Information processing device, information processing method, and information processing program

Abstract

To improve the usability of a user who uses the analysis results of a search query.SOLUTION: An information processing device comprises an acceptance unit, a generation unit, and a provision unit. The acceptance unit accepts input of a reference query serving as a search query to be analyzed by an operator. The generation unit generates content including nodes corresponding to each of a plurality of query groups obtained by classifying the search queries searched before and after a reference query, labels assigned to the query groups as information indicating categories of the search queries constituting each query group, and directed links connecting the nodes on the basis of a search order of the search queries constituting each query group. The provision unit provides the operator with the content generated by the generation unit.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present application relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are known techniques for providing analysis results of search queries entered into a search engine, such as a technique for generating an analysis graph that can be intuitively understood by thinning out peripheral queries around a central query (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-149551 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques have room for improvement in terms of improving usability for users who utilize the results of analyzing search queries.

[0005] The present application has been made in consideration of the above, and aims to improve usability for users who use the analysis results of search queries. [Means for solving the problem]

[0006] An information processing device according to the present application includes a receiving unit, a generating unit, and a providing unit. The receiving unit receives input of a reference query, which is a search query to be analyzed, from an operator. The generating unit generates content including nodes corresponding to each of a plurality of query groups obtained by classifying search queries searched before and after the reference query, labels assigned to the query groups as information indicating the category of each search query constituting the query group, and directed links connecting each node based on the search order of each search query constituting the query group. The providing unit provides the content generated by the generating unit to the operator. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to improve usability for users who use the analysis results of search queries. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. [Figure 2] FIG. 2 is a diagram showing an example of displaying content according to the embodiment. [Figure 3] FIG. 3 is a diagram showing an example of display of content according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a before-and-after query according to the embodiment. [Figure 5] FIG. 5 is a diagram showing an overview of classification of search queries by the generation AI according to the embodiment. [Figure 6] FIG. 6 is a diagram for explaining a content generation method according to the embodiment. [Figure 7] FIG. 7 is a diagram for explaining a content generation method according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 9] FIG. 9 is a flowchart illustrating an example of a procedure of information processing executed by the information processing device according to the embodiment. [Figure 10]FIG. 10 is a diagram showing an example of displaying content according to a modified example. [Figure 11] FIG. 11 is a diagram showing an example of displaying content according to a modified example. [Figure 12] FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [Embodiment] [1. An example of information processing] An example of information processing according to the embodiment will be described below with reference to the drawings: Fig. 1 is a diagram for explaining an example of information processing according to the embodiment.

[0011] The information processing according to the embodiment is realized by an information processing system including a terminal device 10 shown in Fig. 1 and an information processing device 100 shown in Fig. 1. The terminal device 10 and the information processing device 100 are each connected to a network N (see Fig. 8, for example) by wire or wirelessly. The terminal device 10 and the information processing device 100 can communicate with other devices through the network N.

[0012] The network N includes, for example, a WAN (Wide Area Network) such as the Internet, and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: fifth generation mobile communication system).

[0013] The terminal device 10 is connected to a network N by short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or wireless LAN (Local Area Network), and can communicate with other devices such as the information processing device 100 through the network N.

[0014] The terminal device 10 is used by an operator U who uses the analysis results of a search query provided by the information processing device 100. To use the analysis results of a search query, the operator U may, for example, access a dedicated website managed by the information processing device 100. The operator U may also install a dedicated tool equipped with various functions for using the analysis results of a search query into the terminal device 10 as appropriate. In this case, the operator U can operate the dedicated tool to obtain necessary information from the information processing device 100 as appropriate and use the analysis results of the search results on the terminal device 10.

[0015] Furthermore, when the terminal device 10 receives control information for realizing predetermined information processing from the information processing device 100, the terminal device 10 realizes the information processing in accordance with the control information. Here, the control information is described in, for example, a script language such as JavaScript (registered trademark), a style sheet language such as CSS (Cascading Style Sheets), a programming language such as Java (registered trademark), or a markup language such as HTML (HyperText Markup Language). Note that a predetermined application itself delivered from the information processing device 100 or the like may also be considered as control information.

[0016] FIG. 1 illustrates a case where the terminal device 10 is a notebook PC (Personal Computer), but it may also be, for example, a desktop PC, a smartphone, or a tablet PC.

