Information processing device, information processing method, and program

Abstract

To solve the problem that it is impossible to estimate a user's intention on the basis of user's operation on a web page and perform an appropriate action that corresponds to the intention.SOLUTION: An information processing device 1 comprises: a correspondence storage unit 112 in which one or more pieces of correspondence information are stored that indicate correspondence between an intention identifier based on one or more pieces of operation information and action information for identifying an action performed on a user's terminal device 2; a receiving unit 12 for receiving one or more pieces of operation information; a determination unit 132 for determining the intention identifier that corresponds to the one or more pieces of operation information received by the receiving unit 12; an information acquisition unit 134 for referring to the correspondence storage unit 112 and acquiring action information that corresponds to the intention identifier determined by the determination unit 132; and an action unit 135 for performing an action on the terminal device 2 corresponding to the user identifier, the action being identified by the action information acquired by the information acquisition unit 134.SELECTED DRAWING: Figure 2

Description

Technical Field

[0005] ,

[0001] The present invention relates to an information processing apparatus and the like that estimates a user's intention based on a user's operation on a web page and performs an action corresponding to the intention.

Background Art

[0002] Conventionally, there has been a technique for grasping the situation of visitors to a website in real time (see Patent Document 1). Such a technique includes a user information storage unit that stores two or more pieces of user information that are information about a user and have one or more attribute values, an operation information receiving unit that receives operation information regarding a user's operation on a website from the user terminal of the user who is a visitor to the website, an attribute value acquisition unit that acquires one or more attribute values of the user visiting the website using the operation information, and an attribute value output unit that outputs the one or more attribute values acquired by the attribute value acquisition unit. It is a technique related to a server device.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, based on a user's operation on a web page, it was not possible to estimate the user's intention and perform an appropriate action corresponding to the intention.

Means for Solving the Problems

[0005] The first information processing apparatus of the present invention comprises: a correspondence storage unit that stores correspondence between intent identifiers based on one or more operation information and action information that specifies an action to be performed on the user's terminal device; a receiving unit that receives one or more operation information associated with a user identifier; a determination unit that determines an intent identifier corresponding to the one or more operation information received by the receiving unit; an information acquisition unit that refers to the correspondence storage unit and acquires action information corresponding to the intent identifier determined by the determination unit; and an action unit that performs the action specified by the action information acquired by the information acquisition unit on the terminal device corresponding to the user identifier.

[0006] This configuration allows for the estimation of user intent based on user actions on a web page, and enables appropriate actions to be taken in response to that intent.

[0007] Furthermore, the information processing device of the second invention, compared to the first invention, is an information processing device in which the corresponding information is information indicating the correspondence between an intent identifier, intensity conditions related to intensity information indicating the strength of the user's intent, and action information, and the information acquisition unit acquires intensity information using one or more operation information received by the receiving unit, and, by referring to the corresponding storage unit, acquires action information corresponding to the intensity conditions that match the intent identifier determined by the determination unit and the intensity information.

[0008] With this configuration, it is possible to estimate the user's intent and the strength of that intent based on the user's actions on the web page, and to take appropriate actions corresponding to that intent and its strength.

[0009] Furthermore, the information processing device of this third invention, compared to the first invention, is an information processing device in which the corresponding information is information that shows the correspondence between an intent identifier, an abstraction condition relating to abstraction information indicating the level of abstraction of the user's intent, and action information, and the information acquisition unit acquires abstraction information using one or more operation information received by the receiving unit, and, by referring to the corresponding storage unit, acquires action information corresponding to the abstraction condition that matches the intent identifier determined by the determination unit and the abstraction information.

[0010] With this configuration, it is possible to estimate the user's intent and the level of abstraction of that intent based on the user's actions on the web page, and to take appropriate actions corresponding to that intent and level of abstraction.

[0011] Furthermore, the information processing device of the fourth invention is an information processing device in which, compared to the first invention, the corresponding information is information that shows the correspondence between an intent identifier, attribute value conditions relating to one or more user attribute values, and action information, and the information acquisition unit acquires user attribute values, refers to the corresponding storage unit, and acquires action information corresponding to the user attribute value conditions that match the intent identifier and user attribute value determined by the determination unit.

[0012] With this configuration, it is possible to estimate the user's intent based on the user's actions on the web page and take appropriate actions corresponding to that intent and user attribute values.

[0013] Furthermore, the information processing device of this fifth invention is an information processing device in which, with respect to any one of the first to fourth inventions, the information acquisition unit acquires unique information in one or more operation information from one or more operation information, and the action unit performs an action using the action information and the unique information.

[0014] With this configuration, it is possible to estimate the user's intent based on the user's actions on a web page and take appropriate actions corresponding to that intent, using unique information obtained from the operation information.

[0015] Furthermore, the information processing device of the sixth invention further comprises, with respect to any one of the first to fourth inventions, an intention storage unit that stores two or more intention identifiers associated with a user identifier, and an intention storage unit that stores the intention identifiers determined by the determination unit in the intention storage unit in association with a user identifier, and an information acquisition unit that acquires action information corresponding to two or more intention identifiers associated with one user identifier and the two or more intention identifiers stored by the intention storage unit.

[0016] With such a configuration, it is possible to estimate a plurality of intentions of a user based on the user's operations on a web page and perform appropriate actions corresponding to the plurality of intentions.

[0017] Further, in the information processing apparatus of the seventh invention, for any one of the first to fourth inventions, the intention identifier is associated with one or more operation conditions based on two or more pieces of operation information, and the determination unit detects an operation condition that matches the one or more pieces of operation information and determines an intention identifier corresponding to the operation condition.

[0018] With such a configuration, it is possible to estimate the intention of a user based on the pattern of the user's operations on a web page and perform appropriate actions corresponding to the intention.

[0019] Further, in the information processing apparatus of the eighth invention, for any one of the first to fourth inventions, a model storage unit stores a model obtained by learning processing of machine learning using two or more pieces of teacher data having one or more pieces of operation information and intention identifiers, and the determination unit performs prediction processing of machine learning using the one or more pieces of operation information and the model and determines an intention identifier.

[0020] With such a configuration, it is possible to estimate the intention of a user based on the user's operations on a web page by means of an algorithm of machine learning and perform appropriate actions corresponding to the intention.

Advantages of the Invention

[0021] According to the information processing apparatus of the present invention, it is possible to estimate the intention of a user based on the user's operations on a web page and perform appropriate actions corresponding to the intention.

Brief Description of the Drawings

[0022] [Figure 1] Conceptual diagram of information system A in Embodiment 1 [Figure 2] Block diagram of the information system A [Figure 3]Flowchart for explaining an operation example of the information processing apparatus 1 [Figure 4] Flowchart for explaining an example of consensus diagram determination processing [Figure 5] Flowchart for explaining an example of the same action processing [Figure 6] Flowchart for explaining an example of the previous processing [Figure 7] Diagram showing the same user information management table [Figure 8] Diagram showing the same first correspondence information management table [Figure 9] Diagram showing the same second correspondence information management table [Figure 10] Diagram showing the same strength management table [Figure 11] Diagram showing the same abstraction level management table [Figure 12] Diagram showing the same operation information management table [Figure 13] Diagram showing the same user intention management table [Figure 14] Block diagram of the information system B in the second embodiment [Figure 15] Flowchart for explaining an operation example of consensus diagram determination [Figure 16] Overview diagram of the computer system in the above embodiment [Figure 17] Block diagram of the same computer system

Modes for Carrying Out the Invention

[0023] Hereinafter, embodiments of an information processing apparatus and the like will be described with reference to the drawings. In the embodiments, components denoted by the same reference numerals perform the same operations, and thus the description may be omitted again.

[0024] (Embodiment 1) In this embodiment, an information system is described that includes an information processing device that receives one or more operation information, obtains an intent identifier from the one or more operation information, and performs an action corresponding to the intent identifier for the user. The action is, for example, an action using unique information obtained from the operation information.

[0025] Furthermore, this embodiment describes an information system that includes an information processing device that also acquires intent strength information and performs actions for the user corresponding to the intent identifier and the intensity information.

[0026] Furthermore, in this embodiment, we will describe an information system that includes an information processing device that also acquires abstraction information of intent and performs actions on the user corresponding to the intent identifier and the abstraction information.

[0027] Furthermore, in this embodiment, we will describe an information system that includes an information processing device that determines an action using two or more intent identifiers.

[0028] Furthermore, in this embodiment, an information system comprising an information processing device that performs actions corresponding to operating conditions will be described.

[0029] In this specification, information X being associated with information Y means that information Y can be obtained from information X, or information X can be obtained from information Y, and the method of association is irrelevant. Information X and information Y may be linked, may reside in the same buffer, may information X be contained in information Y, or information Y may be contained in information X, and so on.

[0030] Figure 1 is a conceptual diagram of information system A in this embodiment. Information system A comprises an information processing device 1 and one or more terminal devices 2.

[0031] Information processing device 1 is a device that performs actions on terminal device 2 based on operation information. Information processing device 1 is usually a so-called server. Information processing device 1 may be a cloud server, ASP server, etc., but the type is not limited. Information processing device 1 may also function as a web server.

[0032] Terminal device 2 is a terminal used by the user. Terminal device 2 is a terminal that accesses one or more web servers B and outputs web pages. Terminal device 2 is a terminal that accepts operations on web pages. Terminal device 2 is, for example, a terminal that transmits operation information based on the operations it has received to the information processing device 1. Terminal device 2 is, for example, a so-called personal computer, tablet terminal, smartphone, etc., but the type is not limited.

[0033] The information processing device 1 and one or more terminal devices 2 can communicate with each other via a network such as the Internet. Furthermore, each of the one or more terminal devices 2 and one or more web servers (not shown) may also communicate with each other via a network such as the Internet.

[0034] Furthermore, each of the one or more terminal devices 2 can communicate with the web server B via a network such as the Internet. It is also preferable that the information processing device 1 can communicate with the web server B via a network such as the Internet.

[0035] Web server B is a server that stores web pages and sends web pages to terminal device 2 in response to requests from terminal device 2. Web server B is, for example, a server for operating a website. Web server B may also send operation information to information processing device 1 in response to operations received from terminal device 2. The website is, for example, a so-called e-commerce site, but it is not an e-commerce site, and may be an information provision site, etc., and its type is not limited. Also, web server B is a cloud server, ASP server, etc., but its type is not limited.

