Information processing device, information processing method and information processing program

Abstract

To analyze a change in a user's needs in order to appropriately grasp it.SOLUTION: An information processing device 100 comprises: an identification unit 132 which identifies retrieval queries of a plurality of users who perform a predetermined action; a processing unit 133 which generates classification of the retrieval queries and explanation contents of each cluster by inputting information about the retrieval queries identified by the identification unit 132 and an instruction sentence which instructs outputting the explanation contents in which each cluster is explained on the basis of the retrieval queries classified into each cluster, while clustering the retrieval queries into the plurality of clusters by taking correlation for each retrieval query into consideration, to a model in which learning has been performed so as to output a character string following an inputted character string; and a provision unit 144 which provides information for displaying the plurality of clusters clustered by the model and the explanation contents.SELECTED DRAWING: Figure 6

Description

[Technical Field]

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

[0002] Conventionally, there is a technology in query analysis devices that generates an analytical graph that allows intuitive understanding of changes in user needs over time using queries entered into a search site. One known technology generates an analytical graph that allows intuitive understanding by thinning out peripheral queries around a central query that serves as a reference. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6983269 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional technology has room for further improvement, for example, in order to properly grasp changes in user needs.

[0005] The present application has been made in view of the above, and aims to perform an analysis to appropriately grasp changes in user needs. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objective, the information processing device is characterized by having an identification unit that identifies search queries of multiple users performing a predetermined behavior, a processing unit that classifies the search queries identified by the identification unit and generates explanatory content for each cluster by inputting information about the search queries identified by the identification unit and instruction sentences that instruct the search queries to be clustered into multiple clusters taking into account the relevance of each search query and to output explanatory content that describes each cluster based on the search queries classified into each cluster into a model that has been trained to output a string following the input string, and a provision unit that provides information for displaying the multiple clusters clustered by the model and the explanatory content. [Effects of the Invention]

[0007] According to one aspect of the embodiment, analysis can be performed to appropriately understand changes in user needs. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a prompt according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of a crystallization result according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a configuration of a terminal device according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of the configuration of an information processing device according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating an example of a search behavior storage unit according to the embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 9]FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, a mode for carrying out the present invention (hereinafter referred to as an embodiment) will be described with reference to the drawings. Note that the present invention is not limited to the embodiment described below. Furthermore, in the description of the drawings, the same parts are given the same reference numerals.

[0010] (Embodiment) [1. Information Processing System Configuration] An information processing system 1 shown in Fig. 1 will be described. As shown in Fig. 1, the information processing system 1 includes a terminal device 10 and an information processing device 100. The terminal device 10 and the information processing device 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication. Fig. 1 is a diagram showing an example of the configuration of the information processing system 1 according to an embodiment.

[0011] The terminal device 10 is an information processing device used by an administrator who performs, for example, customer journey analysis of users for marketing purposes. The administrator appropriately understands changes in user needs by performing, for example, customer journey analysis. The terminal device 10 may be any device that can implement the processes in the embodiment. The terminal device 10 may also be a device such as a smartphone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. FIG. 2 shows a case where the terminal device 10 is a smartphone.

[0012] The terminal device 10 is, for example, a smart device such as a smartphone or tablet, and is a mobile terminal device that can communicate with any server device via a wireless communication network such as 4G to 5G (Generations) or LTE (Long Term Evolution). The terminal device 10 also has a screen such as a liquid crystal display with a touch panel function, and may accept various operations on displayed data such as content, such as tapping, sliding, and scrolling, performed by an administrator using a finger or a stylus. In FIG. 2, the terminal device 10 is used by an administrator P1.

