JP7122768B2 - Goods purchase timing suggestion program - Google Patents

Description

The present invention relates to an article purchase timing proposal program for proposing an article to be purchased and the timing of purchasing the article.

2. Description of the Related Art Conventionally, stationery, office equipment, and personal computers necessary for offices have been appropriately purchased by each company according to their internal needs. In the manufacturing industry, purchasing of machinery and equipment necessary for manufacturing is also considered as necessary. Furthermore, in the case of a trading company, purchases of articles to be the subject of commercial transactions are made as appropriate.

The prices of such goods to be purchased often change according to market conditions, economic conditions, various events, natural disasters, climate, social conditions, international conditions, and the like. On the purchasing side, we want to purchase products with excellent performance and functions at the lowest possible price. Also, if you are a trading company, you can secure more profit by selling goods at a high price that you purchased as cheaply as possible. It is common not only for trading companies but also for resale by shops and individuals to purchase based on the same idea.

However, in order to purchase goods at a lower price, it is necessary to ascertain market conditions, economic conditions, various events, natural disasters, climate, social conditions, international conditions, etc., and to determine the appropriate timing. there were.

SUMMARY OF THE INVENTION Accordingly, the present invention has been devised in view of the above-described problems, and its object is to provide an article purchase timing proposal program capable of proposing an article to be purchased and an appropriate timing for purchasing the article. is to provide

In order to solve the above-described problems, a product purchase timing proposal program for proposing a timing for purchasing a product made up of stationery includes regional information about the region to which the purchaser who purchases the product belongs, interest rate , exchange rate, stock prices of each brand , precious metals, bitcoin, and information acquisition step of acquiring market information related to recent market conditions, including price movements of any one of them; A combination of reference regional information, reference market information related to past market conditions consisting of interest rates, exchange rates, stock prices of each issue , precious metals, or bitcoin price movements, and three or more levels of association with the purchase timing. and a proposing step of proposing a purchase timing based on the area information and the market information obtained in the information obtaining step.

Even without special skills or experience, it is possible to propose an article to be purchased and an appropriate timing for purchasing the article.

1 is a block diagram showing the overall configuration of a system to which the present invention is applied; FIG. It is a figure which shows the specific structural example of a search apparatus. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention.

Hereinafter, a product purchase timing proposal program to which the present invention is applied will be described in detail with reference to the drawings.

First Embodiment FIG. 1 is a block diagram showing the overall configuration of an article purchase timing proposal system 1 in which an article purchase timing proposal program to which the present invention is applied is installed. The article purchase timing proposal system 1 includes an information acquisition unit 9 , a search device 2 connected to the information acquisition unit 9 , and a database 3 connected to the search device 2 .

The information acquisition unit 9 is a device for a person using this system to input various commands and information. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an imaging device capable of capturing an image, such as a camera. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper document. Moreover, the information acquisition part 9 may be integrated with the searching device 2 which will be described later. The information acquisition unit 9 outputs the detected information to the searching device 2 . Further, the information acquisition unit 9 may be configured by means for specifying position information by scanning map information. The information acquisition unit 9 also includes a temperature sensor, a humidity sensor, a flow rate sensor, and other sensors capable of specifying substances and physical properties. The information acquisition unit 9 may be configured by means for automatically retrieving character strings and data posted on sites on the Internet.

The database 3 accumulates various information necessary for proposing product purchase timing. Information necessary for proposing product purchase timing includes reference transaction information related to the past transaction status of each purchaser obtained in advance, reference market information related to the past market condition of each product, and Reference inventory information on the inventory status of each item, pre-obtained reference area information on the region to which each purchaser belongs, pre-obtained reference financial statement information obtained from the past financial statements of each purchaser, pre-obtained each Reference attribute information related to purchaser attributes, pre-acquired reference industry information related to the industry to which each purchaser belongs, pre-acquired reference external environment information related to the external environment of each purchaser, and purchases made by each purchaser A data set of the timing, or items purchased by each purchaser and the timing of the purchase is stored.

In other words, in addition to reference market information, the database 3 stores reference transaction information, reference inventory information, reference regional information, reference financial statement information, reference attribute information, reference industry information, and reference external environment information. and the purchase timing purchased by each purchaser, or the article purchased by each purchaser and the purchase timing thereof are associated with each other and stored.

The search device 2 is composed of an electronic device such as a personal computer (PC), for example, but in addition to the PC, it is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc. It may be one that is made into. A user can obtain a search solution by this search device 2 .

FIG. 2 shows a specific configuration example of the search device 2. As shown in FIG. This searching device 2 performs wired or wireless communication with a control unit 24 for controlling the entire searching device 2 and an operation unit 25 for inputting various control commands via operation buttons, keyboards, etc. A communication unit 26 for searching, an estimating unit 27 for making various judgments, and a storage unit 28, represented by a hard disk, for storing a program for performing a search to be executed are connected to the internal bus 21, respectively. . Further, the internal bus 21 is connected with a display unit 23 as a monitor for actually displaying information.