[0036] Figure 2 is a block diagram of information system A in this embodiment. The information processing device 1 that constitutes information system A includes a storage unit 11, a receiving unit 12, a processing unit 13, and a transmitting unit 14.

[0037] The storage unit 11 includes a user storage unit 111, a corresponding storage unit 112, an operation storage unit 113, and an intent storage unit 114. The processing unit 13 includes an operation storage unit 131, a decision unit 132, an intent storage unit 133, an information acquisition unit 134, and an action unit 135.

[0038] The terminal device 2 includes a terminal storage unit 21, a terminal receiving unit 22, a terminal processing unit 23, a terminal transmission unit 24, a terminal receiving unit 25, and a terminal output unit 26.

[0039] The storage unit 11 of the information processing device 1 stores various types of information. These types of information include, for example, user information, correspondence information, operation information, and intent identifiers, which will be described later.

[0040] The user storage unit 111 stores one or more user information. User information refers to information about a user. User information includes a user identifier and one or more user attribute values.

[0041] A user identifier is information that identifies a user. Examples of user identifiers include a user ID, email address, phone number, and user's name.

[0042] User attribute values ​​are attribute values ​​of a user identified by a user identifier. One or more user attribute values ​​may be static or dynamic. Static attribute values ​​are typically attribute values ​​that do not change, but can also be thought of as attribute values ​​that do not change moment by moment. Examples of static attribute values ​​include name, age, address, telephone number, user-specific image, credit card number, email address, terminal device identifier, and password. The terminal device identifier is information that identifies the terminal device used by the user, and examples include Cookie ID, session identifier, IP address, and MAC address. Dynamic attribute values ​​are attribute values ​​that can change dynamically due to user actions, etc. Examples of dynamic attribute values ​​include real-time dynamic attribute values ​​and history-based dynamic attribute values. Real-time dynamic attribute values ​​are attribute values ​​that change moment by moment in real time. Examples of real-time dynamic attribute values ​​include the time spent on the web page the user is currently viewing (hereinafter referred to as "page" as appropriate), and the number of web pages viewed during the current stay. History-based dynamic attribute values ​​are dynamic attribute values ​​obtained using the history of user actions during past visits. For example, history-based dynamic attribute values ​​are scores calculated using purchase count, purchase amount, total purchase amount, average time spent on the site, average page views, number of visits, and other user attribute values ​​(e.g., purchase count, total purchase amount).

[0043] The correspondence storage unit 112 stores one or more correspondence information. The correspondence information in the correspondence storage unit 112 is usually associated with web server B. Associating with web server B may also mean associating with a website or web page. In other words, it is preferable that the method of determining intent and the actions to be performed differ depending on the website.

[0044] Correspondence information is information used to determine the action corresponding to a determined intention. Correspondence information is information that shows the correspondence between an intention identifier and action information. Correspondence information includes, for example, operation conditions and action information. Operation conditions correspond to the intention identifier. Operation conditions are conditions relating to one or more operation information. Operation conditions may also be operation patterns as described later. Operation conditions may include conditions relating to the number of times a particular operation is performed. Operation conditions may include conditions relating to the time spent on a particular web page. Operation conditions may include conditions relating to the order of two or more particular operations. Operation conditions may also be conditions relating to combinations of two or more particular operations.

[0045] Correspondence information may also be information showing the correspondence between intent identifiers, action information, and intensity information. Information showing the correspondence with intensity information may also be information showing the correspondence with intensity conditions, for example. Intensity conditions are conditions related to intensity information. An example of an intensity condition is "intensity information >= 3". Intensity information is information indicating the intensity of the user's intent. An example of intensity information is a natural number from "1" to "5", "A", "B", or "C".

[0046] Correspondence information may also be information showing the correspondence between intent identifiers, action information, and abstraction information. Information showing the correspondence with abstraction information may also be information showing the correspondence with abstraction conditions, for example. Abstraction conditions are conditions related to abstraction information. An example of an abstraction condition is "Abstraction Information >= 4". Abstraction information is information indicating the level of abstraction of the user's intent. An example of abstraction information is a natural number from "1" to "5", "A", "B", or "C".

[0047] Correspondence information may also be information showing the correspondence between intent identifiers, action information, and user attribute values. Information showing the correspondence with user attribute values ​​may also be information showing the correspondence with user attribute value conditions, for example. User attribute value conditions are conditions relating to one or more user attribute values. It is preferable that user attribute value conditions include conditions relating to one or more dynamic attribute values. It is preferable that user attribute value conditions include conditions relating to one or more real-time dynamic attribute values. It is preferable that user attribute value conditions include conditions relating to one or more dynamic attribute values ​​that utilize historical information. For example, user attribute value conditions are "Total purchase amount >= 10,000 yen", "Number of purchases >= 5", and "Time spent >= 3 minutes".

[0048] Correspondence information may also be information that shows the correspondence between intent identifiers, intent patterns, and action information. An intent pattern is, for example, a condition relating to two or more intent identifiers. An intent pattern is, for example, a condition relating to one or more intent identifiers and one or more operation information. If an intent pattern includes conditions relating to two or more intent identifiers, the intent pattern may also include conditions relating to the order of those two or more intent identifiers, or conditions relating to combinations of two or more intent identifiers. A condition relating to the order of two or more intent identifiers is a condition relating to the order in which each of the two or more intent identifiers is determined. The order of two or more intent identifiers is determined based on the time information corresponding to each of the two or more intent identifiers.

[0049] An intent identifier is information that identifies an intent based on one or more operational information. Typically, an intent identifier identifies an intent based on two or more operational information. For example, an intent identifier identifies an intent based on the history of two or more operational information (two or more operational information based on operations at different times). An intent identifier may consist of, for example, an ID that identifies the intent (intent ID) and a string that describes the intent. It is preferable that the intent identifier is associated with one or more operational conditions based on two or more operational information.

[0050] Operation information refers to information about actions a user has taken on a web page. Examples of operation information include information indicating access to a page, viewing a page, clicking a button on a page, selecting an anchor, performing an action to jump to another page, entering information into a field, adding a product to favorites, and entering a product name and performing a search. Operation information may also include information about the results of an operation. Examples of results include the result of scrolling, or the relative coordinates of the window's center on the web page. Other examples of results include the product identifier and attribute values ​​of products displayed in the window after scrolling (e.g., price, product image, size, stock quantity, availability, styling examples). Finally, examples of results include the product identifier of a purchased product, the product identifier of an item added to the cart, and the product identifier of an item added to favorites. Product identifiers are examples such as product ID and product name.

[0051] Operation information includes, for example, "rightButtonON" (indicating the right mouse button was pressed), "drug object A" (indicating object A was dragged), "<Purchase Item ID>123 <Quantity>3" (indicating that 3 units of the item identified by 123 were purchased), and "jump http: / / www.xxx.co.jp" (indicating that a webpage identified by the URL "http: / / www.xxx.co.jp" was accessed). The operation information here is, for example, information about primitive operations, but it is preferable that it is information that allows for the determination of the meaning and significance of the operation. In other words, the data structure and granularity of the operation information are not specified. The operation information usually identifies the operation performed by the user, but it may also include information about processing performed by the information processing device 1 as a result of the user's operation. Note that the operation information received by the receiving unit 12 and the operation information stored in the operation storage unit 113 may be different. The operation information received by the receiving unit 12 and the operation information stored in the operation storage unit 113 may have different data structures, for example. For example, the operation information received by the receiving unit 12 may be primitive operation information (e.g., "rightButtonON"), while the operation information stored in the operation storage unit 113 may be information that allows the meaning and significance of the operation to be determined (e.g., "Page XX has been displayed"). In this case, the processing unit 13 uses the received operation information to construct the operation information to be stored in the operation storage unit 113. In this case, the processing unit 13 obtains, for example, operation information from the storage unit 11 that corresponds to the received primitive operation information.

[0052] Furthermore, it is preferable that the operation information is associated with time information, user identifier, and page identifier.

[0053] Time information identifies the time when an operation was performed. This time information can include, for example, the day, date, time, or duration (e.g., a sales period). Note that the time of operation can also be the time when the operation information is received. In other words, the time of operation only needs to be roughly identifiable as the time of the user's operation; strict accuracy is not required.

[0054] A page identifier is information that identifies a webpage being manipulated. Examples of page identifiers include URLs, URIs, and webpage IDs. A webpage can also refer to a website. Here, we can consider "webpage" to be synonymous with "website." Therefore, a page identifier can also be information that identifies a website.

[0055] An operation pattern is a pattern of operations identified by one or more operation information. Examples of operation patterns include: "information indicating that the user visited the webpage two or more times during a sale period," "information indicating that the user performed a search N or more times (where N is a natural number greater than or equal to 2) using the same product name as the key," "information indicating that the user (1) accessed the top page, (2) accessed the link to their favorite products, and (3) clicked the 'Also Recommended' link," "information indicating that the user (1) accessed the page for products that are not yet in stock, and (2) jumped to another page or logged out within a threshold time," and "the user has added more than one item above the first threshold to their favorites, and has not added any items to their cart for more than the second threshold time while having added more than one item above the first threshold to their favorites." Note that operation patterns can also be considered examples of operation conditions.

[0056] Action information is information that identifies an action to be performed on the user's terminal device 2. An action can also be described as a process or operation. Action information includes, for example, a function name, a pointer to a program to jump to, a module name, and a method name. Examples of action information include: "Information indicating that a banner that allows access to sale items will be sent to terminal device 2," "Information indicating that an email informing of a sale will be sent when a sale is held," "Information indicating that a chat message will be sent to terminal device 2 stating that the user can check the details with a store employee," "Information indicating that the following processes will be carried out: (1) obtaining product information from the web page the user is viewing or product information in their favorites, and (2) sending a banner to terminal device 2 to access a web page containing product information for products whose product type matches the obtained product information, and which is a featured page for recently popular products," "Information indicating that information will be sent to terminal device 2 regarding registration for restock emails," and "Information indicating that the following processes will be carried out: (1) detecting that a favorite product has become a sale item, and (2) after such detection, sending an email to terminal device 2 informing the user that the favorite product has become a sale item."

