Apparatus, method and program for providing personalized updates on AI models

Abstract

To provide a device, a method and a program which can notify a user of interest of a personalized report when an AI model is updated.SOLUTION: An information providing device analyzes an interest of a user to an AI model and information regarding the AI model, and individually creates, when AI model information is updated, a personalized report to be provided to the user who is interested in the AI model on the basis of the interest of the user related to the updated information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an apparatus, method, and program that analyzes information (information processing, content, etc.) about an AI model and individually provides personalized update information to users who have an interest in the AI ​​model. [Background technology]

[0002] The system and method of Patent Document 1 detect changes (updates) in online content and determine whether the updates are meaningful. Whether a content update is meaningful is determined based on the nature of the content itself (e.g., whether it is a meaningful part like a news headline or a meaningless part like an advertisement) and how users have interacted with the content in the past, such as by clicking or zooming on the content. Users can also specify parts of the content to give them meaning.

[0003] The system and method of Patent Document 1 is expected to use technology that automatically analyzes content. If a change in content is determined to be significant, the system notifies the user of what has changed and how much of the content has changed. The user receives a notification on their client device. The notification may include a portion of the content or a visual design to attract the user's attention.

[0004] Non-Patent Document 1 proposes a semi-automated approach to help users understand the differences between two versions of software release notes (notes showing changes made when upgrading software). This approach collects relevant information about the release and automatically creates a list of changes. It then generates release notes targeted at specific readers according to the information required (e.g., by filtering the information to reduce the amount of information). The data displayed can also be based on the general needs of specific readers, such as focusing on technical information for technical users and non-technical information for non-technical users. For example, it is possible to group user stories by episodes or to hide information about user-generated bug reports. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] U.S. Patent No. 9,830,400 [Non-patent literature]

[0006] [Non-Patent Document 1] Sebastian Klepper, Stephan Krusche & Bernd Bruegge, “Semi-Automatic Generation of Audience-Specific Release Notes”, Proceedings of the International Workshop on Continuous Software Evolution and Delivery (CSED), May 2016, pp. 19-22 Summary of the Invention [Problem to be solved by the invention]

[0007] The system and method of Patent Document 1 determine whether a user's interaction with the content (e.g., clicking, zooming, etc.) results in a meaningful change in the content. However, the system and method do not analyze why the user performed that interaction. Furthermore, while the system and method may allow the user to specify something meaningful to the user, the user cannot specify information that does not yet exist, and therefore does not handle entirely new information within the content. Furthermore, the system and method notifies the user of changes to the content, but does not identify the user's interaction that led to the notification.

[0008] The approach of Non-Patent Document 1 provides information at the group level, rather than at the individual user level. As a result, many users in the group receive information, but the information may not necessarily be relevant to each user. Also, as in Patent Document 1, the data displayed to the user includes only what has changed, not the reason why the user is being notified.

[0009] The present invention aims to provide an apparatus, method, and program that can analyze user interests and AI model information regarding an AI model, and, when the AI ​​model is updated, can individually notify users who are interested in the AI ​​model of a personalized report. [Means for solving the problem]

[0010] The information providing device of the present invention analyzes user interests in an AI model and information related to the AI ​​model, and when the AI ​​model information is updated, creates and provides personalized reports individually to users who are interested in the AI ​​model based on the user interests related to the updated AI model information.

[0011] The information providing device may include a first module that generates user interest categories based on user interests in an AI model and assigns the generated interest categories to the user interests; a second module that generates AI model information topics based on information about the AI ​​model and the user interest categories, assigns the interest categories corresponding to the generated AI model information topics, and triggers a report to the user in accordance with an update of AI model information; and a third module that, when the report to the user is triggered, identifies interested users based on the interest categories corresponding to the updated AI model information topics and the user interests corresponding to the interest categories, and creates a personalized report for the identified users.

