Learning model generation method, challenge support system, and program

Abstract

To provide a learning model generation device that generates a learning model that can present a challenge environment where a user's challenge is highly likely achieved.SOLUTION: In a challenge support system, a learning model generation device comprises: an attribute information reference unit 203 that refers to attribute information indicating the attribute of a user who has a challenge to be achieved; an environment condition generation unit 204 that, on the basis of the attribute information, generates a challenge environment condition as an environment condition that is a set of a plurality of environmental elements stored in a storage unit in relation to the environment where the user tackles the challenge; an achievement degree reference unit 208 that refers to the degree of achievement of the challenge when the challenge is executed by the user in the challenge environment condition; a learning data storage unit 209 that stores, in the storage unit 202, a set of the degree of achievement, the challenge environment condition, and the attribute information, as learning data; and a learning model generation unit 210 that, on the basis of the learning data, generates a learning model that is trained to have the attribute information as input and the challenge environment condition as output.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a learning model generation method, a challenge support system, and a program. [Background technology]

[0002] People often have challenges they want to achieve but find it difficult to achieve. There are challenges, for example, walking to maintain and improve health, These include going for a checkup, quitting smoking, studying English conversation, etc.

[0003] As one of these challenges, a team was created to improve exercise habits for the purpose of maintaining and improving health. Patent Document 1 describes a real-time health management and driving test that takes into account the impact on health. It enables users to plan exercises and perform efficient exercises easily. The exercise management device described in Patent Document 1 is a device that adjusts the exercise time to suit the user. The system manages the user's exercise by using an analytical model to derive exercise recommendation information that recommends exercise. do. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 5694206 Summary of the Invention [Problem to be solved by the invention]

[0005] Exercise information including duration, number of steps, and speed in the exercise management device described in Patent Document 1 In this way, the specific challenge content of the exercise plan depends on the achievement of the plan by the user who takes the challenge. This may affect whether or not it is possible.

[0006] The factors related to the achievement of a user's challenge are not only the challenge to be performed but also the In addition, there are factors that are related to the external environment in which the user makes the challenge. It is a factor that influences the motivation to carry out a challenge. Even if the content of the challenge presented to the user is feasible for the user, If users try to challenge in an environment where they lack the motivation to do so, execution will be stagnate. As a result, the challenge may not be achieved.

[0007] Therefore, the present invention provides a challenge environment in which a user is more likely to achieve a challenge. The object of the present invention is to provide a learning model generation device that generates a learning model capable of presenting the above. [Means for solving the problem]

[0008] A learning model generation device according to one aspect of the present invention is a device for generating a learning model for a user having a challenge to be achieved. An attribute information reference unit that references attribute information indicating an attribute, and The challenge is performed in the environment where the challenge is performed. an environmental condition generating unit that generates a range environmental condition; The achievement reference section refers to the achievement level of the challenge when it is executed by the user, and the achievement level and the challenge are recorded. A set of the challenge environmental conditions and the attribute information is stored in a storage unit as learning data. Based on the learning data, attribute information is input, and the challenge environment conditions and achievement level (estimated A learning model generation unit that generates a learning model that is trained to output a . Effect of the Invention

[0009] According to the present invention, a challenge environment in which a user is likely to complete a challenge is provided. It is possible to provide a learning model generation device that generates a presentable learning model. [Brief description of the drawings]

[0010] [Figure 1] 1 is a schematic diagram of a challenge support system according to an embodiment of the present invention. [Diagram 2] FIG. 1 is a block diagram of a learning model generating device according to an embodiment of the present invention. [Diagram 3] FIG. 13 is a diagram illustrating an example of an attribute element according to the embodiment. [Figure 4] FIG. 1 is a diagram illustrating an example of an environmental element according to an embodiment of the present invention. [Diagram 5] FIG. 1 is a diagram illustrating an example of an environmental element according to an embodiment of the present invention. [Figure 6] FIG. 2 is a block diagram of a challenge management device according to the present embodiment. [Figure 7] 13 is an example of challenge information according to the embodiment. [Figure 8] 1 is a diagram illustrating an outline of the processing in the challenge support system according to this embodiment. FIG. [Figure 9] 2 is a diagram illustrating the generation of a first learning model in the learning model generating device according to the present embodiment. FIG. [Figure 10] FIG. 13 is a diagram explaining the generation of a second learning model based on achievement level. [Figure 11] FIG. 13 is a diagram explaining the generation of a second learning model based on acceptance. [Figure 12] A diagram explaining the generation of a second learning model based on input from a user. [Figure 13] 10 is a diagram illustrating an example of challenge management information in a challenge management device. FIG. [Figure 14] 1 is a diagram for explaining an outline of the process of updating the first learning model according to the present embodiment. FIG. [Figure 15]11 is a diagram illustrating another example of challenge management information in the challenge management device. FIG. [Figure 16] 11A to 11C are diagrams illustrating a display process of an estimated achievement level based on attribute information according to the embodiment. [Figure 17] FIG. 11 is a diagram illustrating an example of attribute information. [Figure 18] FIG. 13 is a diagram illustrating an example of a challenge environmental condition. [Figure 19] FIG. 11 is a diagram illustrating an example of attribute information. [Figure 20] FIG. 13 is a diagram illustrating an example of a challenge environmental condition. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] A preferred embodiment of the present invention will be described with reference to the accompanying drawings. , components with the same reference numerals have the same or similar configurations.

[0012] FIG. 1 shows an outline of a challenge support system 10 according to this embodiment. The learning support system 10 includes a learning model generating device 101, user terminals 102a and 102b, and In addition, when there is no particular need to distinguish between the user terminal 10 and the challenge management device 103, 2a and 102b are referred to as user terminals 102. The challenge management device 103 is A configuration device 101 and a user terminal 102 are connected to each other so as to be able to communicate with each other through a network N. do.

[0013] The learning model generating device 101 executes a predetermined program to generate a challenge A learning model that generates environmental conditions for a challenge managed by the management device 103. The learning model generation device 101 is, for example, a server. The environmental conditions and the learning model generation process by the learning model generation device 101 will be described later. do.

[0014] The user terminal 102 executes a predetermined program to operate the challenge management device 1. The user terminals 102a and 102b transmit and receive necessary information regarding the challenge to and from the user terminals 102a and 102b. 02b respectively include communication units 1021a and 1021b and display units 1022a and 1022b. The communication unit 1021 communicates with the challenge management device 103 through the network N. The display unit 1022 displays information acquired from the challenge management device 103 or A screen required for inputting information to be transmitted to the challenge management device 103 is displayed. 02 is, for example, an information processing device such as a smartphone, PC, or tablet. The user terminal 102 is, for example, a smartphone or a tablet, and The challenge management device 103 and Sends and receives information.