[0057] The operation storage unit 113 stores one or more operation information based on operations performed by the user. Preferably, the operation information here is associated with a user identifier, a page identifier, and time information. The page identifier here is, for example, the page currently being output to the user's terminal device 2, which is identified by the user identifier, and is the identification information of the page being operated on. The page identifier may also be the identification information of pages that the user has accessed in the past. The operation information in the operation storage unit 113 is usually information stored in the operation storage unit 131, which will be described later, but the process leading up to its storage is not relevant.

[0058] The intent storage unit 114 stores intent identifiers that identify the intent based on the user's actions. Typically, the intent storage unit 114 stores one or more intent identifiers associated with one or more user identifiers. The intent identifiers in the intent storage unit 114 are intent identifiers determined by the determination unit 132. It is preferable that the intent identifiers in the intent storage unit 114 are associated with time information. The time information associated with the intent identifier is information that identifies the time when the user performed an action on the page and the intent identifier was determined.

[0059] The receiving unit 12 receives one or more operation information associated with a user identifier. The receiving unit 12 usually receives operation information directly or indirectly from the terminal device 2. However, the receiving unit 12 may also receive operation information from the web server B. In addition, the receiving unit 12 may receive operation information stored in other devices from those other devices. The operation information received by the receiving unit 12 is usually associated with time information. The time information associated with the operation information is generally information that identifies the time when the operation was performed.

[0060] The processing unit 13 performs various processes. These processes include, for example, those performed by the operation storage unit 131, the decision unit 132, the intention storage unit 133, the information acquisition unit 134, and the action unit 135.

[0061] The processing unit 13 may, for example, analyze the operation information stored in the operation information storage unit 114 and obtain the dynamic attribute values ​​of each user. The processing unit 13 may, for example, update the user's dynamic attribute values ​​based on the received operation information. If the received operation information is a website submission instruction, the processing unit 13 measures the time spent on the website, which is the time until an instruction to move to another website or a logout instruction is received, and stores the time spent in the user storage unit 111. The processing unit 13 may also, for example, increment the number of visits to the website or web page of the server device 1 based on a received login instruction or a received website submission instruction, and store it in the user storage unit 111. The processing unit 13 may also, for example, if the received instruction is a product purchase instruction, increment the number of purchases based on the received purchase instruction, and store it in the user storage unit 111. Furthermore, the processing unit 13 calculates each user's score by substituting one or more parameters from among website or web page dwell time, number of purchases, purchase amount, total purchase amount, page views, average dwell time, and number of visits into the score calculation formula. The score calculation formula is stored in the storage unit 11. The score calculation formula is information about the formula used to calculate a user's score. For example, a higher user score is considered to indicate a more important user. The score calculation formula is an increasing function that takes one or more of the following information as parameters: website or web page dwell time, number of purchases, purchase amount, total purchase amount, page views, average dwell time, and number of visits.

[0062] The operation storage unit 131 stores the operation information received by the receiving unit 12 in the operation storage unit 113. The operation storage unit 131 stores the operation information received by the receiving unit 12 in the operation storage unit 113, for example, by associating it with one or more pieces of information from among the user identifier, page identifier, and time information.

[0063] The operation storage unit 131, for example, when the receiving unit 12 receives operation information, obtains a user identifier that is paired with the operation information. The operation storage unit 131 also obtains time information, which is the current time, from a clock (not shown), for example. The operation storage unit 131 also obtains a page identifier included in the operation information, for example. Then, the operation storage unit 131 stores the operation information received by the receiving unit 12 in the operation storage unit 113, associating it with the user identifier, page identifier, and time information.

[0064] The determination unit 132 determines an intent identifier corresponding to one or more operation information received by the receiving unit 12. Determining the intent identifier is equivalent to determining the intent. Alternatively, determining the intent identifier may also mean determining the action information.

[0065] The determination unit 132, for example, detects an operation condition that matches one or more operation information items and determines an intent identifier corresponding to that operation condition. Alternatively, the determination unit 132 may detect an operation condition that matches one or more operation information items corresponding to a user identifier from one or more operation conditions in the corresponding storage unit 112 and determine an intent identifier corresponding to that operation condition.

[0066] The determination unit 132 acquires, for example, one or more operation information that is paired with a user identifier. The determination unit 132 acquires, for example, one or more operation information that is paired with a user identifier from the operation storage unit 113. The determination unit 132 also acquires, for example, operation information received by the receiving unit 12. Next, the determination unit 132 determines, for example, an operation condition that matches the acquired one or more operation information from the operation conditions stored in the corresponding storage unit 112, and acquires an intent identifier corresponding to that operation condition. The determination unit 132 may acquire action information corresponding to the determined operation condition instead of acquiring an intent identifier.

[0067] Furthermore, the determination unit 132 may, for example, obtain intensity information corresponding to the determined operating conditions from the corresponding storage unit 112. Also, the determination unit 132 may, for example, obtain abstraction level information corresponding to the determined operating conditions from the corresponding storage unit 112.

[0068] The timing of the determination unit 132's determination of the intent identifier is not specified. It is preferable for the determination unit 132 to perform processing to acquire the intent identifier each time the receiving unit 12 receives operation information. However, the determination unit 132 may also perform processing to acquire the intent identifier at a predetermined time, such as when it receives instructions from an administrator terminal (not shown) of the information processing device 1 or web server B. It should be noted that even if such processing is performed, there may be cases where the intent identifier cannot be acquired.

[0069] The intention storage unit 133 stores the intention identifier determined by the determination unit 132 in the intention storage unit 114, associating it with the user identifier. The intention storage unit 133 may also acquire time information and store the intention identifier in the intention storage unit 114, associating it with that time information. The intention storage unit 133 may, for example, acquire time information from a clock (not shown), or acquire time information received by the receiving unit 12.

[0070] The information acquisition unit 134 refers to the corresponding storage unit 112 and acquires action information corresponding to the intent identifier determined by the determination unit 132. The information acquisition unit 134 may also acquire action information determined by the determination unit 132.

[0071] The information acquisition unit 134 may refer to the corresponding storage unit 112 and acquire action information and intensity information corresponding to the intent identifier determined by the determination unit 132.

[0072] The information acquisition unit 134 may refer to the corresponding storage unit 112 and acquire action information and abstraction level information corresponding to the intent identifier determined by the determination unit 132.

[0073] The information acquisition unit 134 preferably acquires unique information for one or more operation information from one or more operation information. Unique information is information specific to the corresponding operation information, or information specific to the page that is the target of the operation indicated by the corresponding operation information. Unique information may include, for example, a product identifier (e.g., product name) or one or more product attribute values ​​(e.g., product type, price).

[0074] The information acquisition unit 134 is preferably an information acquisition unit that acquires action information corresponding to two or more intent identifiers associated with a single user identifier, and the intent storage unit 133 has stored two or more intent identifiers.

[0075] The information acquisition unit 134 acquires intensity information using, for example, one or more operation information received by the receiving unit 12. Then, the information acquisition unit 134 refers to, for example, the corresponding storage unit 112 and acquires action information corresponding to the intensity condition that matches the intent identifier determined by the determination unit 132 and the intensity information. The information acquisition unit 134 also acquires intensity source information from, for example, one or more operation information. Then, the information acquisition unit 134 acquires intensity information corresponding to the intensity source information. Intensity source information is information from which intensity information is acquired. Intensity source information is, for example, the time spent on a web page by the user, the number of times the web page has been viewed, and the number of product names searched. The information acquisition unit 134 acquires intensity information that is paired with the intensity condition that the intensity source information satisfies. In such cases, two or more intensity conditions and intensity information are managed in pairs. Furthermore, the information acquisition unit 134 acquires stronger intensity information, for example, the longer the time spent on the web page. The information acquisition unit 134 acquires stronger intensity information, for example, the more times a web page has been viewed. The information acquisition unit 134 acquires weaker intensity information, for example, the more product names that have been searched for. This is because it is not particularly focused on any specific product.

[0076] The information acquisition unit 134 acquires abstraction information using, for example, one or more operation information received by the receiving unit 12. Then, the information acquisition unit 134 refers to, for example, the corresponding storage unit 112 and acquires action information corresponding to the abstraction condition that matches the intent identifier determined by the determination unit 132 and the abstraction information. The information acquisition unit 134 also acquires, for example, source abstraction information from one or more operation information. Then, the information acquisition unit 134 acquires abstraction information corresponding to the source abstraction information. Source abstraction information is information from which abstraction information is acquired. Source abstraction information is, for example, the time spent on a web page by a user, the number of web page views, and the number of product names searched. The information acquisition unit 134 acquires, for example, abstraction information that is paired with the abstraction condition that the source abstraction information satisfies. In such cases, two or more abstraction conditions and abstraction information are managed in pairs. Furthermore, the information acquisition unit 134 acquires, for example, higher abstraction information the shorter the time spent on the web page. The information acquisition unit 134 acquires lower-level abstraction information, for example, the more times a web page has been viewed. The information acquisition unit 134 acquires higher-level abstraction information, for example, the more times a product name has been searched.

[0077] The information acquisition unit 134 acquires intensity information and abstraction information using, for example, one or more operation information received by the receiving unit 12. Then, the information acquisition unit 134 refers to, for example, the corresponding storage unit 112 and acquires the intent identifier determined by the determination unit 132, and action information corresponding to the intensity information and abstraction information.

[0078] The action unit 135 performs the action specified by the action information acquired by the information acquisition unit 134 on the terminal device 2 corresponding to the user identifier.

[0079] It is preferable for the action unit 135 to perform an action in accordance with the action information and intensity information acquired by the information acquisition unit 134.

[0080] The action unit 135 preferably performs an action in accordance with the action information and abstraction level information acquired by the information acquisition unit 134.

[0081] The action unit 135 preferably performs an action using the action information and unique information acquired by the information acquisition unit 134.

[0082] The transmitting unit 14 transmits various types of information. The transmitting unit 14 typically transmits various types of information to the terminal device 2.

[0083] The terminal storage unit 21, which constitutes the terminal device 2, stores various types of information. These types of information include, for example, a user identifier.

[0084] The terminal reception unit 22 accepts input such as instructions and information. The input of instructions and information can also be called an operation. Instructions and information include, for example, a page identifier that identifies a page and an access instruction. An access instruction is an instruction to access a page such as a web page and has a page identifier. Here, reception is a concept that includes receiving information entered from input devices such as keyboards, mice, and touch panels, receiving information transmitted via wired or wireless communication lines, and receiving information read from recording media such as optical discs, magnetic discs, and semiconductor memory.

