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

Abstract

To further appropriately analyze a relation between a user and a target shown by a prescribed query.SOLUTION: An information processing device according to the present application includes a specification unit, a processing unit and a provision unit. The specification unit specifies retrieval queries of a plurality of users having used a prescribed query for retrieval. The processing unit allows a generative AI to classify the retrieval queries into a plurality of phases by inputting the information regarding the retrieval queries specified by specification unit to the generative AI, and to generate explanation content explaining the phase for each of the phases. The provision unit provides information for displaying information expressing the plurality of phases classified by the generative AI together with the explanation content generated by the generative AI.SELECTED DRAWING: Figure 6

Description

Technical Field

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

Background Art

[0002] With the spread of the Internet, various information analysis techniques have been proposed. For example, various query log analysis techniques have been proposed. The query log analysis technique can be applied to, for example, search-linked advertisements. Also, the query log analysis technique can be used for, for example, funnel analysis for marketing and consideration of the timing of appeals such as advertisements.

[0003] Conventionally, a technique for analyzing the relationship between a user and an object indicated by a predetermined query is known. As an example, a technique for analyzing the relationship between a user and an object indicated by a reference query by identifying search queries input by a plurality of users who have input the reference query and determining the appropriateness of the search queries is known.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the conventional technology, for example, there has been room for further improvement in appropriately analyzing the relationship between a user and an object indicated by a predetermined query.

[0006] The present application has been made in view of the above, and an object thereof is to more appropriately analyze the relationship between a user and an object indicated by a predetermined query.

Means for Solving the Problems

[0007] The information processing apparatus according to the present application includes a specifying unit that specifies search queries of a plurality of users used for searching with a predetermined query, and inputs information related to the search query specified by the specifying unit to a generation AI, so as to classify the search query into a plurality of phases for the generation AI, and a processing unit that generates explanatory content explaining the phases for each phase, and a providing unit that provides information for displaying information indicating the plurality of phases classified by the generation AI together with the explanatory content generated by the generation AI.

Effect of the Invention

[0008] According to one aspect of the embodiment, there is an effect that the relationship between the user and the object indicated by the predetermined query can be more appropriately analyzed.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0010] Hereinafter, embodiments for implementing the information processing apparatus, information processing method, and 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 apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Also, in the following embodiments, the same parts are denoted by the same reference numerals, and duplicate explanations are omitted.

[0011] (Embodiment) [1. Configuration of Information Processing System] The 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 communicably connected by wire or wirelessly via a predetermined communication network (network N). FIG. 1 is a diagram showing a configuration example of the information processing system 1 according to the embodiment.

[0012] The terminal device 10 is an information processing device used by an administrator who performs user behavior analysis and the like for marketing. The administrator performs user trend analysis, for example, by performing user intention analysis in addition to user behavior analysis. The terminal device 10 may be any device as long as it can realize the processing in the embodiment. Also, the terminal device 10 may 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 the case where the terminal device 10 is a smartphone.

[0013] The terminal device 10 is a smart device such as a smartphone or a tablet, and is a portable terminal device that can communicate with any server device via a wireless communication network such as 4G to 5G (Generation) or LTE (Long Term Evolution). Further, the terminal device 10 has a screen such as a liquid crystal display, and has a screen having a touch panel function, and may receive various operations on display data such as content, such as tap operations, slide operations, and scroll operations, by a finger or a stylus from a manager. In FIG. 2, the terminal device 10 is used by the manager P1.

[0014] The information processing device 100 is an information processing device aimed at more appropriately analyzing the relationship between the user and the object indicated by a predetermined query, and may be any device as long as it can realize the processing in the embodiment. The information processing device 100, for example, phase-classifies search queries arranged in time series using a generation AI and visualizes the classification results on a scatter diagram. At this time, the information processing device 100, for example, determines a query (reference query) that becomes the starting point of the time series, and visualizes the output result output by inputting information regarding the time difference between the search queries searched before and after the reference query and the reference query to the generation AI. In this way, the information processing device 100 performs phase classification of search queries by, for example, determining a reference query and using the time difference from the surrounding search queries. The information processing device 100 is an information processing device that provides services such as user behavior analysis for marketing. In the following embodiment, when a query is specified, the information processing device 100 performs processing using the specified query as a reference query. At this time, the query may be specified in any manner, for example, by a manager or the like. Further, it may be predetermined by a manager or the like of the information processing device 100, or may be automatically set by the information processing device 100 based on a predetermined rule. In FIG. 2, the case where the query is specified by the manager P1 is taken as an example for explanation.

