Device and method

Abstract

The present disclosure makes it possible to provide advice appropriate for a user while suppressing dependency on an electronic device. A prompt generation device 10 according to the present disclosure comprises: an information acquisition unit 11 that acquires user information about a user who uses a terminal 5 (an example of an electronic device) and usage information relating to the user's usage history of the terminal 5; a determination unit 12 that determines, on the basis of the usage information, at least one piece of countermeasure information relating to countermeasures against an addiction to the terminal 5; and a generation unit 14 that generates a prompt to be input to a generation AI model 31 for generating advice information with respect to the addiction, on the basis of the usage information and the countermeasure information.

Description

Apparatus and method

[0001] One aspect of the present disclosure relates to an apparatus and a method.

[0002] Conventionally, techniques for notifying a user when the user is dependent on a smartphone have been disclosed. For example, Patent Literature 1 discloses a communication device that identifies multiple applications that the user has used consecutively based on the application usage history of the mobile device, and outputs advice information notifying the user that the user is dependent on the use of the mobile device based on the application transition status among the identified multiple applications.

[0003] Japanese Patent Application Laid-Open No. 2019-45939

[0004] In order to break free from dependency on electronic devices, users may search for information on countermeasures for electronic device dependency, select an appropriate action for themselves, and then execute that action. Even if a user is notified of their dependency on electronic devices, as in the technology described in Patent Literature 1, the user who receives the notification must perform many processes. As a result, some users may end up ignoring their dependency on electronic devices.

[0005] Therefore, an object of the present disclosure is to provide an apparatus and method that can provide advice tailored to the user while reducing dependency on electronic devices.

[0006] The device disclosed herein includes an information acquisition unit that acquires user information of a user who uses an electronic device and usage information regarding the user's usage history of the electronic device, a determination unit that determines at least one piece of countermeasure information regarding countermeasures for electronic device addiction based on the usage information, and a generation unit that generates a prompt to be input into a generation AI model for generating advice information for addiction based on the user information and the countermeasure information.

[0007] According to one aspect of the present disclosure, it is possible to provide advice tailored to the user while reducing dependency on electronic devices.

[0008] FIG. 1 is a system block diagram showing the configuration of a processing system including an apparatus according to an embodiment of the present disclosure. FIG. 2 is a functional block diagram showing the configuration of an apparatus according to an embodiment of the present disclosure. FIG. 3 is a diagram showing an example of a prompt output by an apparatus according to an embodiment of the present disclosure. FIG. 4 is a diagram showing an example of the configuration of advice information. FIG. 5 is a flowchart showing the procedure of a process for generating advice information by a processing system. FIG. 6 is a system block diagram showing the configuration of a processing system including an apparatus according to another embodiment of the present disclosure. FIG. 7 is a functional block diagram showing the configuration of an apparatus according to another embodiment of the present disclosure. FIG. 8 is a diagram showing an example of a prompt output by an apparatus according to an embodiment of the present disclosure. FIG. 9(a) is a system block diagram showing the configuration of a system according to another embodiment, and FIG. 9(b) is a system block diagram showing the configuration of a system according to another embodiment. FIG. 10 is a diagram showing an example of the hardware configuration of an apparatus according to an embodiment of the present disclosure.

[0009] The present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0010] 1 is a system block diagram showing the configuration of a processing system including an apparatus according to an embodiment of the present disclosure. The processing system 1 shown in FIG. 1 includes a terminal 5, a prompt generation device 10, a dependency-related server device 20, and a model server device 30, which are configured to be able to communicate with each other via a network NW including a wireless communication network and a fixed communication network. The prompt generation device 10 is an example of an apparatus. The prompt generation device 10 constitutes a generation device that determines countermeasure information based on usage information acquired from the terminal 5 and generates advice information based on the user information and the countermeasure information.

[0011] The terminal 5 is an example of an electronic device. The terminal 5 is, for example, a personal computer, a smartphone, a tablet terminal, a feature phone, a server device, a game device, or the like. The terminal 5 is, for example, a device used by a user who intends to use an application. The terminal 5 in this embodiment is, for example, a smartphone. Note that while only one terminal is illustrated in FIG. 1 , the processing system 1 may include any number of terminals 5, two or more. Furthermore, the electronic device is not limited to a terminal, and may be a device capable of providing some kind of notification to a user.

[0012] The terminal 5 has, for example, at least one application. The application is software capable of executing at least one function such as web browsing, social networking services (SNS), communication, games, etc. The application is operated, viewed, and otherwise used by the user. Hereinafter, an application may be simply referred to as an "app."

[0013] The terminal 5 of this embodiment may have installed thereon, for example, an application that executes the functions of the generative AI model 31 described below.

[0014] The dependency-related server device 20 of this embodiment includes a dependency information database 21. The dependency information database 21 stores dependency information as information related to dependency on the terminal 5. The dependency information includes countermeasure information related to countermeasures for dependency on the terminal 5 (electronic device). Addiction on the terminal 5 includes, for example, addiction to electronic devices or apps within electronic devices, such as smartphone addiction and digital addiction.

[0015] Smartphone addiction includes, for example, a state in which one feels stressed when one is not operating terminal 5 or a specific app within terminal 5, a state in which one is unaware while operating terminal 5 or a specific app within terminal 5 that a large amount of time and money is being consumed. More specifically, smartphone addiction includes states such as, for example, "I feel uneasy if I don't have my smartphone at hand," "I think about my smartphone all day and can't help but touch it," "I check my email app or SNS app more than necessary (I feel I have to reply immediately)," "I'm casually surfing the web or watching videos and before I know it, a lot of time has passed," and "I realized I'd spent more than my allowance."

[0016] The countermeasure information included in the addiction information database 21 is, for example, information regarding an approach to the user to alleviate or eliminate the addiction of the terminal 5. The countermeasure information may be information input by an expert on smartphone addiction via the terminal 5 or another terminal. The countermeasure information may be pre-stored in the addiction information database 21 by control of the terminal 5 or another terminal. The countermeasure information may be information obtainable from any web page that contains information regarding countermeasures for smartphone addiction. Note that while only one overall information database is illustrated in FIG. 1, the processing system 1 may include any number of overall information databases, two or more.

[0017] The countermeasure information may include, for example, first countermeasure information on a method for suppressing use of the terminal 5 and second countermeasure information on a method for suggesting user activities in the real world, as a method of approaching the user. The countermeasure information has first countermeasure information and second countermeasure information corresponding to the degree of dependency described below. The first countermeasure information may include, for example, information calling for a reduction in at least one indicator of the usage time of the terminal 5, the number of times at least one function of the terminal 5 is used, and the amount of investment (charge amount) in at least one app in the terminal 5. The first countermeasure information may include, for example, information suggesting treatment by a specialist. The second countermeasure information may include, for example, at least one of real-world event information and store information. The second countermeasure information may include, for example, at least one of real-world event information and store information related to targets other than the terminal 5 and the apps in the terminal 5.

[0018] The dependency information stored in the dependency information database 21 further includes an estimation threshold for estimating the degree of dependency of the user on the terminal 5. The estimation threshold is used to evaluate the degree of dependency indicated by the indicators of the usage history of the electronic device. The estimation threshold can be set for each terminal 5 and each app that can be installed on the terminal 5.