[0085] The means of inputting instructions and information can be anything, such as a touch panel, keyboard, mouse, or menu screen. The terminal reception unit 22 can be implemented using device drivers for input means such as touch panels and keyboards, or control software for menu screens.

[0086] The terminal processing unit 23 performs various processes. These processes include, for example, changing instructions and information received by the terminal receiving unit 22 into instructions and information in a structure to be transmitted, and changing the information received by the terminal receiving unit 25 into a structure to be output.

[0087] The terminal processing unit 23 configures, for example, operation information based on the operation received by the terminal reception unit 22.

[0088] The terminal processing unit 23 retrieves a page using, for example, a page identifier received by the terminal receiving unit 22. The terminal processing unit 23 accesses a web server (not shown) identified by the page identifier received by the terminal receiving unit 22 and receives the page.

[0089] The terminal transmission unit 24 transmits the operation information acquired by the terminal processing unit 23 to the web server corresponding to the web page that was operated on.

[0090] The terminal transmission unit 24 may also transmit the operation information acquired by the terminal processing unit 23 to the information processing device 1.

[0091] The terminal receiving unit 25 receives various types of information. For example, the terminal receiving unit 25 receives various types of information from the information processing device 1. For example, the terminal receiving unit 25 receives web pages and processing results from a web server.

[0092] The terminal output unit 26 outputs the information received by the terminal receiving unit 25. The information received by the terminal receiving unit 25 includes, for example, web pages and various other types of information.

[0093] In this context, output usually refers to displaying data on a screen, but it can also be understood as a concept that includes projection using a projector, printing with a printer, sound output, transmission to external devices, storage on recording media, and transfer of processing results to other processing devices or other programs.

[0094] The storage unit 11, user storage unit 111, corresponding storage unit 112, operation storage unit 113, intention storage unit 114, and terminal storage unit 21 are preferably made of non-volatile recording media, but can also be made of volatile recording media.

[0095] The process by which information is stored in the storage unit 11, etc. is not relevant. For example, information may be stored in the storage unit 11, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 11, etc., or information input via an input device may be stored in the storage unit 11, etc.

[0096] The receiving unit 12 and the terminal receiving unit 25 are usually implemented by wireless or wired communication means, but they may also be implemented by means of receiving broadcasts.

[0097] The processing unit 13, operation storage unit 131, decision unit 132, intention storage unit 133, information acquisition unit 134, action unit 135, and terminal processing unit 23 can typically be implemented using a processor, memory, etc. The processing procedures of the processing unit 13, etc., are typically implemented in software, and this software is recorded on a recording medium such as ROM. However, it may also be implemented in hardware (dedicated circuitry). The processor can be a CPU, MPU, GPU, etc., and the type is not limited.

[0098] The transmitting unit 14, the action unit 135, and the terminal transmitting unit 24 are implemented, for example, by wireless or wired communication means, but may also be implemented by broadcasting means.

[0099] The terminal reception unit 22 can be implemented using device drivers for input means such as touch panels and keyboards, or control software for menu screens, etc.

[0100] The terminal output unit 26 may or may not be considered to include output devices such as a display or speakers. The terminal output unit 26 can be implemented using driver software for an output device, or driver software for an output device and an output device.

[0101] Next, we will explain an example of the operation of information system A. First, we will explain an example of the operation of information processing device 1 using the flowchart in Figure 3.

[0102] (Step S301) The receiving unit 12 determines whether or not it has received one or more operation information associated with the user identifier. If operation information is received, the unit proceeds to step S302; otherwise, the unit proceeds to step S308.

[0103] (Step S302) The operation storage unit 131 obtains a user identifier corresponding to the operation information received in step S301. This user identifier is the identifier of the user who performed the operation that was the basis for the operation information received in step S301.

[0104] (Step S303) The operation storage unit 131 contains information including the operation information received in step S301, and constitutes the information to be stored. It is preferable that the information to be stored includes time information. The operation storage unit 131 may acquire time information received in step S301, or it may acquire time information from a clock (not shown).

[0105] (Step S304) The operation storage unit 131 stores the information configured in step S303 in the operation storage unit 113, associating it with the user identifier acquired in step S302.

[0106] (Step S305) The determination unit 132 determines the intent identifier using the operation information accumulated in step S304. Using the operation information accumulated in step S304 means using the operation information received in step S301. An example of the intent determination process, which is the process of determining the intent identifier, will be explained using the flowchart in Figure 4.

[0107] (Step S306) The intention storage unit 133 stores the intention identifier etc. determined in step S305 in the intention storage unit 114, associating it with the user identifier obtained in step S302. The intention identifier etc. may consist of the intention identifier alone, or it may be information that includes the intention identifier plus one or more of the information from intensity information and abstraction information. It is preferable that the intention identifier etc. includes time information corresponding to when an intention is detected.

[0108] (Step S307) The action unit 135, etc., performs the action corresponding to the intent identifier determined in step S306. The process returns to step S301. An example of such an action will be explained using the flowchart in Figure 5.

[0109] (Step S308) The processing unit 13 determines whether or not it is time to execute an action. If it is time to execute an action, it proceeds to step S309; ​​otherwise, it proceeds to step S313.

[0110] The timing of the action execution is not limited to any specific event, but could be, for example, a predetermined time, when an instruction to execute the action is received from a terminal (not shown) of the administrator of the information processing device 1, or when an instruction is received from a terminal (not shown) of the operator of the web server B.

[0111] (Step S309) The processing unit 13 assigns 1 to counter i.

[0112] (Step S310) The determination unit 132 determines whether or not the i-th user identifier for which the action should be performed exists. If the i-th user identifier exists, the unit proceeds to step S311; otherwise, it returns to step S301.

[0113] The i-th user identifier is, for example, the i-th user identifier among the user identifiers stored in the user storage unit 111. Furthermore, the i-th user identifier is, for example, the i-th user identifier among the user identifiers identified by the received instruction. Such an instruction is an instruction to perform an action.

[0114] (Step S311) The determination unit 132 obtains the i-th user identifier. Proceed to step S305. After executing steps S305 to S307, proceed to step S312.

[0115] (Step S312) The processing unit 13 increments counter i by 1. The process returns to step S310.

[0116] (Step S313) The receiving unit 12 determines whether or not it has received information. If information has been received, it proceeds to step S314; otherwise, it returns to step S301. The information may include, for example, user information and correspondence information. The receiving unit 12 receives, for example, user information from terminal device 2. The receiving unit 12 also receives, for example, correspondence information from an administrator's terminal (not shown) of information processing device 1.

[0117] (Step S314) The processing unit 13 stores the information received in step S313 in an appropriate storage area. The process returns to step S301. The processing unit 13 also stores the user information received in step S313 in the user storage unit 111. In addition, the processing unit 13 stores the corresponding information received in step S313 in the corresponding storage unit 112.

[0118] In the flowchart of Figure 3, it is preferable for the processing unit 13 to use the received operation information to acquire one or more dynamic attribute values ​​of the user and store them in the user storage unit 111.

[0119] Furthermore, in the flowchart of Figure 3, processing is terminated by power off or processing termination interrupts.

[0120] Next, an example of the intent determination process in step S305 will be explained using the flowchart in Figure 4.

[0121] (Step S401) The determination unit 132 obtains one or more operation information items from the operation storage unit 113 that are paired with the user identifier. The one or more operation information items here may consist only of the operation information received immediately before, but it is preferable to include past operation information. Past operation information is, for example, operation information received in a session different from the session corresponding to the operation information received immediately before. The different session may be at a different time, on a different day, etc.

[0122] (Step S402) The determination unit 132 assigns 1 to counter i.

[0123] (Step S403) The determination unit 132 determines whether or not the i-th operation condition to be evaluated exists in the corresponding storage unit 112. If the i-th operation condition exists, the process proceeds to step S404; otherwise, the process proceeds to step S411. The i-th operation condition to be evaluated is, for example, the i-th operation condition out of all the operation conditions in the corresponding storage unit 112. Alternatively, the i-th operation condition to be evaluated is, for example, the i-th operation condition corresponding to the target website (web page).

[0124] (Step S404) The determination unit 132 obtains the i-th operation condition to be evaluated from the corresponding storage unit 112.

[0125] (Step S405) The determination unit 132 analyzes one or more operation information obtained in step S401 and determines whether or not it matches the i-th operation condition obtained in step S404. If it matches the i-th operation condition, the unit proceeds to step S406; otherwise, the unit proceeds to step S411.

[0126] (Step S406) The information acquisition unit 134 acquires the intent identifier corresponding to the i-th operation condition from the corresponding storage unit 112.

[0127] (Step S407) The information acquisition unit 134 acquires intensity source information from one or more operation information acquired in step S401. Note that it may not be possible to acquire intensity source information at this point.

[0128] (Step S408) The information acquisition unit 134 acquires intensity information corresponding to the intensity source information acquired in step S407. Note that it may not be possible to acquire intensity information at this point.

[0129] (Step S409) The information acquisition unit 134 acquires abstraction source information from one or more operation information acquired in step S401. Note that it may not be possible to acquire abstraction source information at this point.

[0130] (Step S410) The information acquisition unit 134 acquires abstraction information corresponding to the abstraction source information acquired in step S409. Note that it may not be possible to acquire abstraction information at this point.

[0131] (Step S411) The determination unit 132 increments the counter i by 1. Return to step S403.

[0132] (Step S412) The determination unit 132 obtains an intent identifier, etc., which is paired with the user identifier, from the intent storage unit 114. The determination unit 132 also obtains the intent identifier, etc., obtained in steps S406 to S410. Here, the intent identifier, etc., may be just the intent identifier, or it may be information that includes the intent identifier plus one or more pieces of information from intensity information and abstraction information.

[0133] (Step S413) The determination unit 132 assigns 1 to counter i.

[0134] (Step S414) The determination unit 132 determines whether or not the i-th intention pattern to be evaluated exists, using the intention identifier. If the i-th intention pattern exists, the process proceeds to step S415; otherwise, it returns to the higher-level process.

