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

Abstract

To provide an information processing device, an information processing method, and an information processing program capable of associating further useful attribute information with a site.SOLUTION: An information processing device includes: a collection unit; a classification unit; an extraction unit; and a determination unit. The collection unit collects search queries which are input by a user when the user has stayed at a prescribed site. The classification unit classifies the collected queries into clusters on the basis of association information associated with the search query. The extraction unit extracts a specific word on the basis of a search query contained in a cluster for each cluster. The determination unit uses the specific word extracted for each cluster as input, inputs a prompt for generating an attribute name of the prescribed cite to a generative AI, and determines an output result of the generative AI as the attribute name of the prescribed site.SELECTED DRAWING: Figure 3

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] Conventionally, a technique for using land use data provided by a country in various services has been known. The land use data has, for example, attribute information of locations such as fields, farmlands, and parks associated therewith.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, there has been room for further improvement in associating more useful attribute information with locations.

[0005] The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of associating more useful attribute information with locations.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes a collection unit, a classification unit, an extraction unit, and a determination unit. The collection unit collects a search query input by a user when staying at a predetermined location. The classification unit classifies the collected search query into clusters based on the associated information associated with the search query. The extraction unit extracts specific words based on the search query included in each cluster for each cluster. The determination unit inputs the specific word extracted for each cluster, inputs a prompt for generating the attribute name of the predetermined location to a generation AI, and determines the output result of the generation AI as the attribute name of the predetermined location.

Effect of the Invention

[0007] According to one aspect of the embodiment, there is an effect that more useful attribute information can be associated with a location.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Mode for Carrying Out the Invention

[0009] 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 descriptions are omitted.

[0010] (Embodiment) First, with reference to FIG. 1, the processing executed by the information processing apparatus according to the embodiment will be described. FIG. 1 is a diagram showing the processing executed by the information processing apparatus according to the embodiment.

[0011] As shown in FIG. 1, the information processing system S according to the embodiment includes an information processing apparatus 1, a user terminal 100, and a log server 200.

[0012] The information processing system S shown in FIG. 1 collects search queries input by a user when staying at a predetermined location, classifies the collected search queries into clusters, extracts specific words based on the search queries for each cluster, inputs the extracted specific words, and inputs a prompt for generating an attribute name of the predetermined location to a generation AI, and determines the output result of the generation AI as the attribute name of the predetermined location.

[0013] Specifically, first, the information processing apparatus 1 collects a log of search queries input by a user when staying at a predetermined location from the log server 200 (step S1). The predetermined location is, for example, a facility, a region, or the like. Also, the staying user is not a user whose place of residence is the predetermined location, but a user who was temporarily present at the predetermined location. Also, the staying user is not simply a user who passed by the predetermined location, but a user who stayed for a predetermined time or more (more than the time during which a predetermined action can be performed at the predetermined location). Also, the search query is a search query related to the predetermined location. For example, the information processing apparatus 1 collects search queries related to a facility input by a user staying at the facility.

[0014] Next, the information processing apparatus 1 clusters the collected search queries (step S2). Specifically, the information processing apparatus 1 classifies the collected search queries into clusters based on the associated information associated with the search queries. The associated information includes the content of the search query, the content of the information selected by the user from the search results provided by the search query, the user's attribute information, the attribute information of a predetermined location (such as population and facility attributes), the number of other users who stayed at the predetermined location during the period when the user stayed, and the like. The information processing apparatus 1 performs cluster classification using a model that has learned the above associated information as an explanatory variable and the cluster to be classified as a target variable. That is, the information processing apparatus 1 inputs the associated information into the model and uses the cluster output from the model as the classification result.

[0015] Next, for each cluster, the information processing apparatus 1 extracts a specific word based on the search queries included in the cluster (step S3). For example, the information processing apparatus 1 extracts the most frequent word among the words of the search queries included in the cluster as the specific word. In addition, the information processing apparatus 1 performs semantic analysis of the words of the search query and extracts the meaning with the most occurrences as the specific word. Further, the information processing apparatus 1 may use a generative AI that has been trained to output a specific word with the words of the search query as input. Specifically, the generative AI is a language model that performs natural language processing such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers). And the generative AI is within the information processing apparatus 1 and is independently created by the operator who manages the information processing apparatus 1. Note that it is desirable to perform learning so that the input information is not used as a new answer to anonymize information such as the input personal information.

[0016] Note that for clusters in which the number of included search queries is less than a predetermined number, the information processing apparatus 1 does not perform (forbids) the specific word extraction process. This can reduce the extraction of inappropriate specific words.

