Information processing system, information processing apparatus, and information processing method

Abstract

To predict an effect of an intervention when a result related to a target and a situation of the intervention cannot be acquired in association with each other and features acquired by respective devices about the target are different.SOLUTION: The first information processing device includes a first acquisition unit configured to acquire a first feature quantity representing a target and a result related to the target, a first prediction unit configured to predict a status of an intervention that may affect the result based on the first feature quantity, and a first prediction model training unit configured to train a prediction model for predicting an effect of the intervention by federated learning based on a third feature quantity converted from the first feature quantity, the result, and the status of the intervention. The second information processing device includes a second acquisition unit configured to acquire a second feature quantity representing the target and a situation of the intervention, a second prediction unit configured to predict the result based on the second feature quantity, and a second prediction model training unit configured to train the prediction model by federated learning based on a third feature quantity converted from the second feature quantity, the result, and the situation of the intervention. The third feature quantity is a feature quantity converted from the first feature quantity and the second feature quantity so that the feature quantity distributions are similar.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing system, an information processing device, and an information processing method. [Background technology]

[0002] There are known techniques for predicting the effects of interventions implemented to affect outcomes related to a target. For example, Patent Literature 1 describes a technique for predicting an increase in the rate of product purchases (an example of the effect of an intervention) due to an intervention, namely, displaying an advertisement for a product, based on the characteristics of a user (an example of a target). According to this technique, a prediction model is generated that predicts the effect of displaying an advertisement based on the user's characteristics, using training data that links the user's characteristics, whether or not the advertisement was displayed, and whether or not the product was purchased. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2021 / 235200 Brochure Summary of the Invention [Problem to be solved by the invention]

[0004] Here, the organization that knows the status of the intervention regarding the target (e.g., an advertising distributor that knows whether an advertisement was displayed to a user) may be different from the organization that knows the results obtained regarding the target (e.g., an advertiser that knows whether a user purchased a product). It may be difficult to exchange information between such different organizations in a way that links the status of the intervention and the results. At least some of the characteristics that can be acquired regarding the target may differ between such different organizations. For example, an organization that knows the status of the intervention may be able to acquire the user's email address but not their gender, while an organization that knows the results may not be able to acquire the user's email address but their gender. The technology described in Patent Document 1 has a problem in that the effect of the intervention cannot be predicted when the organizations that can acquire the status of the intervention regarding the target and the results obtained regarding the target are different, and when at least some of the characteristics that can be acquired regarding the target differ between the organizations.

[0005] The present disclosure has been made in consideration of the above-mentioned problems, and one exemplary purpose thereof is to provide a technology that can predict the effect of an intervention from each feature when the intervention status for a subject and the results obtained for the subject cannot be linked and obtained, and at least some of the features that can be obtained with the intervention status for the subject and the features that can be obtained with the results are different. [Means for solving the problem]

[0006] an information processing system according to an exemplary aspect of the present disclosure, comprising: a first information processing device and a second information processing device; a first acquisition means for acquiring a first feature representing a target and a result obtained for the target; a first prediction means for predicting an intervention status that may have affected the result based on the first feature; and a first prediction model training means for training a prediction model that predicts an effect of the intervention by associative learning between the first information processing device and the second information processing device, based on a third feature converted from the first feature, the result, and the intervention status; and a second information processing device for training a prediction model that predicts an effect of the intervention by associative learning between the first information processing device and the second information processing device, based on the third feature converted from the second feature, the result, and the intervention status, and the third feature is a feature converted from the first feature and the second feature so that feature distributions are similar in a single feature space.

[0007] An information processing device according to an exemplary aspect of the present disclosure includes an acquisition means for acquiring features representing a target and results obtained regarding the target; a prediction means for predicting an intervention status that may have affected the results based on the features; and a prediction model training means for training a prediction model that predicts the effect of the intervention based on converted features converted from the features, the results, and the intervention status through associative learning between the device and another information processing device that can acquire the intervention status, wherein the converted features are features converted from the features and other features acquired about the target by the other information processing device so that the feature distributions are similar in the same feature space.