[0015] Note that in FIG. 1, the case where the terminal device 10 and the information processing device 100 are separate devices is shown, but the terminal device 10 and the information processing device 100 may be integrated.

[0016] FIG. 2 is a diagram showing an example of information processing of the information processing system 1 according to Embodiment 1. When the administrator P1 designates a query (corresponding to a predetermined query), the information processing device 100 receives the designation of the query (step S101). The information processing device 100 uses the designated query as a reference query and identifies search queries used by a plurality of users who performed a search using the reference query (step S102). For example, when "powdered milk" is the reference query, the information processing device 100 identifies other search queries of a plurality of users who performed a search using the keyword "powdered milk" as a search query. For example, if user U1 has performed searches such as "childcare" or "baby" before and after the search for "powdered milk", and user U2 has performed searches such as "breast milk" or "cow's milk" before and after the search for "powdered milk", the information processing device 100 identifies search queries such as "childcare", "baby", "breast milk", and "cow's milk". Note that the information processing device 100 may narrow down and identify search queries for a plurality of users who performed a search that satisfies a predetermined condition with respect to the reference query in step S102. For example, the information processing device 100 may narrow down and identify search queries for a plurality of users who performed a search for the reference query within a predetermined period, or may narrow down and identify search queries for a plurality of users who performed a search for the reference query a predetermined number of times or more. Further, the information processing device 100 may identify search queries that satisfy a predetermined condition among the search queries identified in step S102 and perform the following processing. For example, the information processing device 100 may identify search queries searched by two or more users among a plurality of users who performed a search using the reference query and perform the following processing.

[0017] ​Also, the information processing device 100 specifies the search date and time when the search query was searched, with the search date and time of the reference query (which may be the input date and time) as the reference date and time (t = 0) (step S103). At this time, the information processing device 100 specifies the relative search date and time of the search query with respect to the reference date and time. For example, when the information processing device 100 conducted a search for "child-rearing" the day before the search for "powdered milk", it specifies a relative search date and time based on t = 0, such as "child-rearing; t = -1". In this way, the information processing device 100 specifies the search date and time of all the search queries specified in step S102. Also, the information processing device 100 may narrow down the search queries whose time difference between the search date and time of the reference query and the search date and time of the search query satisfies a predetermined condition and perform the subsequent processing.

[0018] Also, by specifying the search query and the search date and time in this way, the information processing device 100 generates time series information indicating the time series of the search queries (step S104). Then, the information processing device 100 uses a generative AI such as a GPT (Generative Pre-trained Transformer) model to classify the time series information of the search queries into phases (step S105). Note that classifying the time series information of the search queries into phases may be read as classifying the search queries arranged in time series into phases.

[0019] Here, the generative AI according to the embodiment will be described. When the information processing apparatus 100 inputs the time-series information generated in step S104 into the generative AI, the generative AI executes phase classification using the time-series information generated in step S104 as input information and outputs a phase classification result. That is, the information processing apparatus 100 classifies the time-series information into phases by causing the generative AI to execute phase classification. Further, the information processing apparatus 100 inputs a prompt as input information into the generative AI together with the time-series information generated in step S104. For example, the information processing apparatus 100 inputs, as input information into the generative AI, a prompt that instructs to classify the time-series information into a plurality of phases. The generative AI outputs a phase classification result obtained by classifying the time-series information according to the prompt. FIG. 3 is a diagram showing an example of a prompt according to the embodiment. The information processing apparatus 100 inputs, as a prompt into the generative AI, an instruction sentence such as "There is time-series data of characteristic search keywords on the Internet starting from the search behavior of <"base keyword"> below. Please express it in accordance with the format based on the content readable from this data and the following steps and elements.", the "elements" specifying the elements, the "output format" specifying the format of the output result, the "input data format" specifying the format of the input information, and the "input data" specifying the input information. The generative AI outputs a phase classification result based on these pieces of information.

