した地域特性を有した他の販売ストアにおける販売実績を参照し、この販売ストアでの販売予測を行う。 That is, the prediction module 41 corrects the item of the product and the required inventory amount predicted based on the region information based on the handling status of the product in a region having similar region characteristics, thereby obtaining the item of the product to be stocked. And the inventory requirement for this product. In addition, the computer 10 refers to the sales results in another sales store having a regional characteristic similar to the location of the sales store, and performs sales prediction in this sales store.
　通知モジュール２１は、予測した在庫すべき商品の項目と、この商品の在庫必要量とを、この商品を販売する業者が所持する業者端末に通知する（ステップＳ２６）。ステップＳ２６の処理は、上述したステップＳ１４の処理と同様である。 (4) The notification module 21 notifies the trader terminal owned by the trader who sells the product of the predicted item of the product to be stocked and the required inventory amount of the product (step S26). The process in step S26 is the same as the process in step S14 described above.
　以上が、第二販売処理である。 The above is the second sales process.
　図５に基づいて、販売システム１が実行する学習処理について説明する。図５は、コンピュータ１０が実行する学習処理のフローチャートを示す図である。上述した各モジュールが実行する処理について本処理に併せて説明する。 The learning process performed by the sales system 1 will be described with reference to FIG. FIG. 5 is a diagram illustrating a flowchart of the learning process executed by the computer 10. The processing executed by each module described above will be described together with this processing.
　学習モジュール４３は、過去の所定の期間又は同日における予測した在庫すべき商品の項目とこの商品の在庫必要量とを学習する（ステップＳ３０）。ステップＳ３０において、学習モジュール４３は、例えば、過去１か月や、過去一週間や、過去の同日において、上述した第一販売処理や第二販売処理において予測した商品の項目とこの商品の在庫必要量を学習する。 The learning module 43 learns the predicted items to be stocked in the past predetermined period or the same day and the necessary stock amount of the products (step S30). In step S30, the learning module 43 determines, for example, in the past month, the past week, or the same day in the past, the item of the product predicted in the first sales process or the second sales process described above and the inventory of this product. Learn the amount.
　記憶モジュール３０は、学習結果を記憶する（ステップＳ３１）。ステップＳ３１において、記憶モジュール３０は、学習した日付と、学習結果とを対応付けて記憶する。 (4) The storage module 30 stores the learning result (Step S31). In step S31, the storage module 30 stores the learned date and the learning result in association with each other.
　予測モジュール４１は、上述した第一販売処理や第二販売処理において、この学習結果を加味したうえで、在庫すべき商品の項目と、この商品の在庫必要量とを予測する（ステップＳ３２）。第一販売処理を例として、この処理を説明する。ステップＳ３２において、予測モジュール４１は、取得した地域情報に基づいて予測した在庫すべき商品の項目と、この商品の在庫必要量とに、学習した結果を加味して、販売ストアにて在庫すべき商品の項目と、この商品の在庫必要量とを予測する。 In the first sales processing and the second sales processing described above, the prediction module 41 predicts an item of a product to be stocked and a necessary stock amount of the product after taking the learning result into consideration (step S32). This processing will be described using the first sales processing as an example. In step S32, the prediction module 41 should stock the item in the sales store in consideration of the learning result, in addition to the item of the product to be stocked, which is predicted based on the acquired area information, and the necessary stock amount of the product. The item of the product and the required inventory of the product are predicted.
　一例として、第一販売処理を例として、地域情報が、診療情報である場合について説明する。予測モジュール４１は、上述したステップＳ１３の処理において、在庫すべき商品の項目として、薬品Ｄを特定し、この薬品Ｄの在庫必要量として、１８個を予測している。ここで、予測モジュール４１は、学習結果として、過去のこの時期における薬品Ｄの在庫必要量が２０個である場合、地域情報に基づいた予測結果と、学習結果とのの平均値を、在庫すべき商品の在庫必要量と予測する。平均値とすることにより、一方の情報に基づいた予測結果とするよりもより正確な在庫必要量を予測できることが期待可能である。 場合 As an example, a case where the regional information is medical treatment information will be described using the first sales processing as an example. In the processing of step S13 described above, the prediction module 41 specifies the medicine D as the item of the commodity to be stocked, and predicts 18 pieces of the necessary stock of the medicine D as the stock. Here, when the required inventory amount of the medicine D at this time in the past is 20 as the learning result, the prediction module 41 stores the average value of the prediction result based on the regional information and the learning result in inventory. Predict the required inventory of goods. By using the average value, it can be expected that the required inventory amount can be more accurately predicted than a prediction result based on one information.