[0135] (Step S415) The decision unit 132 obtains the i-th intention pattern to be evaluated. Next, the decision unit 132 determines whether the intention identifier obtained in step S412 matches the i-th intention pattern. If it matches the i-th intention pattern, the process proceeds to step S406; otherwise, it proceeds to step S416. Note that if the process proceeds to step S406, steps S406 to S410 are executed before proceeding to step S416.

[0136] (Step S416) The determination unit 132 increments the counter i by 1. Return to step S414.

[0137] Next, an example of the action in step S307 will be explained using the flowchart in Figure 5.

[0138] (Step S501) The action unit 135 assigns 1 to counter i.

[0139] (Step S502) The action unit 135 determines whether or not the i-th determined intent identifier exists. If the i-th determined intent identifier exists, the process proceeds to step S503; otherwise, it returns to the higher-level process.

[0140] (Step S503) The action unit 135 obtains action information from the corresponding storage unit 112 that is paired with the i-th determined intent identifier.

[0141] (Step S504) The action unit 135 performs preprocessing. An example of preprocessing will be explained using the flowchart in Figure 6. Note that preprocessing may not be performed.

[0142] (Step S505) The action unit 135 performs an action using the action information acquired in step S503 or the action information modified by the preprocessing in step S504.

[0143] (Step S506) The action unit 135 increments the counter i by 1. Return to step S502.

[0144] In addition, in the flowchart of Figure 5, before step S503, one or more types of information from intensity information, abstraction information, and user attribute values ​​may be obtained, and action information that pairs with the i-th determined intent identifier may be obtained.

[0145] Next, an example of the preprocessing in step S504 will be explained using the flowchart in Figure 6.

[0146] (Step S601) The action unit 135 assigns 1 to counter i.

[0147] (Step S602) The action unit 135 determines whether or not the i-th variable exists in the acquired action information. If the i-th variable exists, the unit proceeds to step S603; otherwise, the unit proceeds to step S606.

[0148] (Step S603) The action unit 135 obtains the information to be assigned to the i-th variable. Typically, the action unit 135 obtains the information to be assigned to the i-th variable using the operation information that formed the basis of the determined intent identifier.

[0149] (Step S604) The action unit 135 assigns the information obtained in step S603 to the i-th variable in the obtained action information.

[0150] (Step S605) The action unit 135 increments the counter i by 1. Return to step S602.

[0151] (Step S606) The action unit 135 uses the intensity information to determine whether or not to change the action information. If the action information is to be changed, the unit proceeds to step S607; otherwise, the unit proceeds to step S609. Whether or not to change the action information using the intensity information is usually predetermined for each action information or each intent identifier.

[0152] (Step S607) The action unit 135 obtains intensity information that is paired with the intent identifier of interest.

[0153] (Step S608) The action unit 135 modifies the action information to correspond to the intensity information obtained in step S607. However, there may be cases where the action unit 135 does not need to modify the action information, such as when the intensity information is at its default value.

[0154] (Step S609) The action unit 135 uses the abstraction level information to determine whether or not to change the action information. If the action information is to be changed, the process proceeds to step S607; otherwise, the process proceeds to step S609. Note that whether or not to change the action information using the abstraction level information is usually predetermined for each action information or each intent identifier.

[0155] (Step S610) The action unit 135 obtains abstraction information that corresponds to the intent identifier of interest.

[0156] (Step S611) The action unit 135 modifies the action information to correspond to the abstraction level information obtained in step S610. Note that the action unit 135 may not need to modify the action information if the abstraction level information is at its default value, for example.

[0157] In the flowchart of Figure 6, the action unit 135 used intensity information and abstraction information to modify the action information. However, the action unit 135 or the information acquisition unit 134 may acquire action information corresponding to an intent identifier and one or more types of information from intensity information, abstraction information, and user attribute values.

[0158] Next, an example of the operation of terminal device 2 will be described. The terminal reception unit 22 of terminal device 2 receives input such as instructions and information. Next, the terminal processing unit 23 changes the instructions and information received by the terminal reception unit 22 into instructions and information of a structure to be transmitted. The terminal transmission unit 24 transmits such instructions and information to the web server B corresponding to the instructions (for example, the web server B corresponding to the URL included in the instructions). The terminal receiving unit 25 also receives information such as a web page from the web server B that sent the instructions. Next, the terminal processing unit 23 changes the structure to output the information received by the terminal receiving unit 25. Next, the terminal output unit 26 acquires the information (for example, a web page).

[0159] Furthermore, the terminal processing unit 23 of the terminal device 2 may configure operation information based on the operation received by the terminal receiving unit 22, for example. The terminal transmission unit 24 may also transmit the operation information acquired by the terminal processing unit 23 to the information processing device 1. In response to the transmission of operation information, the terminal receiving unit 25 receives various types of information from the information processing device 1, for example. The various types of information are, for example, information corresponding to the intent identifier determined by the information processing device 1 in response to the transmission of operation information.

[0160] Furthermore, in addition to the functions of a well-known web server, web server B may also transmit operation information received from terminal device 2 to information processing device 1 in pairs with the user identifier corresponding to terminal device 2. Alternatively, in addition to the functions of a well-known web server, web server B may also process the operation information received from terminal device 2 and transmit the resulting operation information to information processing device 1 in pairs with the user identifier corresponding to terminal device 2. The operation information received from terminal device 2 may be, for example, primitive operation information (e.g., rightButtonON(ButtonID)), and the operation information obtained after processing the operation information may be information that a person can use to determine the meaning and significance of the operation (e.g., "Page XX has been displayed").

[0161] The following describes a specific example of the operation of information system A in this embodiment. In information system A, it is assumed that the one or more web servers B accessed by terminal device 2 are servers for an e-commerce site.

[0162] Furthermore, the user storage unit 111 of the information processing device 1 stores the user information management table shown in Figure 7. The user information management table stores records that have "user identifier," "name," "email address," "static attribute value," and "dynamic attribute value."

[0163] "Static attribute values" are information received and stored by the information processing device 1 from the terminal device 2 or the web server B. In this case, "static attribute values" include "gender," "age," "married / unmarried," "place of origin," and "administrator flag." "Married / unmarried" indicates whether the user is single or married. The "administrator flag" indicates whether the user is the administrator of the information processing device 1. Here, a user with an administrator flag value of "1" is the administrator, and a user with an administrator flag value of "0" is not the administrator.

[0164] "Dynamic attribute values" are information obtained by the processing unit 13 by analyzing the operation information of the operation storage unit 113 or the received operation information. "Dynamic attribute values" here include "real-time dynamic attribute values" and "history information-based dynamic attribute values". "Real-time dynamic attribute values" here include "time spent" and "number of pages viewed". "Time spent" is the time spent on the site during the current visit. "Number of pages viewed" is the number of pages viewed on the site during the current visit. "History information-based dynamic attribute values" here include "number of visits", "number of purchases", "total purchase amount", "average page views", "score", etc. "Number of visits" is the number of times the user has visited this EC site (for example, the site including pages identified by URL1 and URL2). "Number of purchases" is the number of times the user has purchased products on this EC site. "Total purchase amount" is the total amount of money the user has spent on products on this EC site. "Average page views" is the average number of pages viewed per visit by the user. "Score" is the user's score. Here, it is assumed that the storage unit 11 stores a calculation formula that calculates a score using an increment function that takes one or more attribute values ​​from among "number of visits," "number of purchases," "total purchase amount," and "average number of page views" as parameters. The processing unit 13 then obtains one or more attribute values ​​from among "number of visits," "number of purchases," "total purchase amount," and "average number of page views" for each user, substitutes one or more attribute values ​​into the increment function, and calculates each user's score. It is preferable that this calculation formula calculates the score using one or more pieces of information from static attribute values. For example, the calculation formula may be one that increases the score value in the case of member "1." For example, it is preferable that the calculation formula multiplies the score value by 1.1 in the case of member "1," and does not change the score value in the case of member "0." The technique by which the processing unit 13 analyzes operation information and obtains dynamic attribute values ​​is a known technique, so a detailed explanation is omitted.

[0165] Furthermore, the corresponding storage unit 112 stores the first corresponding information management table shown in Figure 8 and the second corresponding information management table shown in Figure 9.

[0166] The first correspondence information management table is a table that manages one or more records that have "correspondence information" and "user intent". "Correspondence information" here includes "intent identifier", "operation condition", "intensity condition", "abstraction level condition", "user attribute value condition", and "action information". "Operation condition" is a condition relating to one or more operation information. "Operation condition" can also be said to be a condition of a pattern relating to one or more operation information, so it can also be called "operation pattern". "Intensity condition" is a condition relating to intensity information. "Abstract level condition" is a condition relating to abstract level information. "User attribute value condition" is a condition relating to one or more user attribute values. Note that "correspondence information" always has the attribute values ​​"operation pattern" and "action information", but "intensity condition", "abstraction level condition", and "user attribute value condition" may be "NULL". In other words, action information may be determined from operation conditions alone, or it may be determined based on operation conditions plus one or more conditions from intensity conditions, abstraction levels, and user attribute value conditions. "User intent" is information that explains the user's intent when it matches the record in the first correspondence information management table, and it explains the significance of this record.

[0167] The "operation condition" for the record with "ID=1" in the first correspondence information management table is that, in the operation information corresponding to a single user identifier, "the number of times page X has been visited during the sale period is 3 or more, and the number of times page X has been visited outside of the sale period is 1 or less." The value corresponding to the variable "$sale period" (for example, 2022 / 3 / 1~2022 / 3 / 31, 2021 / 12 / 1~2021 / 12 / 31) is stored in storage unit 11, associated with the page identifier "page X." Furthermore, "time information ⊃ $sale period" indicates that "the time information corresponding to the operation information (here, jump(page X)) is included in the sale period." "time information != $sale period" indicates that "the time information corresponding to the operation information (here, jump(page X)) is not included in the sale period." Furthermore, the action information "send(banner ad 1)" for the record "ID=1" in the first correspondence information management table is a function that sends a banner ad called "banner ad 1" to terminal device 2. It should be assumed that "banner ad 1" is a banner that allows access to sale items. In other words, the record "ID=1" is a record that sends a banner that allows access to sale items to terminal device 2 to a user who intends to buy sale items.

