JP6634971B2 - Information providing method, information providing apparatus, and information providing program - Google Patents

Description

  The present invention relates to an information providing method, an information providing device, and an information providing program.

  2. Description of the Related Art Conventionally, a collaborative filtering technique is known as a technique for identifying information that is highly likely to be of interest to a user searching for an item on a Web or a database and presenting the information as recommended information. As a collaborative filtering method, for example, there is a method of specifying a similar user based on information of the user or information accessed by the user, and presenting information accessed by the similar user as recommended information. Further, as a collaborative filtering method, there is a method in which information similar to information accessed by a user is specified based on the similarity of the information itself, and presented as recommended information.

  Note that Patent Documents 1 to 3 and the like disclose techniques for recommending information related to content being viewed by a user. Further, Patent Literatures 4 to 6 and the like disclose techniques for presenting information suitable for a user's interests, preferences, operations, and behaviors.

JP 2006-48320 A JP 2011-135183 A JP 2012-22365 A JP 2004-259189 A JP-A-10-228482 JP 2005-267483 A

  However, in the above-mentioned collaborative filtering method, there is a possibility that appropriate information cannot be presented as recommended information. Further, there is a possibility that the recommended information cannot be presented at an appropriate timing.

  In one aspect, an object of the present invention is to provide an information providing method, an information providing apparatus, and an information providing program capable of presenting appropriate information to a user at an appropriate timing.

  In one aspect, the information providing method includes, based on at least one of information on a search item selected by a user when searching for an item in an item search system, and a user's operation history in the search system, the user is provided with a plurality of items. Classifying users into a first group of users whose number of types of operations is smaller than a predetermined number, based on the number of types of operations performed by the users in the search system; It is detected that the specific user classified into the first type of user has performed an operation of a type that the specific user has not performed for a predetermined period of time. In the case, among the users classified into the same user group as the specific user, based on the past operation history of the user classified into the second type of user, The determining the information to be provided to a particular user, and outputs, the information providing method processing computer executes.

  Appropriate information can be presented to the user at an appropriate timing.

It is a figure showing roughly the composition of the information service system concerning one embodiment. FIG. 3 is a diagram illustrating a hardware configuration of a server. It is a functional block diagram of a server. FIG. 4A is a diagram illustrating an example of a data structure of a user context table, and FIG. 4B is a diagram illustrating an example of a data structure of a user transition path table. FIG. 5A is a diagram illustrating an example of a data structure of a user group table, and FIG. 5B is a diagram illustrating an example of a data structure of a user list table. It is a figure showing an example of a search screen. FIGS. 7A and 7B are diagrams for explaining a method of determining a satisfied person and a pursued person. It is a flowchart which shows a user classification process. It is a flowchart which shows a determination process. It is a flowchart which shows the process of step S24 of FIG. It is a flowchart which shows the process of step S26 of FIG. It is a flowchart which shows an information provision process. FIGS. 13A to 13C are diagrams illustrating specific examples of the state transition of the user. It is a figure showing the example of a user transition path table. FIGS. 15A and 15B are diagrams illustrating an example of providing information.

  Hereinafter, an embodiment of an information providing system as a search system will be described in detail with reference to FIGS.

  FIG. 1 schematically shows a configuration of an information providing system 100 according to an embodiment. The information providing system 100 according to the present embodiment is a system used for searching for a replacement part of a part (item) currently adopted by a user, for example, at the time of design revision of an electronic device or the like. When the information providing system 100 receives input of information on an item such as a hard disk, a solid state drive (SSD), or a diode currently employed by the user, the information providing system 100 extracts information on a substitute for the item from the database and To provide.

  The information providing system 100 includes a server 10 as an information providing device and a user terminal 70, as shown in FIG. The server 10 and the user terminal 70 are connected to a network 80 such as the Internet.

  The server 10 executes a substitute component search process and a component search process. In the replacement part search process, the server 10 searches for a replacement part on the database based on the information of the currently adopted part (item) input at the user terminal 70, and returns the search result to the user terminal 70. Output to In the component search process, the server 10 searches for a component in the database based on the component (item) search condition (“memory with rated voltage α” or the like) input at the user terminal 70 and searches. The result is output to the user terminal 70. The server 10 also performs a process of monitoring a user operation and presenting information on a recommended operation to the user at a timing required by the user.