　なお、予測モジュール４１は、上述した平均値に限らず、その他の数値を予測してもよい。例えば、地域情報に基づいた予測結果と、学習結果との間に所定の閾値以上のずれが存在していた場合、地域情報に基づいた予測結果を優先し、この予測結果に基づいて、在庫すべき商品の在庫必要量と予測してもよい。また、平均値ではなく、学習結果に応じて所定の係数を設定し、この係数に基づいて、地域情報に基づいた予測結果を補正する構成であってもよい。 予 測 Note that the prediction module 41 is not limited to the above-described average value, and may predict other numerical values. For example, if there is a difference equal to or greater than a predetermined threshold between the prediction result based on the region information and the learning result, the prediction result based on the region information is prioritized and the inventory is determined based on the prediction result. It may be estimated as the necessary inventory amount of the product to be manufactured. Further, a configuration may be adopted in which a predetermined coefficient is set according to the learning result instead of the average value, and the prediction result based on the area information is corrected based on the coefficient.
　予測モジュール４１は、地域情報が、上述した他の例であっても、上述した診療情報の場合と同様に、在庫すべき商品の項目とこの商品の在庫必要量との予測結果に、学習結果を加味することにより、在庫すべき商品の項目とこの商品の在庫必要量と予測する。 Even if the area information is the other example described above, the prediction module 41 adds the learning result to the prediction result of the item of the product to be stocked and the necessary inventory amount of this product, similarly to the case of the medical information described above. Is added, the item of the commodity to be inventoried and the necessary inventory amount of this commodity are predicted.
　すなわち、予測モジュール４１は、地域情報に基づいて予測した商品の項目と在庫必要量とを、学習結果に基づいて補正することにより、在庫すべき商品の項目とこの商品の在庫必要量とを予測する That is, the prediction module 41 corrects the item of the product and the required inventory amount predicted based on the regional information based on the learning result, thereby predicting the item of the product to be inventoried and the required inventory amount of the product. Do
　また、別の一例として、第二販売処理を例として、地域情報が、診療情報である場合について説明する。予測モジュール４１は、上述したステップＳ２５の処理において、在庫すべき商品の項目として、薬品Ｄを特定し、この薬品Ｄの在庫必要量として、１８個を予測し、類似する地域特性を有する地域におけるこの薬品Ｄの取扱状況が、１５個である。ここで、予測モジュール４１は、学習結果として、過去のこの時期における薬品Ｄの在庫必要量が２０個である場合、地域情報に基づいた予測結果と、類似する地域特性を有する地域におけるこの商品の取扱状況との平均値と、学習結果との平均値を、在庫すべき商品の在庫必要量と予測する。平均値とすることにより、地域情報及び類似した地域特性を有する商品の取扱状況に基づいた予測結果とするよりもより正確な在庫必要量を予測できることが期待可能である。 As another example, a case where the regional information is medical treatment information will be described using the second sales processing as an example. In the processing of step S25 described above, the prediction module 41 specifies the medicine D as an item of the commodity to be inventoried, predicts 18 medicines as the necessary inventory amount of the medicine D, and predicts 18 medicines in an area having similar regional characteristics. The handling status of this medicine D is 15. Here, if the inventory requirement amount of the medicine D at this time in the past is 20 as the learning result, the prediction module 41 determines that the prediction result based on the region information and the prediction result based on the region information indicate that this product in the region having similar region characteristics is obtained. The average value of the handling status and the average value of the learning result are predicted as the required inventory amount of the product to be inventoried. By using the average value, it can be expected that the required inventory amount can be more accurately predicted than a prediction result based on the regional information and the handling status of products having similar regional characteristics.