[0020] In addition, the generative AI outputs explanatory content that explains each phase for each phase classified based on the phase classification result. When time-series information and a prompt are input, the generative AI outputs the explanatory content together with the phase classification result of the phase classification. That is, in step S105, the information processing device 100 phase-classifies the time-series information of the search query and generates explanatory content. In other words, in step S105, the information processing device 100 causes the generative AI to perform phase classification and generate explanatory content. The information processing device 100 inputs a prompt including an instruction sentence that instructs the generative AI to generate explanatory content that reflects information about the search query (for example, the target indicated by the search query) included in each phase indicated by the phase classification result for each phase, thereby causing the generative AI to perform phase classification and generate explanatory content.

[0021] Then, the information processing apparatus 100 transmits information for displaying the phase classification result and the explanatory content to the terminal device 10 (step S106). When the terminal device 10 receives the information transmitted from the information processing apparatus 100, it displays the phase classification result and the explanatory content based on the received information. Further, the information processing apparatus 100 transmits information for superimposing and displaying the explanatory content on the phase classification result. For example, the information processing apparatus 100 transmits information for superimposing and displaying each explanatory content generated for each phase in association with the phase. In the terminal device 10, the explanatory content is superimposed and displayed on the phase classification result. FIG. 4 is a diagram showing an example of the phase classification result according to the embodiment. Using FIG. 4, the case where it is classified into six phases (E1 to E6) will be described as an example. In FIG. 4, the vertical axis represents the score, and the horizontal axis represents the time series. The score on the vertical axis reflects the number of searches for search queries by a plurality of users. Also, the search date and time of the search query with respect to the reference date and time are reflected in the time series on the horizontal axis. Further, since the information processing apparatus 100 generates explanatory content of "information collection for pregnancy confirmation and initial response" for phase E1, generates explanatory content of "health management and doubt resolution in the second trimester of pregnancy" for phase E2, generates explanatory content of "preparation for childbirth and interest in naming" for phase E3, generates explanatory content of "preparation near childbirth and interest in commemorative photography" for phase E4, generates explanatory content of "preparation for childcare after childbirth and care of the newborn" for phase E5, and generates explanatory content of "progress of childcare and collection of childcare support information" for phase E6, "information collection for pregnancy confirmation and initial response" is displayed as the explanatory content for phase E1, "health management and doubt resolution in the second trimester of pregnancy" is displayed as the explanatory content for phase E2, "preparation for childbirth and interest in naming" is displayed as the explanatory content for phase E3, "preparation near childbirth and interest in commemorative photography" is displayed as the explanatory content for phase E4, "preparation for childcare after childbirth and care of the newborn" is displayed as the explanatory content for phase E5, and "progress of childcare and collection of childcare support information" is displayed as the explanatory content for phase E6.Note that the phase classification result shown in FIG. 4 is an example, and the number of regions to be phase-classified and the like may not be particularly limited.

[0022] In this way, the information processing apparatus 100 phase-classifies search queries arranged in time series using a generation AI, and visualizes them on a scatter diagram together with the titles of the plurality of phases that have been phase-classified. By visualizing the search queries in time series, it becomes possible to analyze the user's tendencies, and thus it is considered that it can be used for funnel analysis for marketing and consideration of the timing of appeals such as advertisements.

[0023] (Variation 1 of information processing: Phase classification according to changes in user tendencies) In the above embodiment, the information processing apparatus 100 may perform phase classification and generation of explanatory content, for example, by inputting a prompt including an instruction sentence instructing that phases be classified according to changes in the actions of a plurality of users to the generation AI. For example, the information processing apparatus 100 may perform phase classification and generation of explanatory content using a prompt including an instruction sentence such as "phase classification at the timing when the user's actions change". Further, the information processing apparatus 100 may perform phase classification and generation of explanatory content, for example, by inputting a prompt including an instruction sentence instructing that phases be classified according to changes in the intentions of a plurality of users to the generation AI. For example, the information processing apparatus 100 may perform phase classification and generation of explanatory content using a prompt including an instruction sentence such as "phase classification at the timing when the user's intentions change".