[0017] Information processing device 100 is operated and managed by a service provider that provides various online services. For example, the service provider operates a search service that, as one of the various online services, acquires information corresponding to a search query entered by a user who uses the online service from information publicly available on the Internet and provides the acquired information.

[0018] The information processing device 100 is typically a server device, but may also be realized by a mainframe, a workstation, etc. Furthermore, when the information processing device 100 is realized by a server device, it may be realized by a single server device, or may be realized by a cloud system in which multiple server devices and multiple storage devices operate in cooperation with each other.

[0019] The information processing device 100 also has a function of providing an operator U with analysis results of a search query using a search history accumulated in a search service. The information processing device 100 executes information processing according to an embodiment described below in relation to providing analysis results of a search query. Processing function units that the information processing device 100 has for realizing the information processing according to the embodiment will be described later.

[0020] 1, the terminal device 10 transmits information about a reference query, which is a search query to be analyzed, to the information processing device 100 in accordance with an operation of an operator U on a dedicated website W. For example, the terminal device 10 transmits information about a search query (e.g., "job change") entered in an input box BX provided on the dedicated website to the information processing device 100 in accordance with an operation of a search button BT.

[0021] When the information processing device 100 receives input of a reference query from an operator U through a dedicated website W (step S01), it acquires previous and subsequent queries (examples of "target queries"), which are search queries that have been searched within a specified period before and after the time of searching the reference query and whose relevance exceeds a specified standard (step S02).

[0022] For example, the information processing device 100 identifies a reference query from the search history, and evaluates the relevance of the search query so that, among search queries searched in a predetermined period before and after the search time of the identified reference query, the relevance of a search query that is frequently searched in both a predetermined period chronologically before (i.e., in the past) and a predetermined period chronologically after (i.e., in the future) the search time is relatively higher than that of a search query searched in either the predetermined period before or the predetermined period after the search time.The information processing device 100 then acquires previous and next queries based on the evaluation result of the relevance of the search query.

[0023] 4 is a diagram illustrating an example of previous and next queries according to an embodiment. As illustrated in FIG. 4, when the reference query input from the operator U is "job change," the information processing device 100 acquires, as previous and next queries, search queries such as "hello work," "job change website," and "how to write a resignation letter," each of which has a degree of relevance exceeding a predetermined standard.

[0024] After acquiring the preceding and following queries, the information processing device 100 classifies the search query acquired as the preceding and following queries into one of a plurality of query groups to which information indicating the behavior of the user who input the reference query is attached as a label LB (step S03).

[0025] The information processing device 100 can classify search queries acquired as context queries, for example, by using a generation AI that has been trained to generate answers to input questions. Fig. 5 is a diagram illustrating an overview of search query classification by the generation AI according to the embodiment.

[0026] As shown in FIG. 5, the information processing device 100 classifies search queries into multiple query groups, taking into consideration the information on the search queries acquired as the preceding and following queries and the high degree of relevance to the reference query, and can classify search queries by inputting instruction information (also referred to as a "prompt") that instructs the device to attach summary information summarizing user behavior based on the search queries belonging to the query group as a label LB for the query group.

[0027] As shown in Figure 5, the generation AI classifies the search query "Hello Work" into a group of queries with the label LB "job change concrete stage." In other words, the information indicating the category of the search query "Hello Work" becomes "job change concrete stage."

[0028] For example, the search query: "job change site" is classified into a group of queries to which the label LB of "job change agent utilization" is assigned. In other words, the information indicating the category of the search query: "job change site" is "job change agent utilization."

[0029] For example, the search query: "How to write a resignation letter" is classified into a group of queries with the label LB "preparation for job hunting." In other words, the category information for the search query: "how to write a resignation letter" is "preparation for job hunting."

[0030] Furthermore, the instruction information EX-1 shown in Figure 5 is an example of instruction information used to instruct the generation AI to classify the search queries acquired as previous and next queries and to assign a label LB to the query group into which the search queries are classified as information indicating the category of the search queries.

[0031] In addition, the information processing device 100 can also classify each search query by inputting instruction information to the generation AI that instructs the AI ​​to sort each search query into one of multiple classification destinations to which information indicating user behavior is pre-assigned as a label LB, taking into account the search query information and the high degree of relevance to the reference query.

[0032] The instruction information EX-2 shown in FIG. 5 is an example of instruction information when giving an instruction to the generation AI to sort the search query acquired as the preceding or following query into one of multiple pre-labeled classification destinations.