[0015] The challenge management device 103 executes a predetermined program to allow a user to enter a challenge. The challenge management device 103 manages the challenges to be fought. Based on the learning model generated by and the user's attribute information, The challenge environmental conditions are associated with a user's challenge to manage the challenge.

[0016] The challenge managed by the challenge management device 103 is, for example, As described in Publication 47, users can transfer their funds to the blockchain network. The funds are deposited on the blockchain and distributed according to whether the challenge is met or not. Alternatively, companies may provide funds to employees and receive rewards based on the results of the challenge. It may be a challenge in which funding is allocated according to the outcome.

[0017] Each part of the learning model generating device 101 will be described with reference to FIG. 2 and FIG. 3 to FIG. 5. FIG. 2 shows a block diagram of the learning model generation device 101. 1 includes a communication unit 201, a storage unit 202, an attribute information reference unit 203, an environmental condition generation unit 204, and an environmental Environment candidate generation unit 205, environment element presentation unit 206, suitability acquisition unit 207, achievement level reference unit 208 , a learning data storage unit 209, and a learning model generation unit 210. Each unit of the learning model generating device 101 uses a storage area such as a memory. The program is stored in the memory area and executed by the processor. It is possible.

[0018] The communication unit 201 is a network for connecting the learning model generating device 101 to an external terminal and an information processing device. Controls communication through work N.

[0019] The storage unit 202 stores various information used in the processing of the learning model generation device 101. The memory unit 202 includes a learning model storage unit 2021, an attribute element memory unit 2022, and an environmental element memory unit 2023. The matching unit 2023 and the matching degree storage unit 2024 .

[0020] The learning model storage unit 2021 stores the learning model M1 generated by the learning model generation device 101. and learning model M2 are stored in the memory. The learning models M1 and M2 will be described later.

[0021] The attribute element storage unit 2022 stores attribute items, which are items in the attribute information indicating the attributes of the user. An example of the attribute items stored in the attribute element storage unit 2022 is shown in FIG. In Figure 3, attribute item A is “basic attributes,” “health,” “personality,” “values,” and “recognition.” There are items such as "knowledge bias," and for each attribute item A, attribute item B is set as a subitem. It is being done.

[0022] By storing the information of each user as a value corresponding to each attribute item B, The attribute information about the object is stored in the learning model generating device 101.

[0023] For example, in the "cognitive bias" category, attribute item B includes "time discounting" and "probability weighting". "," "Risk and loss aversion," "Conformity tendency," and "Sunk cost." The "value of the reward for a certain behavior" item is used to evaluate the future value of the reward compared to its present value. This item is about the tendency to underestimate future values ​​over time. For a given event, it tends to overestimate events that occur with a low probability, while overestimating events that occur with a high probability. The item "Risk and loss aversion" is about the tendency to underestimate the impact of risk. A tendency to avoid the challenges that come with making decisions and to prioritize losses over gains The item "conformity tendency" is about the tendency to make decisions based on the people around you. This item is about the tendency to be influenced by opinions and actions and to take similar actions. The "" item is a desire to seek psychological justification for expenses that are no longer recoverable. In other words, cognitive bias is a term used to describe the tendency to It is a psychological disposition that influences one's actions and judgments about things.

[0024] The environmental element storage unit 2023 stores the external environment of the user when the user performs the challenge. The environmental elements, which are items in the environmental conditions that indicate the environment, are stored in the environmental element storage unit 2023. An example of stored environmental elements is shown in FIGS.

[0025] In Figures 4 and 5, environmental element A is "funder," "challenge method," and "achievement "How to evaluate the level of success," "How to support," "Incentives," "Incentive allocation (successful ) ", "Incentive allocation (when failure occurs)" and "Progress display in the app" elements. do.

[0026] In addition, environmental element B is a sub-item for each environmental element A, and is a requirement corresponding to each environmental element A. Environmental element C is a subitem for each environmental element B, and corresponds to each environmental element B. element.

[0027] The "funder" is the provider of the funds for the incentives that arise when the challenge is achieved. For example, you can have yourself, your family, or associates in your business provide the funds. do.

[0028] The "challenge method" indicates how the user will tackle the challenge. For example, When environmental element B is "yourself," you judge your achievement based on your own results. In addition, when environmental element B is "competition," the achievement judgment is based on the results of other users. Figure 4 shows a case where a company offers multiple challenges as part of employee benefits. In the case where the program is provided to employees of the same department, the elements of "intra-department" and "inter-department" are included in the environmental element C. For example, if the challenge method is "competition" and "within the department," In this way, the members of the department will take on a common challenge, and each member will be ranked according to their ranking. If the number of points reaches a certain level, the challenge is deemed to be complete. , and compete in teams consisting of at least one member. In addition, when environmental element B is "cooperation," multiple people do not compete, but each Each member will carry out their own challenge, with the goal of achieving everyone's challenge. In other words, if even one person fails, the challenge for everyone will be considered a failure. .

[0029] "Method of evaluating achievement" indicates the method of evaluating the achievement of the challenge. For example, There is a challenge to walk a certain number of steps per day for a certain number of days over a certain period of time. In this case, the following are examples of methods for evaluating the degree of achievement: (A): The number of days achieved is counted as the number of days to complete the challenge. Calculate the achievement level by dividing the achievement level by the range period, i.e., (Number of days achieved) / (Number of days specified) x (B): The number of steps recorded for each day is calculated based on the number of steps recorded for each day. The record with the largest number of steps is referenced, and the total number of steps is calculated as the total number of steps if the goal is achieved. A method of calculating the degree of achievement by dividing by.

[0030] For example, let's say there is a challenge to "walk 8,000 steps or more per day for 20 or more days in 30 days." Here, during the period, 10 days will be 4000 steps, 10 days will be 6000 steps, and 10 days will be 1000 steps. In this case, according to the above method (A), the achievement level is (10 days) / (20 days) × 100 = 50%. Also, according to the above (B) method, the total number of steps is 8000 × Considering that 20 is 160,000 steps, (6,000 steps x 10 days + 8,000 steps x 10 days) / 160,000 steps = 87.5%.

[0031] Also, other evaluation methods can be used if the challenge is different. For example, 100 Let's say there is a challenge to improve the time of the meter dash. In this case, the evaluation method is the time. The degree of achievement is evaluated by the reduction rate of the time. Specifically, (reduced number of seconds) / (initial number of seconds) x The achievement level is calculated as 100. For example, if a person has a 100 meter sprint time of 15.0 seconds, If the time is reduced to 14.5 seconds, the time reduction rate (achievement level) = 0.5 seconds / 15.0 seconds = 3.3 The result is %.