[0168] The "Operation Condition" for the record "ID=2" in the first correspondence information management table indicates that "(1), (2), and (3) operation information appear in order" within the operation information for one session corresponding to a single user identifier. Note that other operation information may be included between each of (1), (2), and (3). Furthermore, the intensity condition "3 or more" for "ID=2" indicates that the intensity information is 3 or more.

[0169] The intensity information is determined by referring to the intensity management table in Figure 10. The intensity management table has two or more records, each containing an "ID," an "intensity condition," and "intensity information." The "ID" is the information that identifies the record. The "intensity condition" is the condition for determining the intensity information. For example, the intensity condition "1 minute < dwell time <= 3 minutes" means that the dwell time on the page of interest is "longer than 1 minute and 3 minutes or less." The "intensity information" is the intensity information obtained when the corresponding intensity condition is met. The page of interest is the page that was last jumped to in the operation conditions (for example, the "recommended page" in the record with "ID=2"). The source of intensity information here is the dwell time.

[0170] The "User Attribute Value Condition" for the record with "ID=2" in the first correspondence information management table is that the user's dynamic attribute value "Total Purchase Amount" is 10,000 yen or more. Furthermore, "$product name=get_goodsname()", which constitutes the action information of the record with "ID=2" in the first correspondence information management table, is a function that retrieves one or more product names displayed on the page of interest. Furthermore, "recommend($product name)", which constitutes the same action information, is a function that retrieves product information related to the one or more retrieved product names from the storage unit 11 or a recording medium (not shown) and sends it to the terminal device 2 (recommends). In other words, the record with "ID=2" is a record that recommends products related to the product being viewed to a user who intends to "buy something but hasn't decided specifically" and whose total purchase amount to date is 10,000 yen or more.

[0171] The "Operation Condition" of the record with "ID=3" in the first correspondence information management table indicates that operation information matching "search($product name)" appears five or more times in the operation information for a specific period corresponding to a single user identifier (the product has been searched for five or more times). The strength condition "3 or more" for this record indicates that the same product name has been searched for three or more times. In other words, the strength information here is obtained by "strength information = maximum number of searches for the same product name". Furthermore, the action information "send(chat guidance)" for this record indicates that a chat guidance message stating "You can check the details with a store employee" will be sent to terminal device 2. In other words, the record with "ID=3" is a record that enables the sending of the above chat guidance to terminal device 2 when a user with the intention of "wanting a product" is detected and the strength condition of 3 or more indicates such an intention. This chat guidance is stored in storage unit 11.

[0172] The "Operation Conditions" of the record with "ID=4" in the first correspondence information management table indicate that the operation information appeared in the order of (1) and (2), and that the time spent on page (2) (the page for items not yet in stock) was 1 minute or less. In other words, the operation conditions may also include one or more dynamic attribute values ​​of the user (for example, real-time dynamic attribute values, in this case, time spent). The action information of the record, "send (In Stock Email Registration Notice)," is a function that sends an in stock email registration notice to terminal device 2. In other words, the record with "ID=4" is a record that sends an in stock email registration notice to the user's terminal device 2 if the user has the intention of "waiting for the product to be in stock" and has made one or more purchases. The in stock email registration notice is stored in storage unit 11.

[0173] The "Operation Conditions" of the record with "ID=5" in the first correspondence information management table indicate that the user logged out without purchasing or removing any items from the buffer "Favorite Items" when the variable "$Number of Favorite Items" corresponding to a single user identifier was 5 or more. The action information of the record indicates that if the product name stored in the variable "$Favorite Items" becomes a sale item, a sale notification will be sent to terminal device 2. "sale_goods($Favorite Items)" is a function that returns a value indicating whether the product corresponding to the product name stored in the variable "$Favorite Items" is a sale item. "send(Sale Notification)" is a function that sends a sale notification to terminal device 2 when a favorite item becomes a sale item for a user who intends to wait for their favorite item to become cheaper in a later sale. The sale notification is stored in storage unit 11.

[0174] The record with "ID=6" in the first correspondence information management table is a record that enables sending a chat message to terminal device 2 when the operation information corresponding to a specific period in which operation information matching "search($product name)" appears 20 or more times and the abstraction level condition that the abstraction level information is 5 or higher is met.

[0175] The level of abstraction information is determined by referring to the level of abstraction management table in Figure 11. The level of abstraction management table has two or more records, each containing an "ID," "level of abstraction condition," and "level of abstraction information." The level of abstraction condition "3 <= number of product names <= 5" indicates that the number of product names searched is 3 or more and 5 or less. In other words, the more types of products being searched, the less specific (more abstract) the desired product is.

[0176] The second correspondence information management table (Figure 9) is a table that manages one or more records that have "correspondence information" and "user intent". Here, "correspondence information" has "intent identifier", "intent pattern", and "action information". "Intent pattern" is a condition that has one or more intent identifiers. An "intent pattern" may be a condition consisting only of two or more intent identifiers, or a condition using one or more intent identifiers and one or more operation information.

[0177] The action information for "ID=1" in Figure 9 indicates that a 10% discount ticket will be sent to terminal device 2 of a user whose intent identifiers "1" and "3" match. In other words, the record for "ID=1" in Figure 9 is a record that sends a 10% discount ticket to terminal device 2 of a user who has a desired product and intends to buy it during a sale.

[0178] The record with "ID=2" in Figure 9 represents a user who intends to buy sale items. This record enables the system to send the URL of the sale item page (sale item URL) to the user if the item they searched for is on sale.

[0179] Furthermore, the operation storage unit 113 stores an operation information management table having the structure shown in Figure 12. The operation information management table is a table that manages operation information and other data stored by the operation storage unit 131. The operation information management table manages one or more records that have "ID", "user identifier", "time information", "page identifier", and "operation information".

[0180] Furthermore, the intent storage unit 114 stores a user intent management table having the structure shown in Figure 13. The intent management table is information stored by the intent storage unit 133 and is a table that manages intent identifiers, etc., corresponding to user identifiers. The user intent management table has one or more records that have "ID", "user identifier", "intent identifier", "time information", and "page identifier".

[0181] In this situation, information system A operates as follows: The user (in this case, Yamada A) uses terminal device 2 to access a web server B and perform tasks such as searching for, viewing, and purchasing product information.

[0182] The terminal device 2 then receives input from the user and sends one or more operation information to the web server B. The terminal device 2 also sends the one or more operation information to the information processing device 1.

[0183] The receiving unit 12 of the information processing device 1 receives the one or more operation information, associating it with the user identifier "P001". The operation storage unit 131 obtains the user identifier "P001" associated with the received operation information. Next, the operation storage unit 131 obtains the time (hour information (e.g., 2022 / 3 / 31 20:15:38)) from a clock (not shown). The operation storage unit 131 also obtains the page identifier (identifier of the page operated by the user (e.g., "Top_page")) associated with the received operation information. The operation storage unit 131 also obtains the received operation information (e.g., "access(top_page)"). Next, the operation storage unit 131 configures the information to be stored. Next, the operation storage unit 131 stores the configured information in the operation information management table (see Figure 12). This record is the record with "ID=692".

[0184] Furthermore, the determination unit 132 attempts to determine the intent identifier using the accumulated operation information. In other words, the determination unit 132 attempts to determine the intent identifier according to the flowchart in Figure 4. However, let's assume that the determination unit 132 was unable to determine the intent identifier.

[0185] Next, suppose the user enters "PC" into the product search field on the top page, identified as "top_pag," and clicks the search button. Terminal device 2 then receives this instruction, constructs the operation information "search("PC")," and sends it to a web server B. As a result, terminal device 2 receives the search results from web server B and outputs them.

[0186] Furthermore, terminal device 2 transmits the operation information "search("PC")" to information processing device 1.

[0187] Next, the receiving unit 12 of the information processing device 1 receives the operation information "search("PC")" associated with the user identifier "P001". The operation storage unit 131 retrieves the user identifier "P001" associated with the received operation information. Next, the operation storage unit 131 retrieves the time (hour information (e.g., 2022 / 3 / 31 20:15:50)) from a clock (not shown). The operation storage unit 131 also retrieves the page identifier (e.g., "Top_page") associated with the received operation information. The operation storage unit 131 also retrieves the received operation information "search("PC")". Next, the operation storage unit 131 configures the information to be stored. Next, the operation storage unit 131 stores the configured information in the operation information management table (Figure 12). This record is the record with "ID=693".

[0188] Next, the decision unit 132 attempts to determine the intent identifier using the accumulated operation information. In other words, the decision unit 132 attempts to determine the intent identifier according to the flowchart in Figure 4. Specifically, the decision unit 132 obtains one or more operation information items that are paired with the user identifier "P001" from the operation information management table.

[0189] The decision unit 132 then determines whether one or more acquired operation information matches each record in the first correspondence information management table. Here, the decision unit 132 determines that the newly received operation information "search("PC")" has satisfied the operation condition "number of occurrences (search($product name))>=5" for "ID=3". The decision unit 132 also determines that the strength information is "strength information = maximum number of searches for the same product name = 3", and that the strength condition "3 or more" has been satisfied.

[0190] Next, the decision unit 132 obtains the intent identifier "1" which is paired with the user identifier "P001" from the user intent management table (Figure 13). Thus, the decision unit 132 has obtained intent identifiers "1" and "3" which are paired with the user identifier "P001".

[0191] Next, the determination unit 132 retrieves the intent identifier "A" from the second correspondence information management table, which corresponds to the intent pattern in which intent identifiers "1" and "3" match.

[0192] Next, the intent storage unit 133 acquires the time information "2022 / 3 / 31 20:15:50" and the page identifier "Top_page". Then, the intent storage unit 133 stores two records, each containing the time information and page identifier, and each containing the newly acquired intent identifiers "3" and "A", in the user intent management table shown in Figure 13, paired with the user identifier "P001". These records are the records with "ID=58.59".

[0193] Next, the action unit 135 obtains the action information "send (chat guidance)" which is paired with the intent identifier "3" from the first correspondence information management table in Figure 8. Next, the action unit 135 executes the action information "send (chat guidance)". In other words, the action unit 135 reads the chat guidance from the storage unit 11 and sends the chat guidance to the terminal device 2 that sent the operation information (the terminal device 2 corresponding to the user identifier "P001").