[0033] After classifying the search queries, the information processing device 100 generates content CNT-1 including nodes ND corresponding to each of a plurality of query groups resulting from the classification of the preceding and following queries, labels LB assigned to the query groups as information indicating the category of each search query constituting the query group, and directed links LK connecting each node based on the search order of each search query constituting the query group (step S04). Figures 6 and 7 are diagrams for explaining a method for generating content CNT-1 according to an embodiment.

[0034] 6, the information processing device 100 acquires search data within a target period of a user who has searched for the reference query (step S11). For example, in step S11, an example is shown in which, as search data of person A who searched for the reference query: "job change", search queries searched by person A within a target period for acquiring previous and following queries, categories corresponding to the search queries, and search dates which are the dates on which each of the search queries was first searched are acquired.

[0035] 6, the information processing device 100 aggregates and averages the search dates of the search queries by category, and sorts them by search date. For example, in step S12, an example is shown in which the earliest search date for "stage of concretely realizing a job change" is "February 15th," followed by the second earliest search date for "preparation for a job change" is "February 22nd," and the third earliest search date for "mental health care" is "February 28th."

[0036] In step S13 shown in FIG. 6, the information processing device 100 extracts all time-series behavioral patterns of users who searched for the reference query. For example, the information processing device 100 extracts all behavioral patterns consisting of a combination of a category that is a start point and a category that is an end point in time series, based on the search date. For example, in step S13, as one of Mr. A's behavioral patterns, a pattern is extracted in which the category: "job change concrete stage" is the start point, the category: "job change preparation" is the end point, and the time difference between the start point and the end point is: "7 days." The information processing device 100 extracts all time-series behavioral patterns of users who searched for the reference query for each user.

[0037] 7, the information processing device 100 aggregates the behavioral patterns of each user. For each behavioral pattern, the information processing device 100 counts the number of users and calculates the median of the time difference between the start point and end point of the behavioral pattern (step S15). The information processing device 100 extracts a predetermined number of behavioral patterns from those with the highest number of users, and generates content CNT-1 by drawing directed links connecting nodes in a format that reflects the time difference between the start points of the extracted behavioral patterns and the user overlap rate between the start points (step S16).

[0038] Returning to FIG. 1, the information processing device 100 transmits the generated content CNT-1 to the terminal device 10, thereby providing it to the operator U (step S05).

[0039] The terminal device 10 displays the content CNT-1 received from the information processing device 100 on a website W. The operator U browses the content CNT-1 displayed on the terminal device 10. Figures 2 and 3 are diagrams showing a display example of the content CNT-1 according to the embodiment.

[0040] 2, the operator U can display the time difference between the nodes connected by the directed links by specifying the directed links that make up the content CNT-1 with the mouse pointer PT. That is, the information processing device 100 can display information indicating the average time (for example, 6.6 days) from the user action indicated by the label attached to the starting node to the user action indicated by the end node.

[0041] 2, the operator U can specify a directed link constituting the content CNT-1 with the mouse pointer PT to display information indicating the percentage of users with the behavior pattern corresponding to the specified directed link to the total number of users who entered the reference query. That is, the information processing device 100 can display information indicating that the percentage of users who searched for a search query belonging to the query group corresponding to the end node, following a search query belonging to the query group corresponding to the start node, is 19.9% ​​of users who searched for the reference query: "job change."

[0042] For example, as shown in Figure 3, operator U can specify a node that constitutes content CNT-1 using a mouse pointer or the like to display a detailed explanation of the label (also known as a "category") attached to the query group corresponding to the node, as well as information about the search queries belonging to the query group.

[0043] As described above, the information processing device 100 according to the embodiment can visualize the behavior of a user who searched for a reference query from search query information. Furthermore, the information processing device 100 can grasp at a glance what search queries the user who searched for the reference query entered and in what order. Thus, the information processing device 100 according to the embodiment can improve usability for users who use search query analysis results.

[0044] [2. Equipment configuration] An example of the functional configuration of the information processing device 100 according to the embodiment will be described below with reference to Fig. 8. Fig. 8 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 8, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.

[0045] (Communication unit 110) The communication unit 110 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 110 is connected to a network N by wire or wirelessly. The information processing device 100 transmits and receives information to and from other devices such as the terminal device 10 via the network N.

[0046] (Storage unit 120) The storage unit 120 stores, for example, programs and data used for control and calculation by the control unit 130. For example, the storage unit 120 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. For example, the storage unit 120 has a search history DB 121 and a drawing information DB 122. Note that the storage unit 120 is not particularly limited to the example shown in FIG. 7 and can store data necessary for executing the information processing according to the embodiment as appropriate.