[0032] Such an "achievement evaluation method" is stored as an environmental element C. Two environmental factors, Method A and Method B, corresponding to Methods (A) and (B), are shown. Evaluation methods can be added or changed appropriately depending on the challenge. " is not changed for each user, but is set in advance for each challenge in the challenge information described later in FIG. The method may be such that a common method of evaluating the achievement level is used for each user. .

[0033] "How to support" is a section that allows users to choose "supporters", "support methods", and "responses" to support their challenges. The various options shown in Figure 4 are set as environmental element C. It is being done.

[0034] The “incentive” in Figure 5 is the incentive that can be acquired when a user completes a challenge. This sets the "type," "amount," and "decrease in value over time" of the sentiv. In the "Type" category, the form of incentive provision is set as environmental element C. " is an incentive that is provided to a company in order to promote the environment. This is set as element C. "Diminishment of value over time" is the effect of the challenge being completed slowly. This is an environmental element that sets incentives to be reduced if For example, for environmental factor C, the responses were "Does not decrease," "Decreases (20% / week)," and "Decreases There is an element of "Decrease (50% / week)". Here, "Decrease (20% / week)" means, for example, 4 If there is a weekly challenge, the incentive amount will be The incentive is reduced by 20% of the initial amount over time. By making the user take the challenge, it is possible to motivate the user to take the challenge positively.

[0035] "Incentive allocation (successful)" and "Incentive allocation (failed)" are incentive allocations. The various options shown in Figure 5 are used to determine the environmental factors. It is designated as C.

[0036] "Progress display in app" refers to the progress display in the app installed on each user's device. This sets the display mode for your challenge progress. Environmental elements are provided to set the display mode. Some people feel motivated when they see the progress being made.

[0037] "Products and services used" are the products and services used to complete the challenge. As an example, consider environmental element C "supplements" and "exercise support" in environmental element B. For example, a training menu for weight loss is provided. The challenge recommends that users use the following proteins during the challenge: Included in the environment as a supplement or in 10 minutes of strength training once a day This menu is included in the environmental conditions.

[0038] When a mail-order company recommends products to a customer, the customer If you can recommend the best product, it will lead to a purchase. Even if you don't feel that the product is valuable, by continuing to use it, you can improve your weight. If this has the effect of reducing the number of purchases, the reliability of the mail order company's recommendations will increase, and the customer will be more likely to make a purchase. It is not just a user's temporary evaluation of a product, but also the user's experience using the product. The product recommendations that take into account the value that the user can get are optimal for the user. It can be said that there is.

[0039] For example, if user A with certain attributes takes Protein A and does 10 minutes of strength training once a day, When a person performs a weight loss program, the achievement rate of a certain goal (e.g., losing 2 kg of weight) is 80% (weight If the user A's weight is reduced by 1.6 kg, the online shopping company can sell the product to user B who has the same attributes as user A. In contrast, User A took Protein A and did 10 minutes of strength training once a day. If User B is recommended, he / she may be able to lose weight, and User B's satisfaction will be improved. It can be said that this is a recommendation with a high degree of familiarity. You may inform the patient that achievement is estimated at 80% of the target weight loss of 2 kg.

[0040] If User B's actual weight loss is 1.8 kg, the achievement rate is 90%. B's attributes, challenge environment conditions (supplement A intake, 10 minutes of strength training once a day) It is possible to train a learning model using training data with a 90% success rate. In this way, users can easily create and share their own evidence based on real challenges that many other users have performed. The recommendations are calculated based on the customer's experience, so you won't be overly distracted by product designs or advertisements. This will help customers achieve the value they are looking for, ultimately resulting in high customer satisfaction. degree is obtained.

[0041] The combination of each environmental element C creates the environmental conditions for a given challenge. In addition, the environmental conditions do not need to include all environmental elements C that correspond to all environmental elements A. It may be information that partially includes environmental elements.

[0042] Furthermore, the items in the environmental elements C are merely examples and are not limited to those shown here. For example, the allocation of "incentives" shown in Figure 5 can be calculated in smaller monetary units. In addition, the item of "incentive distribution" may be included here. The allocation ratio is not limited to the one shown in the example. Furthermore, it is possible to allocate the shares to more parties than just two people. It may be possible to set up incentive allocation between the users and the app. Regarding "Progress display in environmental element B", Regarding the display method in C, items other than those shown here may be provided.

[0043] The compatibility memory unit 2024 stores compatibility and The attribute information and environmental condition candidates associated with the degree of suitability are stored as learning data.

[0044] The attribute information reference unit 203 acquires user attribute information from the user terminal 102. Alternatively, the attribute information reference unit 203 may be an information processing device (not shown) that stores and manages user attribute information. The system accesses the network (shown in the figure) via network N and obtains the attribute information of the target user.

[0045] The environmental condition generating unit 204 generates environmental requirements regarding the environment in which the challenge is performed based on the attribute information. A challenge environment is an environmental condition that is a set of multiple environmental elements stored in the element memory unit 2023. The environmental condition generating unit 204 receives attribute information and outputs environmental conditions. Based on the learning model M2 learned as above and stored in the learning model storage unit 2021, Generate range environmental conditions.

[0046] The environment candidate generating unit 205 refers to a plurality of environmental elements to generate an environmental condition including a plurality of environmental conditions. The environment candidate generation unit 205 functions in the generation process of the learning model M2. It is a part.

[0047] The environmental element presentation unit 206 refers to a plurality of environmental elements and presents the plurality of environmental elements to the user. The environmental element presentation unit 206 displays each environmental element on the display unit 1022 of the user terminal 102. The information used to generate a screen for the user terminal 102 is generated and transmitted to the user terminal 102.

[0048] The suitability acquisition unit 207 acquires the plurality of environmental condition candidates from the users involved in the generation of the learning model M2. and matching the challenge of the user to the user under multiple candidate environmental conditions. The fitness is the degree of fitness of a user who is presented with a certain challenge environment condition. The degree of achievement when actually performing a challenge under the range of environmental conditions or the degree of achievement when actually performing a challenge under the range of environmental conditions Acceptance indicates the extent to which a user can accept a problem and be convinced to take on the challenge. degrees.

[0049] The achievement level reference unit 208 accesses the challenge management device 103 through the communication unit 201. By doing so, the achievement level managed by the challenge management device 103 is referred to. The achievement level calculated from the results of the user's actual challenge (actual achievement level) and the estimated achievement level described below. The achievement level referred to by the achievement level reference unit 208 is the actual achievement level. It is the degree of maturity.

[0050] The learning data storage unit 209 stores the set of the achievement level, the challenge environmental condition, and the attribute information as learning data. The learning data stored in the learning data storage unit 209 is stored in the memory unit 202 as learning data. The data is used to generate a learning model M1.