The controller 24 is a so-called central control unit for controlling each component implemented in the search device 2 by transmitting control signals via the internal bus 21 . In addition, the control unit 24 transmits commands for various controls through the internal bus 21 according to operations through the operation unit 25 .

The operation unit 25 is embodied by a keyboard or a touch panel, and a user inputs an execution command for executing a program. The operation unit 25 notifies the control unit 24 when the execution command is input by the user. Upon receiving this notification, the control unit 24 cooperates with each component including the estimation unit 27 to execute desired processing operations. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The estimation unit 27 estimates a search solution. The estimation unit 27 reads various information stored in the storage unit 28 and various information stored in the database 3 as necessary information in executing the estimation operation. This estimation unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

The display unit 23 is composed of a graphic controller that creates a display image based on control by the control unit 24 . The display unit 23 is implemented by, for example, a liquid crystal display (LCD).

When the storage unit 28 is configured with a hard disk, predetermined information is written to each address based on the control by the control unit 24, and this information is read as necessary. The storage unit 28 also stores a program for executing the present invention. This program is read and executed by the control unit 24 .

The operation of the product purchase timing proposal system 1 having the above configuration will be described.

The product purchase timing proposal system 1 is premised on the formation of a combination of reference market information and reference transaction information, as shown in FIG. 3, for example.

Reference market information is various information about market conditions. The market conditions referred to here may target a single company, the entire industry including the company, the entire Japan, or the entire world, or may be market conditions at the level of individual goods. Examples of this reference market information include price movements of interest rates, exchange rates, stock prices of each brand, crude oil, futures, precious metals, bitcoins, etc., as well as price movements of individual commodities. The individual goods referred to here include any movable property that is the object of commercial transactions, and includes any movable property such as stationery, household goods, food, and clothing, as well as large articles such as automobiles and ships. In addition to personal computers and individual electronic components that make up them, furniture such as desks and chairs, and all other electrical products are also included in this article. This reference market condition information may be displayed as a time-series chart, a line graph, or the like for these targets. Further, information such as Bollinger band, MACD, moving average line, etc. may be attached. In addition, this market information may include the fundamental indicators of the company of each stock. Return on equity) and other indicators may be included. Information such as charts, Bollinger bands, MACD, moving averages, etc. showing price movements between currencies may also be attached to exchange rates. The reference market condition information may categorize the market potential itself.

Reference transaction information is any information relating to previous transactions with past borrowers. Whereas reference consumption behavior information is information that shows how money has actually been spent, this reference transaction information indicates how fair the actual purchase and sale was, It is an indication of the integrity and security of the counterparty and whether the firm has made a successful trade. The reference transaction information also includes the transaction amount and scale. This reference transaction information can be obtained from deposit/withdrawal and settlement data in a bank account at a financial institution. You can obtain deposit and withdrawal information from these. The transaction information for reference can be obtained from the quotation, the statement of delivery, and the invoice. For example, if the product is sold or purchased on an EC (electronic commerce) site, it can also be obtained from the EC site. In addition, the transaction information for reference may also reflect the content of the evaluation by the evaluator regarding the products and services actually traded through the EC site. The higher the evaluation content, the more legitimate and fair the consumption behavior and purchase can be considered. The reference transaction information may be extracted from information such as the quality of the deliverables, adherence to delivery deadlines, politeness of pre-transaction messages, and the like. Also, if there is a defect in the product delivered in the transaction made through the EC site, the defect may be extracted through writing on the EC site, and control may be performed to lower the evaluation content. The reference transaction information may reflect the presence or absence of fraudulent transactions determined from past order data. Fraudulent transactions are identified here by purchasing many low-priced products that can only be purchased once a day under different names, or by skillfully changing the address so that it cannot be identified as the same person. If so, it may be extracted through monitoring technology on the Internet. The sincerity and safety of the trading partner may be extracted from account deposit/withdrawal details, accounting data, websites, financial statements, and ledger information. When extracting this, we acquire and learn about higher risk trading partners in advance, and use machine learning to distinguish from these account deposit and withdrawal details, accounting data, websites, financial statements, etc. good too. In addition, if negotiations have been made with a trading partner in the past and the transaction history includes a paper document or electronic data of the document, reference transaction information may be extracted from the transaction history document. Also, if the individual is a self-employed person, the reference transaction information may be extracted from the main customer information described in the site or SNS launched for the self-employment. When this reference consumption behavior information is applied to the above-described reference information P34 to P36, for example, the reference information P34 can be obtained from the following: 4 points out of 5-level evaluation, reference information P35, business partner is △◆ company, purchased PC for 55,000 yen, EC site evaluation 2 points out of 5-level evaluation, etc.

In the example of FIG. 3, as input data, for example, reference market information P11 to P13, reference transaction information F to I, etc. are arranged. An intermediate node shown in FIG. 3 is obtained by combining reference market information as such input data with reference transaction information. Each intermediate node is also connected to an output. In this output, purchase timings are arranged as output solutions.