[0047] (Search History DB121) The search history DB 121 stores the search history of users who use the search service. The search history stored in the search history DB 121 includes information on the search query used in the search and information indicating the search date and time.

[0048] (Drawing information DB122) The drawing information DB 122 stores information on the format used when generating the content CNT-1. The drawing information stored in the drawing information DB 122 stores information such as shapes used when drawing the nodes ND that make up the content CNT-1 and the type and size of arrows used when drawing the directed links LK that connect the nodes ND. For example, the length of the line of the directed link LK may be set in advance according to a time difference, and the thickness of the line of the directed link LK may be determined in advance based on the number of users who have input search queries that belong to the query group corresponding to the node ND.

[0049] (control unit 130) The control unit 130 is a controller, and is realized by a CPU (Central Processing Unit), MPU (Micro Processing Unit), etc., executing various programs (examples of "information processing programs") stored in a storage device inside the information processing device 100 using RAM as a working area.

[0050] Furthermore, the control unit 130 may be realized by an integrated circuit such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or a general purpose graphic processing unit (GPGPU).

[0051] As shown in FIG. 8, the control unit 130 has a receiving unit 131, a classification unit 132, a generation unit 133, and a provision unit 134, and each of these units realizes or executes the functions and actions of the information processing described below.

[0052] Note that control unit 130 may have an internal configuration divided into multiple processing units that realize or execute the information processing functions and actions described below. Also, control unit 130 is not limited to the configuration shown in Fig. 8, and may have other configurations as long as they perform the information processing described below, and may have other functional units other than those shown in Fig. 8.

[0053] (Reception Department 131) The receiving unit 131 receives an input of a reference query, which is a search query to be analyzed, from an operator U (see FIG. 1, for example), via the communication unit 110. The receiving unit 131 passes information about the received input reference query to the classifying unit 132.

[0054] (Classification section 132) The classification unit 132 acquires search queries whose relevance exceeds a predetermined standard among the search queries searched during a predetermined period before and after the time of searching the reference query (an example of a "target query", see, for example, Figure 4), and classifies the acquired previous and next queries into one of multiple query groups to which information indicating the behavior of the user who entered the reference query is attached as a label LB.

[0055] Specifically, the classification unit 132 identifies a reference query from the search history, and evaluates the relevance of the search query so that, among search queries searched in a predetermined period before and after the search time of the identified search query, the relevance of a search query that is frequently searched in both a predetermined period chronologically before (i.e., in the past) and a predetermined period chronologically after (i.e., in the future) the search time is relatively higher than that of a search query searched in either a predetermined period before or a predetermined period after the search time.The classification unit 132 then acquires previous and next queries based on the evaluation result of the relevance of the search query.

[0056] Next, the classification unit 132 classifies each search query into multiple query groups, taking into consideration the previous and following queries, information about each acquired search query, and the degree of relevance to the reference query, for the generation AI that has been trained to generate answers to input questions. The classification unit 132 also inputs instruction information that instructs the generation AI to classify each search query into multiple query groups, taking into consideration the previous and following queries, information about each acquired search query, and the degree of relevance to the reference query. The label is information that indicates the category of the search query.

[0057] In addition, the classification unit 132 may classify each search query by inputting instruction information to a generation AI that has been trained to generate answers to input questions, instructing the AI ​​to sort each search query into one of multiple classification destinations to which information indicating user behavior is pre-labeled, taking into account the previous and following queries (an example of a "target query"), information about each acquired search query, and the high degree of relevance to the reference query.

[0058] The classification of the preceding and following queries performed by the classification unit 132 may be performed by the operator U. In this case, the information processing device 100 receives the classification data generated by the operator U from the terminal device 10 and can use the data to generate content.

[0059] (Generation unit 133) The generation unit 133 generates content CNT-1 (see, for example, Figure 1) that includes nodes ND corresponding to each of multiple query groups obtained by classifying search queries searched before and after a reference query, labels LB assigned to the query groups as information indicating the category of each search query that makes up the query group, and directed links LK that connect each node based on the search order of each search query that makes up the query group.

[0060] For example, the generation unit 133 uses the classification results by the classification unit 132 to extract a time-series behavioral pattern of each user based on the search order of the target queries belonging to the query group, and generates content CNT-1 that draws nodes ND corresponding to the start and end points of the extracted behavioral patterns and directed links LK connecting the nodes ND.