[0017] Subsequently, the information processing apparatus 1 inputs the specific words extracted for each cluster, inputs a prompt for generating the attribute name of a predetermined location to the generation AI, and determines the output result of the generation AI as the attribute name of the predetermined location (step S4). That is, the information processing apparatus 1 uses the generation AI that generates a new attribute name with the plurality of specific words extracted from the plurality of clusters as input. Specifically, the generation AI is a language model that performs natural language processing such as GPT or BERT. And the generation AI is within the information processing apparatus 1 and is independently created by the operator who manages the information processing apparatus 1. It is desirable that the input information conceals information such as personal information by performing learning so that it is not used as a new answer.

[0018] For example, when the predetermined location is a stadium, the information processing apparatus 1 determines new attribute names such as "a stadium for watching professional baseball" or "a stadium for the general public to play baseball".

[0019] Subsequently, the information processing apparatus 1 provides the information of the determined attribute name to the user terminal 100 (step S5). For example, the information processing apparatus 1 provides the information of the attribute name as an explanation when the user selects a predetermined location in the map application. Also, the information processing apparatus 1 provides the above attribute name as new attribute information to the operator who provides services related to the predetermined location so that search and the like can be performed.

[0020] As described above, according to the information processing apparatus 1 according to the embodiment, more useful attribute information can be associated with the location for the user (map application user or operator).

[0021] Next, with reference to FIG. 2, a configuration example of the information processing system S according to the embodiment will be described. FIG. 2 is a block diagram showing a configuration example of the information processing system S according to the embodiment. As shown in FIG. 2, in the information processing system S according to the embodiment, an information processing apparatus 1, a plurality of user terminals 100, and a log server 200 are connected to a network N by wire or wirelessly. The network N is, for example, a network such as the Internet, a WAN (Wide Area Network), or a LAN (Local Area Network).

[0022] The information processing apparatus 1 is a server apparatus that executes the information processing method according to the embodiment. The information processing apparatus 1 cooperates with a plurality of user terminals 100 and a log server 200, and is an information processing apparatus that provides API (Application Programming Interface) services and various data for various applications (hereinafter referred to as apps) to the plurality of user terminals 100, and is realized by a server apparatus, a cloud system, or the like.

[0023] Further, the information processing apparatus 1 may be an information processing apparatus that provides some kind of Web service online to the plurality of user terminals 100. For example, as a Web service, the information processing apparatus 1 may provide services such as Internet connection, search service, SNS (Social Networking Service), electronic commerce (EC: Electronic Commerce), electronic payment, online game, online banking, online trading, accommodation / ticket reservation, video / music distribution, news, map, route search, route guidance, route information, operation information, weather forecast, etc. Actually, the information processing apparatus 1 may cooperate with various servers that provide the above Web services and mediate the Web services, or may be in charge of the processing of the Web services.

[0024] The user terminal 100 is a terminal device held by a user who uses information on attribute names. The user terminal 100 can use any type of terminal device such as a smartphone, a desktop PC, a notebook PC, or a tablet PC. The user terminal 100 transmits various types of information to the information processing device 1 and receives information provided from the information processing device 1 and the like.

[0025] The log server 200 is a server device that stores various log data of a user such as a search query and provides the log data to the information processing device 1. The log server 200 is not limited to a server device and may be realized by a cloud system or the like.

[0026] Next, with reference to FIG. 3, a configuration example of the information processing device 1 will be described.

[0027] FIG. 3 is a diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes a collection unit 31, a classification unit 32, an extraction unit 33, a determination unit 34, and a provision unit 35. The storage unit 4 stores model information 41.

[0028] The communication unit 2 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 2 is connected to a network via wire or wirelessly.

[0029] The control unit 3 is a controller, which is realized, for example, by a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), when various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing apparatus 1 are executed using a RAM or the like as a work area. Further, the control unit 3 is a controller and may be realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).

[0030] The storage unit 4 is realized, for example, by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0031] The model information 41 is information regarding a model that takes the above-specified word as an input and outputs an attribute name at a predetermined location.

[0032] FIG. 4 is a diagram showing an example of the model information 41. As shown in FIG. 4, the model information 41 includes items such as "model ID" and "model information".

[0033] The "model ID" is identification information for identifying a model. The "model information" is information regarding the model and includes, for example, input parameters of the model, coefficients, and the like.

[0034] Next, each function (collection unit 31, classification unit 32, extraction unit 33, determination unit 34, and provision unit 35) of the control unit 3 of the information processing apparatus 1 will be described.