[0019] The estimated threshold is set, for example, according to each indicator of the usage information (usage history). The usage information includes, as the usage history, at least one indicator of the usage time of the terminal 5 (app), the number of times at least one function (app) of the terminal 5 has been used, and the amount of money invested (charged amount) in at least one app in the terminal 5. The usage information of this embodiment includes, as the usage history, at least one of the usage time of at least one app included in the terminal 5 and the number of times at least one app included in the terminal 5 has been launched (number of launches).

[0020] The estimation threshold may include, for example, at least one of a time threshold related to usage time, a count threshold related to the number of activations, and a monetary threshold related to investment amount. The estimation threshold may be determined based on feature quantities such as an average, a median, or a distribution related to indicators of usage history of multiple users. The multiple users may include users who have undergone a diagnostic check for smartphone addiction (digital addiction).

[0021] The model server device 30 shown in FIG. 1 is a device that enables the provision of content using at least one generative AI model. A generative AI model is a model that can generate content in response to a prompt containing input information, according to the instructions and output format indicated by the prompt, and return the content as response information. The prompt can also include input information, in which case the generative AI model generates response information targeted at the input information. The generative AI model may be, for example, an interactive AI that includes a large-scale language model (LLM) and a user interface (UI) for interacting with the user, enabling text or voice chat with the user. Examples of such generative AI include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc. In this embodiment, the model server device 30 is capable of providing content provision functionality using the generative AI model 31 as a large-scale language model.

[0022] The generative AI model 31 may be stored in the model server device 30, or may be stored in another device connected to the model server device 30 via a network and configured to allow information exchange with the user via the model server device 30. The generative AI model 31 may also exist externally (for example, on the cloud). Note that while only one model server device 30 is illustrated in FIG. 1, the processing system 1 may include multiple model server devices 30. The generative AI model 31 has a function of generating advice information. The function of the generative AI model 31 will be described later.

[0023] A Retrieval-Augmented Generation (RAG) system application is installed in the prompt generation device 10, and the RAG system operates. The RAG system is a type of prompt extension technology used for, for example, corporate information linkage of generative AI models (such as LLMs). Specifically, when a generation request is made to a generative AI model using an instruction statement (a sentence input to a prompt) based on a generation request for content, etc., the system searches for related information (reference information) in advance and requests the generative AI model to generate the obtained information together with the instruction statement.

[0024] FIG. 2 is a functional block diagram showing the configuration of an apparatus according to an embodiment of the present disclosure. The prompt generation device 10 of this embodiment shown in FIG. 2 includes, as functional components, an information acquisition unit 11, a determination unit 12, a generation unit 14, and an advice acquisition unit 15. The prompt generation device 10 acquires user information and usage information obtained from the terminal 5, and transmits a prompt including action information determined based on the usage information to the model server device 30. The prompt generation device 10 also accepts response information from the model server device 30 in response to the prompt. This response information includes, for example, advice information. The functions of each functional unit of the prompt generation device 10 will be described in detail below.

[0025] The information acquisition unit 11 acquires user information about the user who uses the terminal 5 and usage information related to the user's usage history of the terminal 5. The user information includes at least one of the user's preference information and attribute information. The preference information includes information such as hobbies, favorite foods, and favorite topics. The preference information includes, for example, "soccer" and "eating local specialties and gourmet foods." The attribute information includes information such as age (age group), gender, address, and career history. The attribute information includes, for example, information such as "in his 30s," "male," and "living in Tokyo."

[0026] The preference information and attribute information may be received through an input operation by the user to the terminal 5. The preference information may be estimated by the terminal 5 or the information acquisition unit 11 based on an app that the user has installed on the terminal 5 and a search history of web pages that the user has searched for using a search engine. The information acquisition unit 11 may acquire information registered in the terminal 5 or an app in the terminal 5 as the attribute information.

[0027] The information acquisition unit 11 of this embodiment acquires usage information related to the usage history of at least one app included in the terminal 5. The information acquisition unit 11 may acquire usage information of multiple apps or usage information of the entire terminal 5.

[0028] The determination unit 12 determines countermeasure information related to countermeasures against addiction of the terminal 5 based on the usage information. The determination unit 12 estimates the user's degree of dependency on the terminal 5 based on the usage information, and determines at least one piece of countermeasure information based on the degree of dependency. The determination unit 12 includes a dependency estimation unit 13. The dependency estimation unit 13 estimates the user's degree of dependency on the terminal 5. Note that the usage information acquired from the terminal 5 by the information acquisition unit 11 may include the user's degree of dependency on the terminal 5 or an app in the terminal 5. In this case, the determination unit 12 does not need to include the dependency estimation unit 13.

[0029] The degree of dependency is a value indicating the degree to which the user desires to use the terminal 5. The degree of dependency on the terminal 5 includes at least one of the degree of dependency on use of the terminal 5 as a whole and the degree of dependency on use of at least one app included in the terminal 5. The dependency estimation unit 13 estimates the degree of dependency of the user on the terminal 5, for example, based on the usage history of at least one or more apps included in the terminal 5. The dependency estimation unit 13 may estimate the degree of dependency of the user on each app, for example, based on the usage history of each app included in the terminal 5. The following describes dependency (addiction) on an app in the terminal 5 as an example.

[0030] The dependency estimation unit 13 estimates the user's dependency on the terminal 5, for example, based on the usage information and an estimation threshold. The dependency estimation unit 13 acquires dependency information related to the terminal 5 from the dependency information database 21. For example, the dependency estimation unit 13 acquires, from the dependency information database 21, an estimation threshold including at least one of a time threshold, a number threshold, and an amount threshold.

[0031] The dependency estimation unit 13 determines that the degree of dependency tends to be higher, for example, when a time ratio, which is the ratio of the usage time of the app to a time threshold, is greater than 1. The dependency estimation unit 13 determines that the degree of dependency tends to be higher, for example, when a launch ratio, which is the ratio of the number of times the app is launched to a count threshold, is greater than 1. The dependency estimation unit 13 determines that the degree of dependency tends to be higher, for example, when an amount ratio, which is the ratio of the amount invested in the app to a amount threshold, is greater than 1.

[0032] The dependency estimation unit 13 may estimate the degree of dependency based on, for example, the magnitudes of the time ratio, the activation ratio, and the monetary amount ratio. For example, the dependency estimation unit 13 may determine that the degree of dependency is high when any of the values ​​of the time ratio, the activation ratio, and the monetary amount ratio is greater than a predetermined first threshold (e.g., "5"). The dependency estimation unit 13 may determine that the degree of dependency is medium when any of the values ​​of the time ratio, the activation ratio, and the monetary amount ratio is greater than a predetermined second threshold (e.g., "1") and equal to or less than the first threshold. The dependency estimation unit 13 may determine that the degree of dependency is low when any of the values ​​of the time ratio, the activation ratio, and the monetary amount ratio is equal to or less than a predetermined third threshold (e.g., "1").

[0033] The dependency estimation unit 13 of this embodiment estimates, for example, based on the usage information and the estimation threshold, that the user's dependency on the terminal 5 is a time ratio of "2.5", a startup ratio of "1.5", and a monetary ratio of "8". Because the monetary ratio is greater than the first threshold of "5", the dependency estimation unit 13 estimates that the user's dependency on the terminal 5 is high. The dependency estimation unit 13 outputs the dependency and an index (here, the monetary ratio) that estimates the dependency.

