Information processing unit, information processing method, and information processing program

Abstract

To provide an information processing unit, an information processing method, and an information processing program capable of making an appropriate action proposal according to an action tendency of a user.SOLUTION: An information processing unit 10 includes an access log storage unit 12 that stores input information including access information to an external network by a user of a user terminal, a log analysis unit 13 that classifies the input information according to categories and extracts a category satisfying a predetermined condition as an action tendency of the user, and an action proposal unit 14 that makes an action proposal to the user terminal based on the input information corresponding to the category of the extracted action tendency.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] An embodiment of the present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] In recent years, AI (artificial intelligence) has been used in various fields, and the use of AI that can automatically generate content, known as generative AI, is spreading rapidly. Some generative AI uses large-scale learning models that have learned a large number of natural languages ​​and programming languages ​​to perform tasks such as generating text and summarizing text according to user instructions with high accuracy. By using generative AI, users can accurately obtain the information they need when searching for information on the Internet.

[0003] Conventionally, a system has been disclosed in which an AI-based dialogue system that automatically responds to user questions calculates the similarity between questions from multiple users and uses similar questions for learning, thereby efficiently learning question and answer patterns and improving the accuracy of answers to user questions. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-219737 A Summary of the Invention [Problem to be solved by the invention]

[0005] In an AI dialogue system, the AI ​​can automatically generate texts etc. according to the conditions of a user's instructions, and can also select past instructions from the user's history, which is highly convenient. However, when a user searches etc., even though there is a lot of overlap in the user's daily actions, they need to input the answers to the AI ​​each time, which can be cumbersome.

[0006] The present invention has been made in consideration of the above circumstances, and aims to provide an information processing device, an information processing method, and an information processing program that can make appropriate action suggestions in line with a user's behavioral tendencies. [Means for solving the problem]

[0007] An information processing device according to an embodiment of the present invention is characterized in that it comprises an access log storage unit that stores input information including access information by a user of a user terminal to an external network, a log analysis unit that classifies the input information according to categories and extracts the categories that satisfy predetermined conditions as behavioral tendencies of the user, and a behavior suggestion unit that makes behavioral suggestions to the user terminal based on the input information corresponding to the extracted category of the behavioral tendency. Effect of the Invention

[0008] According to the embodiments of the present invention, an information processing device, an information processing method, and an information processing program are provided that are capable of making appropriate action suggestions in line with the user's behavioral tendencies. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an information processing device according to an embodiment of the present invention. [Diagram 2] FIG. 11 is an explanatory diagram showing an example of input information including user access information stored in an access log storage unit. [Diagram 3] FIG. 11 is an explanatory diagram showing an example of a behavioral tendency of a user extracted based on input information. [Figure 4] FIG. 11 is an explanatory diagram showing an example of a suggested action proposed to a user based on an analyzed behavioral tendency. [Diagram 5] FIG. 13 is an explanatory diagram showing an example of a screen when an action suggestion proposed by an action suggestion unit is changed. [Figure 6] 4 is a flowchart showing an example of an information processing method according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. FIG. 1 is a diagram showing an example of the configuration of an information processing device 10 according to the present embodiment.

[0011] The information processing device 10 according to the embodiment extracts behavioral tendencies that are considered to be of high interest to the user from input information such as access information to external networks by the user of the user terminal 20, and suggests actions to the user, such as access destinations, based on the behavioral tendencies.

[0012] The user terminal 20 indicates a terminal capable of communicating with an external network, such as a PC, a smartphone, or a tablet terminal owned by each user, and can communicate with the information processing device 10 via the network. Although FIG. 1 shows three user terminals 20 (20a, 20b, and 20c) owned by each user, the configuration is not limited to this. The information processing device 10 is connected to each of the user terminals 20 in a communicable manner, and various data are transmitted and received.

[0013] The generation AI server 100 is a server that has a learning model that has learned information on the network and program languages, and automatically generates answers to user inputs. It is communicably connected to the information processing device 10 via the network, and automatically generates answers to any input from the user or the information processing device 10 based on the learning model according to the conditions specified by the input.

[0014] A specific configuration of the information processing device 10 according to this embodiment will be described. The information processing device 10 includes an input information receiving unit 11, an access log storage unit 12, a log analysis unit 13, an action suggestion unit 14, and a suggestion generation unit 15.