The purchase timing is information indicating when the item to be purchased was purchased. This purchase timing may be indicated, for example, in terms of days, years, months, and days in the Christian era, or may be indicated in units of weeks, months, or years. This purchase timing may be indicated, for example, in relation to the acquisition date or acquisition period of the above-described reference market information. For example, if the reference market information shows the price movement of goods during the acquisition period from December 1st to December 31st, the purchase timing is determined from the last day (December 31st) of the acquisition period. It may indicate whether or not the item was purchased after the passage of days.

Each combination (intermediate node) of the reference market information and the reference transaction information is associated with the purchase timing as the output solution through three or more degrees of association. The market condition information for reference and the transaction information for reference are arranged on the left side through the degree of association, and each purchase timing is arranged on the right side through the degree of association. The degree of relevance indicates the degree of relevance with which purchase timing the reference market information and the reference transaction information arranged on the left side are highly relevant. In other words, this degree of association is an index that indicates the high possibility that each reference market information and reference transaction information is associated with the purchase timing. It indicates accuracy in selecting a probable purchase timing. In the example of FIG. 3, w13 to w22 are shown as association degrees. These w13 to w22 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of correlation between each combination as an intermediate node and the purchase timing as an output. , conversely, the closer to one point, the lower the degree of correlation between each combination as an intermediate node and the purchase timing as an output.

The discriminating device 2 acquires in advance the degrees of association w13 to w22 of three or more stages shown in FIG. In other words, when proposing an actual purchase timing, the discriminating device 2 accumulates reference market information, reference transaction information, and data indicating which purchase timing was often adopted in that case. , and by analyzing these, the degree of association shown in FIG. 3 is created. For example, in the transaction history for reference, it is assumed that the company purchases lubricating oil for industrial machinery in bulk several times a year based on the data of deposits and withdrawals to and from the bank account of the financial institution and settlement data. From these data it can be determined that the company has a regular need for lubricants. If the market price of this lubricating oil fluctuates depending on the time of year, it will refer to past market conditions through the reference market condition data and propose the optimal purchase timing through the correlation.

When focusing on the same item, this purchase timing is set so that the degree of relevance w to the purchase timing of purchase at a lower price is set high, and the degree of relevance w to the purchase timing of purchase at a higher price is set to be low. can be

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference market information P11 and the reference transaction information F, past data is analyzed to determine at what purchase timing the price was low, and the degree of association is calculated accordingly. set. In the example of the intermediate node 61a linked in the case of the reference market information P11 and the reference transaction information H, the output of the purchase timing A and the purchase timing B is linked. The degree of relevance of w13, which leads to purchase timing A where the price was cheap, is set to 7 points, and the degree of relevance of w14, which leads to purchase timing B which is higher in price, is set to 2 points.

Further, the degree of association shown in FIG. 3 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

In the example of the degree of relevance shown in FIG. 3, the node 61b is a node that combines reference transaction information F with reference market information P11. is w16. The node 61c is a node that combines the reference market information P12 with the reference transaction information G, and the degree of relevance of the purchase timing B is w17 and the relevance of the purchase timing D is w18.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, when actually determining a new purchase timing from now on, the above-described learned data will be used to search for the purchase timing. In such a case, market information is newly acquired, and transaction information is acquired. Market information corresponds to reference market information, and transaction information corresponds to reference transaction information. The purchaser who newly acquires market information and transaction information does not necessarily have to be the same as the purchaser who previously acquired the above-mentioned reference market information and reference transaction information, and may be different from each other. .

Moreover, the purchaser may be an individual as well as a corporation. It may be a proposal of purchase timing when an individual purchases daily necessities for household use or food and drink at a supermarket.

Based on the newly acquired market information and transaction information, the purchase timing is searched. In such a case, reference is made to the degree of association shown in FIG. 3 (Table 1), which has been acquired in advance. For example, if the newly acquired market information is the same as or similar to P12, and if the acquired transaction information is the same as or similar to reference transaction information I, This node 61d is associated with purchase timing C at w19 and purchase timing D at w20. In such a case, purchase timing C with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the purchase timing D, which has a low degree of association but is recognized as having an association itself, may be selected as the optimum solution. In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

In this way, these optimal solutions are selected using the trained model shown in FIG. It can be realized through artificial intelligence. However, it is not essential to use artificial intelligence in the present invention, and it is possible to use a combination of reference market information, reference transaction information, and three or more levels of association with the purchase timing for the combination. It may be realized in any form.

Table 2 below shows examples of degrees of association w1 to w12 extending from the input.

Intermediate nodes 61 may be selected based on degrees of association w1 to w12 extending from this input. In other words, the greater the degree of association w1 to w12, the heavier the weight in selecting the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weighting in selecting the intermediate nodes 61 may all be the same.

Although the embodiment shown in FIG. 3 described above is an example in which the article to be purchased is determined, the present invention is not limited to this, and as shown in FIG. 4, the article to be purchased is not determined. In some cases, the item to be purchased may be proposed, and the purchase timing may be similarly proposed.

In such a case, a data set consisting of the goods to be purchased and the purchase timing is learned as an output for the degree of association between the reference market information and the reference transaction information described above. For this purchase timing, purchase timings A to E are acquired for each of the items α to ε. The goods needed by the company (individual) can be extracted from the reference transaction information, and the prices of individual goods can be extracted from the reference market information. By collecting data on which goods were purchased at what timing for these reference transaction information and reference market information, the degree of association shown in FIG. 4 described above can be formed. This degree of association reflects what kind of purchase timing should be made for each item.