[0034] As another example, the dependency estimation unit 13 may estimate the dependency based on, for example, the number (types) of time percentages, activation percentages, and monetary percentages that satisfy a condition. For example, if the time percentages, activation percentages, and monetary percentages are greater than a second threshold (e.g., "1"), the dependency estimation unit 13 may determine that the dependency is high. For example, if any two of the time percentages, activation percentages, and monetary percentages are greater than the second threshold (e.g., "1"), the dependency estimation unit 13 may determine that the dependency is medium. For example, if any one of the time percentages, activation percentages, and monetary percentages is greater than the second threshold (e.g., "1"), the dependency estimation unit 13 may determine that the dependency is low. For example, if any one of the time percentages, activation percentages, and monetary percentages is equal to or less than a third threshold (e.g., "1"), the dependency estimation unit 13 may determine that the dependency is extremely low.

[0035] The dependency estimation unit 13 may estimate the dependency based on, for example, the magnitude of each of the time ratio, activation ratio, and monetary ratio, and the number (type) of the time ratio, activation ratio, and monetary ratio that satisfy a condition. Furthermore, the dependency does not need to be expressed in a hierarchy such as high, medium, low, and extremely low as described above. The dependency may be calculated, for example, by a predetermined calculation formula that uses at least one of the time ratio, activation ratio, and monetary ratio as an input variable. The dependency may also be expressed as a numerical value such as a ratio.

[0036] The determination unit 12 determines countermeasure information regarding countermeasures for the addiction of the terminal 5 based on the degree of dependency estimated by the dependency estimation unit 13. The determination unit 12 may determine countermeasure information regarding countermeasures for the addiction of the terminal 5 based on the degree of dependency estimated by the dependency estimation unit 13 and an index that estimates the degree of dependency.

[0037] The determination unit 12 extracts at least one piece of countermeasure information corresponding to the degree of dependency and determines the extracted at least one piece of countermeasure information as countermeasure information corresponding to the user's usage information. For example, the higher the degree of dependency, the more countermeasure information the determination unit 12 may extract that can strongly suppress the user's use of the terminal 5. For example, the higher the degree of dependency, the more countermeasure information the determination unit 12 may extract. In the above example, the determination unit 12 may extract countermeasure information related to the amount based on the fact that the index used to estimate the degree of dependency is the amount ratio.

[0038] The determination unit 12 acquires at least one piece of countermeasure information from the dependency information database 21. For example, if the dependency estimation unit 13 estimates that the user's dependency on the terminal 5 is high based on the monetary ratio, the determination unit 12 extracts first countermeasure information and second countermeasure information from the dependency information database 21. For example, if the dependency estimation unit 13 estimates that the user's dependency on the terminal 5 is medium based on the monetary ratio, the determination unit 12 extracts either the first countermeasure information or the second countermeasure information from the dependency information database 21. For example, if the dependency estimation unit 13 estimates that the user's dependency on the terminal 5 is medium based on the monetary ratio, the determination unit 12 may extract the first countermeasure information from the dependency information database 21. For example, if the dependency estimation unit 13 estimates that the user's dependency on the terminal 5 is low (or extremely low) based on the monetary ratio, the determination unit 12 does not need to extract countermeasure information from the dependency information database 21.

[0039] The method for extracting countermeasure information by the determiner 12 is not limited to the above-described method. For example, the dependency information database 21 may preliminarily assign a dependency label to each of a plurality of countermeasure information. The dependency label is a mark indicating the degree of dependency to which a certain countermeasure information is effective. For example, the dependency information database 21 stores countermeasure information and dependency labels in association with each other. If the dependency estimated by the dependency estimation unit 13 matches the dependency label associated with at least one piece of countermeasure information, the determiner 12 extracts the at least one piece of countermeasure information from the plurality of countermeasure information.

[0040] In the present embodiment, the determining unit 12 extracts at least one piece of countermeasure information from among a plurality of pieces of countermeasure information based on the degree of dependency, but the entity that performs the extraction is not limited to the determining unit 12. For example, a configuration may be adopted in which the generating unit 14, which will be described later, generates a prompt having an instruction to extract countermeasure information and input information including the degree of dependency and a plurality of pieces of countermeasure information, and the generation AI model 31 to which the prompt is input extracts at least one piece of countermeasure information from among a plurality of pieces of countermeasure information based on the degree of dependency.

[0041] The generation unit 14 generates a prompt to be input to a generation AI model 31 for generating advice information for addiction based on user information and countermeasure information. The generation unit 14 outputs a prompt P based on the user information and countermeasure information. The generation unit 14 may, for example, store the prompt P in the model server device 30 or display it on a display device such as a display. The generation unit 14 outputs a prompt that includes, for example, instructions including constraints, an output format, and input information.

[0042] 3 is a diagram illustrating an example of a prompt output by an apparatus according to an embodiment of the present disclosure. As illustrated in FIG. 3, the prompt P includes an instruction to generate advice information, an instruction for an output format, and input information. The prompt P may also include an adjustment condition as a constraint.

[0043] In the example shown in Fig. 3, the generation unit 14 writes a sentence instructing the generation of advice information, "Please generate advice information for measures against smartphone addiction based on the input information," in the hash tag portion of "instructions." Also, in the example shown in Fig. 3, the generation unit 14 writes a sentence instructing the output format of the advice information, "Please generate advice information in text format," in the hash tag portion of "output format."

[0044] The generation unit 14 applies the user information acquired by the information acquisition unit 11, the information on the degree of dependence estimated by the dependence degree estimation unit 13, and the countermeasure information determined by the determination unit 12 to the description in the hashtag portion of the "input information." In the example shown in Fig. 3, the generation unit 14 writes, in the hashtag portion of the "user information," a sentence indicating preference information such as "soccer, local products, B-grade gourmet food" and a sentence indicating attribute information such as "male, in his 30s, residing in Tokyo."

[0045] In the example shown in Figure 3, the generation unit 14 writes a sentence indicating the degree of dependence "high" in the hashtag part of "information related to dependence," a sentence indicating an index estimating the degree of dependence "amount ratio," and a sentence indicating an app related to the degree of dependence "XXX shooting game."

[0046] In the example shown in Figure 3, the generation unit 14 writes, in the hashtag portion of the "Countermeasure Information," sentences indicating first countermeasure information, such as "Reduce charges" and "Use your smartphone in moderation and go out," and sentences indicating second countermeasure information, such as "Prompt treatment is needed," "Go out and make friends," and "Go to an event."

[0047] The generation unit 14 may output a prompt P that instructs the generative AI model 31 to adjust at least one of the content, expression, and content amount of the advice information based on at least one of the user information and the usage information. The generation unit 14 may describe in the prompt P an adjustment condition for adjusting at least one of the content, expression, and content amount of the advice information based on the user information and the usage information.

[0048] For example, the generation unit 14 may adjust the content to include content that is the same as or similar to words and phrases included in the preference information and attribute information from the user information. For example, the generation unit 14 may adjust the way in which the user's preferences are expressed, depending on the preference information from the user information. For example, the generation unit 14 may adjust the amount of content to suit the user's preferences, depending on the preference information from the user information.

[0049] Adjusting the content includes, for example, changing the expression to make the display format of the content of the text easier to read as the dependency level increases. Adjusting the expression includes, for example, changing the expression in the advice information to reduce the degree to which the user is recommended to operate the terminal 5 as the dependency level increases. Adjusting the amount of content includes, for example, adjusting the amount of text.