[0012] In addition, the information provision method of the present invention analyzes user interests in an AI model and information related to the AI ​​model, and when the AI ​​model information is updated, creates and provides personalized reports individually to users who are interested in the AI ​​model based on the user interests related to the updated AI model information.

[0013] The information providing method may include: generating user interest categories based on user interests in an AI model, and assigning the generated interest categories to the user interests; generating AI model information topics based on information about the AI ​​model and the user interest categories, and assigning the interest categories corresponding to the generated AI model information topics, and triggering a report to the user in accordance with an update of AI model information; and when the report to the user is triggered, identifying interested users based on the interest categories corresponding to the updated AI model information topics and the user interests corresponding to the interest categories, and creating a personalized report for the identified users.

[0014] Furthermore, the information providing program according to the present invention may be a program for causing a computer to function as the information providing device described above. [Effects of the Invention]

[0015] According to the present invention, it is possible to provide each user who has an interest in an AI model with a personalized report regarding updates to AI model information, and the user who receives the report can easily understand the relevance of the report to their interest (i.e., why the report was sent to them). [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a diagram illustrating a configuration of an information providing apparatus according to an embodiment. [Figure 2] FIG. 10 is a diagram showing the flow of processing in a first module (module 1) that generates user interest categories in the embodiment. [Figure 3] FIG. 10 is a diagram showing the flow of processing in the initial stage in a second module (module 2) that generates AI model information topics in an embodiment. [Figure 4] FIG. 10 is a diagram illustrating a stage in which the AI ​​model information is updated and module 2 is re-executed in the second module (module 2) that generates AI model information topics in the embodiment. [Figure 5] FIG. 10 is a diagram illustrating a process flow in a third module (module 3) that provides a report to a user in an embodiment. [Figure 6] FIG. 10 is a diagram showing the process flow (continuation of FIG. 5) in a third module (module 3) that provides a report to a user in the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0017] Hereinafter, an example of an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a diagram showing a configuration of an information providing device 10 according to an embodiment. The information providing device 10 receives user interests and AI model information as input data, and outputs (transmits) personalized reports regarding updates to the AI ​​model to each user who has an interest in the AI ​​model. As can be seen from FIG. 1, the information providing device 10 is an information processing device (computer) including a control unit 20, an input unit 30, an output unit 40, a storage unit 50, and repositories 61 to 64.

[0018] The control unit 20 is a part that controls the entire information providing device 10, and realizes processing in each module described below by appropriately reading and executing various programs stored in the storage unit 50. The control unit 20 is not particularly limited, but may be a CPU.

[0019] The memory unit 50 is a storage area for various programs and various data for causing the hardware group to function as the information providing device 10, and may be, but is not limited to, ROM, RAM, flash memory, a hard disk drive (HDD), a solid state drive (SSD), etc.

[0020] A repository means a storehouse or repository, and since the object of storage in the present invention is data, it is a type of storage device. Note that, although four repositories 61 to 64 are shown in Fig. 1, this is for the sake of convenience of explanation, and four physical repositories are not a required configuration, and each repository may be virtual (logical) (for example, included in the storage unit 50).

[0021] From the viewpoint of the data processing flow, the information providing device 10 is composed of at least three software modules (modules 1 to 3 shown in FIGS. 2, 3, and 5). Each module performs processes such as data generation, allocation, and storage, which will be described later. A program describing commands for these processes is stored in the storage unit 50 of the computer, and the CPU of the control unit 20 reads and executes the program. The processing contents (flows) in the three modules 1 to 3 will be explained in detail below.

[0022] <Module 1> 2 is a diagram showing the flow of processing in a first module (module 1) that generates user interest categories. Module 1 performs the following processes: analyzing user interests to generate (define) interest categories; storing (registering) the generated interest categories in the category repository 61; allocating user interests to the generated interest categories to generate a first table; and storing the generated first table in the first repository 62.