[0015] The functions of each unit constituting the information processing device 10 may be realized by executing a predetermined program code using a processor, and are not limited to such software processing. For example, the functions may be realized by hardware processing using an ASIC or the like, or may be realized by a combination of software processing and hardware processing.

[0016] The input information receiving unit 11 receives input information from the user at the user terminal 20. The input information is information related to the user's operation on the user terminal 20, and means a search word used for a search when accessing the Internet using the web browser of the user terminal 20, URL information of the accessed site, an application running on the user terminal, etc. Information such as the access time when accessing the Internet and the location information of the user terminal 20 at the time of access may also be received.

[0017] The access log storage unit 12 stores input information including information about access made to an external network by the user of the user terminal 20. When an external access is made by the user of the user terminal 20, the access log storage unit 12 stores the access information (search words related to the access, the access destination URL), the application being used on the terminal, etc. as input information at any time. In addition, the access log storage unit 12 stores the access time and the location information of the user terminal 20 at the time of external access. The access log storage unit 12 may arrange the input information in chronological order and store it as data on a daily basis. The input information is collected and recorded at any time for each user.

[0018] Furthermore, the access log storage unit 12 uses a database in which website categories corresponding to each URL are registered in advance, and sets and stores a category corresponding to the accessed URL received from the input information receiving unit 11. The category indicates a type according to the content of the website, and means classification information according to content such as sports, history, education, etc. If a category is not registered for the user's accessed URL, the generation AI server 100 may be inquired about the category (website type) of the accessed URL, and the category may be acquired and stored.

[0019] The access log storage unit 12 may delete accesses to URLs of search sites from the input information since they are not related to the user's behavioral tendencies.

[0020] FIG. 2 is an explanatory diagram showing an example of input information including user access information stored in the access log storage unit 12. As shown in FIG.

[0021] As shown in FIG. 2, the search word used when accessing from outside, the URL information of the access destination, and the application used on the terminal are sequentially saved as input information for user Yamada Taro on August 15, 2023. In addition, the location information of the user terminal 20 is also recorded along with the time of access. The URL of the access destination is collated with a database in which the categories of websites are registered in advance, and the category of the URL of the access destination is saved.

[0022] The log analysis unit 13 classifies the input information according to categories, and extracts categories that satisfy a predetermined condition as the user's behavioral tendency. Specifically, each piece of user access information stored in the access log storage unit 12 is classified into set categories, and the frequency of access according to the category is found. Then, a category whose access frequency satisfies a predetermined condition (e.g., 5 or more accesses) is extracted as the behavioral tendency. The behavioral tendency means a category that is considered to be of high interest to the user. The predetermined condition may be, for example, a condition in which categories are arranged in order of frequency of access, and the top four categories are extracted.

[0023] FIG. 3 is an explanatory diagram showing an example of a user's behavioral tendency extracted based on input information. As shown in FIG. 3, the access information of user Yamada Taro is classified into categories, and the frequency of access according to the category is obtained. Then, the categories are arranged in descending order of frequency, and four categories are extracted as behavioral tendencies. The results of classifying the categories of Yamada Taro's access information show that he tends to be highly interested in the fields of sports, history, education (university), and business, and these four categories become his behavioral tendencies.

[0024] The action suggestion unit 14 makes action suggestions to the user terminal 20 based on the input information corresponding to the extracted action tendency category. Specifically, for each category extracted by the log analysis unit 13, a link to an access URL of the input information or the like is transmitted to the user terminal 20 as an action suggestion. The user of the user terminal 20 can check the action suggestion displayed on the terminal screen. The action suggestion may be obtained, for example, based on the user's access log for one week, and suggested when the user starts up the browser.

[0025] In addition, the behavior suggestion unit 14 may check the access time for the extracted behavioral tendency category (if the access time varies, the time period with the highest access) and set the time for making behavior suggestions based on the access time (e.g., after 7 p.m.).

[0026] In addition, for the extracted behavioral tendency category, the access location of the user terminal 20 may be checked (if there is variation in the access location, the location range with the most access) and the location of the terminal for which behavior suggestions are made may be set based on the access location (for example, within a 10 m radius of the location information of the user's home).

[0027] The proposal generation unit 15 inputs input information corresponding to the extracted behavioral tendency category to the generation AI server 100 under predetermined conditions, and obtains an output result by the learning model. The action suggestion unit 14 may make an action suggestion using the information obtained by the proposal generation unit 15. For example, for a link of a destination URL, an input is made to the generation AI server 100 requesting a summary of the description on the site, and the summary result by the learning model is obtained, and this summary is used as an action suggestion.