[0013] The information processing device 100 is an information processing device 100 intended to perform analysis to appropriately grasp changes in user needs, and may be any device capable of implementing the processes described in the embodiments. For example, the information processing device 100 inputs information about search queries and instruction sentences instructing a model trained to output a string following an input string, the information processing device 100 classifying the search queries and generating explanation content for each cluster based on the search queries classified into the clusters, and visualizes the classification results on a graph. In this case, the information processing device 100 determines, for example, the date and time of a predetermined action (e.g., input of a reference query or input of a reference action) that serves as the starting point of the time series, identifies time series information indicating the time series of searches in which previous and next search queries were found, and relevance information indicating the relevance for each search query, and inputs the instruction sentence, instructing the model trained to perform clustering taking into account the time series indicated by the time series information and the relevance indicated by the relevance information, to output a string following the input string, thereby visualizing the results. In this way, the information processing device 100, for example, determines a predetermined behavior and uses the time series of previous and subsequent search queries to crystallize the search query. The information processing device 100 is an information processing device that provides services such as behavioral analysis for customer journey analysis. In the following embodiment, when a predetermined behavior is designated, the information processing device 100 performs processing using the designated predetermined behavior as a reference behavior. At this time, the predetermined behavior may be designated in any manner, and may be designated by an administrator or the like. Furthermore, the predetermined behavior may be determined in advance by an administrator or the like of the information processing device 100, or may be automatically set by the information processing device 100 based on predetermined rules. In FIG. 2, a case where the predetermined behavior is designated by an administrator P1 will be described as an example.

[0014] Although FIG. 1 shows a case where the terminal device 10 and the information processing device 100 are separate devices, the terminal device 10 and the information processing device 100 may be integrated.

[0015] [2. An example of information processing] FIG. 2 is a diagram illustrating an example of information processing by the information processing system 1 according to the first embodiment. For example, when an administrator P1 specifies a predetermined behavior, the information processing device 100 accepts the specification of the predetermined behavior (step S101). For example, the information processing device 100 accepts specification of a search query, a hotel reservation date, and the like as the predetermined behavior. When the specified predetermined behavior is set as a reference behavior, the information processing device 100 identifies search queries used in other searches by multiple users who performed the reference behavior (step S102). For example, if the reference behavior is the "hotel reservation date," the information processing device 100 identifies other search queries of multiple users who performed the reference behavior for "hotel reservation." For example, if user U1 searches for "stock" and "ski wear" before and after the reference behavior for "hotel reservation," and user U2 searches for "rich code" and "long boat" before and after the reference behavior for "hotel reservation," the information processing device 100 identifies search queries such as "stock," "ski wear," "rich code," and "long boat." In step S102, the information processing device 100 may identify search queries by narrowing down the search queries to a plurality of users who have performed searches that satisfy predetermined conditions regarding the reference behavior. For example, the information processing device 100 may identify search queries by narrowing down the search queries to a plurality of users who have input the reference behavior within a predetermined period of time, or may identify search queries by narrowing down the search queries to a plurality of users who have input the reference behavior a predetermined number of times or more. Furthermore, the information processing device 100 may identify search queries that satisfy predetermined conditions from the search queries identified in step S101, and perform the processing described below.

[0016] Furthermore, the information processing device 100 identifies time series information indicating a time series from the search date and time when the search query was searched, with the date and time (which may be the search date and time) when the predetermined behavior was performed set as the reference date and time (t=0) (step S103). At this time, the information processing device 100 identifies the search date and time of the search query relative to the reference date and time. For example, if a search for "ski wear" was performed the day before the "accommodation reservation" was entered, the information processing device 100 identifies the relative search date and time with t=0 as the reference, such as "ski wear; t=-1". In this way, the information processing device 100 identifies the search dates and times of all the search queries identified in step S102. Furthermore, the information processing device 100 may narrow down the search queries to those for which the time difference between the date and time when the predetermined behavior was performed and the search date and time of the search query satisfies a predetermined condition, and perform the process described below.

[0017] Furthermore, in step S103, the information processing device 100 identifies time-series information and identifies relevance information indicating the relevance for each search query identified in step S102 (step S103). For example, the information processing device 100 identifies search queries that are closely related to each search query for the same behavioral purpose, as a relevance to the same behavioral purpose or seasonal purpose. Specifically, if "skiing" is the behavioral purpose, the information processing device 100 identifies "ski wear" and "pockets" as being related to that behavioral purpose (for example, equipment for skiing). Furthermore, the information processing device 100 may narrow down the search queries to those for which the relevance between the behavior of performing a predetermined behavior and the search for the search query satisfies a predetermined condition, and perform the processing described below.