[0050] In the example shown in FIG. 3 , the generation unit 14 describes, as a constraint condition, an adjustment condition including a correspondence between at least one of the content, expression, and length of text of the advice information and the degree of dependency in the description of the hashtag portion of the "adjustment condition." The generation unit 14 may perform adjustment so that the higher the degree of dependency, the more effective the countermeasure information is for the user. Highly effective for the user means that there is a high possibility that the user's dependency on the terminal 5 can be reduced or eliminated. The generation unit 14 may make the length of text longer so as to indicate that the advice information is more important as the degree of dependency increases.

[0051] The prompt P includes the following statements: "Adjust the advice information so that the more effective the information is estimated to be, the earlier it is notified" and "The higher the degree of dependency, adjust the amount of advice information to be longer" by inserting adjustment conditions into the constraints entry field for the generated AI model 31 by the generation unit 14.

[0052] The advice acquisition unit 15 inputs the prompt P to the generative AI model to acquire advice information. The advice acquisition unit 15 inputs the prompt P output by the generation unit 14 to the generative AI model 31. The advice acquisition unit 15 acquires the advice information output from the generative AI model 31.

[0053] The advice acquisition unit 15 outputs the acquired advice information. The advice acquisition unit 15 outputs the acquired advice information to the terminal 5. The terminal 5 notifies the user of the acquired advice information instead of notifying the user of countermeasure information that can be acquired from the dependency information database 21. Furthermore, the advice acquisition unit 15 may, for example, store the acquired advice information in the dependency information database 21. Note that, although the embodiment shows a form in which the advice acquisition unit 15 acquires advice information output from the generation AI model 31 of the model server device 30 and relays it to the terminal 5, the generation AI model 31 may output the advice information directly to the terminal 5 in accordance with the instructions of the prompt P. In this case, for example, the generation unit 14 describes information about the terminal 5, which is the output destination, as an output condition in the description of the prompt P.

[0054] Here, we will explain the function of generating advice information in the generative AI model 31. The generative AI model 31 generates advice information based on the user information, information related to dependency, countermeasure information, and adjustment conditions included in the prompt P. The advice information includes at least one of first countermeasure information, second countermeasure information, first countermeasure strengthening information, and second countermeasure strengthening information.

[0055] The generative AI model 31 may, for example, generate countermeasure information extracted by the decision unit 12 as the first countermeasure information. Furthermore, the generative AI model 31 may, for example, generate countermeasure information estimated to be highly effective for the user from the countermeasure information extracted by the decision unit 12 based on information regarding the degree of dependency as the second countermeasure information. Furthermore, the generative AI model 31 may, for example, generate first countermeasure strengthening information by combining user information and countermeasure information (first countermeasure information or second countermeasure information). Furthermore, the generative AI model 31 may, for example, generate second countermeasure strengthening information by combining at least one of the countermeasure information (first countermeasure information or second countermeasure information) and the first countermeasure strengthening information with at least one of the countermeasure information (first countermeasure information or second countermeasure information) and the first countermeasure strengthening information.

[0056] For example, the generation AI model 31 may extract, from the countermeasure information, countermeasure information that does not correspond to an app included in the information on dependency, and generate at least one of the second countermeasure information, the first countermeasure strengthening information, and the second countermeasure strengthening information. The generation AI model 31 adjusts the advice information based on, for example, an adjustment condition. Details are described below.

[0057] First, an example of generating second action information will be described. The generation AI model 31 extracts, as the second action information, action information including a phrase highly relevant to information related to the indicator for which the dependency level has been estimated. In the prompt P shown in FIG. 3 , a monetary ratio is input as information related to the indicator for which the dependency level has been estimated. Therefore, the generation AI model 31 extracts, as the second action information, action information such as "Let's reduce charges," which includes the phrase "charges," which is highly relevant to the monetary ratio. Furthermore, as an example of generating second action information, the generation AI model 31 may extract, as the second action information, at least one piece of action information including a phrase highly relevant to information included in the user information.

[0058] Next, an example of generating the first countermeasure reinforcement information will be described. For example, the generation AI model 31 generates the first countermeasure reinforcement information by adding, to the first countermeasure information or the second countermeasure information, highly relevant information contained in the user information and information searched for highly relevant words and phrases contained in the user information using the Web or a database (not shown).

[0059] For example, the generation AI model 31 extracts "Let's go to an event," which is countermeasure information including the phrase "event" that is highly related to "eating local specialties and gourmet foods," which is one piece of preference information included in the user information. Here, for example, if information about apps related to the degree of addiction is included in the preference information of the user information, the generation AI model 31 does not use the information about apps related to the degree of addiction from the user information when generating the first countermeasure reinforcement information, since the information does not contribute to reducing or eliminating the user's addiction.

[0060] For example, the generation AI model 31 combines the concept of "event" contained in the extracted countermeasure information with the concept of "eating local specialties and gourmet foods" from the preference information to search for events related to eating local specialties on the web or in a database (not shown). Here, the generation AI model 31 may also use other preference information and attribute information contained in the user information to perform the search. The generation AI model 31 searches for events related to eating local specialties using "living in Tokyo," which is one piece of attribute information, and the preference information "eating local specialties and gourmet foods." For example, the generation AI model 31 obtains information about a food stall event being held in the square in front of XX Station through a web search.

[0061] For example, the generation AI model 31 adds "food stall event," which is information searched for using the web or the like regarding highly relevant words included in the user information, to the extracted countermeasure information "Let's go to an event," to generate first countermeasure reinforcement information such as "Why not try going to the food stall event in the square in front of XX Station?" The first countermeasure reinforcement information may include specific information about the "food stall event," search results, the URL of the web page, etc.

[0062] Next, an example of generating second countermeasure strengthening information will be described. The generation AI model 31 further extracts other countermeasure information (or first countermeasure strengthening information) that is highly relevant to the countermeasure information (or first countermeasure strengthening information), and generates second countermeasure strengthening information by combining the countermeasure information.

[0063] For example, the generation AI model 31 recognizes the first countermeasure reinforcement information, "Why not try going to the food stall event in the plaza in front of XX Station?", as a phrase representing going out. The generation AI model 31 further extracts another countermeasure information highly related to going out, "Please use your smartphone in moderation when you go out." The generation AI model 31 combines the first countermeasure reinforcement information, "Why not try going to the food stall event in the plaza in front of XX Station?", with the countermeasure information, "Please use your smartphone in moderation when you go out." to generate second countermeasure reinforcement information, "Please use your smartphone in moderation when you go out. For example, please try going to the food stall event in the plaza in front of XX Station."

[0064] The generation AI model 31 adjusts the advice information based on the instructions, output format, and adjustment conditions. The adjustment condition for the prompt P shown in FIG. 3 is a condition for adjusting the information so that the information estimated to be more effective is notified earlier. Therefore, the generation AI model 31 rearranges the information included in the advice information in order of estimated effectiveness. For example, the generation AI model 31 determines that the second countermeasure reinforcement information, the first countermeasure reinforcement information, the second countermeasure reinforcement information, and the first countermeasure information are more effective in this order. The generation AI model 31 determines that the second countermeasure reinforcement information is more effective when the number of elements included in the user information and the countermeasure information that are combined with one piece of countermeasure information is greater. The generation AI model 31 determines that the first countermeasure reinforcement information is more effective when the number of elements included in the user information that are combined with countermeasure information is greater.

