Information processing apparatus, information processing method, and non-transitory computer readable storage medium
An information processing apparatus according to the present application includes a specifying unit, a processing unit, and a provision unit. The specifying unit specifies search queries of a plurality of users using a predetermined query for a search. The processing unit causes generative AI to classify the search queries into a plurality of phases and to generate description content describing the phase for each of the phases by inputting information regarding the search queries specified by the specifying unit to the generative AI. The provision unit provides information for displaying information indicating the plurality of phases classified by the generative AI together with the description content generated by the generative AI.
1 . An information processing apparatus comprising:
a central processing unit (CPU) configured to specify search queries of a plurality of users who have used a predetermined query for a search;
the CPU causing generative AI to classify the search queries into a plurality of phases and to generate description content describing the phase for each of the phases by inputting information regarding the search queries specified by the CPU to the generative AI;
the CPU providing information for displaying information indicating the plurality of phases classified by the generative AI together with the description content generated by the generative AI; and
the CPU providing information indicating an alert in a case where, among the plurality of phases, there are adjacent phases having a relevance score between the adjacent phases less than or equal to a predetermined threshold.
2 . The information processing apparatus according to claim 1 , wherein the CPU
causes the generative AI to execute the classification and the generation by inputting time-series information indicating time series of searches in which the search queries have been used for a search to the generative AI with a search date and time when the predetermined query has been used for the search as a reference date and time.
3 . The information processing apparatus according to claim 1 , wherein the CPU
causes the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to classify phases depending on a change in behaviors of the plurality of users.
4 . The information processing apparatus according to claim 1 , wherein the CPU
causes the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to classify phases such that a relevance score between adjacent phases is high.
5 . The information processing apparatus according to claim 1 , wherein the CPU
causes the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to generate the description content reflecting information regarding the search queries included in the phases.
6 . The information processing apparatus according to claim 1 , wherein the CPU specifies conversions of a plurality of users who have performed a predetermined conversion, and the CPU causes the generative AI to classify the conversions into the plurality of phases by inputting information regarding a time difference between the predetermined conversion and conversions performed before or after the predetermined conversion to the generative AI.
7 . The information processing apparatus according to claim 1 , wherein the CPU specifies purchased products of a plurality of users who have purchased a predetermined product, and the CPU causes the generative AI to classify the purchased products into the plurality of phases by inputting information regarding a time difference between the predetermined product and purchased products purchased before or after the predetermined product to the generative AI.
8 . The information processing apparatus according to claim 1 , wherein the CPA specifies selected advertisements of a plurality of users who have selected a predetermined advertisement, and the CPU causes the generative AI to classify the selected advertisements into the plurality of phases by inputting information regarding a time difference between the predetermined advertisement and selected advertisements selected before or after the predetermined advertisement to the generative AI.
9 . The information processing apparatus according to claim 1 , wherein the CPU specifies search queries by narrowing down to a plurality of users who have performed a search using the predetermined query a predetermined number of times or more.
10 . The information processing apparatus according to claim 1 , wherein the CPU provides information for displaying the description content superimposed on a scatter diagram indicating the plurality of phases, wherein a vertical axis of the scatter diagram represents a score reflecting a number of searches by the search queries and a horizontal axis represents time.
11 . An information processing method executed by a computer, the method comprising:
specifying search queries of a plurality of users who has used a predetermined query for a search;
causing generative AI to classify the search queries into a plurality of phases and to generate description content describing the phase for each of the phases by inputting information regarding the search queries specified in the specifying to the generative AI; and
providing information for displaying information indicating the plurality of phases classified by the generative AI together with the description content generated by the generative AI; and
providing information indicating an alert in a case where, among the plurality of phases, there are adjacent phases having a relevance score between the adjacent phases less than or equal to a predetermined threshold.
12 . The information processing method according to claim 11 , the method further comprising:
causing the generative AI to execute the classification and the generation by inputting time-series information indicating time series of searches in which the search queries have been used for a search to the generative AI with a search date and time when the predetermined query has been used for the search as a reference date and time.
13 . The information processing method according to claim 11 , the method further comprising:
causing the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to classify phases depending on a change in behaviors of the plurality of users.
14 . The information processing method according to claim 11 , the method further comprising:
causing the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to classify phases such that a relevance score between adjacent phases is high.
15 . The information processing method according to claim 11 , the method further comprising:
causing the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to generate the description content reflecting information regarding the search queries included in the phases.
16 . A non-transitory computer-readable storage medium storing an information processing program for causing a computer to execute:
specifying search queries of a plurality of users who has used a predetermined query for a search;
causing generative AI to classify the search queries into a plurality of phases and to generate description content describing the phase for each of the phases by inputting information regarding the search queries specified in the specifying procedure to the generative AI;
providing information for displaying information indicating the plurality of phases classified by the generative AI together with the description content generated by the generative AI; and
providing information indicating an alert in a case where, among the plurality of phases, there are adjacent phases having a relevance score between the adjacent phases less than or equal to a predetermined threshold.
17 . The non-transitory computer-readable storage medium according to claim 16 , the method further comprising:
causing the generative AI to execute the classification and the generation by inputting time-series information indicating time series of searches in which the search queries have been used for a search to the generative AI with a search date and time when the predetermined query has been used for the search as a reference date and time.
18 . The non-transitory computer-readable storage medium according to claim 16 , the method further comprising:
causing the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to classify phases depending on a change in behaviors of the plurality of users.
19 . The non-transitory computer-readable storage medium according to claim 16 , the method further comprising:
causing the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to classify phases such that a relevance score between adjacent phases is high.
20 . The non-transitory computer-readable storage medium according to claim 16 , the method further comprising:
causing the generative AI to execute the classification and the generation by inputting, to the generative AI, a prompt instructing to generate the description content reflecting information regarding the search queries included in the phases.