Next, transaction information on the recent transaction status of the proposed purchaser and market information on the recent market status of each item are acquired. Then, using the degree of association shown in FIG. 4 and based on the newly acquired transaction information and market information, the product to be purchased and the timing of the purchase are proposed.

FIG. 5 shows an example in which three or more levels of correlation are set between combinations of reference market information and reference inventory information, and purchase timings for the combinations.

As input data, such reference market condition information and reference stock information are arranged side by side. An intermediate node shown in FIG. 5 is a combination of reference market information and reference stock information as such input data.

Reference inventory information is any information relating to the inventory status of purchased items within the enterprise. For example, if a part required for manufacturing is the article to be purchased, it can be obtained from the inventory data of the part. Instead of this inventory data, it is possible to check the number of goods received through the delivery note of the relevant parts, or count the number of parts used from there, and subtract this from the number of goods received to obtain the number of goods in stock. good. This reference inventory information may be determined, for example, from an image of a warehouse or the like in which articles to be purchased are arranged. Also, based on information such as IC tags affixed to the items and sensors installed in the warehouse where the items are lined up, it is determined whether or not the items remain in the warehouse. You may do so.

The discrimination device 2 acquires in advance the degrees of association w13 to w22 of three or more stages shown in FIG. That is, when proposing an actual purchase timing, the discriminating device 2 accumulates reference market information, reference inventory information, and data as to what the purchase timing was in that case, and analyzes them. , to create the degrees of association shown in FIG.

In the example of the degree of association shown in FIG. 5, node 61b is a node that combines reference stock information with stock information J for reference market condition information P11, and the degree of association of purchase timing C is w15, and purchase timing E is w16. When setting the degree of association, a higher degree of association may be set for a purchase timing at which the purchase was made at a lower price.

Similarly, when such a degree of association is set, market information is newly acquired, and stock information is also acquired. Market information corresponds to reference market information, and inventory information corresponds to reference inventory information. The acquisition method of the inventory information is the same as the acquisition method of the reference inventory information described above.

When searching for the purchase timing, the degree of association shown in FIG. 5 acquired in advance is referred to. For example, if the acquired market information is identical or similar to the reference market information P12 and the inventory information is identical or similar to the reference inventory information M, the combination is associated with a node 61c, and this node 61c is Purchase timing B is associated with a degree of association w17, and purchase timing D is associated with a degree of association w18. As a result of such degree of association, based on w17 and w18, the purchase timing in the case where the market information and inventory information are newly obtained is obtained.

In the above-described embodiment shown in FIG. 5, the item to be purchased is determined as an example, but the present invention is not limited to this. As shown in FIG. 6, the item to be purchased is not determined. In some cases, the item to be purchased may be proposed, and the purchase timing may be similarly proposed.

In such a case, a data set consisting of purchase target products and purchase timings is learned as an output for the degree of association between the reference market information and the reference inventory information described above. For this purchase timing, purchase timings A to E are acquired for each of the items α to ε. The goods required by the company (individual) can be extracted from the reference stock information, and the prices of individual goods can be extracted from the reference market information. By collecting data on which goods were purchased at what timing for these reference transaction information and reference inventory information, the degree of association shown in FIG. 6 described above can be formed.

Next, the stock information about the recent stock status of the proposed purchaser and the market information about the recent market conditions of each item are acquired. Then, using the degree of association shown in FIG. 6 and based on the newly acquired inventory information and market information, the product to be purchased and the timing of purchase thereof are proposed.

FIG. 7 shows an example in which three or more degrees of association are set between combinations of reference market information and reference regional information, and purchase timings for the combinations.

As the input data, such reference market information and reference area information are arranged side by side. An intermediate node shown in FIG. 7 is a combination of reference market information as input data and reference area information.

The reference area information is information about the area to which the individual or corporation to which the proposal belongs belongs. The area to which the individual belongs here includes not only the area of the current address, but also the area of the place of employment, the area of the previous address, and the place of birth. This reference area information may be a group such as the Kanto region, Tokyo, or the like, but may be subdivided at the municipality level, town name, and street address level. While there are such grouped and subdivided areas, business sentiment, events, accidents, incidents, disasters, epidemics, etc. in each segmented area are reflected as this reference area information. Since this reference industry information includes elements governed by the reference external environment information in the first embodiment, it may be configured by citing this reference external environment information. When applying this reference area information, for example, the reference area information J is for Chiyoda Ward, Tokyo, where the 〇〇 incident occurred, and the reference area information K is for Nara Prefecture, such as the business sentiment index 〇〇. .

The discrimination device 2 acquires in advance the degrees of association w13 to w22 of three or more stages shown in FIG. In other words, when proposing an actual purchase timing, the discriminating device 2 accumulates reference market information, reference regional information, and data on what the purchase timing was in that case, and analyzes these. , to create the degrees of association shown in FIG.