[0024] (Variation 2 of information processing: Phase classification according to the relevance score of adjacent phases) In the above-described embodiment, the information processing apparatus 100 may perform phase classification and generation of explanatory content by inputting, for example, a prompt including an instruction sentence that instructs the generation AI to classify phases so that the relevance scores between adjacent phases become high. For example, the information processing apparatus 100 may perform phase classification and generation of explanatory content by inputting, to the generation AI, a prompt including an instruction sentence that instructs to classify phases so that the seasonal or continuous relevance between adjacent phases becomes deep, considering the seasonal or continuous relationship. Further, the information processing apparatus 100 may determine, for example, whether there are any phases among a plurality of phases indicated by the phase classification result in which the relevance score between adjacent phases is equal to or lower than a predetermined threshold. When there are phases in which the relevance score between adjacent phases is equal to or lower than a predetermined threshold, the information processing apparatus 100 may transmit information indicating an alert (warning) to the terminal device 10. In such a case, the information processing apparatus 100 may, for example, notify that the reference query is inappropriate, or may notify to prompt to change the reference query.

[0025] (Variation 3 of information processing: Phase classification using conversion) In the above-described embodiment, the information processing apparatus 100 determines a reference query that is the starting point of the time series, and visualizes the output result output by inputting information regarding the time difference between the search queries searched before and after the reference query and the reference query to the generation AI. However, the example of the query may not be particularly limited. For example, the information processing apparatus 100 may determine a conversion (reference conversion) that is the starting point of the time series, and visualize the output result output by inputting information regarding the time difference between the conversions before and after the reference conversion and the reference conversion to the generation AI. In this case, the information processing apparatus 100 may display the phase classification result obtained by classifying the conversions into a plurality of phases and the explanatory content that explains each phase based on such a phase classification result. Further, for example, the information processing apparatus 100 may determine a product (reference product) purchased by the user who is the starting point of the time series, and visualize the output result output by inputting information regarding the time difference between the purchased products purchased before and after the reference product and the reference product to the generation AI. In this case, the information processing apparatus 100 may display the phase classification result obtained by classifying the purchased products into a plurality of phases and the explanatory content that explains each phase based on such a phase classification result. Further, for example, the information processing apparatus 100 may determine an advertisement (reference advertisement) selected by the user who is the starting point of the time series, and visualize the output result output by inputting information regarding the time difference between the selected advertisements selected before and after the reference advertisement and the reference advertisement to the generation AI. In this case, the information processing apparatus 100 may display the phase classification result obtained by classifying the selected advertisements into a plurality of phases and the explanatory content that explains each phase based on such a phase classification result. As described above, the information processing apparatus 100 may perform the information processing according to the above-described embodiment by determining the reference action using any user behavior information. The information processing apparatus 100 is not limited to search queries, conversions, purchase actions, or selection actions, and may perform the information processing according to the above-described embodiment using any behavior information. Further, the information processing apparatus 100 may perform the information processing according to the above-described embodiment by determining the reference position using the user's position information.

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

[0027] (Communication Unit 11) The communication unit 11 is realized by, for example, a NIC (Network Interface Card) or the like. Then, the communication unit 11 is connected to a predetermined network N by wire or wirelessly, and information is transmitted and received between the communication unit 11 and an information processing device 100 or the like via the predetermined network N.

[0028] (Input Unit 12) The input unit 12 receives various operations from the administrator. In FIG. 2, various operations from the administrator P1 are received. For example, the input unit 12 may receive various operations from the administrator via the display surface by the touch panel function. Further, the input unit 12 may receive various operations from buttons provided on the terminal device 10 or from a keyboard or mouse connected to the terminal device 10. For example, the input unit 12 receives an operation for specifying a reference query. Also, for example, the input unit 12 receives an operation for specifying a reference conversion, a reference product, a reference advertisement, or the like.

[0029] (Output Unit 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 the phase classification result and the explanatory content output by the generation AI transmitted from the information processing device 100.

[0030] (Control Unit 14) The control unit 14 is, for example, a controller, and is realized by various programs stored in a storage device inside the terminal device 10 being executed with the RAM (Random Access Memory) as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. For example, these various programs include the programs of applications installed in the terminal device 10. For example, these various programs include the programs of applications for displaying information (such as phase classification results and explanatory content) transmitted from the information processing device 100. Further, the control unit 14 is 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 operations of information processing 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 for displaying the phase classification result output by the generation AI and the explanatory content transmitted from the information processing device 100. For example, the receiving unit 141 receives information for displaying the phase classification result together with the explanatory content. For example, the receiving unit 141 receives information for superimposing and displaying the explanatory content on the phase classification result.