[0035] The collection unit 31 collects the logs of search queries input by users when they stay at a predetermined location from the log server 200. The predetermined location is, for example, a facility, a region, etc. Also, the staying users are not users whose place of residence is the predetermined location, but users who were temporarily present at the predetermined location. Also, the staying users are not simply users who passed by the predetermined location, but users who stayed for a predetermined time or more (a time sufficient to perform a predetermined action at the predetermined location). Also, the search query is a search query related to the predetermined location. For example, the collection unit 31 collects search queries related to a facility input by users staying at the facility.

[0036] The classification unit 32 clusters the collected search queries. Specifically, the classification unit 32 classifies the collected search queries into clusters based on the associated information associated with the search queries. The associated information is the content of the search query, the content of the information selected by the user from the search results provided by the search query, the user's attribute information, the attribute information of the predetermined location (population, facility attributes, etc.), the number of other users who stayed at the predetermined location during the period when the user stayed, etc. The classification unit 32 performs cluster classification using a model learned with the above associated information as explanatory variables and the cluster to be classified as the target variable. That is, the classification unit 32 inputs the associated information into the model and uses the cluster output from the model as the classification result.

[0037] The extraction unit 33 extracts specific words for each cluster based on the search queries included in the cluster. For example, the extraction unit 33 extracts the most frequent word among the words of the search queries included in the cluster as the specific word. Also, the extraction unit 33 performs semantic analysis of the words of the search query and extracts the meaning with the most meanings of the word as the specific word. Also, the extraction unit 33 may use a generative AI learned to input the words of the search query and output the specific word.

[0038] Note that the extraction unit 33 does not perform (prohibits) the extraction process of specific words for clusters in which the number of included search queries is less than a predetermined number. Thereby, it is possible to reduce the extraction of inappropriate specific words.

[0039] The determination unit 34 uses, as input, the specific words extracted for each cluster, inputs a prompt for generating the attribute name of a predetermined location to the generation AI, and determines the output result of the generation AI as the attribute name of the predetermined location. That is, the determination unit 34 uses the generation AI that generates a new attribute name with the plurality of specific words extracted from the plurality of clusters as input.

[0040] For example, when the predetermined location is a baseball field, the determination unit 34 determines new attribute names such as "a baseball field for watching professional baseball" and "a baseball field for the general public to play baseball".

[0041] The providing unit 35 provides the information of the determined attribute name to the user terminal 100. For example, the providing unit 35 provides the information of the attribute name as an explanation when the user selects a predetermined location in the map application. In addition, the providing unit 35 provides the above attribute name as new attribute information to the service provider that provides the service related to the predetermined location so that the service provider can perform searches and the like.

[0042] Next, with reference to FIG. 5, the processing procedure of the processing executed by the information processing apparatus 1 according to the embodiment will be described. FIG. 5 is a flowchart showing the processing procedure of the processing executed by the information processing apparatus 1 according to the embodiment.

[0043] As shown in FIG. 5, first, the control unit 3 collects the search queries input by the user when staying at a predetermined location from the log server 200 (step S101).

[0044] Subsequently, the control unit 3 classifies the collected search queries into clusters based on the association information associated with the collected search queries (step S102).

[0045] Subsequently, the control unit 3 extracts specific words for each cluster based on the search queries included in the cluster (step S103).

[0046] Subsequently, the control unit 3 uses the specific words extracted for each cluster as input, inputs a prompt for generating the attribute name of a predetermined location to the generation AI, and determines the output result of the generation AI as the attribute name of the predetermined location (step S104).

[0047] Subsequently, the control unit 3 provides the information on the determined attribute name to the user terminal 100 (step S105) and ends the process.

[0048] 〔Others〕 Also, among the processes described in the above embodiment, a part of the processes described as being automatically performed can be manually performed. Alternatively, 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 documents 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.

[0049] Also, each component of each device shown in the drawings is conceptually functional and does not necessarily have to be physically configured as shown. That is, the specific form of the distribution and integration of each device is not limited to that shown, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads and usage situations.

[0050] For example, part or all of the storage unit 4 shown in FIG. 3 may be held not by each device but by a storage server or the like. In this case, each device acquires various information by accessing the storage server.

[0051] 〔Hardware Configuration〕 Further, the information processing apparatus 1 according to the above-described embodiment is realized by a computer 1000 configured as shown in FIG. 6, for example. FIG. 6 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0052] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, etc., and executes various processes. The primary storage device 1040 is a memory device that temporarily stores data used by the arithmetic unit 1030 for various operations, such as a RAM. Further, the secondary storage device 1050 is a storage device in which data used by the arithmetic unit 1030 for various operations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD (Hard Disk Drive), a flash memory, etc.