[0065] Furthermore, the adjustment condition for the prompt P shown in FIG. 3 is a condition that the amount of text is adjusted to be larger as the degree of dependency increases, and since the condition is that the user's degree of dependency is high, the generation AI model 31 adjusts the amount of text in the advice information to be larger. Adjusting the amount of text includes at least one process such as summarizing the extracted notification content, changing the wording of the notification content, and adding specific information. When the user's degree of dependency is estimated to be high, medium, or low, respectively, the amount of text in the advice information may have a correspondence relationship such as approximately five times the amount of text in the countermeasure information, approximately three times the amount of text in the countermeasure information, or approximately twice the amount of text in the countermeasure information. The amount of text in the advice information may be calculated, for example, using a predetermined calculation formula with the degree of dependency as an input variable.

[0066] 4 is a diagram showing an example of the configuration of advice information. In the example shown in FIG. 4, the advice information AD includes at least first advice information AD1 generated based on countermeasure information. The advice information AD may also include second advice information AD2 including information regarding the degree of dependency.

[0067] 4, the generative AI model 31 describes, as first advice information AD1, second countermeasure reinforcement information such as "Please limit your smartphone use when going out. For example, why not visit a food stall event that is currently being held?", and first countermeasure information such as "Please reduce charges." The first advice information AD1 may also describe information such as a URL that may be included in each of the first countermeasure information, the second countermeasure information, the first countermeasure reinforcement information, and the second countermeasure reinforcement information.

[0068] The second advice information AD2 includes advice content that encourages the user to understand themselves by presenting information regarding the user's dependency on the terminal 5 or the apps in the terminal 5. In the example shown in Fig. 4, the generative AI model 31 writes, as the second advice information AD2, "It is estimated that your dependency on apps is 'high'." The second advice information AD2 may be information that prevents the user from feeling that the first advice information AD1 is presented abruptly.

[0069] The processing procedure performed by the processing system 1 and prompt generation device 10 configured as described above, i.e., the flow of the processing method according to this embodiment, will now be described. Fig. 5 is a flowchart showing the procedures for acquiring each piece of information, determining countermeasure information, generating a prompt, and acquiring advice information.

[0070] In the processing method, first, in step S1, the information acquisition unit 11 acquires user information and usage information from the terminal 5. The information acquisition unit 11 acquires user information and usage information from the terminal 5. The information acquisition unit 11 acquires user input information from the terminal 5 as the user information.

[0071] Next, in step S2, the dependency estimation unit 13 of the determination unit 12 estimates the user's dependency on the terminal 5 based on the usage information acquired by the information acquisition unit 11. The dependency estimation unit 13 of this embodiment acquires dependency information from the dependency information database 21. The dependency estimation unit 13 of this embodiment estimates the dependency based on an estimated threshold included in the dependency information and a usage history included in the usage information.

[0072] Next, in step S3, the determination unit 12 determines countermeasure information based on the estimated dependency. The higher the dependency, the more countermeasure information the determination unit 12 extracts and determines as countermeasure information to be input to the prompt.

[0073] In step S4, the information acquisition unit 11 generates a prompt P to be input to the generation AI model 31, which generates advice information for addiction based on the user information and countermeasure information. The generation unit 14 writes instructions, output conditions, and input information (user information and countermeasure information) in the prompt P. The generation unit 14 may also set adjustment conditions and write them in the prompt P.

[0074] In step S5 , the advice acquisition unit 15 outputs the output prompt P to the generated AI model 31 of the model server device 30 , and inputs the prompt P to the generated AI model 31 .

[0075] In step S6, the advice acquisition unit 15 acquires advice information AD generated by the generative AI model 31. Based on the prompt P input in step S9, the advice acquisition unit 15 acquires advice information AD having first advice information AD1 including at least one of first countermeasure information, second countermeasure information, first countermeasure strengthening information, and second countermeasure strengthening information generated in the generative AI model 31. The generative AI model 31 may acquire advice information AD having second advice information AD2 including information regarding the degree of dependency.

[0076] In step S10, the advice acquisition unit 15 outputs the acquired advice information to the terminal 5 and notifies the user. When step S10 is completed, the processing method by the processing system 1 and the prompt generation device 10 shown in the flowchart of FIG. 5 is terminated.

[0077] Next, the effects of the device and method of the present disclosure will be described with reference to an example of a conventional problem. One possible approach to addressing dependency on electronic devices such as smartphones is to provide advice to users informing them of their dependency on mobile devices. To overcome this dependency, users may need to research information related to addressing dependency, select an appropriate action, and then execute that action. Even if users are notified of their dependency on electronic devices, they must still perform a number of processes upon receiving the notification. As a result, some users may choose to continue their dependency on electronic devices. Therefore, it is necessary to provide advice tailored to the user while suppressing dependency on the terminal 5 (electronic device).

[0078] The prompt generation device 10 (an example of a device) of the present disclosure includes an information acquisition unit 11 that acquires user information about a user who uses a terminal 5 (an example of an electronic device) and usage information regarding the user's usage history of the terminal 5; a determination unit 12 that determines at least one piece of countermeasure information regarding countermeasures for addiction to the terminal 5 based on the usage information; and a generation unit 14 that generates a prompt to be input to a generation AI model for generating advice information AD for addiction based on the user information and the countermeasure information. In this case, the at least one piece of countermeasure information is determined based on the usage information including the usage history of the terminal 5. The advice information AD is generated by inputting a prompt P based on the user information and the at least one piece of countermeasure information into the generation AI model 31. Because the usage information regarding the usage history corresponds to the user's degree of dependence on the terminal 5, the countermeasure information can be determined, for example, corresponding to the degree of dependence. Therefore, the advice information AD can be generated as information corresponding to the user's degree of dependence on the terminal 5. Furthermore, because the advice information AD is based on user information, the prompt generation device 10 can prepare, for example, information corresponding to the degree of dependence as the advice information AD and tailored to the user. Therefore, the processing system 1, the prompt generation device 10, and the above-described processing method provide advice tailored to the user while reducing dependency on the terminal 5 (electronic device).

[0079] The prompt generation device 10 of the present disclosure may further include an advice acquisition unit 15 that outputs the prompt P to the generation AI model 31 and acquires advice information AD. In this case, the advice acquisition unit 15 can prepare information that can be notified to the terminal 5 by acquiring the advice information AD.

[0080] In the prompt generation device 10 of the present disclosure, the user information includes at least one of preference information and attribute information of the user. In this case, advice information can be prepared that is in accordance with at least one of the preference information and attribute information included in the user information.

[0081] Furthermore, in the prompt generation device 10 of the present disclosure, the generation unit 14 may generate the prompt to instruct the generation AI model to adjust at least one of the content, expression, and content amount of the advice information AD based on at least one of user information and the usage information. In this case, at least one of the content, expression, and content amount of the advice information AD is adjusted according to the user information and the usage information, compared to countermeasure information, so that the advice information can be notified to the user via the terminal 5 more effectively.