[0061] Specifically, the generation unit 133 counts the number of users for each extracted behavior pattern and calculates the median time difference between the start point and end point of the behavior pattern for each extracted behavior pattern. The generation unit 133 also selects a behavior pattern with the highest number of users and generates content CNT-1 in which directed links are drawn in a format that reflects the number of users and the median time difference corresponding to the selected behavior pattern. The generation unit 133 determines the format for drawing the content CNT-1 by referring to the drawing information DB 122.

[0062] (Provider 134) The providing unit 134 provides the content CNT-1 generated by the generating unit 133 to the operator U (see, for example, FIG. 1). For example, the providing unit 134 can provide the content CNT-1 to the operator U by transmitting information about the content CNT-1 to the terminal device 10 via the communication unit 110.

[0063] Furthermore, for example, when an operator U specifies a directional link LK on a dedicated website W (see, for example, FIG. 1 ), the providing unit 134 provides the operator U with information indicating the median of the time difference between the start point and end point of the behavior pattern corresponding to the specified directional link LK, as well as information indicating the proportion of the number of users corresponding to the behavior pattern corresponding to the specified directional link LK to the total number of users who input the reference query. For example, the providing unit 134 can provide the operator U with information indicating the proportion of the number of users corresponding to the behavior pattern corresponding to the specified directional link LK to the total number of users who input the reference query by transmitting the information to the terminal device 10 via the communication unit 110.

[0064] Furthermore, when the providing unit 134 receives a designation of a node ND from the operator U, it can provide the operator U with information describing the label corresponding to the node ND designated by the operator U and information on the search queries belonging to the query group.

[0065] 3. Processing Procedure According to the Embodiment The following describes the procedure of information processing executed by the information processing device 100 according to the embodiment. Fig. 9 is a flowchart showing an example of the procedure of information processing executed by the information processing device 100 according to the embodiment. The processing procedure shown in Fig. 9 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in Fig. 9 is repeatedly executed while the information processing device 100 is operating.

[0066] As shown in FIG. 9, the receiving unit 131 receives an input of a reference query, which is a search query to be analyzed, from an operator U (see FIG. 1, for example) (Step S101).

[0067] Furthermore, the classification unit 132 acquires search queries whose relevance exceeds a predetermined standard among the search queries searched during a predetermined period before and after the time of searching the reference query (an example of a "target query", see, for example, FIG. 4), and classifies the acquired previous and next queries into one of a plurality of query groups to which information indicating the behavior of the user who entered the reference query is attached as a label LB (step S102).

[0068] Furthermore, the generation unit 133 uses the classification result by the classification unit 132 to extract a time-series behavior pattern of the user for each user based on the search order of the target queries belonging to the query group (step S103).

[0069] The generation unit 133 also generates content CNT-1 that depicts nodes ND corresponding to the start and end points of the extracted behavior patterns, and directed links LK connecting the nodes ND (step S104).

[0070] In addition, the providing unit 134 provides the information on the content CNT-1 generated by the generating unit 133 to the operator U by transmitting it to the terminal device 10 via the communication unit 110 (step S105), and the processing procedure shown in FIG. 9 is terminated.

[0071] [4. Modifications] (4-1. Content corresponding to other criteria queries) The following describes other examples of content generated by the information processing device 100. Figures 10 and 11 are diagrams showing examples of content display according to modified examples.

[0072] When the information processing device 100 receives an input of "Hawaii" as a reference query from the operator U, it can generate content CNT-2 as exemplified in Fig. 10. Furthermore, when the information processing device 100 receives an input of "theme park" as a reference query from the operator U, it can generate content CNT-3 as exemplified in Fig. 11.

[0073] (4-2. Content editing function) Furthermore, the information processing device 100 may accept editing of content displayed on a dedicated website W by an operator U's operation using a pointing device or the like. For example, the information processing device 100 may accept, from the operator U, an editing of a label to be attached to a group of queries. When the operator U has completed editing of the label, the information processing device 100 can display the content with the updated label reflected. Furthermore, the information processing device 100 may accept, from the operator U, an operation to combine or divide nodes. For example, when the information processing device 100 accepts an operation to combine nodes, the information processing device 100 generates a new node by combining the corresponding nodes and requests the operator U to edit the label to be attached to the group of queries associated with the new node. Then, the information processing device 100 displays content in which the label edited by the operator U is attached to the group of queries corresponding to the new node.