[0033] (Transmitting Unit 142) The transmission unit 142 transmits, for example, operation information input by an administrator. For example, the transmission unit 142 transmits information regarding a query (such as information indicating a predetermined query) specified by the administrator to determine a reference query. Also, for example, the transmission unit 142 transmits information regarding a reference conversion, a reference product, a reference advertisement, etc. specified by the administrator to determine a reference conversion, a reference product, a reference advertisement, etc.

[0034] [4. Configuration of Information Processing Apparatus] Next, with reference to FIG. 6, the configuration of the information processing apparatus 100 according to the embodiment will be described. FIG. 6 is a diagram showing a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 6, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. Note that the information processing apparatus 100 may include an input unit (such as a keyboard or a mouse) for receiving various operations from an administrator of the information processing apparatus 100, and a display unit (such as a liquid crystal display) for displaying various information.

[0035] (Communication Unit 110) The communication unit 110 is realized by, for example, a NIC or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and performs information transmission and reception with the terminal device 10 or the like 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. 6, the storage unit 120 includes a search behavior information storage unit 121.

[0037] The search behavior information storage unit 121 stores information regarding the search behavior of a user. Here, 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 a phase classification result or explanatory content. As shown in FIG. 7, the search behavior information storage unit 121 has items such as a "search behavior ID" and "search behavior information".

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

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

[0040] As shown in FIG. 6, the control unit 130 includes an acquisition unit 131, a specification unit 132, a generation unit 133, a processing unit 134, and a provision unit 135, and realizes or executes the operations of information processing 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 can perform the information processing described later.

[0041] (Acquisition unit 131) The acquisition unit 131 acquires various information from the storage unit 120. Further, the acquisition unit 131 stores the acquired various information in the storage unit 120.

[0042] The acquisition unit 131 acquires various information from an external information processing apparatus. The acquisition unit 131 acquires various information from another information processing apparatus such as the terminal device 10.

[0043] The acquisition unit 131 acquires, for example, operation information performed by an administrator. For example, the acquisition unit 131 acquires information regarding a query specified by the administrator (such as information indicating a predetermined query) in order to determine a reference query.

[0044] (Specification unit 132) The specifying unit 132 specifies the search queries of a plurality of users who used the reference query for searching, based on the information acquired by the acquisition unit 131, for example. In other words, the specifying unit 132 specifies, for example, other search queries input by a plurality of users who input the reference query as a search query for searching.

[0045] The specifying unit 132 specifies, for example, the search date and time when the search query was searched, with the search date and time of the reference query as the reference date and time, based on the information acquired by the acquisition unit 131. For example, the specifying unit 132 specifies the relative search date and time of the search query with respect to the reference date and time.

[0046] (Generation unit 133) The generation unit 133 generates time-series information indicating the time series of the search query, based on the search query and the search date and time specified by the specifying unit 132, for example.

[0047] (Processing unit 134) The processing unit 134 inputs the time-series information generated by the generation unit 133 into a generative AI such as a GPT model, for example, to cause the generative AI to perform phase classification on the time-series information of the search query. In other words, the processing unit 134 causes the generative AI to perform phase classification on the search queries arranged in time series, for example. Further, the processing unit 134 causes the generative AI to perform phase classification by inputting a prompt for instructing phase classification together with the time-series information into the generative AI. For example, the processing unit 134 causes the generative AI to perform phase classification by inputting a prompt for instructing phase classification according to changes in the user's behavior and intention into the generative AI. Also, for example, the processing unit 134 causes the generative AI to perform phase classification by inputting a prompt for instructing phase classification so that the relevance score between adjacent phases becomes high into the generative AI.

[0048] The processing unit 134 causes a generative AI such as a GPT model to generate explanatory content (such as a title or summary) that explains the phase by inputting the time-series information generated by the generation unit 133 into the generative AI. Further, the processing unit 134 causes the generative AI to generate explanatory content, for example, by inputting a prompt for instructing the generation of explanatory content together with the time-series information into the generative AI. For example, the processing unit 134 causes the generative AI to execute the generation of explanatory content by inputting a prompt for instructing the generation of explanatory content that reflects information on search queries included in each phase indicated by the phase classification result into the generative AI.