  FIG. 2 shows a hardware configuration of the server 10. As shown in FIG. 2, the server 10 includes a CPU (Central Processing Unit) 90, a ROM (Read Only Memory) 92, a RAM (Random Access Memory) 94, a storage unit (here, an HDD (Hard Disk Drive)) 96, a network, An interface 97 and a portable storage medium drive 99 are provided. These components of the server 10 are connected to a bus 98. In the server 10, the CPU 90 executes a program (including the information providing program) stored in the ROM 92 or the HDD 96 or a program (including the information providing program) read from the portable storage medium 91 by the portable storage medium drive 99. By doing so, the functions as the information acquisition unit 11, the user classification unit 12, the determination unit 14 as the classification unit, the information provision determination unit 16, the provided information selection unit 18, and the notification unit 20 illustrated in FIG. 3 are realized. . FIG. 3 also shows various tables stored in the HDD 96 or the like. The various tables include a user context table 32, a user transition path table 34, a user group table 36, and a user list table 38.

  The information acquisition unit 11 acquires user context information and a user transition path. Here, the context information means information selected on the user terminal 70 by the user. That is, the context information is, for example, a characteristic item of the component selected by the user on the search screen displayed in the component search process (a search item set at the time of search, such as a capacitance value, a rated voltage, and a size). And When acquiring the context information of the user, the information acquisition unit 11 stores the acquired context information in the user context table 32. FIG. 4A shows an example of the data structure of the user context table 32. As shown in FIG. 4A, the user context table 32 has a “user” field and “context 1”, “context 2”,... The user context table 32 stores information on which context (characteristic item) each user has selected and searched for.

  The user transition path means information indicating that the user has transitioned from a certain state to a certain state. In the present embodiment, the user transition path means information that the user presses a certain button on the screen and then presses the same or another button. In the present embodiment, the screen for acquiring the user transition path is a search screen as shown in FIG. In the search screen of FIG. 6, a substitute part can be searched by inputting a part number currently used in the part number column. Also, the buttons of “item candidate”, “select all lines”, “display selected lines”, “output selected lines CSV”, “select selected lines”, and “delete selected lines” can be appropriately pressed by the user. It has become.

  When acquiring the user transition path, the information acquisition unit 11 stores the acquired user transition path in the user transition path table 34. FIG. 4B shows an example of the data structure of the user transition path table 34. As shown in FIG. 4B, the user transition path table 34 has a “user” field, “pre-state” and “post-state” fields, and a “valid flag” field. The “user” field stores user identification information, and the “before” and “after” fields contain user transition paths, ie, information on states corresponding to two buttons pressed by the user in order. Is stored. In the field of “valid flag”, a flag indicating whether or not the user transition path is valid is stored. If the validity flag is “1”, it means that the user transition path is new and valid (can be used for processing). If the valid flag is “0”, it means that the user transition path is old and invalid (cannot be used for processing). That is, a user transition path in which the valid flag is “0” means a state in which the user has transitioned more than a predetermined period ago.

  Returning to FIG. 3, the user classifying unit 12 assigns users having similar search purposes to the same user group based on information stored in the user context table 32 and information stored in the user transition path table 34. (Group). Specifically, the user classifying unit 12 classifies users having similar context information and user transition paths into the same group. As an example, the user classifying unit 12 classifies users based on context information of each user and a user transition path using a self-organizing map (SOM) algorithm. Note that the user classification unit 12 may classify users by using an SVM (Support Vector Machine). Note that the user classifying unit 12 may classify users based on any of the information stored in the user context table 32 and the information stored in the user transition path table 34.

  The user classifying unit 12 stores the result of classifying the user in the user group table 36. FIG. 5A shows an example of the data structure of the user group table 36. As shown in FIG. 5A, the user group table 36 has a “group” field and a “user” field. The “group” field stores identification information of a group (user group), and the “user” field stores identification information of users classified into groups. Users arranged in the row direction mean users classified into the same group.

  The determination unit 14 classifies the user into two types based on the user transition path table 34. Specifically, the determination unit 14 determines that the user is a first-type user (Satisficer) and a second-type user (Maximizer) based on the characteristics of the behavior at the time of the search. Classify. It is assumed that the interval at which the determination unit 14 executes the process of classifying users (repetition interval) is shorter than the interval at which the user classification unit 12 executes user classification (repetition interval).

  Here, the pursuer means a person who always searches for the best and performs a search action. In general, a searcher can obtain good results when performing a search, but the search often takes time. Also, pursuers are less satisfied with the results and more likely to regret. On the other hand, since the satisfied person tends to be satisfied with the found one, the deep search is not performed, and the time required for the search is short. Satisfied persons also have a low tendency to regret search results. Usually, the number of pursuers is small (about 20% of all users), and the number of satisfied persons is large (more than 80% of all users). It should be noted that the pursuiter and the skilled person do not always match.