[0028] FIG. 4 is an explanatory diagram showing an example of action suggestions proposed to a user based on the analyzed behavioral tendency. Action suggestions are displayed on the user's terminal screen for categories extracted based on Yamada Taro's access information. For the sports category, information on the accessed URL and a summary of the URL are displayed. For the history category, information on the accessed URL and a summary of the search word are displayed. The action suggestion display screen displays a "Change Proposal Content" button for changing the proposed content and a "Delete" button for deleting the proposal. When a proposal is deleted, it may be set so that suggestions for that category will not be made from the next time.

[0029] 5 is an explanatory diagram showing an example of a screen for changing an action proposal proposed by the action suggestion unit 14. When the user wishes to change the proposed content, the user enters and sets the link destination etc. that the user wishes to be proposed next time onward. When the proposal change is set, an input is made to the generation AI server 100 requesting a summary of the content on the site for the input access destination URL link, the summary result is obtained by the learning model, and this summary is changed to be the action proposal.

[0030] In this way, the user of the user terminal 20 can automatically obtain appropriate information based on the user's own daily behavioral tendencies.

[0031] Next, the operation of the information processing device 10 according to the present embodiment will be described. Fig. 6 is a flowchart showing an example of an information processing method according to the present embodiment (see Fig. 1 as appropriate).

[0032] The access log storage unit 12 stores input information including information about accesses made by the user of the user terminal 20 to an external network (S10).

[0033] The log analysis unit 13 classifies the input information according to categories, and extracts categories that satisfy predetermined conditions as behavioral tendencies of the user (S11, S12).

[0034] The log analysis unit 13 extracts categories that satisfy a predetermined condition as behavioral tendencies (S12).

[0035] The action suggestion unit 14 suggests an action to the user terminal 20 based on the input information corresponding to the extracted action tendency category (S13).

[0036] According to the information processing device of the embodiment described above, the user's behavioral tendencies are extracted from daily input information including access to external networks by the user of the user terminal, and appropriate behavioral suggestions such as access destinations are made to the user based on the behavioral tendencies, thereby making it possible to make appropriate behavioral suggestions in line with the user's behavioral tendencies.

[0037] The program executed by the information processing device 10 is provided by being pre-installed in a storage circuit such as a ROM. Alternatively, the program may be provided by being stored in a computer-readable storage medium such as a CD-ROM, CD-R, memory card, DVD, or flexible disk as a file in an installable or executable format. The program executed by the information processing device 10 may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network.

[0038] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0039] 10...information processing device, 11...input information receiving unit, 12...access log storage unit, 13...log analysis unit, 14...action suggestion unit, 15...proposal generation unit, 20...user terminal, 100...generation AI server.

Claims

1. an access log storage unit for storing input information including access information of a user of the user terminal to an external network; a log analysis unit that classifies the input information according to a category and extracts the category that satisfies a predetermined condition as a behavioral tendency of the user; a behavior suggestion unit that suggests behaviors to the user terminal based on the input information corresponding to the extracted behavioral tendency category; An information processing device comprising:

2. The access log storage unit stores the time when the user terminal accesses the external network and the location information of the user terminal at the time of access; the action suggestion unit sets a time or a location for which the action suggestion is to be performed based on the access time or the location information; 2. The information processing apparatus according to claim 1,

3. a suggestion generation unit that inputs the input information corresponding to the extracted behavioral tendency category into a learning model that automatically generates answers in accordance with conditions specified by a user under predetermined conditions, and makes action suggestions based on an output result of the learning model; 3. The information processing apparatus according to claim 1, further comprising:

4. storing input information including access information to an external network by a user of the user terminal; classifying the input information according to categories, and extracting the categories that satisfy a predetermined condition as a behavioral tendency of the user; Providing an action suggestion to the user terminal based on the input information corresponding to the extracted category of the behavioral tendency; 13. An information processing method comprising:

5. Computer, A function for storing input information including access information to an external network by a user of the user terminal; A function of classifying the input information according to categories and extracting the categories that satisfy a predetermined condition as a behavioral tendency of the user; a function of making action suggestions to the user terminal based on the input information corresponding to the extracted category of the behavioral tendency; An information processing program characterized by causing the program to function as follows.

Images