[0051] The learning model generation unit 210 receives attribute information based on the learning data and generates a challenge A learning model M1 is generated that is trained to output the environmental conditions and the estimated achievement level.

[0052] In addition, the learning model generation unit 210 uses the environmental condition candidates, the suitability, and the attribute information as learning data. The system is trained to use attribute information as input and challenge environmental conditions as output. The generation process of the learning models M1 and M2 will be described later. If the degree of conformance is the degree of achievement, M1 and M2 are the same.

[0053] FIG. 6 shows a block diagram of the challenge management device 103. 03 includes a communication unit 601, a storage unit 602, an attribute information reference unit 603, and a challenge environment condition acquisition unit. The challenge management device includes a challenge management unit 604, a judgment information acquisition unit 605, and an achievement level calculation unit 606. Each unit of the challenge management device 103 uses a storage area such as a memory in the challenge management device 103. The processor executes the programs stored in the memory area. It can be realized.

[0054] The communication unit 601 is a network for connecting the challenge management device 103 to an external terminal and an information processing device. Controls communication through work N.

[0055] The storage unit 602 stores various information used in the processing by the challenge management device 103. The memory unit 602 includes a challenge memory unit 6021 and a model storage unit 6022.

[0056] The challenge storage unit 6021 stores challenge information as shown in FIG. The user submits these challenges to the environmental conditions set by the challenge management device 103. The challenge information includes the method of evaluating the achievement of each challenge. In addition, the model storage unit 6022 may store the learning model generation device 101. The learning model M1 generated by the above is acquired from the learning model generating device 101 and stored. can be.

[0057] The attribute information reference unit 603 acquires the attribute information of the user. The attribute information of the user is acquired from the user terminal 102. Alternatively, the attribute information reference unit 603 The user's attribute information is then transmitted to an information processing device (not shown) that stores and manages the user's attribute information through a network N. The target user's attribute information is obtained by accessing the

[0058] The challenge environment condition acquisition unit 604 inputs the user's attribute information into the learning model M1, Obtain the user's challenge environmental conditions.

[0059] The judgment information acquisition unit 605 is configured to acquire the judgment information of a user who executes a challenge for which the challenge environment conditions are set. The judgment information used to judge achievement, including the calculation of the achievement level of the challenge, is acquired. For example, In the case of a challenge related to the number of steps, the number of steps is obtained from the user terminal 102. For example, the user terminal 102 is a smartphone equipped with a step counting function. In addition, the determination information can be used in a device other than the user terminal 102. For example, the user who executes the challenge may be a user other than the user who executes the challenge. When making a judgment, judgment information can be obtained from a terminal of the judge or judgment organization.

[0060] The achievement level calculation unit 606 calculates, based on the achievement level evaluation method included in the challenge environmental conditions, Calculate the user's challenge completion level.

[0061] 8 and 9 to 11, the learning model M in the learning model generating device 101 is The generation process of 2 will be explained below.

[0062] In step S801, the attribute information reference unit 203 reads the attribute information stored in the attribute element storage unit 2022. Based on the attribute elements specified in the user profile, attribute information of the user is acquired.

[0063] In step S802, the environmental condition generating unit 204 reads the environmental Get the boundary element.

[0064] In step S803, the compatibility acquisition unit 207 acquires the compatibility as the achievement level. This determination is based on information preset by the administrator of the learning model generation device 101. This is based on.

[0065] If the determination in step S803 is affirmative, in step S804, 205 generates multiple candidate environmental conditions by generating random environmental conditions based on environmental factors. Generate.

[0066] In step S805, the compatibility acquisition unit 207 displays the generated environmental condition candidates to the user. The challenge is transmitted to the terminal 102 and the challenge management device 103 .

[0067] In step S806, the compatibility acquisition unit 207 receives the user's score for each of the environmental condition candidates. The achievement level calculated by the challenge management device 103 as a result of executing the challenge is Obtained for each candidate environmental condition.

[0068] In step S807, the compatibility acquisition unit 207 acquires the achievement level as the compatibility level and the environmental conditions. The combination of the candidate and the attribute information is stored as learning data in the compatibility memory unit 2024. A predetermined threshold may be set, and the storage target of the learning data may be determined based on the threshold. For example, a minimum achievement level is set as a predetermined threshold, and if the achievement level exceeds the minimum achievement level, If the number of samples is more than 100, the samples may be stored as learning data. From the perspective of preventing injuries during the 100m sprint, the challenge of "getting injured during the 100m sprint" The goal of the training is to achieve a 5% or lower success rate for the "100m sprint injury" challenge. The environmental conditions may be output. In this case, the achievement level is set to a predetermined threshold value, i.e., the highest achievement level. If the achievement level does not exceed the maximum achievement level, the data will be stored as learning data. It may be so arranged.

[0069] If a negative determination is made in step S803, the conformity acquisition unit 20 7 judges whether or not to obtain the degree of suitability as the user's acceptance of the environmental conditions.

[0070] If the determination in step S808 is affirmative, then in step S809, The generating unit 205 generates a random environmental condition based on the environmental elements to generate an environmental condition candidate. Generate.

[0071] In step S810, the compatibility acquisition unit 207 displays the generated environmental condition candidates to the user. The candidate environmental conditions are then transmitted to the terminal 102. Here, it is necessary to transmit the candidate environmental conditions to the challenge management device 103. The reason why it is not necessary is that the acceptability is based on the subjective judgment of the user, and the challenge management device This is because there is no need to use the achievement level calculated by 103.

[0072] In step S811, the compatibility acquisition unit 207 receives each environmental condition from the user terminal 102. The acceptability of the candidate is acquired. To acquire the acceptability, the user terminal 102 displays the acceptability on the display unit 102. 2 displays the environmental conditions and allows the user to input the degree of acceptability for those environmental conditions. Good too.

[0073] In step S812, the compatibility acquisition unit 207 acquires the acceptability as the compatibility and the environmental conditions. The combination of the candidate and the attribute information is stored in the compatibility storage unit 2024 as learning data.

[0074] If the determination in step S808 is negative, the environmental element proposal is performed in step S813. The display unit 206 refers to the environmental element storage unit 2023 and displays a list of environmental elements on the user terminal 102. Send.

[0075] In step S814, the compatibility acquisition unit 207 uses the environment displayed on the user terminal 102 The environmental conditions created by the user selecting environmental elements are acquired from the user terminal 102. do.

[0076] In step S815, the compatibility acquisition unit 207 compares the attribute information with the acquired environmental conditions. The set is stored in the compatibility storage unit 2024 as learning data.