  The definition of Satisficer is described in "Simon, H. A. 1955. Behavioral model of rational choice. Quarterly Journal of Economics, 69, 99-118." For the analysis of Maximizer / Satisficer, see "Schwartz, B., Ward, A., Monterosso, J., Lyubomirsky, S., White, K., & Lehman, D. 2002. Maximizing versus satisficing: Happiness is a matter of choice. Journal of Personality and Social Psychology, 83, 1178-1197. "

The determination unit 14 stores the result of classifying the user into the pursuiter and the satisfied person in the user list table 38. FIG. 5B shows an example of the data structure of the user list table 38. As shown in FIG. 5B, the user list table 38 has fields of “user”, “N _{max — U} ”, and “S / M”. The field of “N _{max_U} ” stores the number of reaching state types per session. One session may be a unit time or one search operation. For example, if one session is a unit time, it means the number of button types pressed by the user per unit time. Also, if one session is one search operation, it means the number of button types pressed by the user in one search. Note that _{Nmax_U} counts the number of reachable states as 1, even when an operation of pressing a certain button and then pressing a certain button is performed a plurality of times. The larger the value of _{Nmax_U,} the closer to the _pursuiter . In the present embodiment, the determination unit 14 determines the user's N _{Max_U} is determined that the pursuit's greater than the average value N _A of all the users of the N _{Max_U,} and satisfaction's smaller. For example, it is _assumed that the average value N _A of all the users transitions as indicated by a broken line in FIG. 7A, and the number of states N _{max_U of} a certain user transitions as indicated by a solid line. In this case, while the value of N _{max_U} -N _A shown in FIG. 7B is larger than 0, the determination unit 14 determines that the person is a pursuer, and while the value of N _{max_U} -N _A is 0 or less, Judge as satisfied. In the “S / M” field of FIG. 5B, a flag indicating one of the pursuiter (M) and the satisfied person (S) is stored as a determination result (classification result) of the determination unit 14.

  Based on the user transition path input from the information acquisition unit 11, the information provision determination unit 16 determines that the satisfied person has performed an action that has not been performed for a predetermined period, that is, that the satisfied person has pressed a new button that has not been pressed for a predetermined period. Is detected, it is determined that it is time to provide information, and the provided information selecting unit 18 is notified.

  Upon receiving the notification from the information provision determining unit 16, the provided information selecting unit 18 refers to the user group table 36, the user list table 38, and the user transition path table 34, and the user who has pressed a new button (satisfied person) Select the information to be provided to Specifically, the provided information selection unit 18 specifies pursuers belonging to the same group as the user (satisfied person) who pressed the new button based on the user group table 36 and the user list table 38. Then, the provided information selecting unit 18 extracts the user transition path (only the valid flag = 1) of the specified pursuer from the user transition path table 34, and selects information based on the extracted user transition path as information to be provided. . The information to be provided is, for example, help information of a button to be pressed next.

  The notification unit 20 transmits (notifies) the information to be provided selected by the provided information selection unit 18 to the user terminal 70 used by the user in order to provide the user (satisfied person) who pressed the new button. .

  In addition, the information provision determination unit 16 also monitors the behavior of the user (user transition path) after the notification by the notification unit 20, and when not using the notified information, it is a timing to provide another information. And notifies the provided information selecting unit 18. The provided information selecting unit 18 that has received the notification selects another piece of information to be provided, and the notifying unit 20 transmits (notifies) the selected information to be provided to the user terminal 70.

  Returning to FIG. 1, the user terminal 70 is a terminal such as a PC (Personal Computer), displays the search screen or the like in FIG. 6 on a display unit, and displays search conditions input by the user via the input unit on the server 10. Send to Further, the user terminal 70 receives the result searched by the server 10 based on the search condition, and displays the result on the display unit. Further, when receiving the information to be provided from the server 10, the user terminal 70 displays the information on the display unit.

(Process of server 10)
Next, the processing of the server 10 will be described in detail with reference to the flowcharts of FIGS.

(User classification processing)
First, the user classification process by the user classification unit 12 of the server 10 will be described with reference to the flowchart of FIG. As a premise of the processing in FIG. 8, it is assumed that a parameter t representing time is 0 (initialized). It is assumed that the user group table 36 has been flushed at the stage of starting the processing in FIG. Further, in the present embodiment, for convenience of description, a case will be described in which user classification is performed based only on information stored in the user context table 32.