In the example of the degree of association shown in FIG. 7, node 61b is a node that combines regional information J as reference regional information with respect to reference market condition information P11. is w16. When setting the degree of association, a higher degree of association may be set for a purchase timing at which the purchase was made at a lower price.

Similarly, when such a degree of association is set, market information is newly acquired, and regional information is acquired. Market information corresponds to reference market information, and regional information corresponds to reference regional information. A method for obtaining the area information is the same as the method for obtaining the reference area information described above.

When searching for the purchase timing, the degree of association shown in FIG. 7 acquired in advance is referred to. For example, if the acquired market information is the same or similar to the reference market information P12 and the regional information is the same or similar to the reference regional information M, the combination is associated with the node 61c, and this node 61c is Purchase timing B is associated with a degree of association w17, and purchase timing D is associated with a degree of association w18. As a result of such a degree of association, based on w17 and w18, the purchase timing when the new market information and regional information are actually obtained is obtained.

In the above-described embodiment shown in FIG. 7, the item to be purchased is determined, but the present invention is not limited to this. As shown in FIG. 8, the item to be purchased is not determined. In some cases, the item to be purchased may be proposed, and the purchase timing may be similarly proposed.

In such a case, a data set consisting of products to be purchased and purchase timings is learned as an output for the degree of association between the above-described reference market information and reference regional information. For this purchase timing, purchase timings A to E are acquired for each of the items α to ε. The goods needed by the company (individual) can be extracted from the reference area information, and the prices of individual goods can be extracted from the reference market information. By collecting data on which goods were purchased at what timing with respect to these reference transaction information and reference area information, the degree of association shown in FIG. 8 described above can be formed.

Next, it acquires regional information about the area to which the proposed purchaser belongs and market information about the latest market conditions of each product. Then, using the degree of association shown in FIG. 8 and based on the newly acquired regional information and market information, the product to be purchased and the timing of purchase are proposed.

In addition, when the article to be purchased is not decided yet, when the article to be purchased is proposed and the purchase timing is also proposed, reference is made as shown in FIG. You may make use of financial statement information for An example of financial statement information for reference is data related to all financial statements, including the financial statements of companies that have provided their financial statements. Current Ratio, Current Liabilities, Equity Ratio Total capital, current profit, recurring profit growth rate, current recurring profit, previous recurring profit, sales, repayment capacity, debt redemption period, interest-bearing debt, working capital, cash flow, operating income, depreciation, etc. The financial information for reference may include, in addition to these financial statement figures, information such as whether the company is insolvent, the amount of borrowings from officers, the amount of inventories (inventory), and the like. These reference financial information may be for one year or for several years. The data on these financial statements may contain information on actual subcontractors, suppliers, etc. as book information. can.

In such a case, a data set consisting of products to be purchased and purchase timings is learned as an output for the degree of association between the reference market information and the reference financial statement information. For this purchase timing, purchase timings A to E are acquired for each of the items α to ε. The goods needed by the company (individual) can be extracted from reference financial statement information, and the prices of individual goods can be extracted from reference market information. By collecting data on which goods were purchased at what timing for these reference transaction information and reference financial statement information, the degree of association shown in FIG. 9 described above can be formed.

Next, the latest financial statement information of the proposed purchaser and market information on the latest market conditions of each product are obtained. Then, using the degree of association shown in FIG. 9 and based on the newly acquired financial statement information and market information, the product to be purchased and the timing of purchase are proposed.

In addition, when the article to be purchased has not been decided yet, when the article to be purchased is proposed and the purchase timing is also proposed, reference is made as shown in FIG. User attribute information may be used.

Examples of reference attribute information include all information relating to personal attributes if the proposal destination is an individual. Attribute information for reference includes age, health status, annual income, date of birth, place of birth, home environment (whether the wife is pregnant, a family member has a disability or illness, whether or not they live with grandparents, whether they live with their grandparents, etc.). Whether or not caregivers are at home, whether or not they have been affected by a disaster, the presence and degree of domestic violence and abuse, whether or not they are divorced, household income, whether or not they have public assistance, whether they have a wife and children, and their age composition, children school attendance status), if the child is in school, the tuition fees and future tuition fees, and whether the individual is currently looking for a job or working. Regarding the state of health, whether the individual is in perfect health, or whether or not he or she has any congenital disability and the degree of the disability, and whether or not the individual has acquired a disability after birth and the degree of the disability. Also, whether or not you suffered from any disease after birth, whether or not the disease continues and its degree, allergy status, inflammation status, injury status, chronic disease status, medications you are taking, etc. , including any information indicating health status. The health condition included in this reference attribute information may be derived from medical data such as heart rate, pulse rate, blood data, electrocardiogram data, and X-ray images. Any of these may be obtained through a report from each family, a submitted document, a doctor's certificate, or the like. When applying this reference attribute information to J to M described above, "age 46 years old, hometown: Shizuoka, annual income: 00,000 yen, work at XX company, family environment: wife, eldest son, eldest daughter, family of 4 , My eldest son is a high school student, my eldest daughter is a junior high school student, Health condition: I have had an operation for a stomach ulcer in the past.”, “Age 38, Hometown: Tokyo, Annual income: 〇 million yen, Work at 〇 company, Home environment: With my wife. The eldest daughter is a family of three, the eldest daughter is in elementary school, and her health is good.”