　なお、予測モジュール４１は、上述した平均値に限らず、その他の数値を予測してもよい。例えば、地域情報に基づいた予測結果と、類似する地域特性を有する地域におけるこの商品の取扱状況との平均値と、学習結果との間に所定の閾値以上のずれが存在していた場合、地域情報と類似する地域特性を有する地域におけるこの商品の取扱状況に基づいた予測結果を優先し、この予測結果に基づいて、在庫すべき商品の在庫必要量と予測してもよい。また、平均値ではなく、学習結果に応じて所定の係数を設定し、この係数に基づいて、地域情報と類似する地域特性を有する地域におけるこの商品の取扱状況とに基づいた予測結果を補正する構成であってもよい。 予 測 Note that the prediction module 41 is not limited to the above-described average value, and may predict other numerical values. For example, if there is a difference equal to or more than a predetermined threshold between the prediction result based on the regional information, the average value of the handling status of this product in a region having similar regional characteristics, and the learning result, A prediction result based on the handling situation of the product in a region having a region characteristic similar to the information may be prioritized, and the necessary inventory amount of the product to be stocked may be predicted based on the prediction result. Also, a predetermined coefficient is set according to the learning result instead of the average value, and based on the coefficient, the prediction result based on the area information and the handling situation of this product in a region having a similar regional characteristic is corrected. It may be a configuration.
　予測モジュール４１は、地域情報が、上述した他の例であっても、上述した診療情報の場合と同様に、在庫すべき商品の項目とこの商品の在庫必要量との予測結果と類似する地域特性を有する地域におけるこの商品の取扱状況とに、学習結果を加味することにより、在庫すべき商品の項目とこの商品の在庫必要量と予測する。 Even if the area information is the other example described above, the prediction module 41 determines the area similar to the prediction result of the item of the product to be stocked and the necessary inventory amount of this product, similarly to the case of the medical information described above. By adding the learning result to the handling situation of the product in the region having the characteristic, the items of the product to be stocked and the necessary stock amount of the product are predicted.
　すなわち、予測モジュール４１は、地域情報に基づいて予測した商品の項目と在庫必要量と類似する地域特性を有する地域における商品の取扱状況とによる予測を、学習結果に基づいて補正することにより、在庫すべき商品の項目とこの商品の在庫必要量とを予測する。 In other words, the prediction module 41 corrects, based on the learning result, the prediction based on the item of the product predicted based on the region information and the handling status of the product in a region having a region characteristic similar to the required inventory amount, based on the learning result. The item of the product to be performed and the required inventory of the product are predicted.
　通知モジュール２１は、予測した在庫すべき商品の項目と、この商品の在庫必要量とを、この商品を販売する業者が所持する業者端末に通知する（ステップＳ３３）。ステップＳ３３の処理は、上述したステップＳ１４の処理と同様である。 (4) The notification module 21 notifies the trader terminal owned by the trader who sells the product of the predicted item of the product to be stocked and the necessary inventory amount of the product (step S33). The processing in step S33 is the same as the processing in step S14 described above.
　［提案処理］
　図６に基づいて、販売システム１が実行する提案処理について説明する。図６は、コンピュータ１０が実行する提案処理のフローチャートを示す図である。上述した各モジュールが実行する処理について、本処理に併せて説明する。 [Proposal processing]
The proposal process executed by the sales system 1 will be described with reference to FIG. FIG. 6 is a diagram illustrating a flowchart of the suggestion processing executed by the computer 10. The processing executed by each module described above will be described together with this processing.
　評価受付モジュール２２は、第一販売処理、第二販売処理又は学習処理において予測した商品の項目について、この商品の提供を受けた使用者からの評価を取得する（ステップＳ４０）。ステップＳ４０において、評価モジュール２２は、例えば、この使用者が所持する使用者端末から専用のアプリケーションやウェブサイト等を介して、この商品についての評価（例えば、良かったか悪かったか等のテキスト、数字や記号）を受け付ける。 (4) The evaluation receiving module 22 obtains, from the user who has been provided with the product, the evaluation of the item of the product predicted in the first sales process, the second sales process, or the learning process (Step S40). In step S40, the evaluation module 22 evaluates the product (for example, texts such as good or bad, numbers, etc.) from a user terminal owned by the user via a dedicated application, a website, or the like. Symbol).