In the process of FIG. 8, first, in step S10, the user classification unit 12 determines whether or not t is larger than the threshold value T _U. In this step S10, it is determined whether or not a time T _U (an interval at which the user classification process should be executed) has elapsed since the start of the process of FIG. If the determination in step S10 is negative, the process proceeds to step S12, in which the user classifying unit 12 adds the interval a at which step S10 is repeatedly executed to t (t = t + a), and then returns to step S10.

  Then, when the determination in step S10 is affirmed, the user classifying unit 12 proceeds to step S14. In step S14, the user classifying unit 12 refers to the user context table 32. The user context table 32 stores the user context information acquired by the information acquisition unit 11 as needed.

  Next, in step S16, the user classifying unit 12 executes user classification. In this case, as described above, the user classifying unit 12 classifies the users from the context information of each user using the algorithm of the self-organizing map (SOM) or the like. The user classifying unit 12 stores the result of classifying the user in the user group table 36.

When the above processing is performed, all the processing in FIG. 8 ends. Note that the processing in FIG. 8 is repeatedly executed. For this reason, the user group table 36 is updated with new information every time T _U.

  In the above description, by performing user classification based on the user context table 32, users having similar context information are classified into the same group. However, the present invention is not limited to this, and the user who uses the information providing system 100 may be classified into the same group by further considering the user transition path table 34 in the user classification.

(Determination process)
Next, a determination process performed by the determination unit 14 will be described in detail with reference to FIG. Note that the process in FIG. 9 is a process executed in parallel with the process in FIG. Note that, at the stage of starting the processing in FIG. 9, it is assumed that the parameter t representing time is set to 0. Also, “1 session” indicating an interval at which step S26 to be described later is repeated is a time _TH interval.

In the process of FIG. 9, first, in step S20, the information acquisition unit 11, t is judged whether or not greater than the threshold T _H. In this step S20, it is determined whether or not a time _TH (an interval at which the determination process is to be executed) has elapsed since the start of the process of FIG. If the determination in step S20 is negative, the process proceeds to step S22, where the information acquisition unit 11 adds the interval a at which step S20 is repeatedly executed to t (t = t + a), and then returns to step S20. The value of the interval a may be the same value as the interval a used in FIG. 8, or may be a different value.

  Then, when the determination in step S20 is affirmed, the information acquiring unit 11 proceeds to step S24. In step S24, the information acquisition unit 11 executes a subroutine for generating (updating) a user transition path table. In the present subroutine, the information acquisition unit 11 performs a process according to the flowchart of FIG.

  Hereinafter, step S24 (user transition path table generation (update) processing) will be described with reference to FIG.

(FIG. 10: User Transition Path Table Generation (Update) Processing)
In the process of FIG. 10, first, in step S30, the information acquisition unit 11 determines whether or not it is the first activation. In the case of the first activation, since nothing is stored in the user transition path table 34, the determination in step S30 is affirmed, and the process directly proceeds to step S34. On the other hand, if the determination in step 30 is denied (if it is not the first activation), the process proceeds to step S32, and the information acquisition unit 11 flushes (= 0) all the valid flags in the user transition path table 34, Move to step S34.

  In step S34, the information acquisition unit 11 determines whether there is an unselected user. If the determination is affirmative, the process proceeds to step S36, and the information acquisition unit 11 selects one unselected user.

  Next, in step S38, the information acquisition unit 11 extracts a state set before and after from the state transition accessed by the selected user. For example, suppose that the user U0 has made a state transition as shown in FIG. In this case, as shown in FIG. 14, a set of the before state and the after state of the user U0 can be extracted. In this case, in step S40, the information acquisition unit 11 registers the extracted state transition set in the user transition path table 34. Specifically, if the extracted state transition set does not exist in the user transition path table 34, the information acquisition unit 11 newly adds data of the state transition set and sets the valid flag to 1. On the other hand, when the extracted state transition set already exists in the user transition path table 34, the information acquisition unit 11 changes the validity flag from 0 to 1.

  On the other hand, for example, assume that the user U1 makes a state transition as indicated by a solid arrow in FIG. 13B (a broken line means a state transition that has been accessed in the past). In this case, in step S40, the information acquisition unit 11 sets the valid flag to 0 for the previous state and the rear state corresponding to the broken arrow, and sets the valid flag to 1 for the other states.