[0194] Furthermore, the action unit 135 obtains the action information "send(10% discount ticket, $product name)" which is paired with the intent identifier "A" from the second correspondence information management table in Figure 9. Next, the action unit 135 obtains the variable "$product name" from the obtained action information. Next, the action unit 135 obtains the product name "PC" to be assigned to the variable "$product name" from the operation information "search("PC")". Next, the action unit 135 assigns the product name "PC" to the variable "$product name" and constructs the action information "send(10% discount ticket, PC)" to be executed. Next, the action unit 135 executes the action information "send(10% discount ticket, PC)". In other words, the action unit 135 constructs information for a ticket that gives a 10% discount on a PC and sends this information to the terminal device 2 that sent the operation information (the terminal device 2 corresponding to the user identifier "P001").

[0195] Next, terminal device 2, which corresponds to user identifier "P001", receives and outputs chat instructions. Terminal device 2 also receives and outputs information about a ticket offering a 10% discount on a PC.

[0196] Through the above processing, the information processing device 1 can estimate the user's intent based on the user's actions on the terminal device 2 and provide the user with an appropriate service corresponding to that intent.

[0197] As described above, according to this embodiment, it is possible to estimate the user's intent based on the user's actions on a web page and take appropriate actions corresponding to that intent.

[0198] Furthermore, according to this embodiment, the user's intent and intensity can be estimated based on the user's actions on the web page, and appropriate actions corresponding to that intent and intensity can be taken.

[0199] Furthermore, according to this embodiment, based on the user's actions on a web page, the user's intent and its level of abstraction can be estimated, and an appropriate action corresponding to that intent and level of abstraction can be taken.

[0200] Furthermore, according to this embodiment, the user's intent can be estimated based on the user's actions on a web page, and an appropriate action corresponding to that intent can be taken using unique information obtained from the operation information.

[0201] Furthermore, according to this embodiment, it is possible to estimate multiple user intentions based on the user's actions on a web page and take appropriate actions corresponding to those multiple intentions.

[0202] Furthermore, according to this embodiment, it is possible to estimate the user's intent based on the patterns of user interaction with a web page and take appropriate actions corresponding to that intent.

[0203] The processing in this embodiment may be implemented in software. This software may be distributed by software download or the like. Alternatively, this software may be recorded on a recording medium such as a CD-ROM and distributed. This also applies to other embodiments in this specification. The software that implements the information processing device 1 in this embodiment is the following program. In other words, this program is a program that causes a computer that can access a correspondence storage unit that stores one or more correspondence pieces of information indicating the correspondence between an intent identifier based on one or more operation pieces of information and an action piece of information that specifies an action to be performed on the user's terminal device to function as an action unit that receives one or more operation pieces of information associated with a user identifier, a receiving unit that receives one or more operation pieces of information associated with a user identifier, a determination unit that determines an intent identifier corresponding to the one or more operation pieces of information received by the receiving unit, an information acquisition unit that refers to the correspondence storage unit and acquires the action piece of information corresponding to the intent identifier determined by the determination unit, and an action unit that performs the action specified by the action piece of information acquired by the information acquisition unit on the terminal device corresponding to the user identifier.

[0204] (Embodiment 2) In this embodiment, the difference from Embodiment 1 is that a machine learning algorithm is used to determine the intent identifier.

[0205] In other words, in this embodiment, the information processing device obtains an intent identifier using a model acquired using two or more training data sets having one or more operation information each.

[0206] The conceptual diagram of information system B in this embodiment is the same as in Figure 1, except for the reference numerals of the information processing device 3. The information processing device 3 is a device that performs actions on the terminal device 2 based on operation information. The information processing device 3 is typically a so-called server. The information processing device 3 may be, for example, a cloud server, an ASP server, etc., but its type is not limited. The information processing device 3 may also function as a web server.

[0207] The information processing device 3 and one or more terminal devices 2 can communicate via a network such as the Internet. Furthermore, one or more terminal devices 2 and one or more web servers (not shown) may also communicate via a network such as the Internet. In addition, it is preferable that the information processing device 3 can communicate with web server B via a network such as the Internet.

[0208] Figure 14 is a block diagram of information system B in this embodiment. Information system B comprises an information processing device 3 and one or more terminal devices 2.

[0209] The information processing device 3 comprises a storage unit 31, a receiving unit 12, a processing unit 33, and a transmitting unit 14. The storage unit 31 comprises a user storage unit 111, a corresponding storage unit 112, a model storage unit 311, an operation storage unit 113, and an intent storage unit 114. The processing unit 33 comprises a learning unit 330, an operation storage unit 131, a decision unit 332, an intent storage unit 133, an information acquisition unit 134, and an action unit 135.

[0210] The storage unit 31, which constitutes the information processing device 3, stores various types of information. These types of information include, for example, two or more training data sets, a model (described later), user information, correspondence information, operation information, and intent identifiers.

[0211] Two or more training data sets are information for constructing the model described later. Each of the two or more training data sets for obtaining a multi-class classification model has one or more operational information as an explanatory variable and an intent identifier as an objective variable. It is preferable that such training data has an objective variable value that does not correspond to any of the intent identifiers. For obtaining a binary classification model, each of the two or more training data sets has one or more operational information as a positive example and one or more operational information as a negative example for each intent identifier.

[0212] The model storage unit 311 stores one or more models. A model can also be called a learner, predictor, learning model, or predictive model. A model is information formed by machine learning learning processes using two or more training data sets. A model is information used in machine learning predictive processes to obtain intent identifiers. A model is information obtained through machine learning learning processes using two or more training data sets.

[0213] The model is, for example, information for predicting one intent identifier from two or more intent identifiers using one or more operation information. In this case, the model is a so-called multi-class classification model. The model is, for example, information for predicting whether or not an operation information corresponds to one intent identifier using one or more operation information. In this case, the model is a so-called binary classification model. When the model is a binary classification model, the model storage unit 311 stores two or more models, each associated with a different intent identifier.

[0214] The machine learning algorithms used here are not limited to deep learning, random forests, decision trees, SVMs, etc. Furthermore, various machine learning functions and existing libraries can be used, such as the TensorFlow library, the R language's random forest module, fastText, and TinySVM.

[0215] The processing unit 33 performs various processes. These processes include, for example, those performed by the learning unit 330, the operation storage unit 131, the decision unit 332, the intention storage unit 133, the information acquisition unit 134, and the action unit 135.

[0216] The learning unit 330 performs machine learning training using two or more training data sets and obtains a model. The learning unit 330 stores the model in the model storage unit 311. If the information processing device 3 does not perform training, the learning unit 330 is unnecessary.

[0217] The learning unit 330, for example, uses two or more training data sets for multi-class classification to perform machine learning training and obtain a model for multi-class classification.

[0218] Furthermore, the learning unit 330 performs machine learning training using, for example, two or more training data for binary classification corresponding to each of the two or more intent identifiers, and obtains a binary classification model.

[0219] The determination unit 332 determines an intent identifier corresponding to one or more operation information received by the receiving unit 12. The determination unit 332 uses the one or more operation information received by the receiving unit 12 and the model in the storage unit 31 to perform machine learning prediction processing and determine the intent identifier.

[0220] The determination unit 332, for example, uses one or more operation information received by the receiving unit 12 and a multi-class classification model to perform machine learning prediction processing and determine the intent identifier.

[0221] The decision unit 332 performs machine learning prediction processing for each of two or more intent identifiers, using one or more operation information received by the receiving unit 12 and the model paired with that intent identifier, to determine whether or not it corresponds to that intent identifier. The decision unit 332 then obtains the intent identifier corresponding to the model predicted to be a match. The decision unit 332 also obtains a score through machine learning prediction processing and obtains the intent identifier corresponding to the model that is predicted to be a match and whose score satisfies the acquisition conditions. The acquisition conditions are the conditions for obtaining the intent identifier. For example, the acquisition conditions may be that the score is above a threshold or that the score is the highest value.

[0222] The storage unit 31 and the model storage unit 311 are preferably made of a non-volatile recording medium, but can also be made of a volatile recording medium.

[0223] The process by which information is stored in the storage unit 31, etc. is not relevant. For example, information may be stored in the storage unit 31, etc. via a recording medium, information transmitted via a communication line, etc. may be stored in the storage unit 31, etc., or information input via an input device may be stored in the storage unit 31, etc.

[0224] The receiving unit 12 and the terminal receiving unit 25 are usually implemented by wireless or wired communication means, but they may also be implemented by means of receiving broadcasts.

[0225] The processing unit 33, learning unit 330, and decision unit 332 can typically be implemented using a processor, memory, etc. The processing procedures of the processing unit 33, etc., are usually implemented in software, and this software is recorded on a recording medium such as ROM. However, it may also be implemented in hardware (dedicated circuitry). The processor can be a CPU, MPU, GPU, etc., and the type is not limited.

[0226] Next, we will describe an example of the operation of the information processing device 3, which constitutes information system B. Note that the operation example of the information processing device 3 differs from the operation in the flowchart of Figure 3 only in the intent determination operation at S305. Therefore, we will explain this example of intent determination operation using the flowchart of Figure 15. Note that the flowchart in Figure 15 is for the case where two or more binary classification models are used.

[0227] (Step S1501) The determination unit 332 assigns 1 to counter i.

[0228] (Step S1502) The determination unit 332 determines whether or not the i-th intent identifier exists. If the i-th intent identifier exists, the unit proceeds to step S1503; otherwise, the unit proceeds to step S1508.

[0229] (Step S1503) The determination unit 332 obtains the model that corresponds to the i-th intention identifier from the model storage unit 311.

[0230] (Step S1504) The decision unit 332 uses the model acquired in step S1503 and one or more pieces of operation information to perform machine learning prediction processing and obtain a prediction result. It is preferable for the decision unit 332 to also obtain a score. The prediction result is, for example, "1" if it matches the intent identifier, and "0" if it does not.

[0231] (Step S1505) The decision unit 332 proceeds to step S1506 if the prediction result obtained in step S1504 is "1", and to step S1507 if it is "0".

[0232] (Step S1506) The decision unit 332 temporarily stores the i-th intention identifier and score in a buffer (not shown). Note that the decision unit 332 may store only the i-th intention identifier.

[0233] (Step S1507) The determination unit 332 increments counter i by 1. Return to step S1502.

[0234] (Step S1508) The decision unit 332 obtains an intent identifier that matches the acquisition conditions from a buffer (not shown). Note that the decision unit 332 may not be able to obtain an intent identifier at this point. Also, if there are no scores in the buffer (not shown), the decision unit 332 obtains all intent identifiers from the buffer (not shown).