[0074] [5. Hardware Configuration] The information processing device 100 according to the above-described embodiment and each of the modified examples is realized, for example, by a computer 1000 having a configuration as shown in Fig. 12. Fig. 12 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100 according to the embodiment.

[0075] The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0076] The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The primary storage device 1040 is a memory device, such as a RAM, that temporarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), HDD, flash memory, or the like.

[0077] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor or a printer, and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (High Definition Multimedia Interface), etc. The input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, and scanner, and is realized by, for example, USB.

[0078] The input device 1020 may be a device that reads information from an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. The input device 1020 may also be an external storage medium such as a USB memory.

[0079] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic device 1030, and also transmits data generated by the arithmetic device 1030 to other devices via the network N.

[0080] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0081] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the arithmetic device 1030 of the computer 1000 executes a program (for example, an information processing program) loaded onto the primary storage device 1040, thereby realizing the same functions as the control unit 130. That is, the arithmetic device 1030 cooperates with the program (for example, an information processing program) loaded onto the primary storage device 1040 to realize the processing by the information processing device 100 according to the embodiment.

[0082] [6. Other] Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using a known method. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified.

[0083] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0084] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0085] The above describes in detail the embodiments of the present application based on several drawings, but these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0086] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, a control section can be read as control means or a control circuit.

[0087] [7. Effects] The information processing device 100 according to the embodiment includes a receiving unit 131, a generating unit 133, and a providing unit 134. The receiving unit 131 receives input of a reference query, which is a search query to be analyzed, from an operator U. The generating unit 133 generates content CNT-1 including nodes ND corresponding to each of a plurality of query groups obtained by classifying search queries searched before and after the reference query, labels LB assigned to the query groups as information indicating the category of each search query that constitutes the query group, and directed links LK connecting each node based on the search order of each search query that constitutes the query group. The providing unit 134 provides the content CNT-1 generated by the generating unit 133 to the operator U.

[0088] Moreover, the information processing device 100 according to the embodiment further includes a classification unit 132. The classification unit 132 acquires search queries (examples of "target queries") whose relevance exceeds a predetermined standard from among search queries searched during a predetermined period before and after the search of the reference query, and classifies each acquired search query into one of a plurality of query groups to which information indicating the behavior of the user who input the reference query is attached as a label LB. The generation unit 133 uses the classification result by the classification unit 132 to extract a time-series behavior pattern of the user for each user based on the search order of the target queries belonging to the query group, and generates content CNT-1 in which nodes ND corresponding to the start points and end points of the extracted behavior patterns and directed links LK connecting the nodes ND are drawn.

[0089] In addition, the generation unit 133 can tally the number of relevant users for each behavioral pattern, calculate the median time difference between the start point and end point of the behavioral pattern for each behavioral pattern, select the behavioral pattern with the highest number of relevant users, and generate content CNT-1 in which a directional link LK is drawn in a format that reflects the number of relevant users and the median time difference corresponding to the selected behavioral pattern.

[0090] In addition, the classification unit 132 can classify each search query by inputting instruction information to the generation AI, which has been trained to generate answers to input questions, to classify each search query into multiple query groups taking into account the information of each search query acquired as a previous or next query and the high degree of relevance to the reference query, and to attach summary information summarizing user behavior based on the search queries belonging to the query group as a label LB to the query group.

[0091] In addition, the classification unit 132 can classify each search query by inputting instruction information to the generation AI, which has been trained to generate answers to input questions, that instructs the AI ​​to sort each target query into one of multiple classification destinations to which information indicating user behavior is pre-assigned as a label LB, taking into account the information on each search query acquired as the previous or next query and the high degree of relevance to the reference query.

[0092] In addition, when a directional link LK is specified by the operator U, the providing unit 134 can provide the operator U with information indicating the median time difference between the start point and end point of the behavior pattern corresponding to the specified directional link LK, as well as information indicating the percentage of the number of users corresponding to the behavior pattern corresponding to the specified directional link LK to the total number of users who input the reference query.

[0093] Furthermore, when the providing unit 134 receives a designation of a node ND from the operator U, it can provide the operator U with information describing the label corresponding to the node ND designated by the operator U and information on the search queries belonging to the query group.