[0077] In step S816, the learning model generation unit 210 generates a learning model based on the stored learning data. To generate the learning model M2, we use a general machine learning method. For example, the learning model M2 takes attribute information as input, and A neural network that outputs achievement or acceptance is generated based on the training data. The generation of learning model M1, which will be described later, is the same as the generation of learning model M2. Using a similar method, a generation method is adopted that inputs attribute information and outputs achievement levels. The generated learning model is stored in the learning model storage unit 2021. For each challenge, the rule M2 determines the attribute information of the user who makes the challenge. and configured to output a challenge environmental condition.

[0078] Figure 9 shows the environmental condition candidates and achievement scores for a given challenge when the fitness is the achievement score. The candidate environmental conditions are environmental condition A, environmental condition B, and environmental condition C. In addition, some of the environmental elements are exemplified for each environmental condition. In FIG. 9, The actual completion of the challenge will be recorded.

[0079] In addition, environmental factors include the training required to achieve the challenge depending on the challenge content. For example, if the challenge is a 100 meter sprint, If the goal is to shorten the training period, environmental conditions including the necessary strength training items as environmental factors should be considered. A case may be generated.

[0080] FIG. 10 shows the results of the analysis of the environmental conditions and the information indicating the acceptability when the suitability is the acceptability. FIG. 11 shows an example of information when environmental conditions are acquired based on a user's selection. In the case of Figure 11, since it is based on user selection, the acceptability is set to 100% for convenience. is doing.

[0081] Referring to FIG. 12, the process up to generation of the learning model M1 in the challenge support system 10 is Here, a challenge is made by a user who operates the user terminal 102a. It shall be deemed to be.

[0082] In step S1201, the learning model generating device 101 performs the above-mentioned learning model M2 Perform the generation process.

[0083] In step S1202, the attribute information reference unit 603 receives the user's The information and attribute information of the challenge that the user is about to take on is acquired. The information is information for identifying the content of the challenge that the user will attempt.

[0084] Based on the information acquired by the attribute information reference unit 603, the challenge record of the challenge management device The challenge management information stored in the memory 6021 is updated. An example of logical information is shown.

[0085] The challenge management information includes "user name," "user ID," "attribute information," and "challenge The items are "Challenge ID", "Challenge Name", "Challenge Environmental Conditions", and "Level of Attainment".

[0086] "User name" is the user's name or nickname, etc. "User ID" is the user's "Attribute information" is the attribute information of each user. "Challenge I "D" is an ID to identify each challenge. "Challenge Name" is the ID shown in Figure 7. The challenge name of the challenge information. Each user will be assigned a challenge based on the challenge name. The content of the challenge is identified. The "challenge environment conditions" are based on the attribute information of each user. Here, the environmental conditions are generated based on the "challenge ID" generated by the process in Fig. 12. If challenges from "CID001" to "CID004" are generated, The environmental conditions are generated using the learning model M2. The "achievement level" is the degree of each challenge. The degree of achievement is calculated based on the judgment information when the above is executed.

[0087] Information regarding the challenge acquired by the attribute information reference unit 603 in step S1202 Based on the attribute information, "user name", "user ID", "attribute information", "challenge The following information will be recorded: "User name", "Challenge ID", etc.

[0088] In step S1203, the challenge environment condition acquisition unit 604 executes a learning model generation device. In step S1204, the device 101 transmits information related to the challenge and attribute information. Based on the acquired challenge-related information and attribute information, the environmental condition generation unit 204 , and generate the challenge environment conditions using the learning model M2. Here, in the learning model M2, takes the user's attribute information as input and outputs the environmental conditions with the highest degree of suitability. A challenge environmental condition is generated.

[0089] In step S1205, the challenge environment condition acquisition unit 604 The challenge environment condition acquisition unit 604 acquires the challenge environment condition. Based on the conditions, the contents of the "challenge environmental conditions" in the challenge management information are recorded.

[0090] In step S1206, the challenge environmental condition acquisition unit 604 acquires the challenge environmental conditions. In step S1207, the user sends the challenge to the user terminal 102a. The judgment information when the challenge is executed under the environmental conditions is acquired by the user terminal 102a. will be done.

[0091] In step S1208, the determination information acquisition unit 605 receives the determination information from the user terminal 102a. In step S1209, the achievement level calculation unit 606 acquires the achievement level based on the judgment information. The calculated achievement level is recorded in the challenge management information for the target challenge. It is stored in association with the range.

[0092] The determination information acquisition unit 605 acquires the determination information from a terminal other than the user terminal 102a. In this case, the challenge environment condition acquisition unit 604 may The challenge environment conditions are transmitted to the user terminal 102a, and the conditions are displayed on the user terminal 102a. However, the information required for the judgment may not be acquired. This is because the update of the learning model M1 described later The same applies to the new process.

[0093] In step S1210, the achievement level reference unit 208 receives the achievement level from the challenge management device 103. Get achievements.

[0094] In step S1211, the learning data storage unit 209 stores the achievement level, the challenge environment conditions, and the The set of the items and attribute information is stored as learning data in the storage unit 202. A value may be set, and the storage target of the learning data may be determined based on the threshold value. For example, The achievement level is set to a minimum achievement level or a maximum achievement level as a predetermined threshold, and the achievement level is set to a minimum achievement level. If the level of achievement is exceeded or not exceeded, the data will be stored as learning data. It may also be.

[0095] The above process is carried out by a plurality of users other than the user who operates the user terminal 102a. In step S1211, the learning model generation unit 210 A learning model M1 is generated using the training data collected from each user.

[0096] In step S1213, the learning model generation unit 210 sends the In step S1214, the challenge management The device 103 acquires information about the learning model M1 through the communication unit 601 and stores it in the model storage unit The learning model M1 is stored in 6022.

[0097] In this example, the generation of the learning model M1 is explained using the learning model M2. However, the learning model M1, for example, does not use the learning model M2, and the The target may be generated based on environmental conditions.

[0098] The learning data stored in the memory unit 202 by the learning data storage unit 209 may include, for example, This may include external information such as generational achievement averages used to assess maturity. stomach.

[0099] FIG. 14 shows a learning model M1 generated by the learning model generating device 101 using the learning model M2. FIG. 1 is a diagram illustrating the process of relearning the learning model M1 when the learning model M1 has been generated. In this case, the learning model M1 is stored in the model storage unit 6022. Explains how the user who operates the terminal 102b updates the learning model M1 by performing a challenge. do.

[0100] In step S1401, the attribute information reference unit 603 receives the user's The information and attribute information regarding the challenge that the user will attempt is obtained.