　評価判定モジュール４４は、この受け付けた評価が所定の閾値以下であるか否かを判定する（ステップＳ４１）。ステップＳ４１において、評価判定モジュール４４は、受け付けた評価が所定の数以上存在する状態で、かつこの評価が所定の閾値以下（低評価であることを意味する）であるか否かを判断する。評価判定モジュール４４は、所定の閾値以下ではないと判断した場合（ステップＳ４１　ＮＯ）、本処理を終了する。 The evaluation determination module 44 determines whether the received evaluation is equal to or smaller than a predetermined threshold (Step S41). In step S41, the evaluation determination module 44 determines whether or not the received evaluations are equal to or more than a predetermined number and whether the evaluations are equal to or lower than a predetermined threshold (meaning that the evaluations are low). When the evaluation determination module 44 determines that the difference is not equal to or smaller than the predetermined threshold (step S41: NO), the present processing ends.
　一方、ステップＳ４１において、評価判定モジュール４４は、所定の閾値以下であると判断した場合（ステップＳ４１　ＹＥＳ）、代替商品モジュール４５は、この商品と類似したもので他の商品を代替商品案として作成する（ステップＳ４２）。代替商品モジュール４５は、取得モジュール２０が取得した地域情報（例えば、新規に発売された薬品の試験結果や実際に処方された結果）に基づいて、この代替商品案を作成する。 On the other hand, in step S41, when the evaluation determination module 44 determines that the value is equal to or less than the predetermined threshold value (step S41 YES), the substitute product module 45 creates another product similar to this product as a substitute product plan. (Step S42). The alternative product module 45 creates this alternative product plan based on the regional information acquired by the acquisition module 20 (for example, a test result of a newly released drug or a result of an actual prescription).
　提案モジュール２３は、作成した代替商品案を、販売ストアの管理者が所有する管理者端末に提案する（ステップＳ４３）。ステップＳ４３において、提案モジュール２３は、この管理者端末に、商品の項目から低評価のものを除外させる通知、この低評価と類似した代替商品の提案する通知を表示させる。 (4) The proposal module 23 proposes the created alternative product plan to the manager terminal owned by the manager of the sales store (step S43). In step S43, the suggestion module 23 causes the manager terminal to display a notification for excluding items with low evaluations from the item of the item, and a notification for proposing an alternative item similar to the low evaluation.
　以上が、提案処理である。 The above is the proposal process.
　上述した手段、機能は、コンピュータ（ＣＰＵ、情報処理装置、各種端末を含む）が、所定のプログラムを読み込んで、実行することによって実現される。プログラムは、例えば、コンピュータからネットワーク経由で提供される（ＳａａＳ：ソフトウェア・アズ・ア・サービス）形態で提供される。また、プログラムは、例えば、フレキシブルディスク、ＣＤ（ＣＤ－ＲＯＭなど）、ＤＶＤ（ＤＶＤ－ＲＯＭ、ＤＶＤ－ＲＡＭなど）等のコンピュータ読取可能な記録媒体に記録された形態で提供される。この場合、コンピュータはその記録媒体からプログラムを読み取って内部記録装置又は外部記録装置に転送し記録して実行する。また、そのプログラムを、例えば、磁気ディスク、光ディスク、光磁気ディスク等の記録装置（記録媒体）に予め記録しておき、その記録装置から通信回線を介してコンピュータに提供するようにしてもよい。 The means and functions described above are implemented when a computer (including a CPU, an information processing device, and various terminals) reads and executes a predetermined program. The program is provided, for example, in the form of being provided from a computer via a network (SaaS: Software as a Service). The program is provided in a form recorded on a computer-readable recording medium such as a flexible disk, a CD (eg, a CD-ROM), and a DVD (eg, a DVD-ROM, a DVD-RAM). In this case, the computer reads the program from the recording medium, transfers the program to an internal recording device or an external recording device, records the program, and executes the program. In addition, the program may be recorded in advance on a recording device (recording medium) such as a magnetic disk, an optical disk, or a magneto-optical disk, and may be provided to the computer from the recording device via a communication line.
　以上、本発明の実施形態について説明したが、本発明は上述したこれらの実施形態に限るものではない。また、本発明の実施形態に記載された効果は、本発明から生じる最も好適な効果を列挙したに過ぎず、本発明による効果は、本発明の実施形態に記載されたものに限定されるものではない。 Although the embodiments of the present invention have been described above, the present invention is not limited to these embodiments. In addition, the effects described in the embodiments of the present invention merely enumerate the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. is not.
　１　販売システム、１０　コンピュータ {1} Sales system, 10} Computer