  As described above, after the processing up to step S40 is performed, the process returns to step S34. Then, the processing of steps S34 to S40 is repeated until the user transition paths of all users are stored in the user transition path table 34. Thereafter, when the determination in step S34 is denied, the entire process in FIG. 10 ends, and the process proceeds to step S26 in FIG.

  In step S26 in FIG. 9, the determination unit 14 executes a subroutine of a pursuiter / satisfier determination process. Hereinafter, step S26 (pursuiter / satisfier determination process) will be described in detail with reference to FIG.

(Fig. 11: Pursuiter / Satisfier determination process)
In the process of FIG. 11, first, in step S50, the determination unit 14 acquires the number N _{max_U} of reaching state types per session of all users. Here, the number of state transitions for which the valid flag is set to 1 in the user transition path table 34 is _{Nmax_U} .

Next, in step S52, the determination unit 14 calculates the average value N _{A of the} number of arrival state types for all users. Judging section 14 sums the arrival status species number N _{Max_U} for each user acquired in step S50, divided by the number of users, to calculate the average value N _A.

Next, in step S54, the determination unit 14 selects an unselected user. Next, in step S56, the determination unit 14 acquires the number of reaching state species N _{max_U} per session of the selected user.

Next, in step S58, the determination unit 14, the difference between the average value N _A calculated in N _{Max_U} and step S52 obtained in step S56 _(N max_U -N _A) to determine whether greater than zero. If the determination in step S58 is affirmative, the determination unit 14 determines that the user is a pursuer, and in step S60, the “S / M” column of the user list table 38 corresponding to the selected user. To the pursuiter flag M. On the other hand, if the determination in step S58 is negative, the determination unit 14 classifies the user as a satisfactory user, and in step S62, enters the “S / M” column of the user list table 38 corresponding to the selected user. Is given a satisfactory person flag S.

  After the processing in step S60 or S62 is performed, the process proceeds to step S64, and the determination unit 14 determines whether all users have been selected. If the determination in step S64 is negative, the process returns to step S54, and the processes in steps S54 to S64 described above are repeated. On the other hand, if the determination in step S64 is affirmative, the entire process of FIG. 11 is terminated, and the entire process of FIG. 9 is terminated.

As described above, FIG. 10, by the processing of FIG. 11 is executed every time T _H, every predetermined time (one section), the user changes the path table 34 is generated (updated), the user list table 38 is updated.

(Information provision processing)
Next, based on FIG. 12, the information providing process performed by the server 10 (the information providing determining unit 16, the provided information selecting unit 18, and the notifying unit 20) will be described in detail.

  In the process of FIG. 12, first, in step S70, the information provision determination unit 16 waits until there is any state transition of a satisfied person. That is, the information provision determination unit 16 waits until a user classified as a satisfactory user in the user list table 38 presses any button. Here, in the present embodiment, as an example, it is assumed that the user U0 (supposed to be a satisfactory user) in FIG. 14 has transitioned from the “result display” state to the “parts deleted” state as illustrated in FIG. . This state transition means that the user has pressed the “delete selected line” button on the search screen in FIG.

  Basically, if you are satisfied, you will find that it is sufficient if you can find a replacement part for the part you are currently using. Satisfied persons often repeatedly execute a specific operation on the search screen. However, when the replacement part is not found by the search, an operation which is not normally performed may be executed to search for the replacement part. In the present embodiment, information is presented at a timing when such a satisfactory person performs an operation that is not normally performed. That is, the timing at which the satisfactory user U0 transitions to the “parts deleted” state that is not registered in the user transition path table 34 is the timing at which the satisfactory user U0 performs an operation that is not normally performed (an operation performed by a pursuant is performed. Timing).

  When the satisfied person has made a state transition, the information provision determining unit 16 proceeds to step S72, and refers to data in which the valid flag of the user transition path table 34 is 1.

  Next, in step S74, the information provision determination unit 16 determines whether or not the satisfied person has reached a state not recorded in the user transition path table 34 (a state in which the valid flag is 1 and not included in the after state). Judge. If the determination in step S74 is denied, the process returns to step S70. If the determination is affirmed, the process proceeds to step S76. Note that the information provision determination unit 16 notifies the provision information selection unit 18 at the timing when the determination in step S74 is affirmed. In the example of FIGS. 13C and 14, since the user U0 has transitioned to the “parts deleted” state that does not exist in the user transition path table 34, the determination in step S74 is affirmed, and the process proceeds to step S76. become. Note that, at this stage, the server 10 does not yet execute the processing (part deletion) corresponding to the “delete selected row” button.