[0101] Information regarding the challenge acquired by the attribute information reference unit 603 in step S1401 Based on the attribute information, "user name", "user ID", "attribute information", "challenge The attribute information reference unit 603 records each of the contents, such as "name", "challenge ID", and "password". By recording a new challenge, a new challenge is added to the challenge management information. An example of the challenge management information after the challenge is generated is shown in FIG.

[0102] In step S1402, the challenge environmental condition acquisition unit 604 acquires the model Using the learning model M1 stored in 22, a challenge is made based on the user's attribute information. Here, the learning model M1 takes the user's attribute information as input and The environmental conditions with the highest achievement rate and the estimated achievement rate are output. The challenge environmental condition acquisition unit 604 acquires a challenge environmental condition based on the generated challenge environmental condition. Based on this, the contents of the "challenge environmental conditions" of the challenge management information are recorded.

[0103] In step S1403, the challenge environment condition acquisition unit 604 acquires the challenge environment conditions. In step S1404, the user sends the challenge to the user terminal 102b. The judgment information when the challenge is executed under the environmental conditions is acquired by the user terminal 102b. will be done.

[0104] In step S1405, the determination information acquisition unit 605 receives the determination information from the user terminal 102b. In step S1406, the achievement level calculation unit 606 acquires the achievement level based on the judgment information. The calculated achievement level is recorded in the challenge management information for the target challenge. It is stored in association with the range.

[0105] In step S1407, the achievement level reference unit 208 receives the achievement level from the challenge management device 103. Information about the challenge, attribute information, challenge environmental conditions, and achievement level are obtained.

[0106] In step S1408, the learning data storage unit 209 stores the achievement level, the challenge environment conditions, and the The set of the items and attribute information is stored as new learning data for the learning model M1. A certain threshold may be set, and the storage target of the learning data may be determined based on the threshold. For example, a minimum or maximum achievement level is set as a predetermined threshold for the achievement level, and the achievement level is set to the minimum. If the low achievement level is exceeded or the highest achievement level is not exceeded, the data will be stored as learning data. It may be arranged so that

[0107] The above process is carried out by a plurality of users other than the user who operates the user terminal 102b. In step S1409, the new The learning model M1 can be updated using the new learning data.

[0108] In step S1410, the learning model generation unit 210 sends the In step S1411, the challenge management The device 103 acquires information about the learning model M1 through the communication unit 601 and stores it in the model storage unit The learning model M1 is stored in 6022.

[0109] A challenge environment condition may be generated based on the user's attribute information. Instead, multiple challenge environmental conditions may be generated. For example, a learning model M1 generates a challenge environment condition. In the case where A0 is generated, the challenge environmental condition acquisition unit 604 acquires the challenge environmental condition Generate challenge environment conditions A1 and A2 by changing part or all of A0. Changing part or all of the environmental condition A0 means changing the environmental element A, the environmental element B, and the environmental element B. Randomly changing the environmental factor C, or for a given environmental factor A, changing the environmental factor B and the This involves randomly varying the boundary element C.

[0110] That is, the challenge environment condition acquisition unit 604 acquires the challenge generated by the learning model M1. Based on the environmental condition A0, a challenge environmental condition A is created by changing some or all of the environmental conditions. 1, A2, and the challenge environment conditions A0 and the challenge environment conditions A1, A2 are generated by the user. The achievement level reference unit 208 transmits the challenge environmental condition A0 and the challenge environmental condition A 1. Acquire the achievement level when actually performing the challenge in A2. Learning data storage section 209 is a summary of the achievement level, challenge environment conditions and attributes for each challenge environment condition. The set of gender information is stored as new learning data for the learning model M1. The achievement level is determined based on a predetermined threshold. may be provided, and the storage target of the learning data may be determined based on the threshold. For example, The achievement level is set to a minimum achievement level or a maximum achievement level as a predetermined threshold, and the achievement level is set to the minimum achievement level or the maximum achievement level. If the achievement level exceeds or does not exceed the maximum achievement level, it will be stored as learning data. You may do so.

[0111] The user challenges the system under the generated challenge environment conditions A0, A1, and A2. If a challenge environment condition with a higher achievement level than the challenge environment condition A0 is generated, The challenge environment conditions become the learning data for the learning model M1. The environmental conditions generated by 1 can be made to enhance the user's achievement.

[0112] 13 and 15, in the challenge support system 10, the learning model M2 Setting the challenge environment conditions using the learning model M1 The settings will be explained.

[0113] In FIG. 13, user A creates a learning model for challenge 1 based on attribute information A. The challenge was conducted in the environment of the challenge environment condition "Environmental Condition A" generated by Dell M2. The achievement rate of User A was 70%. User B also achieved the same success rate as User A. For a similar challenge, the learning model M2 generates a The challenge is performed in the environment of the challenge environment condition "environment condition A". The achievement rate of the range was 90%.

[0114] In this case, it is assumed that the achievement level of user A is not sufficient. In this case, the learning model M The challenge environment conditions based on 2 are recommended to user A or to users with similar attribute information to user A. In terms of increasing achievement, it is not desirable to do this to users who have only one task.

[0115] Therefore, by the process in FIG. 12, a user having attribute information similar to that of user A is selected. Let us assume that a learning model M1 that generates environmental conditions is obtained. Using the learning model M1, In the challenge with challenge ID "CID101" of User A, Based on this, the challenge environmental condition is set as "environmental condition B". When environmental conditions are set, the achievement rate is 90%. That is, based on the actual achievement rate The learning model M1 generates and updates the model based on the user's It can provide environmental conditions.

[0116] In addition, by using the learning model M1, the variable attribute information of the user is It is also possible to consider appropriate values ​​for the information. This will be explained with reference to 20.

[0117] FIG. 16 is a diagram showing an outline of the process. In step S1601, The referencing unit 603 receives from the user terminal 102 information and attributes of the challenge that the user is to take on. Obtain sexual information.

[0118] In step S1602, the challenge environmental condition acquisition unit 604 performs Based on this, a challenge environmental condition is generated.

[0119] In step S1603, the challenge environmental condition acquisition unit 604 The estimated achievement level of the environment conditions is obtained.

[0120] In step S1604, the challenge environmental condition acquisition unit 604 receives the challenge environmental condition from the user terminal 102. In step S1605, the display unit transmits the challenge environmental conditions and the estimated achievement level to the An estimated achievement level for certain attribute information is displayed in 1022 .

[0121] For example, as shown in Figure 17, among the attribute items A related to the work environment, the employee benefits budget Assume that there is attribute information for the case where the price is set to "5,000 yen." In addition, appropriate information is also available for other items. Information may be entered as a value.

[0122] In this case, the challenge environment conditions and estimated achievement level generated using the learning model M1 are The result is shown in FIG.

[0123] Next, change the value of the attribute information to "4000 yen." In this case, the learning model M1 is used. The challenge environmental conditions and estimated achievement level generated are as shown in FIG. 20.