If the proposal destination is a legal entity, it is all information related to the attributes of the legal entity. The attributes here include the type of business, technical field, history, history, capital, scale, number of employees, years of establishment, etc., but are not limited to these, and include corporate culture, employee morale, It also includes the number of hires.

The data on these reference attribute information may contain information on the goods that the company actually wants to purchase, from which the goods that the company always needs to purchase can be extracted.

In such a case, a data set consisting of products to be purchased and purchase timing is learned as an output for the degree of association between the above-described reference market information and reference attribute information. For this purchase timing, purchase timings A to E are acquired for each of the items α to ε. The goods required by the company (individual) can be extracted from the reference attribute information, and the prices of individual goods can be extracted from the reference market information. By collecting data on which item was purchased at what timing with respect to the transaction information for reference and the attribute information for reference, the degree of association shown in FIG. 10 described above can be formed.

Next, the attribute information of the purchaser to whom the proposal is made and the market information regarding the latest market conditions of each item are acquired. Then, using the degree of association shown in FIG. 10 described above, and based on the newly acquired attribute information and market information, the article to be purchased and the purchase timing are proposed.

In addition, when the article to be purchased is not decided yet, when proposing the article to be purchased and also proposing the purchase timing, reference is made as shown in FIG. Industry information may be used.

An example of reference industry information is any information related to the industry to which the proposed entity belongs. Reference industry information includes the history of the industry, the position of the industry in the global environment, the growth potential of the industry, commercial practices, supply and demand relationships, KSF, KBF, the business model of the industry, the flow of money and goods, etc. is. The data on these reference industry information may contain information on the goods that the company actually wants to purchase, from which the goods that the company always needs to purchase can be extracted.

In such a case, a data set consisting of products to be purchased and purchase timings is learned as an output for the degree of association between the above-described reference market information and reference industry information. For this purchase timing, purchase timings A to E are acquired for each of the items α to ε. The goods required by the company (individual) can be extracted from the reference industry information, and the prices of individual goods can be extracted from the reference market information. By collecting data on which product was purchased at what timing with respect to these reference transaction information and reference industry information, the degree of association shown in FIG. 11 described above can be formed.

Next, the industry information of the purchaser to whom the proposal is made and the market information regarding the latest market conditions of each product are acquired. Then, using the degree of association shown in FIG. 11 and based on the newly acquired industry information and market information, the product to be purchased and the timing of the purchase are proposed.

In addition, when the article to be purchased is not decided yet, when proposing the article to be purchased and also proposing the purchase timing, reference is made as shown in FIG. Industry information may be used.

An example of reference industry information is any information related to the industry to which the proposed entity belongs. Reference industry information includes the history of the industry, the position of the industry in the global environment, the growth potential of the industry, commercial practices, supply and demand relationships, KSF, KBF, the business model of the industry, the flow of money and goods, etc. is. The data on these reference industry information may contain information on the goods that the company actually wants to purchase, from which the goods that the company always needs to purchase can be extracted.

In such a case, a data set consisting of products to be purchased and purchase timings is learned as an output for the degree of association between the above-described reference market information and reference industry information. For this purchase timing, purchase timings A to E are acquired for each of the items α to ε. The goods required by the company (individual) can be extracted from the reference industry information, and the prices of individual goods can be extracted from the reference market information. By collecting data on which product was purchased at what timing with respect to these reference transaction information and reference industry information, the degree of association shown in FIG. 11 described above can be formed.

Next, the industry information of the purchaser to whom the proposal is made and the market information regarding the latest market conditions of each product are acquired. Then, using the degree of association shown in FIG. 11 and based on the newly acquired industry information and market information, the product to be purchased and the timing of the purchase are proposed.

In addition, when the article to be purchased is not decided yet, when the article to be purchased is proposed and the purchase timing is also proposed, reference is made as shown in FIG. You may make it utilize the external environment information for.

Examples of reference external environment information include various information related to external environment information. The external environment information here includes economic data (GDP, employment statistics, industrial production index, capital investment, labor force survey, etc.), household data (household consumption survey, household data, average working hours per week, savings amount, etc.). statistical data, annual income statistical data, etc.), real estate data (office vacancy rate, unit price per tsubo, rent market, land price, vacant house data, etc.), natural environment data (disaster data, temperature data, precipitation data, wind direction data, humidity data) etc.). The external environmental information includes all external information of the company to be screened, in addition to the information reflecting part or all of these data. The external environment information for reference may categorize the external environment itself. In other words, the external environment information for reference in FIG. 12 may be information classified according to types, for example, it may be classified by dividing by data in employment statistics. In addition, they may be categorized according to patterns (for example, patterns such as whether the growth rate of GDP increases rapidly or gradually).