[0008] An information processing device according to an exemplary aspect of the present disclosure includes an acquisition means for acquiring features representing a target and the status of interventions that may have affected a result obtained for the target; a prediction means for predicting the result based on the features; and a second prediction model training means for training a prediction model that predicts the effect of the intervention by associative learning between the device and another information processing device that can acquire the result, based on transformed features converted from the features, the result, and the status of the intervention, wherein the transformed features are features that have been converted from the features and other features acquired for the target by the other information processing device so that the feature distributions are similar in the same feature space.

[0009] An information processing method according to an exemplary aspect of the present disclosure is an information processing method executed by an information processing system including a first information processing device and a second information processing device, the information processing method including: a first acquisition process in which at least one processor included in the first information processing device acquires first feature amounts representing an object and results obtained regarding the object; a first prediction process in which at least one processor included in the first information processing device predicts a state of an intervention that may have affected the results based on the first feature amounts; and a first prediction process in which at least one processor included in the first information processing device predicts an effect of the intervention by associative learning between the first information processing device and the second information processing device based on third feature amounts converted from the first feature amounts, the results, and the state of the intervention. a second acquisition process in which at least one processor included in the second information processing device acquires second features representing a target and the status of the intervention; a second prediction process in which at least one processor included in the second information processing device predicts the outcome based on the second features; and a second prediction model training process in which at least one processor included in the second information processing device trains the prediction model by the associative learning based on the third features converted from the second features, the outcome, and the status of the intervention, wherein the third features are features converted from the first features and the second features so that the feature distributions are similar in the same feature space.

[0010] An information processing method according to an exemplary aspect of the present disclosure includes: an acquisition process in which at least one processor included in an information processing device acquires features representing a target and results obtained regarding the target; a prediction process in which the at least one processor predicts an intervention status that may have affected the results based on the features; and a prediction model training process in which the at least one processor trains a prediction model that predicts the effect of the intervention based on converted features converted from the features, the results, and the intervention status through federated learning with the information processing device itself and another information processing device that can acquire the intervention status, wherein the converted features are features converted from the features and other features acquired about the target by the other information processing device so that the feature distributions are similar in the same feature space.

[0011] An information processing method according to an exemplary aspect of the present disclosure includes: an acquisition process in which at least one processor included in an information processing device acquires features representing a target and the status of interventions that may have affected a result obtained for the target; a prediction process in which the at least one processor predicts the result based on the features; and a prediction model training process in which the at least one processor trains a prediction model that predicts the effect of the intervention by associative learning with the information processing device itself and other information processing devices that can acquire the result, based on transformed features converted from the features, the result, and the status of the intervention, wherein the transformed features are features converted from the features and other features acquired for the target by the other information processing devices so that the feature distributions are similar in the same feature space. [Effects of the Invention]

[0012] According to an exemplary aspect of the present disclosure, when the intervention status for a subject and the results obtained for the subject cannot be linked and obtained, and the features that can be obtained for the subject along with the intervention status and the features that can be obtained along with the results are different, it is possible to provide a technology that can predict the effect of an intervention from each feature. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a block diagram illustrating a configuration of an information processing system according to the present disclosure. [Figure 2] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 3] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 4] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 5] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 6] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 7] 1 is a diagram schematically illustrating an overview of an information processing system according to the present disclosure. [Figure 8] FIG. 1 is a diagram schematically illustrating an overview of each model according to the present disclosure. [Figure 9] 1 is a block diagram illustrating a configuration of an information processing system according to the present disclosure. [Figure 10] FIG. 1 is a flow diagram showing the flow of an information processing method according to the present disclosure. [Figure 11] FIG. 10 is a flowchart showing the flow of an information processing method according to a modified example of the present disclosure. [Figure 12] FIG. 1 is a diagram schematically illustrating an application example using an information processing system according to the present disclosure. [Figure 13] FIG. 2 is a block diagram showing the hardware configuration of a computer that functions as each device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0014] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technologies (part or all of the products or methods) employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0015] First Exemplary Embodiment A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is the basic form of each exemplary embodiment described later. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technology shown in the drawings referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0016] (Overview of Information Processing System 1) The information processing system 1 is a system that generates a predictive model by collaboration between multiple information processing devices, which predicts the effect of an intervention that may affect the outcome of a subject based on the subject's features. Hereinafter, the method of generating a predictive model by collaboration between multiple information processing devices will be referred to as federated learning.