[0018] Then, in step S103, the information processing device 100 inputs information about the search queries identified by the identification unit and instruction sentences that instruct the device to cluster the search queries into multiple clusters taking into account the relevance of each search query and to output explanation content that explains each cluster based on the search queries classified into each cluster, into a model that has been trained to output a character string following the input character string, thereby generating classification of the search queries and explanation content for each cluster (step S104). For example, the information processing device 100 may use a generation AI such as a GPT (Generative Pre-trained Transformer) model as the model. Note that time-series information may be taken into account in the instruction sentences.

[0019] Furthermore, when generating an instruction sentence that takes time-series information into consideration, the information processing device 100 inputs, into the model, an instruction sentence indicating that clustering will be performed taking into consideration the time series indicated by the time-series information and the relevance indicated by the relevance information. Furthermore, the information processing device 100 inputs, into the model, an instruction sentence indicating that explanatory content describing each cluster will be output based on the search queries classified into each cluster. For example, the information processing device 100 generates a search query classification that takes into consideration the time series and the relevance by taking into consideration the time-series information and the relevance information. Furthermore, the information processing device 100 generates explanatory content based on the search query classification. For example, the information processing device 100 generates a search query classification and explanatory content for the purpose of displaying, in a time-series graph, the timing of searches for search queries categorized into "skiing equipment," "marine sports," etc., before and after the reference behavior "hotel reservation." Note that it is also possible to generate a search query classification without generating explanatory content.

[0020] Furthermore, the information processing device 100 inputs, into the model, an instruction sentence that instructs the model to perform clustering that takes into consideration the relevance of each search query indicated by the relevance information to create clusters that include search queries that belong to the same purpose of action. For example, when "skiing" is set as the purpose of action, the information processing device 100 generates a classification of search queries by regarding "ski wear" and "poles" that are related to the purpose of action (for example, equipment for skiing) as being related to the purpose of action.

[0021] In addition, an instruction sentence is input to the model to indicate that clustering should be performed taking into account the relevance indicated by the relevance information, and that clustering should be performed taking into account the relevance of each cluster classified into each cluster. For example, if the clusters are "ski equipment," "snowboard equipment," "marine sports," and "surfing equipment," the information processing device 100 generates a classification of search queries so that "ski equipment" and "snowboard equipment" are related to winter sports and are positioned close to each other when displayed on a graph, taking this into consideration. In addition, "marine sports" and "surfing equipment" are related to summer sports and are positioned close to each other when displayed on a graph, taking this into consideration.

[0022] 3 is a diagram showing an example of a prompt according to the embodiment. The information processing device 100 inputs, as prompts, an instruction such as "Below is time-series data on characteristic search keywords on the Internet, starting from the search behavior of <"base keyword">. Please express the content that can be read from this data in accordance with the format taking into account the steps and elements below," along with an "element" that specifies the element, an "output format" that specifies the format of the output result, an "input data format" that specifies the format of the input information, and "input data" that specifies the input information, into the trained model. The trained model outputs clusters that have been clustered based on this information.

[0023] The instruction sentence is input to the model to perform clustering taking into consideration the time series indicated by the time-series information for the period specified by the user and the specified predetermined period, and the relevance indicated by the relevance information, and to output an alert or correct at least one of the following when explanatory content within the user-specified period differs from explanatory content within the specified predetermined period. For example, if the user-specified period is October, the information processing device 100 may set the specified predetermined period to a longer period, such as 14 months. In this case, when explanatory content generated from the specified predetermined period (14 months) within the user-specified period (October) differs from explanatory content generated from the user-specified period (October), the information processing device 100 outputs an alert or corrects at least one of the following:

[0024] Then, the information processing device 100 provides information for displaying the multiple clusters clustered by the model and explanatory content. For example, the information processing device 100 transmits explanatory content of the multiple clusters to the terminal device 10 (step S105). Upon receiving the information transmitted from the information processing device 100, the terminal device 10 displays the clustering result and the explanatory content based on the received information. Furthermore, the information processing device 100 transmits information for superimposing and displaying the explanatory content on the clustering result. For example, the information processing device 100 transmits information for associating each explanatory content generated for each cluster with the cluster and superimposing and displaying it. In the terminal device 10, the explanatory content is displayed superimposed on the clustering result. FIG. 4 is a diagram illustrating an example of a clustering result according to an embodiment. A case where the results are classified into six clusters will be described using FIG. 4. In FIG. 4, the horizontal axis represents a time series. Furthermore, the time series on the horizontal axis reflects the search date and time of the search query relative to a reference date and time. Furthermore, information processing device 100 generates explanatory content for "ski equipment," "ski wear," "wetsuit," "surf shorts," "surfboard," and "marine sports (other)," and therefore "ski equipment" is displayed as explanatory content, "ski wear" is displayed as explanatory content, "wetsuit" is displayed as explanatory content, "surf shorts" is displayed as explanatory content, "surfboard" is displayed as explanatory content, and "marine sports (other)" is displayed as explanatory content. Note that the clustering result shown in Figure 4 is an example, and the number of areas classified into clusters may not be particularly limited.

[0025] In this way, the information processing device 100 clusters search queries into multiple clusters in consideration of the relevance and time series of each search query, and inputs instruction sentences instructing the model to output explanatory content that explains each cluster based on the search queries classified into each cluster into a trained model that outputs a character string following the input character string, thereby visualizing the classification of the search queries and the explanatory content of each cluster on a generated graph. Visualizing search queries in time series is thought to be useful for examining customer journey analysis, etc.

[0026] [3. Configuration of terminal device] Next, the configuration of the terminal device 10 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of the configuration of the terminal device 10 according to the embodiment. As shown in Fig. 5, the terminal device 10 has a communication unit 11, an input unit 12, an output unit 13, and a control unit 14.

[0027] (Communications Department 11) The communication unit 11 is realized by, for example, a network interface card (NIC), etc. The communication unit 11 is connected to a predetermined network N by wire or wirelessly, and transmits and receives information to and from the information processing device 100, etc., via the predetermined network N.

[0028] (Input section 12) The input unit 12 accepts various operations from the administrator. In FIG. 2, the input unit 12 accepts various operations from the administrator P1. For example, the input unit 12 may accept various operations from the administrator via a display screen using a touch panel function. The input unit 12 may also accept various operations from buttons provided on the terminal device 10 or a keyboard or mouse connected to the terminal device 10. For example, the input unit 12 accepts an operation for specifying a predetermined action.

[0029] (Output section 13) The output unit 13 is a display screen of a tablet terminal or the like realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays information transmitted from the information processing device 100. For example, the output unit 13 displays a plurality of clusters clustered by the model and explanatory content transmitted from the information processing device 100.

[0030] (Control unit 14) The control unit 14 is, for example, a controller, and is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like executing various programs stored in a storage device inside the terminal device 10 using a RAM (Random Access Memory) as a work area. For example, these various programs include application programs installed in the terminal device 10. For example, these various programs include application programs that display information (such as phase classification results and explanatory content) transmitted from the information processing device 100. The control unit 14 is also realized by an integrated circuit, such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0031] As shown in FIG. 5, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and realizes or executes the information processing operations described below.

[0032] (Receiving unit 141) The receiving unit 141 receives, for example, information transmitted from the information processing device 100. For example, the receiving unit 141 receives information transmitted from the information processing device 100 for displaying the classification result of the search query output by the model and explanatory content. For example, the receiving unit 141 receives information for displaying the classification result of the search query together with the explanatory content. For example, the receiving unit 141 receives information for displaying the explanatory content superimposed on the classification result of the search query.

[0033] (Transmitter 142) The transmission unit 142 transmits, for example, operation information performed by the administrator. For example, the transmission unit 142 transmits information about a predetermined action designated by the administrator to determine the predetermined action (information indicating a predetermined query, a reservation date for accommodation, etc.).

[0034] 4. Configuration of Information Processing Device Next, the configuration of the information processing device 100 according to the embodiment will be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Fig. 6, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing device 100 may also have an input unit (e.g., a keyboard or a mouse) that accepts various operations from an administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display) that displays various information.