[0023] The input to Module 1 is user interests regarding the AI ​​model. Here, user interests include, for example, questions, feedback, comments, etc. from the user related to the AI ​​model. In the initial stage, Module 1 analyzes the input user interests and generates (defines) initial interest categories. This analysis can be performed manually, automatically, or in a hybrid manner. The automatic analysis can be performed, for example, by applying natural language processing technology, without any particular limitation.

[0024] For example, as shown in Figure 2, suppose User A comments to an AI model that generates images, "Interesting app. However, when I select the 'fictional character' style, it sometimes generates naked humans no matter what I do. When I enter 'animal' in the description, it sometimes ends up with three eyes, five legs, or two tails." When this comment is entered into Module 1, it is analyzed as a user interest, and an interest category called "inappropriate images" is generated (defined) in relation to "naked humans no matter what I do" (User A's Interest 1), and an interest category called "dysmorphic" is generated (defined) in relation to "three eyes, five legs, or two tails" (User A's Interest 2).

[0025] Similarly, when User B comments, "Even if I enter the description of a person as 'non-white,' it often ends up being a light-skinned person. Sometimes the person's face looks distorted, and the text is difficult to read," Module 1 generates (defines) "racial issues" in relation to "Even if I enter the description of a person as 'non-white,' it ends up being a light-skinned person" (User B's interest 1), "dysmorphia" in relation to "The person's face looks distorted" (User B's interest 2), and "difficult to read text" in relation to "The text is difficult to read" (User B's interest 3).

[0026] The module 1 stores (registers) the generated (defined) interest categories in the category repository 61 . Once the interest categories are defined, module 1 assigns the interest categories corresponding to user A's interests 1 and 2 and user B's interests 1 to 3, respectively, to generate a table (first table) of user interests x interest categories, and stores the generated first table in the first table repository 62. An example of the first table is shown in the lower right of FIG.

[0027] Module 1 can also be configured to re-run as new user interests are accumulated and entered to generate new interest categories or update existing interest categories. The re-run phase performs the same processing as the initial phase described above.

[0028] The interest categories are defined according to the usage of the AI ​​model. For example, in the case of a health-related AI model that diagnoses diseases, many users may have questions about how the AI ​​model handles elderly patients, resulting in the generation of an interest category called "elderly patients." Also, for an AI model that generates images, many users may want to know whether it can generate images with readable text, which may result in an interest category called "text readability."

[0029] Furthermore, user interests that may appear similar but have some differences may generate one or more interest categories. For example, for an AI model that generates images, many users may want to know whether it can generate images with readable text, but some users may refer to English and others to Japanese. As a result, interest categories such as "text readability," "English text readability," and "Japanese text readability" may be generated.

[0030] <Module 2> 3 is a diagram showing the flow of initial processing in the second module (module 2) that generates AI model information topics. Module 2 performs the following processes: generating AI model information topics from AI model information, storing (registering) the generated AI model information topics in the topic repository 63, generating a second table by assigning which AI model information topic deals with which interest category (which topic corresponds to which category), and storing the generated second table in the second table repository 64.

[0031] The inputs to Module 2 are AI model information and interest categories. Here, AI model information refers to information about the AI ​​model, such as the AI ​​model's performance, training data, allowable uses, limitations, biases, etc. The interest categories are defined in Module 1 and registered in Category Repository 4.

[0032] In the initial stage, Module 2 analyzes existing AI model information and generates (defines) initial AI model information topics, where the AI ​​model information topics are defined according to the use cases of the AI ​​model and user interest categories.

[0033] For example, in the case of a health-related AI model that diagnoses diseases, the AI ​​model information may be categorized into general topics such as "performance" and "application," but in the case of AI model information that specifies "performance" related to elderly people, a more specific AI model information topic such as "performance for elderly people" may be generated (defined) in accordance with the interest category of "elderly people." Also, in the case of an AI model that generates images, the AI ​​model information may be categorized into general topics such as "performance" and "limitations," but if the information includes a reference to generating text, a "text" topic may be created (defined).