[0124] The estimated achievement rates in Figures 18 and 20 are 80% for Figure 18 and 40% for Figure 20. In this case, the decrease in the estimated achievement rate is small compared to the reduction in the welfare budget. Therefore, for example, if a company can manage employee attribute information, A company employee operates the user terminal 102 and calculates the employee benefit budget using the employee attribute information. It is possible to consider values ​​for attribute information that can ensure a certain degree of achievement while keeping the In addition, you can change the employee benefit budget for multiple employees at once. The above consideration can be made possible by displaying the average estimated achievement level of each employee when It can also be used as Noh.

[0125] The present embodiment has been described above. The learning model generation device 101 according to the present embodiment An attribute information reference unit 20 that references attribute information indicating the attributes of a user who has a challenge to be completed. 3, and a plurality of items stored in a storage unit regarding an environment in which the challenge is performed based on attribute information. An environmental condition generating unit 20 that generates a challenge environmental condition as an environmental condition that is a set of the environmental elements 4 and the challenge when the challenge is executed by the user under the challenge environment condition. An achievement level reference unit 208 that references the achievement level of a message, and a A learning data storage unit 209 stores the set of the learning data in the memory unit 202 as learning data. Based on this, the learning is trained to take attribute information as input and challenge environmental conditions as output. and a learning model generation unit 210 that generates a learning model M1.

[0126] The environmental condition generating unit 204 generates a certain A challenge environment condition is generated. A user issues a challenge under the challenge environment condition. The degree of achievement when the model is executed is referred to by the achievement degree reference unit 208. 10 uses learning data including assessment results for actual challenges such as achievement. For example, the learning model M1 is a learning model that selects the charac- ter that will give the highest achievement. By outputting the range environmental conditions, the user's challenge may be accomplished. It functions as a learning model that can present a highly challenging environment.

[0127] In addition, the learning model generation unit 210 receives attribute information based on the learning data and generates a channel A learning model is generated that is trained to output the estimated achievement level of the range. This allows the estimated achievement level to be displayed to the user. Users can use the displayed score as a guide to know their chances of completing the challenge. This may allow users to proactively take on the challenge. Therefore, the learning model M1 is designed to find a challenge environment where the user is likely to succeed in the challenge. It functions as a learning model that can present boundaries.

[0128] In addition, in the learning model generating device 101, the environmental condition generating unit 204 receives attribute information as an input. Based on the learning model M2 that has been learned to output the environmental condition and stored in the storage unit 202, Then, the learning model M2 is used to output the challenge environment conditions. By training the model to present the environmental conditions, the learning of the achievement-based learning model M1 is It can be done effectively.

[0129] In addition, in the learning model generating device 101, the attribute information reference unit 203 refers to a user other than the first user. and referring to second attribute information of the second user, and referring to a plurality of environmental elements to generate a plurality of environmental conditions. an environment candidate generating unit for generating an environment condition candidate including the plurality of environment condition candidates, and evaluating the suitability of the challenge of the second user to the second user under multiple candidate environmental conditions. The environmental condition generating unit 204 further includes a degree of conformance acquiring unit 207 for acquiring the environmental condition candidates. The fitness and the second attribute information are machine-learned as second learning data, and the second attribute information and the environmental conditions are A challenge environment condition is generated based on a learning model M2 that relates candidate conditions.

[0130] As a result, the learning model M2 is The second user's challenge is subjected to machine learning using training data including a suitability for the second user. The learning model M2 presents the challenge environment conditions to the user for the generation of the learning model M1. The learning model M2 is presented with challenge environment conditions that suit the user in advance. By training the model to present the following, the learning model M1 based on achievement can be effectively trained. It is possible to do so.

[0131] In addition, in the learning model generating device 101, the conformance acquiring unit 207 acquires conformance of a plurality of environmental condition candidates. Each of the multiple challenges corresponds to a multiple challenge when performed by a second user. The degree of achievement of the range is obtained as the degree of suitability. Since the learning model M2 can be trained using the achievement level when can more appropriately output the challenge environmental conditions.

[0132] In addition, in the learning model generating device 101, the learning model generating unit 210 further Based on this, the learning model M2 is retrained. This makes it possible to present more appropriate challenge environment conditions according to the gender information, The presentation of the final challenge environmental conditions using model M1 will also be more appropriate.

[0133] In addition, in the learning model generating device 101, the environment candidate generating unit 205 generates a plurality of environmental condition candidates. The presentation information for presenting the second user is generated, and the compatibility acquisition unit 207 generates a compatibility score based on the presentation information. The degree of user acceptance of a plurality of candidate environmental conditions based on the plurality of candidate environmental conditions is acquired as the degree of suitability.

[0134] This allows for a user-acceptable challenge without requiring the user to actually perform the challenge. The challenge environment conditions that are likely to be challenged can be judged based on the acceptability. are more likely to take action to complete the challenge, increasing the likelihood of achieving it. By using the acceptability, the learning model M can be calculated without requiring the user to actually perform the challenge. By training 2, the learning model M1 can be effectively trained based on the challenge environment conditions. It is possible to do so.

[0135] The learning model generating device 101 also provides an environmental element that presents a plurality of environmental elements to the second user. a presentation unit 206, and the environmental condition generation unit 204 presents the selected The environmental conditions, which are a set of environmental elements, and the second attribute information are used as the third training data to generate a learning model. Based on the learning model M2, a challenge environmental condition is generated.

[0136] This allows for a user-acceptable challenge without requiring the user to actually perform the challenge. In the case of environmental conditions selected by the user himself, Users are more likely to take action to complete the challenge and are more likely to succeed. By training the learning model M2 without requiring the user to actually perform the challenge, Therefore, learning of the learning model M1 based on the challenging environmental conditions can be effectively performed.

[0137] The challenge support system 10 includes a learning model generation device 101 and a device for managing the challenge. and a challenge management device 103 for managing the challenge.

[0138] The challenge management device 103 uses the learning model generated by the learning model generation device 101. A model storage unit 6022 in which the model M1 is stored, and an attribute information reference unit 6023 for referencing user attribute information. A unit 603 inputs attribute information into a learning model M1 and acquires a challenge environment condition of a user. A challenge environment condition acquisition unit 604 for determining whether or not the challenge completion conditions are met. A judgment information acquisition unit 605 for acquiring judgment information, and a challenge environment based on the judgment information. and an achievement level calculation unit 606 for calculating an achievement level of the challenge in the condition. In the model generating device 101, the achievement level reference unit 208 references the achievement level calculated by the achievement level calculation unit 606. The achievement level in the challenge environment conditions is obtained by referring to the above.