[0049] (Providing unit 135) The providing unit 135 provides, for example, the phase classification result and the explanatory content generated by the processing unit 134 to the administrator who has specified the reference query. For example, the providing unit 135 provides information for displaying the phase classification result and the explanatory content generated by the processing unit 134. For example, the providing unit 135 provides information for superimposing and displaying the explanatory content on the phase classification result.

[0050] [5. Information processing flow] Next, with reference to FIG. 8, the information processing procedure by the information processing system 1 according to the embodiment will be described. FIG. 8 is a flowchart showing the information processing procedure by the information processing system 1 according to the embodiment.

[0051] As shown in FIG. 8, the information processing apparatus 100 identifies search queries of a plurality of users that used a reference query (corresponding to a predetermined query) for searching (step S201).

[0052] The information processing apparatus 100 generates time-series information of the search query based on the information regarding the identified search query (step S202).

[0053] The information processing apparatus 100 causes the generative AI to execute phase classification and generation of explanatory content by inputting the generated time-series information into the generative AI (step S203).

[0054] The information processing apparatus 100 provides information for displaying the phase classification result and the explanatory content (step S204).

[0055] [6. Effect] As described above, the information processing apparatus 100 according to the embodiment includes a specifying unit 132, a processing unit 134, and a providing unit 135. The specifying unit 132 specifies the search queries of a plurality of users who used a predetermined query for searching. The processing unit 134 inputs the information regarding the search query specified by the specifying unit 132 to the generation AI, so as to cause the generation AI to classify the search query into a plurality of phases and generate explanatory content explaining each phase for each phase. The providing unit 135 provides information for displaying the information indicating the plurality of phases classified by the generation AI together with the explanatory content generated by the generation AI.

[0056] Thereby, the information processing apparatus 100 according to the embodiment can appropriately perform visualization of the phase classification of the search query because, for example, it can display the explanatory content together with the phase classification result. Further, the information processing apparatus 100 according to the embodiment can, for example, analyze the relationship between the user and the object indicated by the predetermined query, so that it can enable an appropriate tendency analysis of the user.

[0057] Further, the processing unit 134 inputs time series information indicating the time series of the search in which the search query was searched, with the search date and time when the predetermined query was searched as the reference date and time, to the generation AI, so as to cause the generation AI to perform classification and generation.

[0058] Thereby, the information processing apparatus 100 according to the embodiment can, for example, enable an appropriate tendency analysis of the user along the time series.

[0059] Further, the processing unit 134 inputs a prompt for instructing the generation AI to classify the phase according to the changes in the actions of a plurality of users to the generation AI, so as to cause the generation AI to perform classification and generation.

[0060] As a result, the information processing apparatus 100 according to the embodiment can, for example, enable appropriate trend analysis of the user according to changes in behavior.

[0061] In addition, the processing unit 134 inputs a prompt to the generation AI that instructs the phases to be classified so that the relevance scores between adjacent phases become high, thereby causing the generation AI to perform classification and generation.

[0062] As a result, the information processing apparatus 100 according to the embodiment can classify the phases so that the continuous relevance becomes deeper, rather than the instantaneous relevance such as being taken up in media such as a television, and thus can enable more appropriate trend analysis.

[0063] In addition, the processing unit 134 inputs a prompt to the generation AI that instructs the generation of explanatory content reflecting information on the search query included in the phase, thereby causing the generation AI to perform classification and generation.

[0064] As a result, the information processing apparatus 100 according to the embodiment can, for example, display explanatory content for each phase, and thus can enable more appropriate trend analysis.

[0065] In addition, when there are phases among a plurality of phases where the relevance scores between adjacent phases are equal to or less than a predetermined threshold, the providing unit 135 provides information indicating an alert.

[0066] As a result, the information processing apparatus 100 according to the embodiment can, for example, notify an alert when the continuous relevance of the phases is low, and thus can enable more appropriate trend analysis.

[0067] 〔7. Hardware Configuration〕 Further, the information processing apparatus 100 according to the above-described embodiments is realized by, for example, a computer 1000 having a configuration 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 apparatus 100. The computer 1000 includes 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.

[0068] The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program dependent on the hardware of the computer 1000, and the like.

[0069] The HDD 1400 stores a program executed by the CPU 1100, data used by such a program, and the like. The communication interface 1500 acquires data from other devices via a predetermined communication network and sends it to the CPU 1100, and sends data generated by the CPU 1100 to other devices via a predetermined communication network.