[0035] (Communication unit 110) The communication unit 110 is realized by, for example, a NIC etc. The communication unit 110 is connected to a network N by wire or wirelessly, and transmits and receives information to and from the terminal device 10 etc. via the network N.

[0036] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG.

[0037] The search behavior information storage unit 121 stores information about the search behavior of a user. FIG. 7 shows an example of the search behavior information storage unit 121 according to the embodiment. The information stored in the search behavior information storage unit 121 is used, for example, to generate search query classification results and explanation content. As shown in FIG. 7, the search behavior information storage unit 121 has items such as "search behavior ID" and "search behavior information."

[0038] "Search behavior ID" indicates identification information for identifying search behavior. "Search behavior information" indicates search behavior information. In the example shown in FIG. 7, conceptual information such as "Search behavior information #1" and "Search behavior information #2" is stored in "Search behavior information," but in reality, information indicating which user searched for what search query and when is stored.

[0039] (control unit 130) The control unit 130 is a controller, and is realized by, for example, a CPU or an MPU executing various programs stored in a storage device inside the information processing device 100 using RAM as a work area. The control unit 130 is also realized by, for example, an integrated circuit such as an ASIC or an FPGA.

[0040] 6, the control unit 130 has an acquisition unit 131, an identification unit 132, a processing unit 133, and a provision unit 134, and realizes or executes the information processing action described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 6, and may be any other configuration as long as it performs the information processing described below.

[0041] (Acquisition part 131) The acquiring unit 131 acquires various pieces of information from the storage unit 120. The acquiring unit 131 also stores the acquired various pieces of information in the storage unit 120.

[0042] The acquisition unit 131 acquires various pieces of information from an external information processing device 100. The acquisition unit 131 acquires various pieces of information from other information processing devices 100 such as the terminal device 10.

[0043] The acquisition unit 131 acquires, for example, operation information performed by the administrator. For example, the acquisition unit 131 acquires information about a predetermined behavior designated by the administrator to determine a reference behavior (such as information indicating a predetermined query).

[0044] (Specific Section 132) The identification unit 132 identifies search queries of multiple users who perform a predetermined behavior. For example, the identification unit 132 identifies a search query, a reservation date for accommodation, etc. as the predetermined behavior. For example, the identification unit 132 identifies search queries of multiple users who performed the predetermined behavior based on the information acquired by the acquisition unit 131. In other words, the identification unit 132 identifies other search queries entered for search by multiple users who entered to perform the predetermined behavior based on the predetermined behavior, for example.

[0045] The identification unit 132 identifies time series information indicating the time series of searches in which search queries were searched and relevance information indicating the relevance for each search query, using the date and time when a predetermined behavior was performed as a reference date and time. For example, the identification unit 132 identifies the search date and time when a search query was searched, using the date and time when a predetermined behavior was performed as a reference date and time, based on the information acquired by the acquisition unit 131. For example, the identification unit 132 identifies the search date and time of the search query relative to the reference date and time. For example, the identification unit 132 identifies the time series information from the search date and time of the search query relative to the identified reference date and time. Note that the identification unit 132 may identify only the relevance information without identifying the time series information.

[0046] (Processing unit 133) The processing unit 133 inputs information about the search queries identified by the identification unit 132 and instruction sentences that instruct the model to cluster the search queries into multiple clusters taking into account the relevance of each search query and to output explanatory content describing each cluster based on the search queries classified into each cluster, into a model trained to output a string following the input string, thereby generating classification of the search queries and explanatory content for each cluster. For example, the processing unit 133 inputs instruction sentences that take into account the relevance of each search query into the model, thereby generating one cluster for a search query related to skiing equipment, such as "skis" and "pole," and generating an explanation of the skiing equipment as explanatory content describing the cluster. For example, the processing unit 133 may use a generative AI such as a GPT (Generative Pre-trained Transformer) model as the model.