[0094] For this reason, the information processing device 100 according to the embodiment can visualize the behavior of a user who searched for a reference query from search query information. Furthermore, the information processing device 100 can grasp at a glance what search queries the user who searched for the reference query entered and in what order. For this reason, the information processing device 100 according to the embodiment can improve usability for a user (for example, operator U shown in FIG. 1 ) who uses the search query analysis results.

[0095] Furthermore, the above-described effects can also be realized by the processing executed by each of the above-described units, or by any combination of the processing executed by each unit. [Explanation of symbols]

[0096] N Network 10 Terminal Equipment 100 Information processing device 110 Communications Department 120 Storage section 121 Search History DB 122 Drawing Information DB 130 Control Unit 131 Reception 132 Classification Department 133 Generation part 134 Supply Department

Claims

1. a reception unit that receives an input of a reference query, which is a search query to be analyzed, from an operator; a generation unit that generates content including nodes corresponding to each of a plurality of query groups obtained by categorizing search queries searched before and after the reference query, labels that are assigned to the query group as information indicating the category of each search query that constitutes the query group, and directed links that connect each node based on the search order of each search query that constitutes the query group; a providing unit that provides the content generated by the generating unit to the operator; An information processing device comprising:

2. a classification unit that acquires target queries whose relevance exceeds a predetermined standard from among search queries searched during a predetermined period before and after the time of searching the reference query, and classifies each search query acquired as the target query into one of a plurality of query groups to which information indicating the behavior of the user who input the reference query is attached as the label. and The generation unit Using the classification results by the classification unit, extracting a time-series behavioral pattern of the user for each user based on the search order of the target queries belonging to the query group, and generating the content by drawing the nodes corresponding to the start points and end points of the extracted behavioral patterns and the directed links connecting the nodes.

2. The information processing apparatus according to claim 1, wherein:

3. The generation unit The number of users corresponding to each of the behavioral patterns is tallied, and the median of the time difference between the start point and end point of each of the behavioral patterns is calculated. The behavioral patterns with the highest number of users corresponding to each of the behavioral patterns are selected. The content is generated by drawing the directed links in a format that reflects the number of users corresponding to the selected behavioral patterns and the median of the time difference.

3. The information processing apparatus according to claim 2, wherein:

4. The classification unit The generation AI, which has been trained to generate answers to input questions, classifies the target queries into a plurality of query groups, taking into consideration information about the target queries and the degree of relevance to the reference queries, and inputs instruction information instructing the generation AI to attach summary information summarizing the user's behavior based on the target queries belonging to the query groups as the labels, thereby classifying each of the search queries.

3. The information processing apparatus according to claim 2, wherein:

5. The classification unit The AI ​​is trained to generate answers to input questions, and the AI ​​receives instruction information to instruct the AI ​​to sort each of the target queries into one of a plurality of categories to which information indicating the user's behavior has been previously assigned as the label, taking into consideration the information on the target queries and the degree of relevance to the reference queries. The AI ​​then classifies each of the search queries.

3. The information processing apparatus according to claim 2, wherein:

6. The providing unit When the operator specifies the directed link, the operator is provided with information indicating the median value of the time difference between the start point and the end point of the behavior pattern corresponding to the specified directed link, as well as the percentage of the number of users corresponding to the behavior pattern corresponding to the specified directed link to the total number of users who input the reference query.

4. The information processing apparatus according to claim 3,

7. The providing unit When the node is designated by the operator, information explaining the label attached to the query group corresponding to the designated node and information on the search queries belonging to the query group are provided to the operator.

3. The information processing apparatus according to claim 2, wherein:

8. 1. A computer-implemented information processing method, comprising: a receiving step of receiving an input of a reference query, which is a search query to be analyzed, from an operator; a generation process for generating content including nodes corresponding to each of a plurality of query groups obtained by classifying search queries searched before and after the reference query, labels assigned to the query group as information indicating the category of each search query constituting the query group, and directed links connecting each node based on the search order of each search query constituting the query group; a providing step of providing the content generated by the generating step to the operator; An information processing method comprising:

9. On the computer, an acceptance step for accepting input of a reference query, which is a search query to be analyzed, from an operator; a generation step of generating content including nodes corresponding to each of a plurality of query groups obtained by classifying search queries searched before and after the reference query, labels assigned to the query group as information indicating the category of each search query constituting the query group, and directed links connecting each node based on the search order of each search query constituting the query group; a providing step of providing the content generated by the generating step to the operator; An information processing program characterized by causing the program to execute the above.

Images