WO2024048036A1 - Dispositif de détermination de magasin - Google Patents

Dispositif de détermination de magasin Download PDF

Info

Publication number
WO2024048036A1
WO2024048036A1 PCT/JP2023/023380 JP2023023380W WO2024048036A1 WO 2024048036 A1 WO2024048036 A1 WO 2024048036A1 JP 2023023380 W JP2023023380 W JP 2023023380W WO 2024048036 A1 WO2024048036 A1 WO 2024048036A1
Authority
WO
WIPO (PCT)
Prior art keywords
store
user
information
users
similarity
Prior art date
Application number
PCT/JP2023/023380
Other languages
English (en)
Japanese (ja)
Inventor
亮勢 酒井
哲哉 山口
佑輔 中村
Original Assignee
株式会社Ｎｔｔドコモ
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Ｎｔｔドコモ filed Critical 株式会社Ｎｔｔドコモ
Publication of WO2024048036A1 publication Critical patent/WO2024048036A1/fr

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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services

Definitions

  • One aspect of the present disclosure relates to a store determination device that determines a store that a user is visiting.
  • Patent Document 1 listed below discloses an application server control module that can reveal a dynamic group related to a reference group of people by clustering approaches or encounters between people who are close to a reference person ( Paragraph 0143).
  • the above application server control module reveals a dynamic group related to a reference group of people, it is not possible to determine, for example, a store that a reference person (user) is visiting. Therefore, it is desired to determine the store that the user is visiting.
  • a store determination device includes user proximity information regarding proximity to other users for each user, and store information regarding proximity to other users assumed to be associated with a user visiting the store for each store. It includes a calculation unit that calculates the degree of similarity with the proximity information, and a determination unit that determines the store that the user is visiting based on the degree of similarity calculated by the calculation unit.
  • the degree of similarity between user proximity information for each user and store proximity information for each store is calculated, and the store that the user is visiting is determined based on the calculated degree of similarity. That is, it is possible to determine the store that the user is visiting.
  • a store that a user is visiting can be determined.
  • FIG. 3 is a diagram showing an example of a system configuration of a store determination system including a store determination device according to an embodiment. It is a figure which shows the example of a table of contact information. It is a diagram showing an example of a functional configuration of a store determining device according to an embodiment.
  • FIG. 3 is a diagram showing an example of a table of connection information. It is a figure which shows the example of a table of correct answer information. It is a figure which shows the example of a table of user proximity information. It is a figure showing an example of a table of store proximity information.
  • FIG. 3 is a diagram showing an example of a table of similarity information. It is a figure which shows an example of the degree of similarity for each user and each store.
  • FIG. 2 is a diagram illustrating the problem of store determination according to the prior art. It is a diagram showing an example of the hardware configuration of a computer used in the store determination device according to the embodiment.
  • FIG. 1 is a diagram showing an example of a system configuration of a store determination system 3 including a store determination device 1 according to an embodiment.
  • the store determination system 3 includes a store determination device 1 and one or more mobile terminals 2 (mobile terminals 2a, mobile terminals 2b, mobile terminals 2c, etc. are collectively referred to as mobile terminals 2 as appropriate). It consists of:
  • the store determination device 1 and each mobile terminal 2 are communicatively connected to each other via a network such as a mobile communication network, and are capable of transmitting and receiving information to and from each other.
  • the store determination device 1 is a computer device (server) that determines the store that the user is visiting.
  • a user is a user (person) of a function or service provided by the store determination device 1.
  • Each user carries a mobile terminal 2.
  • a target user whose store the store determination device 1 is visiting is determined is appropriately referred to as a target user.
  • the target user is assumed to be a user who is unsure of the store he or she is visiting.
  • a store is, for example, a building for selling products or a building or area for providing services. Details of the store determination device 1 will be described later.
  • the mobile terminal 2 is a mobile communication terminal that performs mobile communication or a computer device such as a notebook computer.
  • a smartphone is assumed as the mobile terminal 2, but the present invention is not limited to this.
  • the mobile terminal 2 is carried by each user as described above.
  • the mobile terminal 2 is capable of short-range wireless communication using BLE (Bluetooth (registered trademark) Low Energy), which is a part of Bluetooth (registered trademark).
  • BLE Bluetooth (registered trademark) Low Energy
  • the mobile terminals 2 automatically exchange their own identification information with each other by short-range wireless communication without any operation by the user or the like. Coming within a certain distance range is also referred to as being in contact or being in close proximity.
  • the exchange of identification information of the own terminals indicates that each of the mobile terminals 2 has contacted the other mobile terminal 2, or that the user of the mobile terminal 2 has contacted the user of the other mobile terminal 2.
  • a user ID for identifying a user carrying the mobile terminal 2 is used as the identification information of the own terminal (mobile terminal 2), but the present invention is not limited to this.
  • the mobile terminal 2 receives the user ID (contact user ID ), generate contact information regarding contacts between users.
  • FIG. 2 is a diagram showing an example of a table of contact information.
  • the contact information shown in FIG. 2 includes the user ID of the user who carries the mobile terminal 2 (for example, mobile terminal 2a) that is the own terminal, and the information that the mobile terminal 2 has come into contact with another mobile terminal 2 (for example, mobile terminal 2b, etc.).
  • the contact date and time which is the date and time, is associated with the contact user ID, which is the user ID of the user who carries the other mobile terminal 2.
  • the mobile terminal 2 transmits contact information to the store determination device 1 periodically (for example, every minute). Contact information may also be called a BLE log.
  • the mobile terminal 2 is equipped with functions or sensors that a general smartphone has, such as a radio wave positioning function, a positioning function using GPS (Global Positioning System), or a payment function, and information acquired by these functions or sensors. etc. may be transmitted to the store determination device 1.
  • functions or sensors that a general smartphone has, such as a radio wave positioning function, a positioning function using GPS (Global Positioning System), or a payment function, and information acquired by these functions or sensors. etc. may be transmitted to the store determination device 1.
  • FIG. 3 is a diagram showing an example of the functional configuration of the store determination device 1 according to the embodiment.
  • the store determination device 1 includes a storage section 10 (storage section), an acquisition section 11, a calculation section 12 (calculation section), a determination section 13 (determination section), and an output section 14. Consists of.
  • each functional block of the store determination device 1 is assumed to function within the store determination device 1, the present invention is not limited to this.
  • some of the functional blocks of the store determination device 1 are computer devices different from the store determination device 1, and are capable of transmitting and receiving information to and from the store determination device 1 as appropriate within a computer device connected to the store determination device 1 via a network. It is possible to function while doing so.
  • some functional blocks of the store determination device 1 may be omitted, multiple functional blocks may be integrated into one functional block, or one functional block may be decomposed into multiple functional blocks. good.