[0034] The analysis of AI model information, like the analysis of user interests, can be performed manually, automatically, or a hybrid of both. The automatic analysis can be performed, for example, by applying natural language processing technology, without any particular limitation.

[0035] For example, as shown in Figure 3, assume that the following information is input regarding the limitations of the AI ​​model information: "This model cannot output readable text. This model was trained on a dataset containing adult, violent, and sexual content." When this information is input into Module 2, it is analyzed as the limitations of the AI ​​model, and an AI model information topic called "Text output" is generated (defined) in relation to "Cannot output readable text," and an AI model information topic called "Violent and sexual content" is generated (defined) in relation to "Trained on a dataset containing adult, violent, and sexual content."

[0036] Similarly, with regard to bias in AI model information, when the information "This model may lack consideration for communities and cultures that use minority languages. In addition, Western culture is set as the default, which may affect the output," is input, Module 2 generates (defines) the AI ​​model information topic "language is limited" in relation to "lack of consideration for communities and cultures that use minority languages," and the AI ​​model information topic "Western is the default" in relation to "Western culture is set as the default."

[0037] Module 2 stores (registers) the generated (defined) AI model information topics in the topic repository 63. Here, module 2 stores the registered AI model information topics in the topic repository 63 together with information indicating which part of the AI ​​model information the topics correspond to.

[0038] When the AI ​​model information topic is registered in the topic repository 63, the determination of whether the topic repository shown in Figure 3 has been updated becomes "YES", and the process proceeds to the next step. In the next step, which AI model information topic deals with which interest category (which topic corresponds to which category) is assigned, and a report to the user is triggered (except in the initial stage).

[0039] For example, in the case of the aforementioned health-related AI model that diagnoses diseases, the AI ​​model information topic "Elderly Performance" can be assigned to the corresponding interest category "Elderly." Note that an AI model information topic may correspond to zero interest categories, and vice versa. Also, one or more AI model information topics can be generated from the same piece of AI model information.

[0040] Once the AI ​​model information topics are defined in this way, module 2 assigns which AI model information topics correspond to which interest categories, generates a table of AI model information topics x interest categories (second table), and stores the generated second table in the second table repository 64. An example of the second table is shown in the lower right of Figure 3.

[0041] Module 2 can also be configured to be re-executed when a new version of the AI ​​model is released (when the AI ​​model information is updated) to generate new AI model information topics or update existing AI model information topics. The re-execution stage also performs the same processing as the initial stage described above, but the difference is that in the initial stage, even if the determination of whether the topic repository has been updated is "YES," a report to the user is not triggered, whereas in the re-execution stage, a report to the user is triggered.

[0042] Figure 4 is a diagram illustrating the stage where the AI ​​model information has been updated and module 2 has been re-executed. Comparing it with Figure 3, it can be seen that the AI ​​model information, AI model information topics, and second table have each been updated.

[0043] For example, we can see that the "restriction" that was in the AI ​​model information in the initial stage (Figure 3), "This model cannot output easy-to-read text," has been removed and replaced with the information, "This model can output easy-to-read text." We can also see that a new "restriction" has been added to the AI ​​model information, "Faces and people in general may not be generated properly." As a result, in the AI ​​model information topics, "Text output" has been replaced with "Text output (updated)," "Face generation (new)" has been added, and the corresponding part of the second table has been updated. It can also be seen that a report to the user has been triggered.

[0044] <Module 3> 5 is a diagram showing the process flow of the third module (module 3) that provides a report to the user. Module 3 starts processing when a report to the user is triggered in module 2.

[0045] First, a process is performed to read and reference the second table (a table of AI model information topics x interest categories) from the second table repository 64. In the example embodiment, it is determined that the "text output" topic has been updated and that the "face generation" topic has been registered, and the interest categories corresponding to these topics, namely, "hard to read documents" and "ugly shapes", can be determined.