[0053] The output IF 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a monitor and a printer, and is realized by a connector of a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), HDMI (registered trademark) (High Definition Multimedia Interface). Further, the input IF 1070 is an interface for receiving information from various input devices 1020, such as a mouse, a keyboard, and a scanner, and is realized by, for example, USB or the like.

[0054] Note that the input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or 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. Also, the input device 1020 may be an external storage medium such as a USB memory.

[0055] The network IF 1080 receives data from other devices via the network N and sends it to the arithmetic unit 1030, and also sends the data generated by the arithmetic unit 1030 via the network N to other devices.

[0056] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0057] For example, when the computer 1000 functions as the information processing device 1, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 3 by executing the program loaded onto the primary storage device 1040.

[0058] 〔Effect〕 As described above, the information processing apparatus 1 according to the embodiment includes a collection unit 31, a classification unit 32, an extraction unit 33, and a determination unit 34. The collection unit 31 collects search queries input by the user when staying at a predetermined location. The classification unit 32 classifies the collected search queries into clusters based on the associated information associated with the search queries. The extraction unit 33 extracts specific words for each cluster based on the search queries included in the cluster. The determination unit 34 inputs the specific words extracted for each cluster, inputs a prompt for generating the attribute name of the predetermined location to the generation AI, and determines the output result of the generation AI as the attribute name of the predetermined location. With such a configuration, more useful attribute information can be associated with the location for the user.

[0059] As described above, some of the embodiments of the present application have been described in detail with reference to the drawings. However, these are 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.

[0060] 〔Others〕 Also, among the 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.

[0061] Also, each component of each device shown in the drawings is a functional concept, and it is not necessarily physically configured as shown in the drawings. That is, the specific form of the distribution and integration of each device is not limited to that shown in the drawings, and all or part of it can be functionally or physically distributed and integrated in any unit according to various loads and usage situations.

[0062] Also, the respective processes described in the above-described embodiments can be appropriately combined within a range that does not conflict with the processing contents.

[0063] Also, the above-mentioned "section (section, module, unit)" can be read as "means", "circuit", etc. For example, the control unit 3 can be read as a control means or a control circuit.

Explanation of Reference Numerals

[0064] 1 Information processing apparatus 2 Communication unit 3 Control unit 4 Storage unit 31 Collection unit 32 Classification unit 33 Extraction unit 34 Decision unit 35 Provision unit 41 Model information 100 User terminal 200 Log server S Information processing system

Claims

1. A collecting unit that collects search queries input by a user while staying at a predetermined location; A classification unit that classifies the collected search queries into clusters based on the associated information associated with the search queries; An extraction unit that extracts specific words based on the search queries included in each of the clusters; A determination unit that inputs the specific words extracted for each cluster into a generation AI that generates a prompt for generating the attribute name of the predetermined location, and determines the output result of the generation AI as the attribute name of the predetermined location An information processing apparatus comprising:

2. The classification unit: Inputs the associated information into a model learned with the associated information as an explanatory variable and the cluster to be classified as a target variable, and classifies the search queries into the clusters output from the model The information processing apparatus according to claim 1.

3. The associated information: Includes at least one of the content of the search query, the content of the information selected by the user in the search results provided by the search query, the attribute information of the user, the attribute information of the predetermined location, and the number of other users who stayed at the predetermined location during the period when the user stayed The information processing apparatus according to claim 1.

4. The extraction unit: Inputs the collected search queries into a generation AI learned to output the specific words with the words of the search queries as inputs, and uses the specific words output from the generation AI as extraction results The information processing apparatus according to claim 1.

5. The extraction unit: For clusters in which the number of the included search queries is less than a predetermined number, prohibits the extraction process of the specific words The information processing apparatus according to claim 1.

6. An information processing method executed by a computer, comprising: A collecting step of collecting search queries input by a user while staying at a predetermined location; A classification step of classifying the collected search queries into clusters based on the associated information associated with the search queries; An extraction step of extracting specific words based on the search queries included in each of the clusters; A determination step of inputting the specific words extracted for each cluster into a generation AI that generates a prompt for generating the attribute name of the predetermined location, and determining the output result of the generation AI as the attribute name of the predetermined location An information processing method including:

7. A collecting procedure for collecting search queries input by a user while staying at a predetermined location; A classification procedure for classifying the collected search queries into clusters based on the associated information associated with the search queries; An extraction procedure for extracting specific words based on the search queries included in the cluster for each cluster; A determination procedure for inputting the specific words extracted for each cluster as an input, inputting a prompt for generating the attribute name of the predetermined location to the generation AI, and determining the output result of the generation AI as the attribute name of the predetermined location An information processing program for causing a computer to execute.

Images