[0047] Furthermore, the processing unit 133 inputs, as an instruction sentence, a sentence to the model to perform clustering taking into consideration the time series indicated by the time series information and the relevance indicated by the relevance information. For example, by inputting, into the model, an instruction sentence taking into consideration the relevance for each search query and the time series information, the processing unit 133 generates a classification of search queries including the time series of each cluster with respect to a reference date and time when a predetermined action was performed, in addition to the clustering taking into consideration the relevance.

[0048] The processing unit 133 inputs, as an instruction sentence, an instruction sentence to perform clustering that takes into consideration the relevance of each search query indicated by the relevance information to form clusters that include search queries that belong to the same behavioral purpose. For example, by inputting an instruction sentence that takes into consideration the relevance of each search query (e.g., "pockets," "skis," "surfboards," etc.) into the model, the processing unit 133 performs clustering that takes into consideration that "pockets" and "skis," which have the same behavioral purpose of skiing, are included in the same cluster, and a classification of the search queries is generated.

[0049] The processing unit 133 inputs an instruction sentence to the model indicating that clustering should be performed taking into account the relevance indicated by the relevance information and that clustering should be performed taking into account the relevance of each cluster classified into each cluster. For example, if the clusters are "ski equipment," "snowboard equipment," "marine sports," and "surfing equipment," the processing unit 133 generates a classification of search queries such that "ski equipment" and "snowboard equipment" are related to winter sports and are positioned close to each other when displayed on a graph, taking this into consideration. Also, for example, "marine sports" and "surfing equipment" are related to summer sports and are positioned close to each other when displayed on a graph, taking this into consideration.

[0050] The processing unit 133 further inputs, as an instruction sentence, an instruction sentence to output explanatory content describing each cluster based on the search queries classified into each cluster. The processing unit 133 clusters the clusters taking into account the relevance information and the time series information, and generates explanatory content describing each cluster based on the search queries classified into each cluster. For example, the processing unit 133 generates explanatory content that takes into account both the relevance information and the time series information by taking into account the time series indicated by the time series information in addition to the relevance indicated by the relevance information. Furthermore, the processing unit 133 generates explanatory content describing each cluster based on the search queries classified into each cluster within a user-specified range by taking into account the time series information.

[0051] The processing unit 133 performs clustering taking into consideration the time series indicated by the time series information for the period specified by the user and the predetermined period identified by the identification unit 132, and the relevance indicated by the relevance information, and inputs an instruction sentence to the model indicating that, if explanatory content within the period specified by the user differs from explanatory content within the predetermined period identified by the identification unit 132 within the period specified by the user, at least one of outputting an alert or correcting the explanatory content is to be performed. For example, if the period specified by the user is eight months, the processing unit 133 outputs an alert indicating that the explanatory content is different when explanatory content generated based on a search query eight months before and after a reference date and time when a predetermined action was performed differs from explanatory content eight months before and after the reference date and time when a predetermined action was performed and explanatory content generated based on a search query identified for a period longer than the period specified by the user (e.g., 10 months). Furthermore, if the explanatory content is different, the processing unit 133 corrects the explanatory content to generate explanatory content generated based on a search query identified for a period longer than the period specified by the user. Note that, simultaneously with the correction, an alert indicating that the explanatory content is different or an alert indicating that the correction has been made may be output.

[0052] (Provider 134) The providing unit 134 provides information for displaying a plurality of clusters generated by the model and explanatory content. For example, the providing unit 134 provides the plurality of clusters generated by the processing unit 133 and explanatory content to an administrator who has designated a predetermined action.

[0053] Furthermore, the providing unit 134 provides information for superimposing and displaying the explanatory content on the clustering result. For example, the providing unit 134 provides information for superimposing and displaying each of the explanatory contents generated for each cluster in association with the cluster. For example, in the terminal device 10, the explanatory content is superimposed and displayed on the clustering result.

[0054] [5. Information Processing Flow] Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to Fig. 8. Fig. 8 is a flowchart showing the procedure of information processing by the information processing system 1 according to the embodiment.

[0055] As shown in FIG. 8, the information processing device 100 identifies search queries of a plurality of users who perform a predetermined behavior (step S201).