[0139] The challenge support system 10 generates a learning model by the learning model generation device 101. Generation of challenge environment conditions using the learning model by the generation and challenge management device 103 This allows the management of the challenge and the possibility of the user completing the challenge. In order to present a highly feasible challenge environment to the user, Therefore, it is possible to encourage the achievement of the challenge. The functions of the conference management device 103 may be integrated into one device.

[0140] The challenge environmental condition acquisition unit 604 also acquires an estimated challenge environment based on the attribute information. The learning model M1, which can output the degree of achievement, estimates the degree of achievement in the challenge environment. and generating information for displaying the estimated achievement level to a user in a viewable manner. This makes it possible to display the estimated achievement level to the user. Users can proactively take on challenges based on the achievement level set by the user. This can help achieve the goal.

[0141] In this embodiment, the program for operating the learning model generating device 101 is stored in a memory. The program may be stored in a medium. The storage medium storing the program is a non-transitory storage medium. Body (Non-transitory computer readable medium The non-transitory storage medium is not particularly limited, but may be, for example, a USB memory or may be a storage medium such as a CD-ROM.

[0142] The above-described embodiment is intended to facilitate understanding of the present invention and does not limit the present invention. The elements and conditions of the embodiments are merely examples. The above is not limited to the above and may be changed as appropriate. [Explanation of symbols]

[0143] 10... Challenge support system, 101... Learning model generation device, 102a, 102b... User terminal, 103... challenge management device, 203... attribute information reference unit, 204... environmental conditions Generation unit, 205...Environmental candidate generation unit, 206...Environmental element presentation unit, 207...Fitness acquisition unit, 2 08...achievement level reference unit, 209...learning data storage unit, 210...learning model generation unit

Claims

1. An attribute information reference section that references attribute information indicating attributes of a user having a challenge to be achieved. and, Based on the attribute information, a plurality of An environmental condition generating unit that generates a challenge environmental condition as an environmental condition that is a set of environmental elements. When the challenge is performed by the user under the challenge environment conditions an achievement level reference unit that references an achievement level of the challenge; The set of the achievement level, the challenge environment condition, and the attribute information is stored as learning data. A learning data storage unit for storing the learning data in a memory unit; Based on the learning data, the attribute information is input, and the challenge environment conditions are output. A learning model generating unit that generates a learning model that is trained to Generation device.

2. The learning model generation device according to claim 1, The learning model generation unit receives the attribute information based on the learning data, Generate a learning model that is trained to output the estimated completion rate of the challenge. A learning model generation device.

3. The learning model generation device according to claim 1 or 2, The learning model is a first learning model, The environmental condition generating unit is trained to receive the attribute information as an input and output the environmental conditions. The challenge environmental condition is generated based on the second learning model stored in the storage unit. A learning model generation device that creates a learning model.

4. The learning model generating device according to claim 3, The user is a first user, The attribute information is first attribute information of the first user, The learning data is first learning data, The attribute information reference unit further refers to second attribute information of a second user, A candidate environmental condition generating method for generating a candidate environmental condition including a plurality of environmental conditions by referring to the plurality of environmental elements. A complement generator; presenting the plurality of environmental condition candidates to the second user; a suitability acquisition unit that acquires a suitability of the challenge of the second user to the second user; , The environmental condition generating unit generates a second learning result based on the environmental condition candidates, the suitability, and the second attribute information. The second attribute information is machine-learned as learning data, and the second attribute information and the environmental condition candidate are associated with each other. A learning model generation device that generates the challenge environmental conditions based on the two learning models.

5. The learning model generating device according to claim 4, The suitability acquisition unit acquires a plurality of the challenges for each of the plurality of environmental condition candidates. The degree of achievement of the plurality of challenges when performed by the second user is calculated based on the degree of achievement of the plurality of challenges when performed by the second user. A learning model generation device that obtains the degree of agreement.

6. The learning model generating device according to claim 5, The learning model generation unit further regenerates the second learning model based on the learning data. A learning model generation device.

7. The learning model generating device according to claim 4, The environment candidate generation unit is configured to generate a proposal for presenting the plurality of environmental condition candidates to the second user. Generate display information, The suitability acquisition unit is configured to acquire a suitability of the user for the plurality of environmental condition candidates based on the presentation information. A learning model generation device that acquires the acceptability of the user as the degree of suitability.

8. The learning model generating device according to claim 3, The user is a first user, The attribute information is first attribute information of the first user, The learning data is first learning data, The attribute information reference unit refers to second attribute information of a second user, an environmental element presenting unit that presents the plurality of environmental elements to the second user, The environmental condition generation unit selects a set of the environmental elements selected by the second user. The second learning model is machine-learned using the environmental conditions and the second attribute information as third learning data. and generating the challenge environmental conditions based on the model.

9. The learning model generating device according to any one of claims 1 to 8, The attribute information reference unit refers to attribute information including information regarding the cognitive bias of the user. A learning model generation device.

10. A learning model generating device according to any one of claims 1 to 9, a challenge management device for managing the challenge; Equipped with The attribute information reference unit of the learning model generation device is a first attribute information reference unit, The challenge management device A model storage device in which the learning model generated by the learning model generating device is stored. Department and a second attribute information reference unit that references the attribute information of the user; The attribute information is input to the learning model, and the challenge environment conditions of the user are acquired. A challenge environment condition acquisition unit that can obtain A judgment information acquisition unit that acquires judgment information for making a judgment on the achievement condition of the challenge. Tokube and Based on the determination information, a degree of achievement of the challenge under the challenge environment conditions is determined. An achievement level calculation unit that calculates In the learning model generation device, The achievement level reference unit refers to the achievement level calculated by the achievement level calculation unit, A challenge support system that acquires the achievement level in range environmental conditions.

11. The challenge support system according to claim 10, In the challenge management device, The challenge environmental condition acquisition unit estimates the challenge based on the attribute information. The learning model is capable of outputting the degree of achievement, and the estimated degree of achievement in the challenge environment condition is and displaying the estimated achievement level in a viewable manner for the user. A challenge support system that generates information.

12. On the computer, An attribute information reference process that references attribute information indicating attributes of a user having a challenge to be achieved. Reason and Based on the attribute information, a plurality of An environmental condition generation process for generating a challenge environmental condition as an environmental condition which is a set of the environmental elements; 、 When the challenge is performed by the user under the challenge environment conditions an achievement level reference process for referring to an achievement level of the challenge; The set of the achievement level, the challenge environment condition, and the attribute information is stored as learning data. A learning data storage process for storing the learning data in a memory unit; Based on the learning data, the attribute information is input, and the challenge environment conditions are output. A learning model generation process for generating a learning model that is trained so as to Program.

Images