  • the storage unit 10 stores arbitrary information used in calculations in the store determination device 1, results of calculations in the store determination device 1, and the like.
  • the information stored by the storage unit 10 may be appropriately referenced by each function of the store determination device 1.
  • the information stored by the storage unit 10 may be information acquired and stored by the acquisition unit 11, or may be information generated and stored by the acquisition unit 11 or the calculation unit 12, The information may be input and stored by an administrator of the store determination device 1, or may be information stored in advance.
  • the storage unit 10 may store contact information (described above).
  • the storage unit 10 may store connection information regarding connections between users, which is generated based on contact information.
  • Connection refers to continuous contact.
  • FIG. 4 is a diagram showing an example of a table of connection information.
  • the connection information shown in FIG. 4 includes the user ID of the user who carries the mobile terminal 2, the contact user ID that is the user ID of the user who carries another mobile terminal 2 that the mobile terminal 2 has contacted, and the continuation of the contact.
  • a connection start date and time which is the date and time when a certain connection started, and a connection end date and time, which is the date and time when the connection ended, are associated with each other.
  • the connection information may be generated by the acquisition unit 11 based on the contact information, or may be generated by the mobile terminal 2 based on the contact information and transmitted to the store determination device 1.
  • connection information for example, if there is continuous contact for 5 minutes every minute in the contact information, it will be considered as a 5-minute connection, and the start and end of the corresponding contact date and time will be set as the connection start date and time and connection end date and time in the connection information, respectively. It may be generated by doing the following.
  • the storage unit 10 may store correct information regarding the stores visited by the user.
  • FIG. 5 is a diagram showing an example of a table of correct answer information.
  • the correct information shown in Figure 5 includes a user ID, a store ID that identifies the store visited by the user identified by the user ID, a visit date and time that is the date and time when the user visited the store, and a date and time that the user left the store. It is associated with a certain closing date and time.
  • Correct answer information is generated using conventional methods such as radio wave positioning results, location information (history) from GPS etc., payment (history) information by credit card or various electronic money, or contact information via short-range wireless communication. (a visit to the store was determined).
  • the user of the correct answer information that is, the user whose visit to the store has been determined (with high accuracy) using the conventional method
  • the target user may be a user other than the correct user.
  • the target user for which the store determination device 1 determines which store to visit is not a correct user, but a user who cannot acquire the above-mentioned location information, payment information, etc., and can (only) perform contact determination using BLE.
  • the acquisition unit 11 acquires information from other devices via the network, and causes the storage unit 10 to store the acquired information.
  • the acquisition unit 11 may process the acquired information while appropriately referring to various information stored in the storage unit 10, and then store the processed information in the storage unit 10. For example, the acquisition unit 11 may acquire contact information from each mobile terminal 2, generate connection information based on the acquired contact information, and cause the storage unit 10 to store the generated connection information. Further, the acquisition unit 11 may acquire contact information, connection information, correct answer information, user proximity information (described later), store proximity information (described later), etc., and cause the storage unit 10 to store the acquired information.
  • the calculation unit 12 calculates the degree of similarity between user proximity information regarding proximity to other users for each user and store proximity information regarding proximity to other users assumed for the user visiting the store for each store. calculate.
  • the proximity between the users may be the proximity between the mobile terminals 2 carried by the users.
  • the calculation unit 12 may cause the storage unit 10 to store the similarity calculation result, or may output the similarity calculation result to the determination unit 13 and the output unit 14.
  • the calculation unit 12 calculates the user based on at least one of contact information, connection information, correct answer information, past user proximity information, visit determination information (described later), or visit date and time information (described later) stored in the storage unit 10.
  • Proximity information may be generated and the degree of similarity may be calculated based on the generated user proximity information.
  • User proximity information includes the number of other users in close proximity, the number of times the user has been in proximity to other users, the time in proximity to other users, or the possibility that other users in close proximity are visiting or are visiting. It may also include at least one piece of information regarding the store.
  • FIG. 6 is a diagram showing an example of a table of user proximity information.
  • the user proximity information shown in FIG. 6 includes the user ID, the number of contacts, which is the number of other users that the user identified by the user ID came into contact with (proximity to) during the target period, and the number of other users that the user identified during the target period.
  • the number of connections which is the number of times the user connected (proximity), the cumulative connection time (seconds), which is the cumulative time the user connected (proximity) with other users during the target period, and the user's contact during the target period.
  • the average value of the connected user's connection time which is the average of the connection time with other users (in proximity)
  • the first quartile of the connected user's connection time which is the first quartile of the connection time.
  • the second quartile (median) of the connected user's connected time which is the second quartile of the connected time
  • the third quartile of the connected user's connected time which is the second quartile of the connected time.
  • the third quartile and the store ID (The store ID of the first visit candidate, which is the visit flag (described later) held by the contacted user, and the store ID of the second visit candidate, which is the store ID of the second most frequent store, ..., and the nth (n is The store ID of the n-th visit candidate, which is the store ID of the store that has a large number of stores (an integer greater than or equal to 1), and the visit flag, which is the store ID of the store that the user has visited or is likely to visit during the target period. (For example, determined one minute ago. If the store does not exist, "False") is associated. Each associated item (user ID, number of contacts, etc.) is called a data item.
  • the order number is calculated by the calculation unit 12 based on contact information or connection information.
  • the store ID of the first visit candidate, the store ID of the second visit candidate, ..., and the store ID of the nth visit candidate are contact information or connection information, correct answer information, past user proximity information (of (visit flag) and visit determination information (described later) or visit date and time information (described later) by the calculation unit 12.
  • the visit flag is registered or updated by the determination unit 13, which will be described later.
  • the visit flag does not need to be associated with user proximity information.
  • the user's visit flag indicates the store, so in this embodiment, the expression "user who has the visit flag of the store" is used. Do it as appropriate.
  • the number of contacts, the number of connections, the cumulative connection time, the average connection time of the users in contact, the first quartile of the connection time of the users in contact, the second quartile of the connection time of users in contact, And, the third quartile of the connection time of the contacted users is for all contacted users, users whose first visit candidate's visit flag is True (other than False) among contacted users, and second visit among contacted users.
  • a user whose candidate visit flag is True, . . . and a user whose visit flag of the n-th visit candidate among the contacted users is True may be associated in each pattern.
  • the calculation unit 12 calculates the store based on at least one of contact information, connection information, correct answer information, past user proximity information, visit determination information (described later), or visit date and time information (described later) stored in the storage unit 10.
  • Proximity information may be generated and the degree of similarity may be calculated based on the generated store proximity information.
  • Store proximity information is assumed to be the number of other users in close proximity to a user visiting a store, the number of times they have been in close proximity to other users, the time they have been in close proximity to other users, or the number of visits by other users in the vicinity.
  • the information may include at least one piece of information regarding a store that is currently open or that the store may be visiting.
  • FIG. 7 is a diagram showing an example of a table of store proximity information. Similar to the user proximity information, the store proximity information shown in FIG. It is assumed that the information (statistical value) is calculated by the calculation unit 12 or the like every minute, but it is not limited to this. In the store proximity information shown in FIG. 7, the store ID and the user who is visiting the store identified by the store ID (assumed user; user with a visit flag for the store) are assumed to be present during the target period.
  • the number of contacts which is the number of other users who came in contact with (proximity to) the user
  • the number of connections which is the number of times the assumed user connected with (proximity to) other users during the target period
  • the number of connections which is the number of times the assumed user connected with other users during the target period
  • Cumulative connection time (seconds) which is the cumulative time of connection (proximity) with users of
  • connection time of contacted users which is the average of the connection time with other users with whom the assumed user contacted (proximity) during the target period.
  • store IDs (1 to n) of adjacent store candidates are contact information or connection information, correct answer information, past user proximity information (visit flag), and (described later) visit determination information or (described later) It is calculated by the calculation unit 12 based on the visit date and time information.
  • the store proximity information is information that is likely to be obtained when visiting each store, and is calculated by the calculation unit 12 using contact information or connection information of a user who has a visit flag with each store ID. There are various calculation methods, but in this embodiment, it is simply averaged.
  • the store proximity information the number of people in contact, the number of connections, the cumulative connection time, the average connection time of the users in contact, the first quartile of the connection time of the users in contact, the second quartile of the connection time of users in contact, And, the third quartile of the connection time of the contacted user is the connection information of all the users who contacted the user with the visit flag of the store, or the store ID of the user with the visit flag of the store and each adjacent store candidate. may be associated with each pattern of connection information with the corresponding user.
  • user proximity information and store proximity information each include the number of other users in close proximity, the number of times in close proximity to other users, the time in close proximity to other users, or the number of visits by other users in close proximity. Alternatively, it may include at least one piece of information regarding a store that may be visited.
  • the user proximity information and the store proximity information may each include the same type of data item (for the calculation of similarity by the calculation unit 12). When calculating the degree of similarity, calculations are performed between data items of the same type between both pieces of information.
  • the calculation unit 12 calculates the degree of similarity for each user with each candidate store based on the idea that users visiting the same store have similar contact information or connection information. There are various methods for calculating the degree of similarity by the calculation unit 12. Although this embodiment will be described using cosine similarity, the present invention is not limited to this.
  • the store proximity information is expressed by the following formula, regarding each included data item as a vector. Note that st_id indicates the store ID.
  • the user proximity information is expressed by the following formula, regarding each included data item as a vector.
  • the degree of similarity (cosine similarity) between the user proximity information (of one user) and the store proximity information (of one store) calculated by the calculation unit 12 is calculated by the following formula. Note that for a user who answered correctly, the degree of similarity may be set to 1 unconditionally (calculation is performed as usual for stores other than those for visit determination).
  • information associated with the store IDs of the first to nth visit candidates held by the user is used. For example, if the store IDs of adjacent store candidates are "001", “002", “003", "004", and "005", the store ID of the Xth visit candidate in the user proximity information is up to the third candidate. Assume that there is information and the store IDs are "001", "003", and "004" in order. At this time, the similarity is calculated using the information of "001", "003", and "004".
  • the calculation unit 12 may generate similarity information based on the calculated similarity.
  • FIG. 8 is a diagram showing an example of a table of similarity information.
  • the user ID the store ID of the first visit candidate of the user identified by the user ID
  • the store ID of the second visit candidate of the user ...
  • the nth visit of the user The degree of similarity between the candidate store ID and the first visit candidate, which is the degree of similarity between the user proximity information of the user and the store proximity information of the store identified by the store ID of the first visit candidate, and the user proximity of the user.
  • the degree of similarity with the second visit candidate which is the degree of similarity between the information and the store proximity information of the store identified by the store ID of the second visit candidate, ..., the user proximity information of the user and the store of the nth visit candidate.
  • the degree of similarity with the n-th visit candidate which is the degree of similarity with the store proximity information of the store identified by the ID, is associated with the store.
  • the calculation unit 12 may cause the storage unit 10 to store the generated similarity information, or may output it to the determination unit 13 and the output unit 14.
  • the determining unit 13 determines the store that the user is visiting based on the degree of similarity calculated by the calculating unit 12. More specifically, based on the similarity calculation result or similarity information stored by the storage unit 10 or the similarity calculation result or similarity information input from the calculation unit 12, the determination unit 13 Determine the store that the user is visiting.
  • the determination unit 13 may cause the storage unit 10 to store the store determination result, or may output the result to the output unit 14.
  • the determination result may be, for example, the store ID of the store determined to be visited by each user, or the store ID of the store determined to be visited by each of one or more pre-specified users. It may be an ID.
  • a plurality of stores may be determined for each user. For example, the store ID of the first candidate store, the store ID of the second candidate store, and the store ID of the third candidate store may be used. 3 stores, the top 3 stores with the highest weighted reliability (described below, etc.).
  • the determination unit 13 may determine the store that the one user is visiting based on the degree of similarity for each store between the user proximity information of the one user and the store proximity information of each store. For example, in the similarity information shown in FIG. 8, the determination unit 13 determines whether the similarity between the user ID "010" and the first visit candidate is "0.7" to the n-th visit candidate and the similarity is "0.1". Among them, the store with the highest visit candidate value (for example, the store with the store ID "Eating01" which is the first visit candidate of "0.7”) is selected as the store visited by the user identified by the user ID. judge.
  • the determination unit 13 calculates the degree of similarity between the calculated user proximity information of one user and the store proximity information of one store, and the degree of similarity between the calculated user proximity information of one user and the store proximity information of one store. It may be modified based on the degree of similarity with the proximity information, and the determination may be made based on the modified degree of similarity (reliability).
  • the determination unit 13 calculates the degree of similarity between the calculated user proximity information of one user and the store proximity information of one store, and calculates the degree of similarity between the calculated degree of similarity and the user proximity information of each user to whom the one user is close.
  • the degree of similarity with the store proximity information of the one store may be corrected to a value (for example, an average) based on the same, and the determination may be made based on the corrected degree of similarity (reliability).
  • FIG. 9 is a diagram showing an example of similarity for each user and each store.
  • the store IDs of the two stores are "Eating01" and "Eating02." Black circles inside the store indicate users.
  • user U1, user U2, and user U3 are visiting a store with store ID "Eating01.”
  • a solid line between users indicates that the users are in close proximity (contact, connection).
  • the two numerical values shown in parentheses near the user are separated by a comma, the left numerical value indicates the degree of similarity between the user proximity information of the user and the store proximity information of the store with store ID "Eating01", and the right numerical value The degree of similarity between the user proximity information of the user and the store proximity information of the store with the store ID "Eating02" is shown.
  • the degree of similarity after correction is referred to as the degree of reliability.
  • Reliability is reliability.
  • Similarity is a degree of similarity.
  • i is the index number of the user of interest.
  • k is the index number of the user (the user of interest and the contacted user) targeted for average calculation.
  • num_of_k is the number of users targeted for average calculation. That is, the calculation unit 12 calculates the reliability by averaging the similarity with the contacted users for each store (visit flag).
  • FIG. 10 is a diagram showing an example of reliability for each user and each store.
  • FIG. 10 is a diagram in which the similarity in FIG. 9 is replaced with the reliability calculated based on the situation shown in FIG. 9.
  • FIG. 10 is similar to FIG. 9, but the two numerical values shown in parentheses near the user in FIG. 10 separated by a comma are the left numerical value indicating the reliability of the store ID "Eating01" of the user; The numerical value on the right indicates the reliability of the user for the store ID "Eating02".
  • the determination unit 13 has calculated "0.8" as the reliability of the user U1
  • the left numerical value in parentheses near the user U1 in FIG. 10 is "0.8".
  • Other reliability levels were calculated in the same way and replaced. Note that the reliability of the corresponding store of the correct user may be unconditionally set to "1" (however, candidate stores other than the corresponding store are calculated as usual).
  • the determination unit 13 may cause the storage unit 10 to store the calculated reliability calculation result.
  • the determination unit 13 may determine the store that the one user is visiting based on the reliability of each store between the user proximity information of the one user and the store proximity information of each store. For example, similar to the above explanation using FIG. 8, the store that is a visit candidate with the highest value among the reliability of each store by one user is determined as the store visited by the one user.
  • the determining unit 13 determines the number of users who are close to one user in one store, or the number of users who are visiting one store or who are likely to be visiting one store are close to one user in one store.
  • the corrected similarity (reliability) may be further corrected based on at least one of the number of users who have done so, and the judgment may be made based on the further corrected similarity (weighted reliability).
  • the determination unit 13 determines the number of users who are close to one user in one store, and the number of users who are visiting one store or who are likely to be visiting one store, and the number of users who are close to each other in one store.
  • the corrected similarity (reliability) may be further corrected based on the ratio with the value based on the number of users who are using the same function, and the judgment may be made based on the further corrected similarity (weighted reliability).
  • the number of contacts which is the number of other users that the user comes into contact with (nearby) is further shown underlined near each user. For example, since the user U1 is in contact with two users, the user U2 and the user U3, within the same store ID "Eating01", the number of contacts is "2". The number of people in contact is indicated by comma-separated numbers when other users in contact span multiple stores. For example, the number of contacts of user U4 "2,1" means that the number of contacts in store ID "Eating01" is "2" (user U2 and user U5, two people), and the number of contacts in store ID "Eating02" is "2". is "1" (one of the users U6).
  • the corrected reliability is referred to as a weighted reliability.
  • the formula for calculating the weighting described above will be explained. Assume that the average number of contacts (connections) for each store is expressed by the following formula. Assume that the number of contacts (connections) of the user of interest at the relevant store is expressed by the following formula. In this case, the weight is expressed by the following formula: The weighting of the reliability of each store is expressed by the following formula. Note that Reliability on the left side is a weighted reliability, and Reliability on the right side is an (unweighted) reliability.
  • FIG. 11 is a diagram showing an example of weighted reliability for each user and each store.
  • FIG. 11 is a diagram in which the reliability in FIG. 10 is replaced with a weighted reliability calculated based on the situation shown in FIG. 10.
  • FIG. 11 is similar to FIG. 10, but the two numerical values shown in parentheses near the user in FIG. , and the numerical value on the right indicates the weighted reliability of the store ID "Eating02" of the user.
  • the determination unit 13 calculated "0.6" as the weighted reliability of the user U1
  • the left numerical value in parentheses near the user U1 in FIG. 11 is "0.6". It has become.
  • Other reliability levels were calculated in the same way and replaced.
  • the determination unit 13 may cause the storage unit 10 to store the calculated weighted reliability calculation results.
  • the determination unit 13 may determine the store that the one user is visiting based on the weighted reliability of each store between the user proximity information of the one user and the store proximity information of each store. For example, similar to the above explanation using FIG. 8, the visit candidate store with the largest value among the weighted reliability of each store by one user is determined as the store visited by the one user. do.
  • the determination unit 13 may generate visit flag information based on the calculated reliability or weighted reliability.
  • FIG. 12 is a diagram showing an example of a table of visit flag information.
  • the user ID the store ID of the first visit candidate of the user identified by the user ID, the store ID of the second visit candidate, ..., and the store ID of the nth visit candidate.
  • the confidence level or weighted confidence level for the first visit candidate of the user the confidence level or weighted confidence level for the second visit candidate of the user,... and the confidence level for the nth visit candidate of the user.
  • the weighted confidence level and the visit flag are associated with each other. For example, in the visit flag information shown in FIG.
  • the user identified by the user ID visits the store with the highest reliability value of "0.1" or a visit candidate with a predetermined threshold value (for example, "0.5") or more. It is determined that the store is The determination unit 13 assigns (registers, updates) a visit flag of user proximity information based on the determination result. The determination unit 13 may cause the storage unit 10 to store the generated visit flag information.
  • the output unit 14 outputs the similarity calculation result, similarity information or store determination result stored by the storage unit 10, the similarity calculation result or similarity information input from the calculation unit 12, or the similarity calculation result or similarity information input from the determination unit 13. Outputs the input store determination results, or outputs based on those results or information.
  • the output may be, for example, displayed on a display that is one of the output devices 1006 described later, or may be transmitted to another device via the communication device 1004 described later.
  • the output unit 14 may display one or more stores of each user indicated by the determination result input from the determination unit 13 as stores visited by each user.
  • the output unit 14 may generate visit determination information that organizes each user's visit determination to the store based on the determination result by the determination unit 13. More specifically, the output unit 14 collects the results of the determination by the determination unit 13 at a predetermined time point (every minute) for a predetermined period, and organizes (summarizes) the information to generate visit determination information. .
  • FIG. 13 is a diagram showing an example of a table of visit determination information. The visit determination information shown in FIG.
  • the output unit 14 may output the generated visit determination information.
  • the output unit 14 may further organize the generated visit determination information to generate visit date and time information that organizes the visit dates and times of each user to the store. More specifically, in the visit determination information, if there is a visit determination for Y minutes or more in consecutive X minutes, the output unit 14 outputs the information by determining that the visit occurred for the X minutes. Visit date and time information is generated by organizing (combining) the information.
  • FIG. 14 is a diagram showing an example of a table of visit date and time information.
  • the visit date and time information shown in FIG. 14 includes a user ID, a store ID of a store that the user identified by the user ID may be visiting, and a store visit time ( The date is omitted in FIG. 14) and the leaving time (date is omitted in FIG. 14), which is the time at which the person may have left the store.
  • the output unit 14 may output the generated visit date and time information.
  • FIG. 15 is a flowchart illustrating an example of a process executed by the store determination device 1.
  • the calculation unit 12 calculates the similarity between user proximity information regarding proximity to other users for each user and store proximity information regarding proximity to other users assumed for the user visiting the store for each store. degree is calculated (step S1, calculation step).
  • the determination unit 13 determines the store that the user is visiting based on the similarity calculated in S1 (step S2, determination step).
  • FIG. 16 is a flowchart showing another example of the process executed by the store determining device 1.
  • the calculation unit 12 calculates the contact status for each user (number of contacts in the last N minutes, number of connections, cumulative connection time, quartiles of connection time for each user, connection time for each connection). quartiles, etc.) (step S10).
  • the calculation unit 12 acquires (generates) store proximity information for each store from the information of users with visit flags for each store (step S11).
  • the calculation unit 12 checks contact with a user who has a visit flag for each user, lists candidate stores (store ID of Xth visit candidate in user proximity information), and generates user proximity information.
  • the degree of similarity of contact status with each store is calculated (step S12).
  • the calculation unit 12 focuses on one user and calculates the reliability by averaging the degree of similarity with the contacted user with a visit flag (for each store), and also calculates the reliability by using the visit flag information of the most recently contacted user.
  • the degree is corrected (corrected) (step S13).
  • the determining unit 13 determines that the store with the highest reliability level is X or higher (updating the visit flag) (step S14). S12 to S14 are processed (repeatedly) every minute.
  • the output unit 14 or the determination unit 13) derives the store arrival time and store exit time from the minute-by-minute store determination results (step S15).
  • S10 there may be a process to narrow down the users (it is assumed that calculations are performed for all users at once, but if the number is huge, the amount of calculation will be large and it is not practical). For example, all users who are indirectly in contact with the user who visited store A on that day may be extracted. Furthermore, regarding S10, it may be determined whether the user is "eating and drinking type", "apparel type", or "has not visited anywhere” based on the contact status. This determination result may be used as a basis for determining whether to perform subsequent processing, or may be used for correcting (correcting) reliability. Regarding S11, the store proximity information may not be real-time data.
  • the degree of similarity of the connection status with all the flag-bearing users contacted may be obtained, and it may be determined that the store has visited the place with the highest degree of similarity on average for each store.
  • the store determination device user proximity information regarding the proximity to other users for each user, and store proximity information regarding the proximity to other users assumed for the user visiting the store for each store. It includes a calculation unit 12 that calculates the degree of similarity, and a determination unit 13 that determines the store that the user is visiting based on the degree of similarity calculated by the calculation unit 12.
  • the similarity between the user proximity information for each user and the store proximity information for each store is calculated, and the store that the user is visiting is determined based on the calculated similarity. That is, it is possible to determine the store that the user is visiting.
  • the proximity between users may be the proximity between the mobile terminals 2 carried by the users.
  • the proximity between the mobile terminals 2 carried by the users.
  • BLE short-range wireless communication
  • Store proximity information can be secured.
  • the user proximity information and the store proximity information respectively include the number of other users in close proximity, the number of times in close proximity to other users, the time in close proximity to other users, or the number of other users in close proximity to other users.
  • the information may include at least one piece of information regarding a store that the user is visiting or may be visiting.
  • the determination unit 13 determines the store that the one user is visiting based on the degree of similarity for each store between the user proximity information of one user and the store proximity information of each store. may be determined. With this configuration, it is possible to determine the store that one user is visiting.
  • the determination unit 13 calculates the degree of similarity between the calculated user proximity information of one user and the store proximity information of one store, and determines the degree of similarity between the calculated user proximity information of one user and the store proximity information of one store. It may be corrected based on the similarity between the user proximity information and the store proximity information of the one store, and the determination may be made based on the corrected similarity.
  • This configuration allows for a more accurate similarity measure to be used, as the similarity is modified based on the users a user is close to, thereby more accurately determining the store the user is visiting. can do.
  • the determination unit 13 calculates the degree of similarity between the calculated user proximity information of one user and the store proximity information of one store, and The value may be corrected to a value based on the degree of similarity between the user proximity information of each user and the store proximity information of the one store, and the determination may be made based on the corrected degree of similarity.
  • This configuration allows for a more accurate similarity measure to be used, as the similarity is modified based on the users a user is close to, thereby more accurately determining the store the user is visiting. can do.
  • the determination unit 13 determines the number of users who are close to one user in one store, or the number of users who are visiting or are likely to visit one store.
  • the corrected degree of similarity may be further corrected based on at least one of the number of users that a certain user is close to in the one store, and the judgment may be made based on the further corrected degree of similarity.
  • the number of users who are close to one user in one store, or the number of users who are visiting or may be visiting one store are close to each other in one store. Since the similarity is further modified based on at least one of the number of users who .
  • the determination unit 13 determines the number of users who are close to one user in one store, and the number of users who are visiting or may be visiting one store.
  • the corrected similarity may be further corrected based on a ratio with a value based on the number of users with whom each user is close in the same store, and the judgment may be made based on the further corrected similarity.
  • the degree of similarity is further corrected based on the ratio, so a more accurate degree of similarity can be used, thereby making it possible to more accurately determine the store that the user is visiting.
  • visit determination can be performed between adjacent stores.
  • FIG. 17 is a diagram illustrating problems in store determination according to the prior art.
  • a conventional problem is that actual stores are often lined with multiple adjacent stores, and if the separation between adjacent stores is not taken into account, there is a high possibility of erroneous determination.
  • user U10 is originally visiting store B, but in the conventional technology, it is erroneously determined that he is visiting store A.
  • a person passing near a store may be incorrectly determined to have visited the store due to the temporary occurrence of BLE detection.
  • user U11 is originally just walking near store B, but in the conventional technology, it is erroneously determined that he is visiting store B.
  • Store Identification Device 1 it is aimed at users who have difficulty determining their visit using conventional methods using radio positioning, GPS, payment information, etc., and uses BLE logs to accurately identify a specific store visited from among multiple adjacent stores. It can be divided and judged. According to the store determination device 1, it is estimated which store the user is likely to visit by comparing the BLE logs (number of contacts, number of times, etc.) of a group of users visiting a specific store. (introducing the concept of similarity). Furthermore, according to the store determination device 1, the determination accuracy can be improved by considering the visit flag information of the most recently contacted users (introducing the concept of reliability). The store determination device 1 makes it possible to prevent erroneous determination even if the store is an adjacent store. Furthermore, the store determination device 1 makes it possible to prevent erroneous determinations by users, such as passersby, who pass near a particular store.
  • the store determination device 1 compares the user's individual contact information with the contact information of the group A store, B store, etc., and obtains the degree of similarity with each store. Then, the store determination device 1 improves the determination accuracy by considering the visit flag information of the most recently contacted users.
  • the store determination device 1 may target users who can acquire BLE logs but cannot acquire other location information and payment information. Visit determination using information other than BLE (location information and payment information) may be treated as a correct user.
  • visits can be determined in a sequential manner in chronological order.
  • the store determination device 1 introduces the concept of reliability.
  • the reliability utilizes the similarity of connected users with visit flags.
  • the store determination device 1 of the present disclosure may have the following configuration.
  • a store determination device comprising:
  • Proximity between users is the proximity of mobile terminals carried by each user.
  • the store determination device according to [1].
  • User proximity information and store proximity information each include the number of other users in close proximity, the number of times they have been in proximity to other users, the time they have been in proximity to other users, or the fact that other users in the vicinity are visiting or have visited. including at least one piece of information about the store that may be located; The store determination device according to [1] or [2].
  • the determination unit determines the store that the one user is visiting based on the degree of similarity for each store between the user proximity information of the one user and the store proximity information of each store.
  • the store determination device according to any one of [1] to [3].
  • the determination unit determines the degree of similarity between the calculated user proximity information of one user and the store proximity information of one store, and the degree of similarity between the calculated user proximity information of the one user and the store proximity information of the one store. Modify the information based on the similarity with the proximity information, and make a judgment based on the modified similarity.
  • the store determination device according to any one of [1] to [4].
  • the determination unit calculates the degree of similarity between the calculated user proximity information of one user and the store proximity information of one store, and the degree of similarity and the user proximity information of each user to which the one user is close.
  • the degree of similarity with the store proximity information of the one store concerned is corrected to a value based on the degree of similarity, and the judgment is made based on the degree of similarity that has been corrected.
  • the store determination device according to any one of [1] to [5].
  • the determination unit determines the number of users that the one user is close to in the one store, or the number of users who are visiting or may be visiting the one store. further modifying the modified degree of similarity based on at least one of the number of users who are close to each other within the computer; and further making a determination based on the modified degree of similarity.
  • the store determination device according to [5] or [6].
  • the determination unit determines the number of users that the one user is close to in the one store, and the number of users who are visiting or may be visiting the one store. further modifying the modified similarity based on a ratio with a value based on the number of users who are close to each other within the same, and making a determination based on the further modified similarity;
  • the store determination device according to any one of [5] to [7].
  • each functional block may be realized using one physically or logically coupled device, or may be realized using two or more physically or logically separated devices directly or indirectly (e.g. , wired, wireless, etc.) and may be realized using a plurality of these devices.
  • the functional block may be realized by combining software with the one device or the plurality of devices.
  • Functions include judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, These include, but are not limited to, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assigning. I can't do it.
  • a functional block (configuration unit) that performs transmission is called a transmitting unit or a transmitter. In either case, as described above, the implementation method is not particularly limited.
  • the store determination device 1 in an embodiment of the present disclosure may function as a computer that performs processing of the store determination method of the present disclosure.
  • FIG. 18 is a diagram illustrating an example of the hardware configuration of the store determination device 1 according to an embodiment of the present disclosure.
  • the store determination device 1 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.
  • the word “apparatus” can be read as a circuit, a device, a unit, etc.
  • the hardware configuration of the store determination device 1 may be configured to include one or more of each device shown in the figure, or may be configured without including some of the devices.
  • Each function in the store determination device 1 is performed by loading predetermined software (programs) onto hardware such as a processor 1001 and a memory 1002, so that the processor 1001 performs calculations, controls communication by the communication device 1004, and controls communication by the communication device 1004. This is realized by controlling at least one of reading and writing data in the storage 1002 and the storage 1003.
  • the processor 1001 for example, operates an operating system to control the entire computer.
  • the processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, registers, and the like.
  • CPU central processing unit
  • the above-described acquisition unit 11, calculation unit 12, determination unit 13, output unit 14, etc. may be realized by the processor 1001.
  • the processor 1001 reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 to the memory 1002, and executes various processes in accordance with these.
  • programs program codes
  • the program a program that causes a computer to execute at least part of the operations described in the above embodiments is used.
  • the acquisition unit 11, the calculation unit 12, the determination unit 13, and the output unit 14 may be realized by a control program stored in the memory 1002 and operated in the processor 1001, and other functional blocks may also be realized in the same way. Good too.
  • Processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via a telecommunications line.
  • the memory 1002 is a computer-readable recording medium, and includes at least one of ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. may be done.
  • Memory 1002 may be called a register, cache, main memory, or the like.
  • the memory 1002 can store executable programs (program codes), software modules, and the like to implement a wireless communication method according to an embodiment of the present disclosure.
  • the storage 1003 is a computer-readable recording medium, such as an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, or a magneto-optical disk (for example, a compact disk, a digital versatile disk, or a Blu-ray disk). (registered trademark disk), smart card, flash memory (eg, card, stick, key drive), floppy disk, magnetic strip, etc.
  • Storage 1003 may also be called an auxiliary storage device.
  • the storage medium mentioned above may be, for example, a database including at least one of memory 1002 and storage 1003, a server, or other suitable medium.
  • the communication device 1004 is hardware (transmission/reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc., for example.
  • the communication device 1004 includes, for example, a high frequency switch, a duplexer, a filter, a frequency synthesizer, etc. in order to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). It may be composed of.
  • FDD frequency division duplex
  • TDD time division duplex
  • the input device 1005 is an input device (eg, keyboard, mouse, microphone, switch, button, sensor, etc.) that accepts input from the outside.
  • the output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside. Note that the input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).
  • each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information.
  • the bus 1007 may be configured using a single bus, or may be configured using different buses for each device.
  • the store determination device 1 also includes hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA). A part or all of each functional block may be realized by the hardware. For example, processor 1001 may be implemented using at least one of these hardwares.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • PLD programmable logic device
  • FPGA field programmable gate array
  • LTE Long Term Evolution
  • LTE-A Long Term Evolution-Advanced
  • SUPER 3G IMT-Advanced
  • 4G 4th generation mobile communication system
  • 5G 5th generation mobile communication system
  • FRA Fluture Radio Access
  • NR new Radio
  • W-CDMA registered trademark
  • GSM registered trademark
  • CDMA2000 Code Division Multiple Access 2000
  • UMB Universal Mobile Broadband
  • IEEE 802.11 Wi-Fi (registered trademark)
  • IEEE 802.16 WiMAX (registered trademark)
  • IEEE 802.20 UWB (Ultra-WideBand
  • Bluetooth registered trademark
  • a combination of a plurality of systems may be applied (for example, a combination of at least one of LTE and LTE-A and 5G).
  • the input/output information may be stored in a specific location (for example, memory) or may be managed using a management table. Information etc. to be input/output may be overwritten, updated, or additionally written. The output information etc. may be deleted. The input information etc. may be transmitted to other devices.
  • Judgment may be made using a value expressed by 1 bit (0 or 1), a truth value (Boolean: true or false), or a comparison of numerical values (for example, a predetermined value). (comparison with a value).
  • notification of prescribed information is not limited to being done explicitly, but may also be done implicitly (for example, not notifying the prescribed information). Good too.
  • Software includes instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, whether referred to as software, firmware, middleware, microcode, hardware description language, or by any other name. , should be broadly construed to mean an application, software application, software package, routine, subroutine, object, executable, thread of execution, procedure, function, etc.
  • software, instructions, information, etc. may be sent and received via a transmission medium.
  • a transmission medium For example, if the software uses wired technology (coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), etc.) and/or wireless technology (infrared, microwave, etc.) to create a website, When transmitted from a server or other remote source, these wired and/or wireless technologies are included within the definition of transmission medium.
  • wired technology coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), etc.
  • wireless technology infrared, microwave, etc.
  • data, instructions, commands, information, signals, bits, symbols, chips, etc. which may be referred to throughout the above description, may refer to voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, light fields or photons, or any of these. It may also be represented by a combination of
  • system and “network” are used interchangeably.
  • information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values from a predetermined value, or using other corresponding information. may be expressed.
  • determining may encompass a wide variety of operations.
  • “Judgment” and “decision” include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, search, and inquiry. (e.g., searching in a table, database, or other data structure), and regarding an ascertaining as a “judgment” or “decision.”
  • judgment and “decision” refer to receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, and access.
  • (accessing) may include considering something as a “judgment” or “decision.”
  • judgment and “decision” refer to resolving, selecting, choosing, establishing, comparing, etc. may be included.
  • judgment and “decision” may include regarding some action as having been “judged” or “determined.”
  • judgment (decision) may be read as "assuming", “expecting", “considering”, etc.
  • connection means any connection or coupling, direct or indirect, between two or more elements and each other. It may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled.”
  • the bonds or connections between elements may be physical, logical, or a combination thereof. For example, "connection” may be replaced with "access.”
  • two elements may include one or more electrical wires, cables, and/or printed electrical connections, as well as in the radio frequency domain, as some non-limiting and non-inclusive examples. , electromagnetic energy having wavelengths in the microwave and optical (both visible and non-visible) ranges.
  • the phrase “based on” does not mean “based solely on” unless explicitly stated otherwise. In other words, the phrase “based on” means both “based only on” and “based at least on.”
  • any reference to elements using the designations "first,” “second,” etc. does not generally limit the amount or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Thus, reference to a first and second element does not imply that only two elements may be employed or that the first element must precede the second element in any way.
  • a and B are different may mean “A and B are different from each other.” Note that the term may also mean that "A and B are each different from C”. Terms such as “separate” and “coupled” may also be interpreted similarly to “different.”

Landscapes

  • Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

La présente invention aborde le problème de la détermination du magasin qu'un utilisateur visite. Un dispositif de détermination de magasin 1 comprend : une unité de calcul 12 qui calcule le degré de similarité entre des informations de proximité d'utilisateur concernant la proximité entre chacun de multiples utilisateurs et d'autres utilisateurs, et stocke des informations de proximité concernant la proximité entre chaque magasin et d'autres utilisateurs qui sont supposés être des utilisateurs visitant le magasin ; et une unité de détermination 13 qui, sur la base du degré de similarité calculé par l'unité de calcul 12, détermine le magasin qu'un utilisateur visite. La proximité entre des utilisateurs peut être la proximité entre des terminaux portables 2 portés par chacun des utilisateurs. Les informations de proximité d'utilisateur et les informations de proximité de magasin peuvent comprendre au moins un élément d'informations concernant : le nombre d'autres utilisateurs proches ; le nombre d'instances de proximité avérée par rapport à d'autres utilisateurs ; la durée de proximité avérée par rapport à d'autres utilisateurs ; et un magasin que d'autres utilisateurs proches visitent actuellement ou peuvent visiter.
PCT/JP2023/023380 2022-09-01 2023-06-23 Dispositif de détermination de magasin WO2024048036A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2022-139014 2022-09-01
JP2022139014 2022-09-01

Publications (1)

Publication Number Publication Date
WO2024048036A1 true WO2024048036A1 (fr) 2024-03-07

Family

ID=90099348

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2023/023380 WO2024048036A1 (fr) 2022-09-01 2023-06-23 Dispositif de détermination de magasin

Country Status (1)

Country Link
WO (1) WO2024048036A1 (fr)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021157807A (ja) * 2018-01-12 2021-10-07 株式会社Ｊｔｂ総合研究所 情報処理装置、情報処理プログラムおよび情報処理システム
JP2021175015A (ja) * 2020-04-20 2021-11-01 株式会社東芝 近接検知装置、近接検知方法及び近接検知システム

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2021157807A (ja) * 2018-01-12 2021-10-07 株式会社Ｊｔｂ総合研究所 情報処理装置、情報処理プログラムおよび情報処理システム
JP2021175015A (ja) * 2020-04-20 2021-11-01 株式会社東芝 近接検知装置、近接検知方法及び近接検知システム

Similar Documents

Publication Publication Date Title
JP7312161B2 (ja) 在宅予測装置
WO2019193796A1 (fr) Serveur d'interaction
US20220301004A1 (en) Click rate prediction model construction device
WO2024048036A1 (fr) Dispositif de détermination de magasin
US11748424B2 (en) Visiting destination prediction device and visiting destination prediction method
US11016868B2 (en) Application usage estimation device and rule formulation device
WO2024047978A1 (fr) Dispositif de détermination de magasin
JP7542147B2 (ja) 決済情報管理装置
JPWO2019207961A1 (ja) エリア人気度算出装置
WO2020230735A1 (fr) Dispositif de prédiction de demande
US20220198341A1 (en) State estimation device, state estimation program, estimation model, and state estimation method
US20210123765A1 (en) Pastime preference estimation device and pastime preference estimation method
US11570746B2 (en) Check-in determination device
US20210248196A1 (en) Interest estimation device
WO2024024201A1 (fr) Système de détermination d'état de population
WO2023214484A1 (fr) Dispositif d'estimation d'intérêt
US20230395265A1 (en) Blood information estimating apparatus
WO2024190038A1 (fr) Système de traitement de données
WO2023188808A1 (fr) Système de recommandation
WO2023084874A1 (fr) Système de détermination d'état de population et système de génération de modèle
WO2024150513A1 (fr) Dispositif de fourniture de degré de jeunesse et procédé de fourniture de degré de jeunesse
WO2024111207A1 (fr) Dispositif d'estimation de valeur d'attribut
JP7489255B2 (ja) 情報提供装置
WO2024047949A1 (fr) Dispositif d'estimation de poi d'arrêt
US20240354833A1 (en) Behavior predicting device

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: 23859806

Country of ref document: EP

Kind code of ref document: A1