[0056] The information processing device 100 identifies time-series information and relevance information of the search query based on information related to the identified search query (step S202).

[0057] The information processing device 100 performs clustering into clusters taking into consideration the time series indicated by the identified time series information and the relevance indicated by the relevance information, and inputs an instruction sentence to the model instructing it to output explanatory content that explains each cluster (step S203).

[0058] Furthermore, the information processing device 100 generates clusters and explanatory content by inputting the instruction document into a model (step S204).

[0059] The information processing device 100 provides information for displaying the classification results of the search query and the explanation content (step S205).

[0060] [6. Effects] As described above, the information processing device 100 according to the embodiment includes an identification unit 132 that identifies search queries of multiple users who perform a predetermined behavior, a processing unit 133 that classifies the search queries and generates explanatory content for each cluster by inputting information about the search queries identified by the identification unit 132 and instruction sentences that instruct the model to cluster the search queries into multiple clusters taking into account the relevance of each search query and to output explanatory content that explains each cluster based on the search queries classified into each cluster into a model that has been trained to output a string following the input string, and a provision unit 134 that provides information for displaying the multiple clusters clustered by the model and the explanatory content.

[0061] As a result, the information processing device 100 according to the embodiment can, for example, display explanation content together with the classification results of search queries, thereby appropriately visualizing the classification results of search queries. Furthermore, the information processing device 100 according to the embodiment can, for example, classify search queries in consideration of the relevance of each search query, thereby making it possible to perform analysis to appropriately understand changes in user needs.

[0062] Furthermore, the identification unit 132 identifies time series information indicating the time series of searches in which search queries were searched and relevance information indicating the relevance for each search query, using the date and time when a specified action was performed as the reference date and time, and the processing unit 133 inputs into the model an instruction sentence indicating that clustering will be performed taking into account the time series indicated by the time series information and the relevance indicated by the relevance information.

[0063] As a result, the information processing device 100 according to the embodiment can perform analysis to appropriately grasp changes in user needs, for example, by generating a plurality of clusters and explanatory content in chronological order.

[0064] The identification unit 132 identifies relevance information indicating the relevance for each search query, and the processing unit 133 inputs an instruction sentence into the model to perform clustering that takes into consideration the relevance for each search query indicated by the relevance information, so as to create clusters that include search queries that belong to the same behavioral purpose.

[0065] As a result, the information processing device 100 according to the embodiment can perform analysis to appropriately grasp changes in user needs, for example, by classifying search queries into clusters that include the same behavioral purpose and visualizing them on a graph.

[0066] In addition, the identification unit 132 identifies relevance information indicating the relevance for each search query, and the processing unit 133 inputs, as an instruction sentence, an instruction sentence to perform clustering taking into account the relevance indicated by the relevance information and to perform clustering taking into account the relevance of each cluster classified into each cluster into the model.

[0067] As a result, the information processing device 100 according to the embodiment performs clustering that takes into account the relevance of each cluster, so that when displayed on a graph, related clusters are displayed together, allowing for analysis to appropriately grasp changes in user needs.

[0068] The processing unit 133 further inputs, as an instruction sentence, an instruction sentence to the model to output explanation content that explains each cluster based on the search queries classified into each cluster.

[0069] As a result, the information processing apparatus 100 according to the embodiment can display explanation content for each cluster, for example, and therefore can perform analysis to appropriately understand changes in user needs.

[0070] In addition, as an instruction sentence, clustering is performed taking into consideration the time series indicated by the time series information for the period specified by the user and the specified period identified by the identification unit 132, and the relevance indicated by the relevance information, and an instruction sentence is input to the model to the effect that if the explanatory content for the period specified by the user differs from the explanatory content for the specified period identified by the identification unit 132 within the period specified by the user, at least one of outputting an alert or making a correction is to be performed.

[0071] As a result, the information processing device 100 according to the embodiment outputs or corrects an alert when, for example, the explanatory content differs between a period specified by the user and a predetermined period identified by the identification unit 132, so that even if the user cannot specify an appropriate period, analysis can be performed to appropriately grasp changes in the user's needs.