  In step S76, the provided information selecting unit 18 having received the notification extracts a set of paths related to the reached state from among the state transition paths of the user who is the same user classification and pursuer. For example, assume that the user U1 in FIG. 14 has the same user classification and pursuer as the user U0. In this case, as a set of paths related to the state “parts deleted” reached by the user U0, “result display → CSL DL” including “result display →” and “result display → Part selection ”is extracted.

  Next, in step S78, the provided information selecting unit 18 totalizes the states in descending order of arrival number. In the case of the above example, “Result display → Part deletion” with the valid flag = 1 is the state path with the largest number of arrivals.

  Next, in step S80, the provided information selection unit 18 selects one state in descending order of arrival number. In the case of the above example, “display result → delete part” is selected. The provided information selecting unit 18 transmits information (for example, help information) related to the selected state to the notifying unit 20.

  Next, in step S82, the notifying unit 20 transmits the information (help information) related to the state selected by the provided information selecting unit 18 to the user terminal 70 (the user terminal 70 of the satisfied person whose state has transitioned in step S70). To present. For example, as shown in FIG. 15A, as help information of the button “delete selected row” corresponding to the state “delete part”, character information such as “deletion of selected row is effective in deleting part selection man-hour” is presented. I do. When the user presses the “delete selected row” button again from this state, the server 10 executes a process corresponding to the button.

  Next, in step S84, the information provision determination unit 16 determines whether a satisfied person has reached the presented information. That is, it is determined whether or not the user (satisfied person) has pressed the button for presenting the help information. If the determination in step S84 is affirmative, the process proceeds to step S86, and the information provision determination unit 16 registers the information in the user transition path table 34 via the information acquisition unit 11. After that, the entire process of FIG. 12 ends.

  On the other hand, when the determination in step S84 is negative, the process shifts to step S88, and the provided information selecting unit 18 determines whether there is any remaining unselected state among the states totalized in step S78. to decide. If the determination in step S88 is affirmative, the process returns to step S80, where the provided information selecting unit 18 selects one state having the next largest number of arrivals, and in step S82, changes the selected state to the user terminal 70. To present. Thereafter, the processing of steps S84 to S88 is performed in the same manner as described above, and if the determination of step S88 is denied, the entire processing of FIG.

  As described above, by executing the processing in FIG. 12, appropriate information required by the user can be presented at an appropriate timing. Thereby, the operation of the user can be appropriately assisted.

  As shown in FIG. 15A, a "reason" button may be provided in the help information. When the user presses the “reason” button, the notification unit 20 uses the reason information “based on past user trace information...” Prepared in advance as shown in FIG. May be presented on the user terminal 70. Thereby, it is possible to further improve the usability of the user.

  In this embodiment, the information providing unit 16 includes the information provision determining unit 16, the provided information selecting unit 18, and the notifying unit 20. A function as an output unit for determining and outputting is realized.

  As described above in detail, according to the present embodiment, the user classifying unit 12 determines the information (context information) of the characteristic item selected by each user when searching for an item, and the operation history (user transition) of each user. Based on at least one of the paths, similar users are classified into groups (FIG. 8). In addition, the determination unit 14 classifies each user into a pursuiter or a satisfyer based on the number of types of operations (the number of reaching states) performed by each user (S26, FIG. 10). When the information providing determination unit 16 detects that the satisfied person has performed an operation that has not been performed for a predetermined period, the provided information selecting unit 18 determines the state transition path of the pursuiter classified into the same group as the user. , The information to be presented to the user is determined, and is notified to the user terminal 70 via the notification unit 20 (FIG. 12). Thus, at the timing when the user who is a satisfactory user performs an operation that has not been performed for a predetermined period or more (at the timing when the behavior of the user has changed), the user (satisfied person) is similar in search manner and a pursuer. Information based on the operation history of the user can be presented. Therefore, it is possible to present appropriate information at an appropriate timing to a user (satisfied person) who has performed a new operation.

In the present embodiment, the interval T _U at which the user classifying unit 12 classifies users is set to be longer than the interval T _H at which the determining unit 14 classifies users. This makes it possible to determine the pursuiter or the satisfied person by reflecting the latest operation of the user. Therefore, according to the present embodiment, it is possible to appropriately support a user's search operation by appropriately determining whether a user needs to present information and providing information at an appropriate timing.