In such a case, a data set consisting of products to be purchased and purchase timing is learned as an output for the degree of association between the above-described reference market information and reference external environment information. For this purchase timing, purchase timings A to E are acquired for each of the items α to ε. The goods needed by the company (individual) can be extracted from the reference external environment information, and the prices of individual goods can be extracted from the reference market information. By collecting data on which item was purchased at what timing with respect to these reference transaction information and reference external environment information, the degree of association shown in FIG. 12 described above can be formed.

Next, the external environment information of the proposed purchaser and the market information regarding the latest market conditions of each product are acquired. Then, using the degree of association shown in FIG. 12 and based on the newly acquired external environment information and market information, the product to be purchased and the timing of purchase are proposed.

Moreover, according to the present invention, it is characterized in that an optimum physical property and generation mechanism are searched for through association degrees set to three or more stages. The degree of association can be described, for example, by a numerical value from 0 to 100% in addition to the five stages described above, but is not limited to this, and can be described by a numerical value of three stages or more. may be configured.

By searching for the most probable degree of risk based on such a degree of association represented by numerical values of three or more stages, in a situation where there are multiple candidates for the possibility of increased risk, It is also possible to search and display them in order. If it is possible to display to the user in descending order of degree of association in this way, it is possible to preferentially display the most probable degree of risk, and it is possible to call attention to the higher degree of risk.

In addition to this, according to the present invention, it is possible to make a judgment without overlooking even a very low output discrimination result such as a correlation degree of 1%. Remind the user that even output discrimination results with an extremely low degree of correlation are connected as slight signs, and that once in dozens or hundreds of times, the discrimination results may be useful. can do.

Further, according to the present invention, as shown in FIG. 13, determination is made based on the degree of association between combinations of two or more types of information, namely reference information U and reference information V. FIG. The reference information U and V are each reference information including the above reference market information.

At this time, as shown in FIG. 13, the output obtained for the reference information U may be directly used as input data and associated with the output via an intermediate node 61 in combination with the reference information V. FIG. For example, for reference information U (reference market information), after generating an output solution as shown in FIG. The output may be searched.

In addition, the present invention may be provided with a function of automatically placing an order for goods to a purchaser in accordance with the obtained search solution. In other words, after the article to be purchased and the timing of the purchase are proposed by the above-described configuration, the proposed article is automatically ordered to the purchase order recipient at the same proposed timing. good too. In such a case, under the control of the control unit 24, orders may be placed using existing automatic ordering techniques via various sites, e-mails, and telephones.

Furthermore, according to the present invention, there is an advantage that a search policy can be determined by setting thresholds by performing a search based on three or more degrees of association. If the threshold value is lowered, even if the degree of association is 1%, it can be picked up without omission. be. On the other hand, if the threshold is increased, there is a high probability that the optimal risk level can be detected with high probability. Sometimes the solution is overlooked. It is possible to decide which one to place emphasis on based on the way of thinking of the user side and the system side, and it is possible to increase the degree of freedom in selecting such points to place emphasis on.

Furthermore, in the present invention, the degree of association described above may be updated. This update may reflect information provided via a public communication network such as the Internet, for example. Also, when new knowledge about the relationship between the input parameter and the output solution (risk) is discovered, the degree of association is increased or decreased according to the knowledge.

In other words, this update corresponds to learning in terms of artificial intelligence. Since new data is acquired and reflected in the learned data, it can be said that it is a learning act.

Also, the process of initially building a trained model and the above-described updating may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of reading and learning datasets of input data and output data, information equivalent to input data (reference market conditions information, reference location information, reference home pattern information, reference Time information, voice information for reference, security service information for reference, etc.) may be read and learned, and the degree of association related to the output data may be self-formed therefrom.

In addition to the information that can be obtained from the public communication network, this degree of association is updated manually by the system or the user based on the contents of research data, papers, conference presentations, newspaper articles, books, etc. by experts. or automatically. Artificial intelligence may be used in these update processes.

1 Product Purchase Timing Proposal System 2 Discrimination Device 21 Internal Bus 23 Display Unit 24 Control Unit 25 Operation Unit 26 Communication Unit 27 Estimation Unit 28 Storage Unit 61 Node

Claims (9)