Claims (8)

  1. 　販売ストア周辺の地域情報を取得する取得手段と、
    　前記地域情報に基づいて、前記販売ストアにて在庫すべき商品の項目と、その在庫必要量とを予測する予測手段と、
    　を備えることを特徴とするコンピュータシステム。     Acquisition means for acquiring regional information around the sales store;
    A prediction unit for predicting an item of a product to be inventoried in the sales store and a necessary inventory amount based on the regional information;
    A computer system comprising:
  2. 　予測した前記在庫すべき商品の項目と前記在庫必要量とを、その商品を販売する業者に通知する通知手段と、
    　をさらに備えることを特徴とする請求項１に記載のコンピュータシステム。     Notifying means for notifying the seller of the product of the predicted item of the product to be stocked and the required amount of the stock,
    The computer system according to claim 1, further comprising:
  3. 　前記地域情報とは、前記ストア周辺の地域の年齢毎の人口分布、当該地域のＳＮＳ情報、当該地域のニュース、当該地域の診療情報又は当該地域の気象情報のうち少なくとも一つであって、
    　前記予測手段は、前記地域情報に基づいて、前記在庫すべき商品の項目と前記在庫必要量とを予測する、
    　ことを特徴とする請求項１に記載のコンピュータシステム。     The regional information is at least one of population distribution by age of the area around the store, SNS information of the area, news of the area, medical information of the area, or weather information of the area,
    The prediction unit predicts the item of the product to be stocked and the necessary stock amount based on the region information,
    The computer system according to claim 1, wherein:
  4. 　前記診療情報は、予約している患者の病状であって、
    　前記予測手段は、前記予約している患者の数に基づいて、前記在庫すべき商品の項目と前記在庫必要量とを予測する、
    　ことを特徴とする請求項３に記載のコンピュータシステム。     The medical treatment information is a medical condition of a patient who has made a reservation,
    The predicting unit predicts the item of the product to be stocked and the stock required amount based on the number of reserved patients.
    The computer system according to claim 3, wherein:
  5. 　前記取得手段は、前記地域情報と類似した地域特性を有する地域における商品の取扱状況を取得し
    　前記予測手段は、取得した前記商品の取扱状況に基づいて、前記在庫すべき商品の項目と前記在庫必要量とを予測する、
    　ことを特徴とする請求項１に記載のコンピュータシステム。     The obtaining means obtains a product handling status in a region having a local characteristic similar to the regional information, and the predicting device obtains the item of the product to be stocked and the inventory Predict the required amount,
    The computer system according to claim 1, wherein:
  6. 　前記地域特性は、人口数、年齢別の人口構成、気候又は過去に流行った病気のうち少なくとも一つである、
    　ことを特徴とする請求項５に記載のコンピュータシステム。     The regional characteristics are at least one of population number, age-specific population composition, climate, or a disease that has been prevalent in the past,
    The computer system according to claim 5, wherein:
  7. 　コンピュータシステムが実行する販売方法であって、
    　販売ストア周辺の地域情報を取得するステップと、
    　前記地域情報に基づいて、前記販売ストアにて在庫すべき商品の項目と、その在庫必要量とを予測ステップと、
    　を備えることを特徴とする販売方法。     A selling method performed by a computer system,
    Obtaining local information around the sales store;
    Based on the regional information, a step of predicting an item of a product to be stocked in the sales store and a necessary stock amount thereof,
    A selling method comprising:
  8. 　コンピュータシステムに、
    　販売ストア周辺の地域情報を取得するステップ、
    　前記地域情報に基づいて、前記販売ストアにて在庫すべき商品の項目と、その在庫必要量とを予測するステップ、
    　を実行させるためのコンピュータ読み取り可能なプログラム。     For computer systems,
    Steps to get local information around the sales store,
    Estimating, based on the regional information, items of goods to be stocked at the sales store and the necessary stock amount;
    Computer-readable program for executing
PCT/JP2018/028747 2018-07-31 2018-07-31 Computer system, marketing method, and program WO2020026359A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/028747 WO2020026359A1 (en) 2018-07-31 2018-07-31 Computer system, marketing method, and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2018/028747 WO2020026359A1 (en) 2018-07-31 2018-07-31 Computer system, marketing method, and program