Further, in the present embodiment, the user of the arrival state species number N _{Max_U} is, based on whether the average N _A greater or not the number of the arrival state species all users, the user is classified whether pursued person or satisfied person. This makes it possible to easily and appropriately determine whether the user is a pursuer or a satisfied user.

In the above embodiment, the interval T _{H at} which the pursuiter / satisfier determination process (S26) is performed may be changed based on the ratio between pursuers and satisfyers. For example, in the first step, a process by fixing the interval T _H, after operating a predetermined period, when the value of the pursuit toll / satisfaction The number is greater than a predetermined threshold value L, then the short interval T _H If the threshold value T is larger than the predetermined threshold value L, the interval T _H may be increased. In this case, in a system in which there are relatively many pursuers, many types of information to be handled, and various search conditions are input (such as an Internet search system), the interval _TH is short, and there are many satisfied people, In a system with a small number of types or a system in which the purpose of use is limited (such as an in-house system), the interval _TH is long. By doing so, it is possible to appropriately set the interval for executing the pursuiter / satisfier determination process in consideration of the characteristics of the system.

  In the above embodiment, after providing the information as shown in FIGS. 15A and 15B, the user evaluates the information, and reflects the evaluation result when determining the information to be provided in the next and subsequent times. You may do so. In this case, the user's answer to a question such as “Is this information useful?” May be used as the user's evaluation, whether the user actually pressed the button, whether the user has viewed “reason”, Etc. may be evaluated by the user.

  In the above-described embodiment, the case where one information (help information) corresponds to one state has been described, but a plurality of pieces of information may correspond.

In the above embodiment, it was decided to determine whether a satisfactory user whether the user is pursued person at each interval T _H, the invention is not limited thereto. For example, aggregate the respective user of the determination result for each interval T _H (Pursuit's / satisfaction's) in multiple periods, the one with a lot of pursuit's satisfaction and user may determine the result of each user.

  In the above embodiment, when a satisfactory person presses a button that has not been pressed for a predetermined period, help information corresponding to the button may be presented. In this case, since the notification unit 20 only needs to read out the help information corresponding to the button pressed by the satisfied person from the database, the provided information selection unit 18 may be omitted.

  Note that the above processing functions can be realized by a computer. In this case, a program describing the processing contents of the functions that the processing device should have is provided. By executing the program on a computer, the processing functions are realized on the computer. The program describing the processing content can be recorded on a computer-readable recording medium (excluding a carrier wave).

  When the program is distributed, it is sold in the form of a portable recording medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. Alternatively, the program may be stored in a storage device of a server computer, and the program may be transferred from the server computer to another computer via a network.

  The computer that executes the program stores, for example, the program recorded on the portable recording medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes processing according to the program. Note that the computer can also read the program directly from the portable recording medium and execute processing according to the program. Further, the computer can also execute processing in accordance with the received program each time the program is transferred from the server computer.

  The above embodiment is a preferred embodiment of the present invention. However, the present invention is not limited to this, and various modifications can be made without departing from the spirit of the present invention.