[0082] Furthermore, in the prompt generation device 10 of the present disclosure, the determination unit may estimate the user's degree of dependency on the electronic device based on the usage information and determine the countermeasure information based on the degree of dependency. In this case, countermeasure information corresponding to the degree of dependency is determined, so that effective advice information can be prepared for the user corresponding to the degree of dependency. Note that the dependency estimation unit 13 of the determination unit 12 does not need to estimate the degree of dependency. In this case, the usage information may include the user's degree of dependency on the terminal 5.

[0083] In the prompt generation device 10 of the present disclosure, the countermeasure information may include at least one of information on a method for suppressing use of the electronic device and information on a method for suggesting activities for the user in the real world. In this case, the advice information is generated based on the user information and the countermeasure information, and therefore a variety of advice information can be generated.

[0084] [Modification] The processing system and device may generate a prompt P so as to generate new advice information based on advice information that has already been generated. Fig. 6 is a block diagram showing the configuration of a processing system including a device according to an embodiment of the present disclosure. In the example shown in Fig. 6, the processing system 1A includes a terminal 5, a prompt generation device 10A, a dependency related server device 20A, and a model server device 30. The dependency related server device 20A of this embodiment differs from the dependency related server device 20 of the above-described embodiment in that it includes a dependency information database 21 and a past information database 22.

[0085] The past information database 22 stores past information. The past information includes advice information that has already been generated and effect information regarding the effect of the advice information on the user. Advice information that has already been generated is referred to as "already-released information." The advice acquisition unit 15 of the prompt generation device 10A outputs the advice information generated by the generation AI model 31 to the terminal 5, and also outputs the advice information to the past information database 22 as already-released information. The past information database 22 stores already-released information.

[0086] The terminal 5 acquires effect information regarding the effect on the user during a post-notification period, which is a predetermined period after the advice information, which is the same information as the previously released information stored in the past information database 22, is notified to the terminal 5. The effect information includes information on at least one indicator included in the usage information. That is, the effect information includes at least one dependency indicator of the usage time of the terminal 5 (app), the number of times at least one function (app) of the terminal 5 is used, and the amount of investment (charge amount) in at least one app in the terminal 5. The terminal 5 acquires each of the above-mentioned dependency indicators during a pre-notification period, which is a period before the advice information is notified to the terminal 5 and is the same length as the post-notification period. The terminal 5 also acquires each of the above-mentioned dependency indicators during the post-notification period.

[0087] The terminal 5 calculates, as an example of effect information, an effect ratio, which is the ratio of each dependency indicator in the pre-notification period to each dependency indicator in the post-notification period. The terminal 5 does not have to calculate the effect ratio of each dependency indicator. In this case, the determination unit 12 may calculate the effect ratio. The terminal 5 outputs effect information including the calculated effect ratio to the past information database 22. The terminal 5 associates previously released information with effect information corresponding to the same advice information as the previously released information, and stores the association information as past information in the past information database 22.

[0088] The past information database 22 further stores expected effect conditions. The expected effect conditions are conditions used when determining whether or not there is an effect for the effect information. The expected effect conditions include an effect threshold, which is a predetermined threshold for the effect rate of each dependent indicator included in the effect information. The effect threshold is, for example, 1. The effect threshold may be set for each dependent indicator. The expected effect conditions may be set by input by a user (administrator) via the terminal 5 or another terminal.

[0089] The expected effect condition, for example, if the effect rate of a certain dependency indicator is less than a threshold, indicates that the dependency indicator (any of the usage time, number of launches, or amount charged) has decreased in the post-notification period compared to the pre-notification period. In other words, if the effect rate of a certain dependency indicator is less than a threshold, indicates that the advice information (existing information) has been effective in reducing or eliminating the user's dependency on the terminal 5. The expected effect condition, for example, if the effect rate of a certain dependency indicator is equal to or greater than a threshold, indicates that the dependency indicator (any of the usage time, number of launches, or amount charged) has increased or remained unchanged in the post-notification period compared to the pre-notification period. In other words, if the effect rate of a certain dependency indicator is equal to or greater than a threshold, indicates that the advice information (existing information) has not been effective in reducing or eliminating the user's dependency on the terminal 5.

[0090] The expected effect condition may indicate that the existing information is effective in reducing or eliminating the user's dependence on the terminal 5 when, for example, the effect percentage included in the effect information is less than the effect threshold for all dependency indicators. The expected effect condition may indicate that the existing information is effective in reducing or eliminating the user's dependence on the terminal 5 when, for at least one dependency indicator, the effect percentage included in the effect information is less than the effect threshold. The expected effect condition may indicate that the existing information is effective in reducing or eliminating the user's dependence on the terminal 5 when, for at least multiple dependency indicators, the effect percentage included in the effect information is less than the effect threshold. Furthermore, the expected effect condition may indicate that the existing information is not effective in reducing or eliminating the user's dependence on the terminal 5 when, for at least one dependency indicator, the effect percentage included in the effect information is equal to or greater than the effect threshold and deviates from the effect threshold by a predetermined value.

[0091] The prompt generation device 10A of this embodiment differs from the prompt generation device 10 of the above-described embodiment in that it generates a prompt P to be input to a generation AI model 31 for generating advice information further based on past information.

[0092] The information acquiring unit 11 acquires past information in addition to the user information, usage information, and countermeasure information. The information acquiring unit 11 acquires past information from the past information database 22. The information acquiring unit 11 further acquires expected effect conditions from the past information database 22.

[0093] 7 is a functional block diagram showing the configuration of a device according to another embodiment of the present disclosure. As shown in FIG. 7, the prompt generation device 10A further includes a determination unit 16. The determination unit 16 determines whether the effect information satisfies predetermined expected effect conditions. The determination unit 16 determines whether the effect ratio of each dependency indicator in the effect information included in the past information acquired by the information acquisition unit 11 is less than the effect threshold included in the expected effect conditions or greater than or equal to the effect threshold.

[0094] The determination unit 16 determines that the effect information satisfies the expected effect condition when the effect ratio of at least one dependent indicator is less than the effect threshold. The determination unit 16 determines that the effect information does not satisfy the expected effect condition when the effect ratio of at least one dependent indicator is equal to or greater than the effect threshold. For example, if the effect ratio of the dependent indicators, time, the effect ratio of the number of activations, and the effect ratio of the billing amount, is 1, the effect threshold included in the expected effect condition is 1, and the determination unit 16 determines that the public information does not satisfy the expected effect condition. The determination unit 16 may detect the dependent indicator with the largest increase in effect ratio among the dependent indicators.

[0095] The function of the determination unit 16 to determine whether the effect information satisfies the predetermined expected effect conditions may be realized by the terminal 5, or may be instructed by a prompt generated by the generation unit 14 and realized by the generation AI model 31. In these cases, the prompt generation device 10A does not need to include the determination unit 16. The prompt may include, as input information, past information including existing information and effect information, and the expected effect conditions.

[0096] The generation unit 14 generates a prompt to be input to the generation AI model 31 for generating advice information, based on the user information, countermeasure information, and past information. When the determination unit 16 determines that the effect information does not satisfy the expected effect condition, the generation unit 14 generates a prompt to be input to the generation AI model 31 for generating advice information different from advice information that has already been generated and is included in the past information, based on the user information, countermeasure information, and past information.

[0097] Generating advice information that is different from advice information (existing information) that has already been generated includes deleting at least one piece of information contained in the existing information, adding at least one piece of information that is not contained in the existing information, etc.