In an article purchase timing proposal program that proposes the timing to purchase an article consisting of stationery,
an information acquisition step of acquiring regional information on the region to which the purchaser who purchases the goods belongs, and market information on recent market conditions including interest rates, exchange rates, stock prices of each brand, precious metals, and price movements of any of bitcoins;
Pre-obtained reference regional information on the region to which the purchaser who purchased the above goods in the past belongs, and reference market information on past market conditions consisting of interest rates, exchange rates, stock prices of each brand, precious metals, or bitcoin price movements and a proposal step of proposing a purchase timing based on the regional information and the market information obtained in the information obtaining step, using a combination having three or more levels of association with the purchase timing. A product purchase timing proposal program characterized by executing a product purchase timing proposal program. In an article purchase timing proposal program that proposes an article to be purchased consisting of stationery and the purchase timing,
an information acquisition step of acquiring regional information on the region to which the proposed purchaser belongs and market information on recent market conditions including interest rates, exchange rates, stock prices of each brand, precious metals, and price movements of any one of bitcoins;
A combination having previously acquired reference area information relating to the region to which each purchaser belongs, and reference market information relating to past market conditions including interest rates, exchange rates, stock prices of each brand, precious metals, and price movements of any of bitcoins; Based on the regional information and the market information acquired in the information acquisition step, the products to be purchased and their A goods purchase timing proposal program characterized by causing a computer to execute a proposal step of suggesting purchase timing. In an article purchase timing proposal program that proposes the timing to purchase an article consisting of stationery,
Acquisition of information to acquire financial statement information obtained from the recent financial statements of the purchaser of the proposed purchaser and market information on recent market conditions consisting of interest rates, exchange rates, stock prices of each brand, precious metals, and price movements of any of Bitcoin. a step;
Reference financial statement information obtained from each purchaser's past financial statements obtained in advance, and reference market information related to past market conditions consisting of interest rates, exchange rates, stock prices of each issue, precious metals, or bitcoin price movements and a proposal step of proposing a purchase timing based on the financial statement information and the market information obtained in the information obtaining step by using a combination having three or more levels of association with the purchase timing. A product purchase timing proposal program characterized by executing a product purchase timing proposal program. In an article purchase timing proposal program that proposes an article to be purchased consisting of stationery and the purchase timing,
Acquisition of information to acquire financial statement information obtained from the recent financial statements of the purchaser of the proposed purchaser and market information on recent market conditions consisting of interest rates, exchange rates, stock prices of each brand, precious metals, and price movements of any of Bitcoin. a step;
Reference financial statement information obtained from each purchaser's past financial statements obtained in advance, and reference market information related to past market conditions consisting of interest rates, exchange rates, stock prices of each issue, precious metals, or bitcoin price movements and the goods purchased by each purchaser and the timing of purchase thereof in three or more levels of association, based on the financial statement information and the market information obtained in the information obtaining step, An article purchase timing proposal program for causing a computer to execute a proposal step of proposing an article to be purchased and the purchase timing thereof. In an article purchase timing proposal program that proposes the timing to purchase an article consisting of stationery,
an information acquisition step of acquiring attribute information relating to the attributes of the purchaser to whom the proposal is made and market information relating to recent market conditions, including price fluctuations of any of interest rates, exchange rates, stock prices of each brand, precious metals, and bitcoin;
A combination of reference attribute information on the attributes of each purchaser acquired in advance and reference market information on past market conditions consisting of interest rates, exchange rates, stock prices of each brand, precious metals, or bitcoin price movements, and A proposing step of proposing a purchase timing based on the attribute information and the market information obtained in the information obtaining step by using three or more levels of correlation with the purchase timing. Product purchase timing suggestion program. In an article purchase timing proposal program that proposes an article to be purchased consisting of stationery and the purchase timing,
an information acquisition step of acquiring attribute information relating to the attributes of the purchaser to whom the proposal is made and market information relating to recent market conditions, including price fluctuations of any of interest rates, exchange rates, stock prices of each brand, precious metals, and bitcoin;
A combination having previously obtained reference attribute information relating to the attributes of each purchaser and reference market information relating to past market conditions including price movements of any of interest rates, exchange rates, stock prices of each brand, precious metals, and bitcoins; Articles to be purchased and their purchase based on the attribute information and the market information acquired in the information acquisition step by using three or more levels of association with the goods purchased by each purchaser and the timing of purchase thereof A goods purchase timing proposal program characterized by causing a computer to execute a proposal step of proposing the timing of. In an article purchase timing proposal program that proposes the timing to purchase an article consisting of stationery,
From the external environment information related to economic data, household budget data, real estate data, natural environment data as the external environment of the buyer of the proposal, interest rate, exchange rate, stock price of each brand, precious metal, bitcoin price movement an information acquisition step of acquiring market information about recent market conditions,
Reference external environment information related to any of economic data, household data, real estate data, and natural environment data as the external environment of each purchaser acquired in advance, interest rate, exchange rate, stock price of each brand, precious metal, bitcoin using a combination of reference market information relating to past market conditions consisting of price movements and three or more levels of correlation with the purchase timing, combining the external environment information and the market information acquired in the information acquisition step A goods purchase timing proposal program characterized by causing a computer to execute a proposal step of proposing a purchase timing based on the purchase timing. In an article purchase timing proposal program that proposes an article to be purchased consisting of stationery and the purchase timing,
From the external environment information related to economic data, household budget data, real estate data, natural environment data as the external environment of the buyer of the proposal, interest rate, exchange rate, stock price of each brand, precious metal, bitcoin price movement an information acquisition step of acquiring market information about recent market conditions,
Reference external environment information related to any of economic data, household data, real estate data, and natural environment data as the external environment of each purchaser acquired in advance, interest rate, exchange rate, stock price of each brand, precious metal, bitcoin obtained in the information acquisition step by using a combination of reference market information on past market conditions consisting of price movements of an article purchase timing proposal program for causing a computer to execute a proposal step of proposing an article to be purchased and the purchase timing thereof based on the market information and the external environment information. 9. The product purchase timing suggestion program according to any one of claims 1 to 8, wherein the proposing step uses the degree of association corresponding to a weighting coefficient of each output of a neural network node in artificial intelligence. .

Images