[0235] In the flowchart of Figure 15, if a multi-class classification model is used, the decision unit 332 operates as follows: The decision unit 332 uses one or more operation information and the model in the storage unit 31 to perform machine learning prediction processing and obtain an intent identifier. At this point, the decision unit 332 may also obtain information indicating that there is no intent.

[0236] As described above, according to this embodiment, based on the user's actions on a web page, a machine learning algorithm can be used to estimate the user's intent and take appropriate actions corresponding to that intent.

[0237] Figure 16 shows the external appearance of a computer that executes the program described herein to realize the various embodiments of the information processing device 1, information processing device 3, etc. described above. The embodiments described above can be realized with computer hardware and computer programs executed thereon. Figure 16 is an overview of this computer system 300, and Figure 17 is a block diagram of the system 300.

[0238] In Figure 16, the computer system 300 includes a computer 301 with a CD-ROM drive, a keyboard 302, a mouse 303, and a monitor 304.

[0239] In Figure 17, the computer 301 includes, in addition to the CD-ROM drive 3012, an MPU 3013, a bus 3014 connected to the CD-ROM drive 3012, a ROM 3015 for storing programs such as boot-up programs, a RAM 3016 connected to the MPU 3013 for temporarily storing instructions for application programs and providing temporary storage space, and a hard disk 3017 for storing application programs, system programs, and data. Although not shown here, the computer 301 may further include a network card for providing connectivity to a LAN.

[0240] The program that causes the computer system 300 to execute the functions of the information processing device 1, etc., as described above, may be stored on the CD-ROM 3101, inserted into the CD-ROM drive 3012, and then transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into the RAM 3016 during execution. The program may also be loaded directly from the CD-ROM 3101 or the network.

[0241] The program does not necessarily have to include an operating system (OS) or third-party program that causes the computer 301 to execute the functions of the information processing device 1, etc., as described above. The program only needs to include the instruction portion that calls the appropriate function (module) in a controlled manner and obtains the desired result. How the computer system 300 operates is well known, so a detailed explanation is omitted.

[0242] In the above program, steps such as sending information and receiving information do not include hardware-based processing, such as processing performed by a modem or interface card in the transmission step (processing that can only be performed by hardware).

[0243] Furthermore, the computer running the above program may be a single computer or multiple computers. In other words, it may perform centralized processing or distributed processing.

[0244] Furthermore, it goes without saying that in each of the above embodiments, two or more communication means present in a single device may be physically implemented in a single medium.

[0245] Furthermore, in each of the above embodiments, each process may be implemented by centralized processing using a single device, or by distributed processing using multiple devices.

[0246] It goes without saying that the present invention is not limited to the embodiments described above, and various modifications are possible, all of which are also included within the scope of the present invention. [Industrial applicability]

[0247] As described above, the information processing device according to the present invention has the effect of estimating the user's intent based on the user's actions on a web page and taking appropriate actions corresponding to that intent, and is useful as a server or the like to support e-commerce sites. [Explanation of Symbols]

[0248] A, B Information Systems 1.3 Information Processing Devices 1 Server device 2 Terminal devices 11, 31 Storage section 12 Receiver 13, 33 Processing Unit 14. Transmitter 21 Terminal storage section 22 Terminal Reception Section 23 Terminal Processing Unit 24 Terminal transmission unit 25 Receiving part of the terminal 26 Terminal output section 111 User storage section 112 Compatible storage unit 113 Operation and storage unit 114 Operation Information Storage Unit 114 Intent Storage Unit 131 Operation Storage Unit 132, 332 Decision Section 133 Intention Storage Unit 134 Information Acquisition Department 135 Action Section 311 Model Storage Unit 330 Learning Department

Claims

1. A correspondence storage unit stores: first correspondence information having operation conditions, which are conditions related to operation information, which is information about the actions a user performs on a web page, and an intent identifier that identifies the intent; second correspondence information showing the correspondence between the intent identifier, intensity information indicating the strength of the user's intent, and action information that identifies the action to be performed on the user's terminal device; and third correspondence information having intensity conditions, which are conditions related to intensity source information, which is information obtained using operation information, and intensity information. A receiving unit that receives operation information associated with a user identifier, A determination unit that uses the first correspondence information to determine the operation conditions that match the operation information received by the receiving unit, and determines the intent identifier corresponding to the operation conditions, An information acquisition unit uses the third correspondence information to acquire intensity source information using the operation information received by the receiving unit, determines the intensity conditions that match the intensity source information, acquires intensity information corresponding to those intensity conditions, and uses the second correspondence information to acquire the action information corresponding to the intent identifier determined by the determination unit and the acquired intensity information. An information processing device comprising: an information acquisition unit and an action unit that performs the action specified by the action information acquired by the information acquisition unit on a terminal device corresponding to the user identifier.

2. A correspondence storage unit stores: first correspondence information having operation conditions, which are conditions related to operation information, which is information about the actions a user has taken on a web page, and an intent identifier that identifies the intent; second correspondence information showing the correspondence between the intent identifier, abstraction information indicating the level of abstraction of the user's intent, and action information that identifies the action to be taken on the user's terminal device; and third correspondence information having abstraction conditions, which are conditions related to the source abstraction information, which is information obtained using operation information, and abstraction information. A receiving unit that receives operation information associated with a user identifier, A determination unit that uses the first correspondence information to determine the operation conditions that match the operation information received by the receiving unit, and determines the intent identifier corresponding to the operation conditions, An information acquisition unit uses the third correspondence information to acquire abstraction source information using the operation information received by the receiving unit, determines an abstraction condition that matches the abstraction source information, acquires abstraction information corresponding to the abstraction condition, and uses the second correspondence information to acquire the action information corresponding to the intent identifier determined by the determination unit and the acquired abstraction information. An information processing device comprising: an information acquisition unit and an action unit that performs the action specified by the action information acquired by the information acquisition unit on a terminal device corresponding to the user identifier.

3. A correspondence storage unit stores first correspondence information having operation conditions, which are conditions related to operation information that are information about the actions a user has taken on a web page, and an intent identifier that identifies the intent, and second correspondence information that shows the correspondence between the intent identifier, attribute value conditions related to user attribute values, and action information that identifies the actions to be taken on the user's terminal device, A user storage unit that stores user information having a user identifier and user attribute values, A receiving unit that receives operation information associated with a user identifier, A determination unit that uses the first correspondence information to determine the operation conditions that match the operation information received by the receiving unit, and determines the intent identifier corresponding to the operation conditions, An information acquisition unit acquires from the user storage unit a user attribute value that is paired with the user identifier corresponding to the operation information received by the receiving unit, and using the second correspondence information, acquires the action information corresponding to the attribute value condition in which the intent identifier determined by the determination unit matches the acquired user attribute value, An information processing device comprising: an information acquisition unit and an action unit that performs the action specified by the action information acquired by the information acquisition unit on a terminal device corresponding to the user identifier.

4. A correspondence storage unit stores correspondence information including a second correspondence information that shows the correspondence between an intent identifier, intensity information indicating the strength of the user's intent, and action information that identifies the action to be taken on the user's terminal device, and a third correspondence information that has intensity conditions, which are conditions related to the intensity source information, which is information obtained using operation information, and intensity information. A receiving unit that receives operation information associated with a user identifier, A model storage unit stores a model obtained through a machine learning learning process using two or more training data sets having operation information and intent identifiers, A decision unit that uses the aforementioned operation information and the aforementioned model to perform machine learning prediction processing and determine the aforementioned intent identifier, An information acquisition unit acquires intensity source information using the operation information received by the receiving unit, determines the intensity conditions that match the intensity source information using the third correspondence information, acquires intensity information corresponding to the intensity conditions, and acquires the action information corresponding to the intention identifier determined by the determination unit and the acquired intensity information using the second correspondence information. An information processing device comprising: an information acquisition unit and an action unit that performs the action specified by the action information acquired by the information acquisition unit on a terminal device corresponding to the user identifier.

5. A correspondence storage unit stores correspondence information including a second correspondence information that shows the correspondence between an intent identifier, abstraction information indicating the level of abstraction of the user's intent, and action information that identifies the action to be taken on the user's terminal device, and a third correspondence information that has abstraction conditions and abstraction information, which are conditions related to the source abstraction information, which is information obtained using operation information. A receiving unit that receives operation information associated with a user identifier, A model storage unit stores a model obtained through a machine learning learning process using two or more training data sets having operation information and intent identifiers, A decision unit that uses the aforementioned operation information and the aforementioned model to perform machine learning prediction processing and determine the aforementioned intent identifier, An information acquisition unit acquires abstraction source information using the operation information received by the receiving unit, determines an abstraction condition that matches the abstraction source information using the third correspondence information, acquires abstraction information corresponding to the abstraction condition, and acquires action information corresponding to the intention identifier determined by the determination unit and the acquired abstraction information using the second correspondence information. An information processing device comprising: an information acquisition unit and an action unit that performs the action specified by the action information acquired by the information acquisition unit on a terminal device corresponding to the user identifier.

6. The intent identifier, attribute value conditions related to user attribute values, and action information that identifies the actions to be taken on the user's terminal device. A correspondence storage unit where second correspondence information indicating the correspondence is stored, A user storage unit that stores user information having a user identifier and user attribute values, A receiving unit that receives operation information associated with a user identifier, A model storage unit stores a model obtained through a machine learning learning process using two or more training data sets having operation information and intent identifiers, A decision unit that uses the aforementioned operation information and the aforementioned model to perform machine learning prediction processing and determine the aforementioned intent identifier, An information acquisition unit acquires from the user storage unit a user attribute value that is paired with the user identifier corresponding to the operation information received by the receiving unit, and acquires from the second correspondence information the action information corresponding to the attribute value condition in which the intent identifier determined by the determination unit matches the acquired user attribute value, An information processing device comprising: an information acquisition unit and an action unit that performs the action specified by the action information acquired by the information acquisition unit on a terminal device corresponding to the user identifier.

7. An information processing method that causes a computer to perform all the processing performed by the information processing device described in any one of claims 1 to 6.

8. Computers, A program for causing an information processing device to function as described in any one of claims 1 to 6.

Images