In addition, regarding the description of the above embodiments, the following supplementary notes are further disclosed.
(Supplementary Note 1) The user is classified into a plurality of user groups based on at least one of information on a search item selected by the user when searching for an item in the item search system and an operation history of the user in the search system.
On the basis of the number of types of operations performed by the users in the search system, each user is referred to as a first type of user whose number of types of operation is smaller than a predetermined number, and a second type of user whose number of types of operation is larger than the predetermined number. Divided into different types of users,
When a specific user classified as the first type of user detects that the specific user has performed an operation of a type that has not been performed for a predetermined period, the specific user is classified into the same user group as the specific user. Among the classified users, information to be provided to the specific user is determined based on a past operation history of the user classified as the second type of user, and output,
An information providing method, wherein a computer executes processing.
(Supplementary Note 2) The information providing method according to Supplementary Note 1, wherein an interval at which the classifying process is executed is longer than an interval at which the classifying process is executed.
(Supplementary Note 3) The computer is configured to change an interval at which the classifying process is executed based on a ratio between the number of the first type users and the number of the second type users in the search system. 3. The information providing method according to claim 1 or 2, wherein
(Supplementary note 4) The information according to any one of Supplementary notes 1 to 3, wherein in the classification process, an average of the number of types of operations performed by the users in the search system is set to the predetermined number. Delivery method.
(Supplementary Note 5) A user who classifies users into a plurality of user groups based on at least one of information on a search item selected by a user when searching for an item in the item search system and a user's operation history in the search system. A classifier,
On the basis of the number of types of operations performed by the users in the search system, each user is referred to as a first type of user whose number of types of operation is smaller than a predetermined number, and a second type of user whose number of types of operation is larger than the predetermined number. A division unit for classifying users into different types;
When a specific user classified as the first type of user detects that the specific user has performed an operation of a type that has not been performed for a predetermined period, the specific user is classified into the same user group as the specific user. An output unit that determines information to be provided to the specific user based on a past operation history of the user classified as the second type of user among the classified users, and outputs the information;
An information providing device comprising:
(Supplementary Note 6) The information providing apparatus according to Supplementary Note 5, wherein an interval at which the classifying process is executed is longer than an interval at which the classifying process is executed.
(Supplementary Note 7) The sorting unit changes an interval at which the sorting process is performed based on a ratio between the number of the first type users and the number of the second type users in the search system. 7. The information providing device according to claim 5 or 6, wherein
(Supplementary note 8) The information provision according to any one of Supplementary notes 5 to 7, wherein the classification unit sets the predetermined number to an average of the number of types of operations performed by the user in the search system. apparatus.
(Supplementary Note 9) The user is classified into a plurality of user groups based on at least one of information on a search item selected when the user searched for the item in the item search system and an operation history of the user in the search system.
On the basis of the number of types of operations performed by the users in the search system, each user is divided into a first type of user whose number of types of operation is smaller than a predetermined number and a second type of user whose number of types of operation is larger than the predetermined number Divided into different types of users,
When a specific user classified as the first type of user detects that the specific user has performed an operation of a type that has not been performed for a predetermined period, the specific user is classified into the same user group as the specific user. Among the classified users, information to be provided to the specific user is determined based on a past operation history of the user classified as the second type of user, and output,
An information providing program for causing a computer to execute processing.

10. Server (information providing device)
12 User classification unit 14 Judgment unit (classification unit)
16 Information provision judgment unit (part of output unit)
18 Provided information selection unit (part of output unit)
20 Notification part (part of output part)

Claims (6)

Based on at least one of the information on the search item selected when the user searched for the item in the item search system and the operation history of the user in the search system, the user was classified into a plurality of user groups,
On the basis of the number of types of operations performed by the users in the search system, each user is referred to as a first type of user whose number of types of operation is smaller than a predetermined number, and a second type of user whose number of types of operation is larger than the predetermined number. Divided into different types of users,
When a specific user classified as the first type of user detects that the specific user has performed an operation of a type that has not been performed for a predetermined period, the specific user is classified into the same user group as the specific user. Among the classified users, information to be provided to the specific user is determined based on a past operation history of the user classified as the second type of user, and output,
An information providing method, wherein a computer executes processing.   2. The information providing method according to claim 1, wherein an interval at which the classifying process is executed is longer than an interval at which the classifying process is executed.   The computer performing the process of changing an interval at which the process of performing the classification is performed based on a ratio between the number of the first type of users and the number of the second type of users in the search system. The information providing method according to claim 1 or 2, wherein:   The information provision according to any one of claims 1 to 3, wherein in the classification processing, an average of the number of types of operations performed by the users in the search system is set to the predetermined number. Method. A user classification unit that classifies the user into a plurality of user groups based on information of a search item selected when the user has searched for the item in the item search system, and at least one of a user's operation history in the search system;
On the basis of the number of types of operations performed by the users in the search system, each user is referred to as a first type of user whose number of types of operation is smaller than a predetermined number, and a second type of user whose number of types of operation is larger than the predetermined number. A division unit for classifying users into different types;
When a specific user classified as the first type of user detects that the specific user has performed an operation of a type that has not been performed for a predetermined period, the specific user is classified into the same user group as the specific user. An output unit that determines information to be provided to the specific user based on a past operation history of the user classified as the second type of user among the classified users, and outputs the information;
An information providing device comprising: Based on at least one of the information on the search item selected when the user searched for the item in the item search system and the operation history of the user in the search system, the user was classified into a plurality of user groups,
On the basis of the number of types of operations performed by the users in the search system, each user is referred to as a first type of user whose number of types of operation is smaller than a predetermined number, and a second type of user whose number of types of operation is larger than the predetermined number. Divided into different types of users,
When a specific user classified as the first type of user detects that the specific user has performed an operation of a type that has not been performed for a predetermined period, the specific user is classified into the same user group as the specific user. Among the classified users, information to be provided to the specific user is determined based on a past operation history of the user classified as the second type of user, and output,
An information providing program for causing a computer to execute processing.

Images