Publications (1)

Publication Number Publication Date
WO2020026359A1 true WO2020026359A1 (en) 2020-02-06

Family

ID=69231590

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/028747 WO2020026359A1 (en) 2018-07-31 2018-07-31 Computer system, marketing method, and program

Country Status (1)

Country Link
WO (1) WO2020026359A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115994788A (en) * 2023-03-20 2023-04-21 北京永辉科技有限公司 Data processing analysis method and device

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002140592A (en) * 2000-10-30 2002-05-17 Nippon Medical School Medical care support system using network
JP2004310556A (en) * 2003-04-08 2004-11-04 Aos:Kk Sales support system, program and method
JP2004326411A (en) * 2003-04-24 2004-11-18 Life Business Weather:Kk Power demand forecasting device and system
JP2005539330A (en) * 2002-09-18 2005-12-22 ミツイ ブッサン ロジスティックス，インコーポレイテッド Delivery chain management system and method
JP2016024542A (en) * 2014-07-17 2016-02-08 オリンパス株式会社 Medical treatment support device
JP2017027434A (en) * 2015-07-24 2017-02-02 トヨタホーム株式会社 Air conditioning apparatus selection assist system
JP2018036969A (en) * 2016-09-01 2018-03-08 株式会社博伸社 Outlet exploitation support system

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002140592A (en) * 2000-10-30 2002-05-17 Nippon Medical School Medical care support system using network
JP2005539330A (en) * 2002-09-18 2005-12-22 ミツイ ブッサン ロジスティックス，インコーポレイテッド Delivery chain management system and method
JP2004310556A (en) * 2003-04-08 2004-11-04 Aos:Kk Sales support system, program and method
JP2004326411A (en) * 2003-04-24 2004-11-18 Life Business Weather:Kk Power demand forecasting device and system
JP2016024542A (en) * 2014-07-17 2016-02-08 オリンパス株式会社 Medical treatment support device
JP2017027434A (en) * 2015-07-24 2017-02-02 トヨタホーム株式会社 Air conditioning apparatus selection assist system
JP2018036969A (en) * 2016-09-01 2018-03-08 株式会社博伸社 Outlet exploitation support system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115994788A (en) * 2023-03-20 2023-04-21 北京永辉科技有限公司 Data processing analysis method and device

Similar Documents

Publication Publication Date Title
Luo et al. The impact of platform protection insurance on buyers and sellers in the sharing economy: A natural experiment
Dhar et al. The effect of forced choice on choice
Raman et al. Execution: The missing link in retail operations
Folkes et al. Buyers' and sellers' explanations for product failure: Who done it?
Bolton et al. Price-based global market segmentation for services
Che et al. Investigating effects of out-of-stock on consumer stockkeeping unit choice
US20120253828A1 (en) System and method for sensitivity or nutritional factor exposure monitoring
US20130254120A1 (en) Recall Exchange Platform
Siu et al. Service quality in grocery retailing: The study of a Japanese supermarket in Hong Kong
US20090319331A1 (en) Methods and apparatus to respond to recalls
Patel et al. Determining patient preferences of community pharmacy attributes: a systematic review
JP2018139036A (en) Analysis device
JP2021056643A (en) Information processor, information processing method and information processing system
Leuschner et al. Establishing logistics service strategies that increase sales
WO2015159409A1 (en) Information delivery device and information delivery method
Lim et al. Do it right the first time: Vehicle routing with home delivery attempt predictors
JP3667726B2 (en) Sales management apparatus and method
Herbig et al. Design guidelines for assistance systems supporting sustainable purchase decisions
Coleman et al. Access to allergen-free food among Black and White children with food allergy in the FORWARD study
CN111083211A (en) User touch method and system based on big data platform
WO2020026359A1 (en) Computer system, marketing method, and program
Bendall‐Lyon et al. The influence of mass communication and time on satisfaction and loyalty
JP2010157122A (en) Sample merchandise questionnaire management system
Zhuo Do low‐price guarantees guarantee low prices? Evidence from competition between Amazon and Big‐Box stores
US20220138683A1 (en) Property Inventory Tracking

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18928984

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18928984

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP