JP2002304568A - Correlated item detection method and device, recommended item introduction method and device, correlated item detection program, recommended item introduction program - Google Patents

Abstract

(57) [Summary] [Problem] Introduce items that small groups of clients are interested in in common. SOLUTION: An item identifier whose number of clients is not between the upper limit value and the lower limit value of the client access number of the analysis source item is deleted, and a list of client identifiers accessing the remaining item identifiers is obtained from an access history map to a related client group. Extract as The related client group is narrowed down, and a list of item identifiers accessed by each client of the narrowed down related client group is extracted as a related item group from the access history map. The related item group is narrowed down, the number of clients of each item identifier of the narrowed related item group is obtained from the access history map, and the item identifier whose client access number is not between the upper limit value and the lower limit value of the client number of the correlated item is deleted. And sends the remaining item identifier to the provider server as a correlated item detection response.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION The present invention extracts similar correlated items based on client interests based on evaluation inputs to products and the like from clients, sales histories of products, access histories to Web pages, and the like. The present invention relates to a correlation item detection / introduction method and apparatus for recommendation introduction for introducing a recommended item to a client based on the detection of a correlated item to be introduced and a recommended item to the client based on the access history of a specific client.

[0002]

2. Description of the Related Art As a conventional example of correlation detection (or recommendation introduction) based on client interest, there is a method of extracting correlated items by a collaborative filtering method and introducing them to a client. For example, Japanese Patent Application Laid-Open No. H11-5090919, "Automatic Collaborative
In the "item recommendation method and device using filtering", a group of clients who give similar high evaluations (or low evaluations) to the same item based on the evaluation value input by the "client to be referred" to the item And introduce the items that the client group highly appreciates. In Japanese Patent Application No. 2000-209827 “Recommended information introduction method, recommended information introduction system, and recording medium recording recommended information introduction program”, items accessed by “client to be introduced” based on the access history. This section introduces the items that are commonly accessed by the clients that are accessing.

[0003]

According to these methods, a client can receive an introduction of an item of interest from a group of clients having the same interest as the client, or can correlate with a specified group of items. Can receive a certain group of items, but has the following problems. 1) In the recommended introduction, items that the entire person is interested in are likely to be introduced regardless of their main interests. In correlation detection, regardless of the characteristics of the item group that is the source of the analysis, items that are totally interested are detected as correlated items. In extreme cases, the results are the same no matter what you specify for the group of items from which you want to analyze. For example, despite being introduced by a group of clients who are mainly interested in shogi, bestseller books unrelated to their main interests are likely to be introduced. Here, the "main interest" is a characteristic interest in which the client group is distinguished from the others. 2) In recommendation referrals, usually the client's interests are not only for items of a genre that interests more people, but also for items of interest that are shared by a small group of clients with similar interests. Show strong interest. Similarly, in correlation detection, there are many cases where an item that a small number of client groups are interested in is more interesting (worthy) than an item that a large number of client groups are commonly interested in. However, the logic of “introducing an item that the client group is interested in” cannot introduce an item that the small group of clients are interested in.

[0004] It is an object of the present invention to make it difficult to introduce items that are irrelevant to one's main interest and who are interested in the whole, and to introduce items that a small group of clients are interested in in common. It is to provide a method and a device that can be performed.

[0005]

In order to achieve the above-mentioned object, the present invention provides a method of identifying each item included in a list of each item identifier in access history data which is a history of a client accessing an item provider server. The number of clients accessed during the period is obtained, and an item identifier whose number of clients is not within a specified range is deleted from the original access history data for detecting a correlation to perform correlation detection. .

Here, terms used in the present specification will be described. Item: Electronic information such as a product, an advertisement, text information or music information or information. -Client: A user who browses and purchases items using the item provider server. Depending on the method of assigning a client identifier, it refers to a client terminal (a terminal such as a computer terminal, a digital TV, a set-top box, or an information home appliance that accesses an item provider server or a recommended item introduction server via a network) used by the client. . Item provider: A company that runs a business that provides items to multiple clients for browsing / selling.

[0007] An EC site for introducing / selling items such as CDs / books, a search / directory site for introducing / searching for items such as Web contents and information, and a plurality of EC sites for integrating items such as merchandise. A company that operates an online mall site that offers referrals and sales.

[0008] Not only the above-mentioned electronic company via a network, but also a company such as a mail order dealer or a department store that stores the product purchase history of the client electronically.

[0009] A server operated by the company is called an item provider server. Client identifier: The client identifier is an identifier capable of uniquely identifying a client by both the item provider server and the correlated item detection / introduction device. The client number notified by each company, the client number recorded on a card, the member number manually input from the client, the Cookie of the browser
There is a means for adding a time stamp or the like recorded using a function. Item identifier: The item identifier is an identifier capable of uniquely identifying an item in both the item provider server and the correlated item detection / introduction device. For example, when each page of a Web page is used as an item,
URL becomes an item identifier.・ Access: The act of clients browsing, purchasing, and evaluating items. -Access history: Data that records the actions of clients browsing and purchasing items. In one example, it is composed of a client identifier, an item identifier, a purchase amount, and the like. Similarly, when an evaluation value is given to an item, the access history is represented by a client identifier, an item identifier, an evaluation value, and the like. Item evaluation value (item evaluation value): An item evaluation value is a value that is a measure for determining the value of an item, and is a numerical value indicating the degree of interest of the user in the item, as well as the observation of the item. The total purchase amount, the total number of accesses, or a composite value thereof during the period. In this device, as the group of items that are the source of the correlation item analysis,
It is also used to select meaningful items to be extracted as an item group as a correlation result. The number of client accesses to the item (the number of client accesses): the number of clients accessing the item within a unit period such as one month. No matter how many times the same client accesses the same item, it counts as one.

A band pass filter for the number of client accesses (a band pass filter for the number of client accesses,
Bandpass filter): A filter that extracts only items within a preset range (lower limit, upper limit) of the number of client accesses based on the number of client accesses to the item.

[0011]

Next, embodiments of the present invention will be described with reference to the drawings.

FIG. 1 is a configuration diagram of a correlation item detection / introduction device according to an embodiment of the present invention.

The correlation item detection / introduction device 1 is connected to the item provider server 2 and has an input / output unit 11, a correlation item analysis processing unit 12, an access history processing unit 13, a bandpass filter processing unit 14, and an analysis list storage unit 15. And an access history map management unit 16.

The input / output unit 11 inputs and outputs (displays) various data. The correlation item analysis processing unit 12 performs a main process for detecting a correlation item (reading data from the access history map management unit 16, writing data to the analysis list storage unit 15, and downloading data from the analysis list storage unit 15). Reading). The band-pass filter processing unit 14 stores the band-pass condition in the band-pass condition storage unit 14a.
In response to a request from the correlation item analysis processing unit 12, a band pass filter process is performed on the analysis source item list 15a and the related item list 15c of the analysis list storage unit 15. The analysis list storage unit 15 stores the analysis source item list 15a and the related client list 15
b, Hold and manage the related item list 15c. The analysis source item list 15a stores an item group (a list of item identifiers) that is a source of the correlation item analysis. The related client list 15b stores a group of clients (list of client identifiers) accessing the analysis source item list 15a. The related item list 15c stores an item group (list of item identifiers) accessed by the client group, an item evaluation value of each item, and the number of client accesses. The access history map management unit 16 processes the access history transmitted from the item provider server 2 and generates an access history map.

Next, the operation of this embodiment will be described.

In the present embodiment, a correlation analysis is performed based on an access history (composed of a user identifier, an item identifier, a time list, etc.) of access (purchase and browsing of goods) to the item provider server 2. An example will be described.
In addition, even when an evaluation value is given to an item, a similar flow can be used. 1. Generation of access history map (FIG. 2) 1) From client 4 to item provider server 2
Browsing / purchasing items (step 21) The client 4 accesses the item provider server 2 to browse posted information, purchase products, input an evaluation value indicating the degree of interest, and the like, and access history. Is stored in the item provider server 2. This processing may be performed on merchandise sales data in a normal mail-order company or the like, or merchandise sales data in a normal store.

2) Correlation item detection / introduction device 1 from item provider server 2 (access history processing unit 1)
3) Transmission of access history to (Step 22) The item provider / server 2 collects the access history saved in 1) periodically or collectively when analysis / introduction is desired, and collects the correlated item detection / introduction device 1. (Access history processing unit 13). The access history includes a list of, for example, “client identifier, item identifier, purchase fee”, “client identifier, item identifier, access time”, “client identifier, item identifier, evaluation value indicating degree of interest”, and the like.

3) Generation of Access History Map by Access History Processing Unit 13 (Step 23) The access history processing unit 13 converts the access history received in 2) into a map format which can be easily processed by the correlation analysis process.
The access history map is, for example, a list of item identifiers accessed by each client for each client identifier (Table 1), and a list of client identifiers, item evaluation values, and the number of client accesses for each item for each item identifier (Table 1). Table 2). When generating the same map, the number of client accesses is calculated by counting the number of clients accessing each item received during the observation period (the number of times the same client accesses the same item is counted as 1). ).

[0019]

[Table 1]

[0020]

[Table 2] 4) Recording from the access history processing unit 13 to the access history map data 16a of the access history map management unit 16 (Step 24) The access history processing unit 13 stores the access history map generated in 3) in the access history map management unit 16. It is recorded in the access history map data 16a. 2. Correlation Item Detection (FIGS. 3 and 4) 1) Correlation item detection request from the item provider server 2 to the correlation item detection / introduction device 1 (correlation item analysis processing unit 12) (step 31). A list of item identifiers that are the source of the correlation item analysis together with the correlation item detection request, the client access number upper limit and client access lower limit of the analysis source item, and the client access number upper limit and client access lower limit of the correlation item It transmits to the correlation item detection / introduction device 1 (correlation item analysis processing unit 12).

2) Recording of band pass conditions from the correlation item analysis processing unit 12 to the band pass filter processing unit 14 (step 32) The correlation item analysis processing unit 12 sets the upper limit of the number of client accesses of the analysis source item received in 1) The value, the lower limit of the number of client accesses, the upper limit of the number of client accesses of the correlation item, and the lower limit of the number of client accesses are stored in the band-pass condition storage unit 14a of the band-pass filter processing unit 14.
To record.

3) Recording from the correlation item analysis processing unit 12 to the analysis source item list 15a of the analysis list storage unit 15 (step 33) The correlation item analysis processing unit 12 converts the list of item identifiers received in 1) into an analysis list The information is recorded in the analysis source item list 15a of the storage unit 15.

4) Request of analysis source item band pass from correlation item analysis processing unit 12 to band pass filter processing unit 14 (step 34) Correlation item analysis processing unit 12 requests analysis source item band pass to band pass filter processing unit 14. Send

5) Acquisition of Client Access Number from Access History Map Management Unit 16 by Band Pass Filter Processing Unit 14 (Step 35) The band pass filter processing unit 14
5 is read from the analysis source item list 15a, and the client access number is acquired from the access history map management unit 16 for each item identifier.

6) Filtering of Item Identifiers by Bandpass Filter Processing Unit 14 (Step 36) The client access number lower limit value and the client access number upper limit value of the analysis source item recorded in the bandpass condition storage unit 14a are read. ), The client access count is checked for each item identifier acquired, and an item identifier that is less than the client access count lower limit value or exceeds the client access count upper limit value of the analysis source item is analyzed by the analysis source item list 15a of the analysis list management unit 15.
, And returns an analysis source item bandpass response from the bandpass filter processing unit 14 to the correlation item analysis processing unit 12.

7) Related Client Group Extraction Process by Correlation Item Analysis Processing Unit 12 (Step 37) The correlation item analysis processing unit 12 that has received the analysis source item band pass response, the analysis source item list recorded in 6) For each item identifier recorded in 15a, a list of client identifiers accessing each item identifier is extracted from the access history map data 16a of the access history map management unit 16. This list of client identifiers is called a related client group. The correlation item analysis processing unit 12 records the related client group in the related client list 15b of the analysis list storage unit 15.

8) Process of narrowing down related client group in correlation item analysis processing section 12 (step 38) The correlation item analysis processing section 12 narrows down the related client group extracted in 7). As an example for narrowing down, the related client groups are sorted in the descending order of the number of accesses to the respective items stored in the analysis source item list 15a of the analysis list storage unit 15 (the order of the overlapping), and NNg2 are set as a new related client group and are recorded in the related client list 15b of the analysis list recording unit 15.

9) Extraction processing of related item group by correlation item analysis processing section 12 (step 39) The correlation item analysis processing section 12 includes the analysis list recording section 15
For each client identifier recorded in the related client list 15b, the access history map management unit 16 stores a list of item identifiers accessed by the client together with the item evaluation value and the number of client accesses.
From the access history map data 16a. This list of item identifiers is called a related item group. The correlation item analysis processing unit 12 stores the related item group, the item evaluation value for each item, and the number of client accesses in the related item list 1
Record at 5c.

10) Process of narrowing down related item group in correlation item analysis processing section 12 (step 40) The correlation item analysis processing section 12 narrows down the related item group extracted in 9). As an example for narrowing down, the related item groups are rearranged in the order of the number of accesses by the clients of the related client list 15b of the analysis list storage unit 15 (the order of the overlapping),
The top three NNg items are set as a new related item group. Also,
In another example, the related item groups are rearranged in descending order of the item evaluation value, and the top three NNg items are set as new related item groups.

The correlation item analysis processing section 12 stores the related item group and its item evaluation value in the analysis list storage section 1.
5 in the related item list 15c.

11) Related Item Band Pass Request from Correlation Item Analysis Processing Unit 12 to Band Pass Filter Processing Unit 14 (Step 41) The correlation item analysis processing unit 12 sends a related item band pass request to the band pass filter processing unit 14. Send.

12) Acquisition of Client Access Number from Access History Map Management Unit 16 by Band Pass Filter Processing Unit 14 (Step 42) The band pass filter processing unit 14
5 is read from the related item list 15c, and the client access number is acquired from the access history map management unit 16 for each identifier.

13) Filtering of the item identifier by the band-pass filter processing unit 14 (step 43) The client access number lower limit value and the client access number upper limit value of the correlation item recorded in the band-pass condition storage unit 14a are read, 12). Check the number of client accesses for each item identifier acquired in step 1 and delete the item identifiers that are less than the lower limit of the number of client accesses of the related item or that exceed the upper limit of the number of client accesses of the related item from the related item list of the analysis list storage unit 15. , The related item band pass response is returned from the band pass filter processing unit 14 to the correlation item analysis processing unit 12.

14) Correlation item detection response from the correlation item analysis processing unit 12 to the item provider server 2 (Step 44) The item list 15c is used as a correlation item detection result, and the analysis list storage unit 1 in which the correlation item detection response is the correlation detection result.
5, the list of item identifiers recorded in the related item list 15c and the item evaluation value of each item,
Item provider / request source of correlation item detection
Send to server 2. 3. Introduction of recommended items to the client based on the history of the client (FIGS. 6 and 7) 1) Request for introduction of recommended items from item provider server 2 to correlation item detection / introduction device 1 (correlation item analysis processing unit 12) (step) 51) The item provider server 2 requests the recommended item introduction together with the recommended item introduction request, the client identifier, the client access number upper limit and the client access number lower limit of the analysis source item, and the client access number upper limit and the client access of the correlated item. The lower limit of the number is transmitted to the correlation item detection / introduction device 1 (correlation item analysis processing unit 12).

2) Recording of band-pass conditions from correlation item analysis processing section 12 to band-pass filter processing section 14 (step 52) Same as 2-2) 3) Correlation item analysis processing section 12 to analysis list storage section 15 Recording in the analysis source item list 15a (step 53) Based on the client identifier received in 1), the correlation item analysis processing unit 12 stores a list of item identifiers accessed by the client during the observation period in an access history map. It is read from the access history map data of the management unit 16 and recorded in the analysis source item list of the analysis list storage unit 15.

4) Filtering of item identifiers by the band-pass filter processing unit 14 (steps 54 to 6)
3) Processing similar to 2-4) to 2-13) (steps 34 to 4)
Perform 3).

5) Response of recommended item introduction from correlation item analysis processing unit 12 to item provider server 2 (step 64) Upon reception of the related item band pass response, correlation item analysis processing unit 12 The item list 15c is used as a recommended item introduction result. The client identifier received in 3-1) together with the recommended item introduction response and the item identifier recorded in the related item list 15c of the analysis list storage unit 15 that is the recommended item introduction result. List and item rating values for each item,
Item provider / request source of correlation item detection
Send to server 2.

The following can be considered as another embodiment of the present invention.

The network is not limited to the Internet. There are a digital interactive TV, an information home appliance network, and the like.

Clients include a PC, a mobile phone, a digital two-way TV, an information home appliance, a communicable word processor, a communicable game machine, a communicable clock, a PDA and other mobile communication terminals.

The input / output is not limited to the Web. Using an electronic mail, a correlation detection request, a recommended item introduction request, a client ID, and the like are transmitted as an electronic mail document or as a title. An e-mail address can be used instead of the client ID. An introduction to the related item list can also be sent as an e-mail document.

In the embodiment shown in FIG. 1, the operation of the band-pass filter processing section is described as an independent processing section so as to clarify the operation. May be checked, and an item identifier that is less than the lower limit of the number of client accesses of the related item or that exceeds the upper limit of the number of client accesses of the related item may be deleted from the related item list 15 c of the analysis list storage unit 15.

In the present embodiment, the collaborative filtering is specially written. However, applying a band-pass filter to the result of other information filtering based on the number of client accesses has the same effect. Therefore, except for the collaborative filtering specific unit (specifically, the analysis list storage unit 15), a more general-purpose information filtering unit (filtering by keyword or filtering by attribute value) is used as a black box, and the output result is band-passed. A filter may be applied.

The processing shown in FIGS. 2, 3, 4, 6, and 7 is performed on a floppy disk, a CD-ROM, a DV
D and the like, and can be executed on a computer such as a personal computer.

[0045]

As described above, according to the present invention, the number of clients accessing each item (the number of purchases, the number of views, the number of evaluations, etc.) is used to set a client access number band-pass filter set in advance. By applying and specifying the range of the number of client accesses of the item to be introduced, the following effects can be obtained. 1) By designating the upper limit of the number of client accesses, it is possible to make it difficult to introduce items that are totally interested irrespective of their main interests. 2) By adjusting the range and position of the bandpass filter, a small group of clients with similar interests can introduce items of common interest.

For example, if there is a person accessing an idol-related item and a shogi-related item,
By narrowing down the upper limit of the filter, items related to shogi (including items related to Go and bonsai) can be introduced.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of a correlation item detection / introduction device according to an embodiment of the present invention.

FIG. 2 is a flowchart illustrating an access history map generation process.

FIG. 3 is a flowchart illustrating a correlation item detection process.

FIG. 4 is a flowchart illustrating a correlation item detection process.

FIG. 5 is an explanatory diagram of a correlation item detection process.

FIG. 6 is a flowchart illustrating a process of introducing a recommended item to a client based on the history of the client.

FIG. 7 is a flowchart illustrating a process of introducing a recommended item to the client based on the history of the client.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Correlated item detection / introduction apparatus 2 Item provider server 3 Network 4 Client 11 Input / output unit 12 Correlated item analysis processing unit 13 Access history processing unit 14 Bandpass filter processing unit 14a Bandpass condition storage unit 15 Analysis list storage unit 15a Analysis Original item list 15b Related client list 15c Related item list 16 Access history map management unit 16a Access history map data 21-24, 31-44, 51-64 Step

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) G06F 17/60 502 G06F 17/60 502 ZEC ZEC 17/30 340 17/30 340A

Claims (25)

[Claims] 1. A correlated item detection method for detecting a correlated item from items provided by an item provider server to a client, wherein each item in access history data that is a history of the client accessing the item provider server. Obtain the number of clients that have accessed each item included in the list of identifiers within a certain period of time, and delete the item identifiers whose number of clients is not within the specified range from the original access history data for detecting correlation. A correlation item detection method, wherein a correlation detection is performed. 2. Designating an item identifier group as a source of correlation detection, extracting a client identifier of a client group accessing an item of the item identifier group,
2. The method according to claim 1, wherein an item group commonly accessed by the clients is detected as a correlated item. 3. The method according to claim 1, wherein the number of clients accessing each item included in the list of item identifiers from which the correlated items are analyzed within a predetermined period is determined by an item provider server that provides the items to the client. Acquired from the access history data, which is the access history, deletes the item identifiers whose number of clients is not within the specified range, and obtains a list of client identifiers accessing the remaining item identifiers from the access history data by a group of related clients. The related client group is narrowed down, a list of item identifiers accessed by each client of the narrowed down related client group is extracted as a related item group from the access history data, and the related item group is narrowed down and narrowed down. Seki Obtain the number of clients that have accessed the item of each item identifier of the consecutive item group within a certain period from the access history data, and delete the item identifier whose number of clients is not within the specified range,
A correlated item detection method for transmitting a remaining item identifier to the item provider server as a correlated item detection response. 4. A list of item identifiers of items accessed by a client having a client identifier targeted for introduction of a recommended item within a predetermined period, based on a history of the client accessing an item provider server that provides the item to the client. Obtained from certain access history data, delete the item identifiers in which the number of clients accessed within a certain period is not within a specified range, and list the client identifiers accessing the remaining item identifiers from the access history data. Extracting the related client group, narrowing down the related client group, extracting a list of item identifiers accessed by each client of the narrowed down related client group as the related item group from the access history data, The group is narrowed down, the number of clients of each item identifier of the narrowed related item group is obtained from the access history map data, and the number of clients accessed within a certain period is deleted from the specified range, and the item identifier is deleted, A recommended item introduction method for sending a client identifier targeted for the recommended item introduction and a remaining item identifier to the item provider server as a recommended item introduction response. 5. Sorting the clients in the group of related clients in descending order of the number of accessing the respective items of the analysis source, and setting a predetermined high-order number as a new group of related clients, whereby the number of related clients is reduced. 5. The method according to claim 3, wherein the narrowing is performed. 6. Sorting the items in the related item group in descending order of the number of accesses by each client of the related client group, and setting a predetermined higher order item as a new related item group, thereby obtaining the related item 5. The method according to claim 3, wherein the group is narrowed down. 7. The related item group is narrowed down by rearranging the related item group in the descending order of the item evaluation value, and setting a predetermined higher number as a new related item group. the method of. 8. The method of claim 1, wherein the client and the item provider server communicate over the Internet. 9. The method according to claim 1, wherein the client and the server communicate via digital interactive TV. 10. The method according to claim 1, wherein the client and the server communicate over an information appliance network. 11. The method according to claim 1, wherein the client is a terminal capable of performing mobile communication. 12. The client is a mobile phone,
The method of claim 11. 13. The method of claim 11, wherein said client is a digital interactive TV. 14. The client is an information home appliance.
The method of claim 11. 15. The method of claim 11, wherein said client is a word processor capable of two-way communication. 16. The method of claim 11, wherein the client is a communicable game console. 17. The method of claim 11, wherein the client is a communicable clock. 18. The method of claim 11, wherein said client is a PDA. 19. An access history in which a client receives access history data, which is a history of accessing an item provider server that provides an item to the client, from the item provider server together with a correlated item detection request for detecting a correlated item. A processing unit, an access history map management unit that stores access history data, an analysis source item list that stores an item group that is a source of a correlation item analysis, and a client group that accesses the item group of the analysis source item list A related client list storing a client identifier of the group, an analysis list storage unit including a related item list storing an item identifier of an item group accessed by the client group, and a bandpass condition storage unit, Note in the department Read the stored client number range of the analysis source item, read out the item identifiers stored in the analysis source item list of the analysis list storage unit, and determine the number of clients that accessed the item of each item identifier within a certain period. Obtained from the access history data, check the number of clients for each item identifier, delete from the analysis source item list of the analysis list management unit the item identifier the number of clients is not included in the client number range of the analysis source item, An analysis source item band response is output, an item identifier stored in the related item list of the analysis list storage unit is read, and the number of clients that have accessed the item of each item identifier within a predetermined period is obtained from the access history data. And stored in the bandpass condition storage unit. The client number range of the related item stored is read out, the number of clients is checked for each of the acquired item identifiers, and the item identifiers whose client numbers are not included in the client number range of the related item are stored in the analysis list storage unit. A band-pass filter processing unit that deletes the item from the item list and outputs a related item band-pass response; receives a correlation item detection request from the item provider server; and issues an analysis source item band-pass request to the band-pass filter processing unit. Upon receiving the analysis source item band pass response from the band pass filter processing unit, extracting a list of client identifiers that accessed the item identifiers recorded in the analysis source item list as a related client group from the access history data, Record in the related client list of the analysis list storage unit, narrow down the related item group, record it in the related client list as a new related client group, and check the client of the client identifier recorded in the related client list. A list of accessed item identifiers is extracted as a related item group from the access history data, the related item group is recorded in a related item list of the analysis list storage unit, the related item group is narrowed down, and a new related item group is performed. When the related item list is recorded in the related item list of the analysis list storage unit, a related item bandpass request is issued to the bandpass filter processing unit, and a related item bandpass response is received from the bandpass filter processing unit. Related Items Correlation item detection and introduction apparatus having a correlation item analytical processing unit to send a list of item identifiers contained in the list to the item provider server. 20. An access history processing unit that receives, from an item provider server, access history data that is a history of a client accessing an item provider server that provides an item to the client, and an access history that stores the access history data. A map management unit, an analysis source item list storing an item group that is a source of a correlation item analysis, an associated client list storing a client identifier of a client group accessing the item group of the analysis source item list, a client group An analysis list storage unit including a related item list storing an item identifier of an item group accessed by the user, and a bandpass condition storage unit, and the number of clients of the analysis source items stored in the bandpass condition storage unit Read range Reading out the item identifiers stored in the analysis source item list of the analysis list storage unit, acquiring the number of clients accessing the items of each item identifier within a certain period from the access history data, and for each item identifier Check the number of clients, delete the item identifiers not included in the client number range of the analysis source item from the analysis source item list of the analysis list management unit, output the analysis source item band response, and The item identifier stored in the item list is read out, the number of clients accessing the item of each item identifier within a predetermined period is obtained from the access history map management unit, and the associated number stored in the bandpass condition storage unit is obtained. Read the client number range of the item and obtain the information The number of clients is checked for each item identifier, and the item identifiers whose number of clients are not included in the range of the number of clients of the related item are deleted from the related item list in the analysis list storage unit, and a band that outputs a related item band pass response A path filter processing unit, receiving a recommended item introduction request together with a recommended item introduction target client identifier from the item provider server, and a list of item identifiers accessed by the client of the client identifier within a certain period of time in the access history. It is extracted from the data as a related item group, recorded in the analysis source item list in the analysis list storage unit, issues an analysis source item band pass request to the band pass filter processing unit, and the analysis source item band is sent from the band pass filter processing unit. Upon receiving the system band pass response, a list of client identifiers that accessed the item identifiers recorded in the analysis source item list is extracted from the access history data as a group of related clients, and the list of related clients in the analysis list storage unit is Recording, narrowing down the related item group, recording the related item group in the related client list as a new related client group, and storing the list of item identifiers accessed by the client whose client identifier is recorded in the related client list as the access history. A related item group is extracted from the data, the related item group is recorded in the related item list of the analysis list storage unit, the related item group is narrowed down, and a related item of the analysis list storage unit is defined as a new related item group. When a related item band pass request is issued to the band pass filter processing unit and a related item band pass response is received from the band pass filter processing unit, the related item band pass response is recorded in the related item list of the analysis list storage unit. A correlated item detection / introduction device having a correlated item analysis processing unit for transmitting a list of item identifiers to the item provider server. 21. The correlated item analysis processing unit reorders the items in the related client group in descending order of the number of accesses to each item stored in the analysis item list, and newly sorts a predetermined higher number. 21. The apparatus according to claim 19, wherein the related client group is narrowed down by setting the related client group. 22. The correlation item analysis processing unit sorts the items in the related item group in descending order of the number of clients accessed in the related client list, and sorts a predetermined number of higher ranks into a new related item group. The apparatus according to claim 19, wherein the related item group is narrowed down by the following. 23. The related item group, wherein the correlated item analysis processing unit sorts the items in the related item group in descending order of the item evaluation value, and sets a predetermined high order item as a new related item group. 21. The apparatus according to claim 19, wherein the filtering is performed. 24. A correlation item detection program for executing the method according to claim 1. Description: 25. A recording medium on which the correlation item detection program according to claim 24 is recorded.