[0098] The generation unit 14 also inputs at least a portion of the past information as input information into the prompt. The generation unit 14 also inputs at least a portion of the past information as input information into the prompt. FIG. 8 is a diagram showing an example of a prompt output by an apparatus according to another embodiment of the present disclosure. In the example shown in FIG. 8, the generation unit 14 enters the existing information acquired by the information acquisition unit 11 and the determination result determined by the determination unit 16 in the prompt PA.

[0099] The generation unit 14 writes the existing information, "Use your smartphone in moderation when going out. For example, why not try going to a food stall event that is currently being held," as second countermeasure strengthening information, and the first countermeasure information, "Keep charges down," in the hashtag portion of the "advice information" of the "past information." The generation unit 14 writes the following in the hashtag portion of the "determination result" of the "past information," as follows: "The effect information does not satisfy the expected effect conditions. In particular, the effect ratio relative to the amount is 1.2, which is an increase compared to the other effect ratios."

[0100] In the example shown in Figure 8, the generation unit 14 enters sentences instructing the generation of advice information in the hashtag portion of "instructions", such as "If the effect information included in the past information results in not satisfying the expected effect conditions, please generate advice information that is different from the existing information," "If the effect information included in the past information results in satisfying the expected effect conditions, you may generate advice information that is the same as the existing information, or you may generate advice information that is different from the existing information," and "Please focus your advice on dependent indicators that have shown a significant increase in the effect rate in the assessment results."

[0101] For example, the generative AI model 31 searches for soccer-related events on the web or in a database (not shown) by combining the concept of "event" included in the extracted countermeasure information with the concept of "soccer" in the preference information, which is different from the concept of "eating local specialties and gourmet foods" in the preference information. The generative AI model 31 searches for soccer-related events using "living in Tokyo," which is one piece of attribute information, and the preference information "soccer." For example, the generative AI model 31 obtains information about a soccer fan interaction event to be held at YY Ground through a web search.

[0102] For example, the generation AI model 31 adds "soccer fan interaction event," which is information searched using the web or the like for highly relevant words contained in the user information, to the extracted countermeasure information "Let's go to an event," and generates the first countermeasure reinforcement information, "Why not go to the soccer fan interaction event being held at YY Ground?"

[0103] For example, the generation AI model 31 recognizes the first countermeasure reinforcement information, "Why don't you go to the soccer fan interaction event being held at YY Ground?", as a phrase representing interaction. The generation AI model 31 further extracts another countermeasure information, "Let's go outside and make friends," that is highly relevant to the interaction. The generation AI model 31 combines the first countermeasure reinforcement information, "Why don't you go to the soccer fan interaction event being held at YY Ground?", with the countermeasure information, "Let's go outside and make friends," to generate second countermeasure reinforcement information, "Let's go outside and make friends. Why don't you go to the soccer fan interaction event being held at YY Ground?"

[0104] The generation AI model 31 generates advice information that differs from the existing information by adding the second countermeasure reinforcement information, "Go out and make friends. Why not go to a soccer fan interaction event being held at YY Ground," to the existing information that includes the second countermeasure reinforcement information, "Use your smartphone in moderation and go out. For example, why not go to a food stall event that is being held," and the first countermeasure information, "Keep your charges down."

[0105] When the determination unit 16 determines that the effect information satisfies the expected effect conditions, the generation unit 14 generates a prompt to be input to the generation AI model 31, based on the user information, countermeasure information, and past information, for generating advice information that is the same as or different from advice information that has already been generated and is included in the past information. In this case, the generation unit 14 may generate a prompt to be input to the generation AI model 31 for generating new advice information that updates the content of the advice information that has already been generated and is included in the past information. The prompt includes a description instructing to update information described in the existing information, or, when information that is the same as or similar to information described in the existing information is detected, to generate advice information to which the information has been added.

[0106] When the determination unit 16 determines that the effect information satisfies the expected effect conditions, the generation unit 14 does not need to generate a prompt to be input to the generation AI model 31 for generating advice information. In this case, the advice acquisition unit 15 may notify the terminal 5 again of the existing information acquired from the past information database 22.

[0107] The processing system 1A and prompt generation device 10A according to the modified example can also provide advice tailored to the user while reducing dependency on the terminal 5. In the processing system 1A and prompt generation device 10A according to the modified example, a prompt PA is generated to be input to a generation AI model 31 that generates advice information based further on past information. This makes it possible to provide effective advice to a user who has already been notified of advice information.

[0108] Furthermore, if the determination unit 16 determines that the effect information does not satisfy the expected effect conditions, the generation unit 14 generates a prompt PA to input to the generation AI model 31, which generates advice information different from the existing information. This makes it possible to prepare advice information different from the existing information that was ineffective, such as advice that the user was not interested in or did not take action on. Therefore, the processing system 1A and the prompt generation device 10A can prepare appropriate advice to reduce or eliminate the user's dependence on the terminal 5.

[0109] Furthermore, when the determination unit 16 determines that the effect information satisfies the expected effect conditions, the generation unit 14 generates a prompt PA to be input to the generation AI model 31, which generates advice information that updates the existing information. As a result, if the user takes action to reduce or eliminate their dependency on the terminal 5 by notifying them of the advice information, it is desirable to continuously suppress the user's dependency on the terminal 5 by continuing to notify them of effective advice information. However, if the content of the advice information is exactly the same as the existing information, it may be found to be ineffective over time or to have not been implemented in the real world, depending on the content of the advice information notified. According to the above-described modified example, the advice information is updated as needed, and appropriate advice information can be prepared for the user in the real world at the stage of generating the prompt PA.

[0110] Note that the processing systems 1 and 1A are not limited to the configurations shown in FIGS. 1 and 6. FIG. 9A is a system block diagram showing the configuration of a system according to another embodiment. As shown in FIG. 9A, in the processing systems 1 and 1A, the terminal 5 may be configured to include the generative AI model 31. This configuration can be realized, for example, by installing an application that executes the functions of the generative AI model 31 and the generative AI model 31 on the terminal 5.

[0111] 9B is a system block diagram showing the configuration of a system according to another embodiment. As shown in FIG. 9B, in the processing system 1, 1A, the terminal 5 may include the prompt generation device 10, 10A and the generation AI model 31. This configuration can be realized, for example, by installing an application that executes the functions of the prompt generation device 10, 10A and an application that executes the functions of the generation AI model 31 on the terminal 5.

[0112] 1, 6, 9(a) and 9(b), the dependency-related server devices 20 and 20A are shown as external servers to the terminal 5, the prompt generation devices 10 and 10A and the model server device 30, but the data (information) stored in the dependency-related server devices 20 and 20A may be included in any of the terminal 5, the prompt generation devices 10 and 10A and the model server device 30. In this case, the dependency-related server devices 20 and 20A do not have to be provided in the processing systems 1 and 1A.

[0113] The device and method of the present disclosure have the following configuration.

[0114] [1] An apparatus comprising: an information acquisition unit that acquires user information of a user who uses an electronic device and usage information regarding the user's usage history of the electronic device; a decision unit that determines at least one piece of countermeasure information regarding a countermeasure for addiction to the electronic device based on the usage information; and a generation unit that generates a prompt to be input into a generation AI model that generates advice information for the addiction based on the user information and the countermeasure information.

[0115] [2] The device according to [1], further comprising an advice acquisition unit that outputs the prompt to the generative AI model and acquires the advice information.