[0070] 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. Further, the CPU 1100 outputs the generated data to the output devices via the input / output interface 1600.

[0071] The media interface 1700 reads the programs or data stored in the recording medium 1800 and provides them to the CPU 1100 via the RAM 1200. The CPU 1100 loads such programs from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded programs. The recording medium 1800 is, for example, an optical recording medium such as 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.

[0072] For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing the programs loaded onto the RAM 1200. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800. As another example, these programs may be acquired from other devices via a predetermined communication network.

[0073] [8. Others] Also, among the respective processes described in the above embodiment, all or part of the processes described as being automatically performed can be manually performed, or all or part of the processes described as being manually performed can be automatically performed by a known method. In addition, regarding the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings, they can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

[0074] [[ID=I3]] Also, each component of each illustrated device is a functional concept, and it is not necessarily physically configured as shown in the figure. That is, the specific form of the dispersion and integration of each device is not limited to that shown in the figure, and all or part of it can be functionally or physically dispersed and integrated in any unit according to various loads and usage situations.

[0075] Also, the embodiments described above can be appropriately combined within a range that does not conflict with the processing content.

[0076] As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are merely examples, and the present invention can be implemented in other forms with various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the column of the disclosure of the invention.

[0077] Also, the "section (section, module, unit)" described above can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition means or an acquisition circuit.

Description of Reference Numerals

[0078] 1 Information processing system 10 Terminal device 11 Communication unit 12 Input unit 13 Output unit 14 Control unit 100 Information processing apparatus 110 Communication unit 120 Storage unit 121 Search behavior information storage unit 130 Control unit 131 Acquisition unit 132 Identification unit 133 Generation unit 134 Processing unit 135 Provision unit 141 Reception unit 142 Transmission unit N Network

Claims

1. An identifying unit that identifies search queries of a plurality of users who used a predetermined query for searching; A processing unit that inputs information regarding the search queries identified by the identifying unit into a generation AI, causing the generation AI to classify the search queries into a plurality of phases and generate explanatory content explaining each phase for each phase; A providing unit that provides information for displaying information indicating a plurality of phases classified by the generation AI together with the explanatory content generated by the generation AI; An information processing apparatus comprising the above.

2. The processing unit: By inputting time-series information indicating the time series of searches in which the search queries were made into the generation AI with the search date and time when the predetermined query was searched as a reference date and time, the generation AI is made to execute the classification and the generation. The information processing apparatus according to claim 1, characterized in that.

3. The processing unit: By inputting a prompt for instructing the generation AI to classify phases according to changes in the actions of the plurality of users into the generation AI, the generation AI is made to execute the classification and the generation. The information processing apparatus according to claim 1, characterized in that.

4. The processing unit: By inputting a prompt for instructing the generation AI to classify phases so that the relevance score between adjacent phases becomes high into the generation AI, the generation AI is made to execute the classification and the generation. The information processing apparatus according to claim 1, characterized in that.

5. The processing unit: By inputting a prompt for instructing the generation AI to generate the explanatory content reflecting information regarding the search queries included in the phases into the generation AI, the generation AI is made to execute the classification and the generation. The information processing apparatus according to claim 1, characterized in that.

6. The providing unit: When there are phases whose relevance score between adjacent phases among the plurality of phases is equal to or less than a predetermined threshold, provides information indicating an alert. The information processing apparatus according to claim 1, characterized in that.

7. An information processing method executed by a computer, comprising: An identifying step of identifying search queries of a plurality of users who used a predetermined query for searching; By inputting information regarding the search query specified by the specific process into the generation AI, the generation AI is caused to classify the search query into a plurality of phases and generate explanatory content explaining the phases for each phase, and a processing step; a providing step of providing information for causing the information indicating the plurality of phases classified by the generation AI to be displayed together with the explanatory content generated by the generation AI; An information processing method characterized by including the above.

8. a specifying procedure for specifying search queries of a plurality of users who used a predetermined query for searching; By inputting information regarding the search query specified by the specifying procedure into the generation AI, the generation AI is caused to classify the search query into a plurality of phases and generate explanatory content explaining the phases for each phase, and a processing procedure; a providing procedure for providing information for causing the information indicating the plurality of phases classified by the generation AI to be displayed together with the explanatory content generated by the generation AI; An information processing program characterized by causing a computer to execute the above.

Images