[0046] Next, a process is performed to read and reference the first table (a table of user interests x interest categories) from the first table repository 62. In the example embodiment, it is determined that the interest category "hard to read documents" is interest 3 for user B, and that the interest category "ugly shapes" is interest 2 for user A, and users A and B are identified as targets for the report. That is, in module 3, based on the interest categories affected by the updated or newly registered AI model information topics, it is determined which users to report to and what their interests are.

[0047] FIG. 6 is a diagram showing the processing flow (continuation of FIG. 5) in the third module (Module 3) that provides reports to users. Module 3 creates a personalized report for each user based on the user's interests identified in the previous processing and the portion of the AI ​​model information related to the updated or newly registered AI model information topic. As described above, Module 2 stores in the topic repository 63 information indicating which portion of the AI ​​model information corresponds to the AI ​​model information topic to be registered. Therefore, the portion of the AI ​​model information related to the updated or newly registered AI model information topic can be identified by referring to the topic repository 63.

[0048] Finally, module 3 sends the report to the identified users at the appropriate time. An example of a report to be sent to each user is shown in the lower right of Figure 6. A report is created for User A stating, "The AI ​​model information has been updated, particularly the text in the section corresponding to the topic 'Face Generation'. This update addresses your 'Interest 2'." Similarly, a report is created for User B stating, "The AI ​​model information has been updated, particularly the text in the section corresponding to the topic 'Text Output'. This update addresses your 'Interest 3'."

[0049] Through the above processing, the information providing device 10 can individually provide personalized reports regarding updates to AI model information to each of user A and user B who have interests in the AI ​​model, and further has the excellent effect of allowing user A and user B who receive the report to easily understand the connection with their interests (i.e., why the report was sent to them).

[0050] Furthermore, this embodiment makes it possible to provide personalized reports regarding updates to AI model information to users who have an interest in AI models, thereby contributing to Goal 9 of the United Nations-led Sustainable Development Goals (SDGs), which is to "Build resilient infrastructure, promote sustainable industrialization and foster innovation."

[0051] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments. Furthermore, the effects described in the above-described embodiments are merely a list of the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments. [Explanation of symbols]

[0052] 1. Module for generating user interest categories 2. Module for generating AI model information topics 3 Modules that provide reports to users 10 Information provision device 20 Control Unit 30 Input section 40 Output section 50 Storage section 61 Category Repositories 62 First Table Repository 63 Topics Repository 64 Second Table Repository

Claims

1. An information providing device that analyzes user interests in an AI model and AI model information related to the AI ​​model, and when the AI ​​model information is updated, individually creates and provides a personalized report to a user who is interested in the AI ​​model based on the user interests related to the updated AI model information, a first module for generating user interest categories based on user interests for an AI model and assigning the generated interest categories to the user interests; a second module that generates AI model information topics based on the AI ​​model information and the user's interest categories, assigns the generated AI model information topics to the corresponding interest categories, and triggers a report to the user according to updates of the AI ​​model information; a third module for identifying an interested user based on interest categories corresponding to the updated AI model information topics and the user's interests corresponding to the interest categories when a report to the user is triggered, and creating a personalized report for the identified user; An information providing device comprising:

2. A computer-implemented information provision method that analyzes user interests in an AI model and AI model information related to the AI ​​model, and when the AI ​​model information is updated, individually creates and provides personalized reports to users who are interested in the AI ​​model based on the user interests related to the updated AI model information, generating user interest categories based on the user's interests for the AI ​​model and assigning the generated interest categories to the user's interests; Generating AI model information topics based on the AI ​​model information and the user's interest categories, allocating the generated AI model information topics to the corresponding interest categories, and triggering a report to the user according to updates of the AI ​​model information; When a report to the user is triggered, identifying an interested user based on interest categories corresponding to the updated AI model information topics and the user's interests corresponding to the interest categories, and creating a personalized report for the identified user; Methods of providing information, including:

3. An information provision program for causing a computer to function as the information provision device described in claim 1.

Images