[0116] [3] The device according to [1] or [2], wherein the user information includes at least one of preference information and attribute information of the user.

[0117] [4] The device according to any one of [1] to [3], wherein the generation unit generates the prompt to instruct the generative AI model to adjust at least one of the content, expression, and content amount of the advice information based on at least one of the user information and the usage information.

[0118] [5] The device according to any one of [1] to [4], wherein the determination unit estimates a degree of dependency of the user on the electronic device based on the usage information, and determines the countermeasure information based on the degree of dependency.

[0119] [6] The device according to any of [1] to [5] above, wherein the information acquisition unit further acquires past information including the advice information that has already been generated and effect information regarding the effect of the advice information on the user, and the generation unit generates a prompt to be input to the generation AI model for generating the advice information, based on the user information, the countermeasure information, and the past information.

[0120] [7] The device described in [6] above, further comprising a judgment unit that judges whether the effect information satisfies a predetermined expected effect condition, and when the judgment unit judges that the effect information does not satisfy the expected effect condition, the generation unit generates a prompt to be input to the generation AI model based on the user information, the countermeasure information, and the past information to generate advice information that differs from the advice information that has already been generated and is included in the past information.

[0121] [8] The device described in [6] or [7] above, further comprising a judgment unit that judges whether the effect information satisfies a predetermined expected effect condition, and when the judgment unit judges that the effect information satisfies the expected effect condition, the generation unit generates a prompt to be input to the generation AI model based on the user information, the countermeasure information, and the past information to generate new advice information that updates the content of the advice information that has already been generated and is included in the past information.

[0122] [9] The device according to any one of [1] to [8] above, wherein the countermeasure information includes at least one of information on a method for suppressing use of the electronic device and information on a method for suggesting activities for the user in the real world.

[0123]

[10] A method comprising the steps of: acquiring user information of a user who uses an electronic device and usage information regarding the user's usage history of the electronic device; determining at least one countermeasure information regarding a countermeasure for an addiction to the electronic device based on the usage information; and generating a prompt to be input into a generative AI model for generating advice information for the addiction based on the user information and the countermeasure information.

[0124] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0125] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0126] For example, the prompt generation device 10, 10A, etc., constituting the conversion system according to an embodiment of the present disclosure may function as a computer that performs processing of the control method of the present disclosure. FIG. 10 is a diagram illustrating an example of the hardware configuration of the prompt generation device 10 according to an embodiment of the present disclosure. Although not illustrated in FIG. 10, the prompt generation device 10A may have a similar configuration. The prompt generation device 10 (10A) described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication prompt generation device 1004, an input prompt generation device 1005, an output prompt generation device 1006, a bus 1007, etc. Note that the prompt generation device 10 (10A) may be configured as a computer device including at least one processor such as a CPU or GPU, or may be configured as a computer device including multiple processors or may include multiple computer devices. The terminal 5, the dependency association server device 20, and the model server device 30 may also have a similar hardware configuration.

[0127] In the following description, the term "device" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the prompt generation device 10 (10A) may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

[0128] Each function of the prompt generating device 10 (10A) is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication by the communication prompt generating device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0129] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the information acquisition unit 11, the determination unit 12, the generation unit 14, the advice acquisition unit 15, and the judgment unit 16 described above may be realized by the processor 1001.

[0130] The processor 1001 also loads programs (program code), software modules, data, etc. from at least one of the storage 1003 and the communication prompt generating device 1004 into the memory 1002 and executes various processes in accordance with these programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the information acquisition unit 11, the determination unit 12, the generation unit 14, the advice acquisition unit 15, and the judgment unit 16 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used for other functional blocks. While the above-described various processes have been described as being executed by a single processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented on one or more chips. The programs may also be transmitted over a network via a telecommunications line.

[0131] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a control method according to an embodiment of the present disclosure.

[0132] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0133] The communication prompt generation device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication prompt generation device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the information acquisition unit 11 and the advice acquisition unit 15 described above may be realized by the communication prompt generation device 1004.

[0134] The input prompt generation device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output prompt generation device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input prompt generation device 1005 and the output prompt generation device 1006 may be integrated into one device (e.g., a touch panel).

[0135] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0136] The prompt generation device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by such hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0137] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0138] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0139] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be sent to another device.

[0140] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0141] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0142] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0143] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0144] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0145] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0146] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0147] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0148] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0149] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0150] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0151] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0152] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0153] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0154] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0155] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0156] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0157] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0158] 1, 1A...processing system, 5...terminal, 10, 10A...prompt generation device (an example of a device), 11...information acquisition unit, 12...determination unit, 13...dependency estimation unit, 14...generation unit, 15...advice acquisition unit, 16...judgment unit, 20...dependency-related server device, 21...dependency information database, 22...past information database, 30...model server device, 31...generated AI model, 1001...processor, 1002...memory, 1003...storage, 1004...communication prompt generation device, 1005...input prompt generation device, 1006...output prompt generation device, 1007...bus, P, PA...prompt, AD...advice information.

Claims

1. An apparatus comprising: an information acquisition unit that acquires user information of a user who uses an electronic device and usage information regarding the user's usage history of the electronic device; a decision unit that determines at least one piece of countermeasure information regarding countermeasures for addiction to the electronic device based on the usage information; and a generation unit that generates prompts to be input into a generation AI model for generating advice information for the addiction based on the user information and the countermeasure information.

2. The device of claim 1, further comprising an advice acquisition unit that outputs the prompt to the generative AI model to acquire the advice information.

3. The device according to claim 1, wherein the user information includes at least one of preference information and attribute information of the user.

4. The device of claim 1, wherein the generator generates the prompt to instruct the generative AI model to adjust at least one of the content, expression, and content amount of the advice information based on at least one of the user information and the usage information.

5. The device according to claim 1, wherein the determination unit estimates the degree of dependency of the user on the electronic device based on the usage information, and determines the countermeasure information based on the degree of dependency.

6. The device described in claim 1, wherein the information acquisition unit further acquires past information including the advice information that has already been generated and effect information regarding the effect of the advice information on the user, and the generation unit generates a prompt to be input to the generation AI model for generating the advice information based on the user information, the countermeasure information, and the past information.

7. The device according to claim 6, further comprising a judgment unit that judges whether the effect information satisfies predetermined expected effect conditions, and when the judgment unit judges that the effect information does not satisfy the expected effect conditions, the generation unit generates a prompt to be input to the generation AI model based on the user information, the countermeasure information, and the past information to generate advice information that differs from the advice information that has already been generated and is included in the past information.

8. The device according to claim 6, further comprising a judgment unit that judges whether the effect information satisfies predetermined expected effect conditions, and when the judgment unit judges that the effect information satisfies the expected effect conditions, the generation unit generates a prompt to be input to the generation AI model based on the user information, the countermeasure information, and the past information to generate new advice information that updates the content of the advice information that has already been generated and is included in the past information.

9. The device of claim 1, wherein the countermeasure information includes at least one of information regarding a method for suppressing use of the electronic device and information regarding a method for suggesting activities for the user in the real world.

10. A method comprising the steps of: acquiring user information of a user who uses an electronic device and usage information regarding the user's usage history of the electronic device; determining at least one countermeasure information regarding a countermeasure for an addiction to the electronic device based on the usage information; and generating a prompt to be input into a generative AI model for generating advice information for the addiction based on the user information and the countermeasure information.