[0072] [7. Hardware Configuration] The information processing device 100 according to the embodiment described above is realized, for example, by a computer 1000 configured as shown in Fig. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0073] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0074] The HDD 1400 stores programs executed by the CPU 1100, data used by these programs, etc. The communication interface 1500 acquires data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0075] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0076] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0077] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0078] [8. Other] Furthermore, among 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. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0079] 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.

[0080] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0081] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, 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 undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0082] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0083] 1. Information Processing Systems 10 Terminal Equipment 11 Communications Department 12 Input section 13 Output section 14 Control Unit 100 Information processing device 110 Communications Department 120 Storage section 121 Search behavior information storage unit 130 Control Unit 131 Acquisition Department 132 Specific part 133 Processing section 134 Provision Department 141 Receiving unit 142 Transmitter N Network

Claims

1. an identification unit that identifies search queries of a plurality of users who perform a predetermined behavior; a processing unit that categorizes the search queries and generates explanatory content for each cluster by inputting information about the search queries identified by the identification unit and instruction sentences that instruct the model to cluster the search queries into a plurality of clusters taking into account the relevance of each search query and to output explanatory content that explains each cluster based on the search queries classified into each cluster, into a model that has been trained to output a character string that follows an input character string; and a providing unit that provides information for displaying a plurality of clusters obtained by the model and the explanatory content; An information processing device comprising:

2. The identification unit using the date and time when the predetermined action was performed as a reference date and time, identifying time series information indicating the time series of searches in which the search queries were searched and relevance information indicating the relevance of each of the search queries; The processing unit As the instruction sentence, an instruction sentence to perform clustering taking into consideration the time series indicated by the time series information and the relevance indicated by the relevance information is input to the model.

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

3. The identification unit Identifying relevance information indicating relevance for each of the search queries; The processing unit As the instruction sentence, an instruction sentence to perform clustering taking into consideration the relevance for each search query indicated by the relevance information so as to form clusters including search queries that belong to the same behavioral purpose is input to the model.

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

4. The identification unit Identifying relevance information indicating relevance for each of the search queries; The processing unit As the instruction sentence, an instruction sentence to perform clustering taking into consideration the relevance indicated by the relevance information and to perform clustering taking into consideration the relevance of each cluster classified into each cluster is input to the model.

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

5. The processing unit As the instruction sentence, an instruction sentence to output explanatory content that explains each cluster based on the search queries classified into each cluster is further input to the model.

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

6. The identification unit using the date and time when the predetermined action was performed as a reference date and time, identifying time series information indicating the time series of searches in which the search queries were searched and relevance information indicating the relevance of each of the search queries; The processing unit The instruction sentence is input to the model to perform clustering taking into consideration the time series indicated by the time series information for the period designated by the user and the predetermined period identified by the identification unit, and the relevance indicated by the relevance information, and to output an alert or make a correction if the explanatory content for the period designated by the user differs from the explanatory content for the predetermined period identified by the identification unit within the period designated by the user.

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

7. 1. A computer-implemented information processing method, comprising: an identifying step of identifying search queries of a plurality of users who have input a predetermined behavior; a processing method for classifying the search queries and generating explanatory content for each cluster by inputting information about the search queries identified in the identification step and instruction sentences that instruct the model to cluster the search queries into a plurality of clusters taking into account the relevance of each search query and to output explanatory content that explains each cluster based on the search queries classified into each cluster, into a model that has been trained to output a character string that follows an input character string; a provision method for providing information for displaying a plurality of clusters obtained by the model and the explanatory content; An information processing method comprising:

8. identifying search queries of a plurality of users who have input a predetermined behavior; a processing step of classifying the search queries and generating explanatory content for each cluster by inputting information about the search queries identified in the identification step and instruction sentences that instruct the model to cluster the search queries into a plurality of clusters taking into account the relevance of each search query and to output explanatory content that explains each cluster based on the search queries classified into each cluster, into a model that has been trained to output a character string that follows an input character string; a providing step of providing information for displaying the plurality of clusters clustered by the model and the explanatory content; An information processing program characterized by causing a computer to execute the above.

Images