[0017] Here, the term "subject" refers to an object for which the effect of an intervention is to be predicted, and examples thereof include, but are not limited to, visitors to a website, patients at a medical institution, etc. The term "features representing the object" refers to information that describes the object, and examples thereof include, but are not limited to, age, gender, preferences, product purchase history, medical history, and pre-existing conditions. The term "intervention" refers to a process or action taken to affect the results obtained for the object, and examples thereof include, but are not limited to, "displaying an advertisement" and "treatment." The term "effect of an intervention" refers to the degree to which the results obtained for the object improve as a result of the intervention, and examples thereof include, but are not limited to, an increase in purchase rate due to displaying an advertisement, and the effect of treatment on the medical condition.

[0018] To generate a predictive model that predicts the effect of an intervention, training data is required, for example, including (i) features related to the subject, (ii) the results obtained for the subject, and (iii) the circumstances of the intervention that may have affected the results. The "circumstances of the intervention" may be, for example, but are not limited to, whether or not an intervention was performed, the type of intervention if performed, the extent of the intervention, etc. Hereinafter, "the results obtained for the subject" may be referred to as "the results for the subject" or simply as "the results." Furthermore, "the circumstances of the intervention that may have affected the results" may be referred to as "the circumstances of the intervention for the subject" or simply as "the circumstances of the intervention."

[0019] Here, the information processing device capable of acquiring the "results" may differ from the information processing device capable of acquiring the "intervention status," and at least some of the features that each of these information processing devices can acquire regarding the target may differ. In such a case, the information processing system 1 can create the above-described prediction model without requiring each information processing device to disclose to each other the features and results or intervention status that it has acquired.

[0020] (Configuration of Information Processing System 1) The configuration of the information processing system 1 will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the information processing system 1.

[0021] As shown in FIG. 1, the information processing system 1 includes an information processing device 10 and an information processing device 20. The information processing devices 10 and 20 are communicatively connected via a network. Each of the information processing devices 10 and 20 has at least a function of training local models as multiple clients in federated learning. Either one of the information processing devices 10 and 20 may further have a function of integrating multiple local models as a server in federated learning. Each of the information processing devices 10 and 20 may be communicatively connected to a device (not shown) that functions as a server in federated learning. The number of information processing devices 10 included in the information processing system 1 is not limited to one and may be multiple. The number of information processing devices 20 included in the information processing system 1 is not limited to one and may be multiple.

[0022] The information processing device 10 is an example of a first information processing device. The information processing device 10 is a device that can acquire a first feature representing an object and a result related to the object, but cannot acquire the status of an intervention that may have affected the result. The first feature will be described in detail later.

[0023] The information processing device 10 includes a first acquisition unit 11, a first prediction unit 12, and a first prediction model training unit 13. The first acquisition unit 11 is an example of a configuration that realizes first acquisition means. The first prediction unit 12 is an example of a configuration that realizes first prediction means. The first prediction model training unit 13 is an example of a configuration that realizes first prediction model training means.

[0024] The first acquisition unit 11 acquires first feature amounts representing an object and results obtained regarding the object. Hereinafter, the information acquired by the first acquisition unit 11 will be referred to as first input information. The first input information includes feature amounts representing an object and results obtained regarding the object. It is desirable that the first input information include a set of the first feature amounts and the results regarding each of a plurality of objects.

[0025] The first prediction unit 12 predicts the status of an intervention that could have affected an outcome related to the target based on a first feature representing the target. Specifically, the first prediction unit 12 predicts the status of an intervention related to the target based on a first feature related to each of multiple targets included in the first input information. For example, the first prediction unit 12 may make the prediction using a model that predicts the status of an intervention related to the target based on the first feature related to the target.

[0026] The first prediction model training unit 13 trains a prediction model that predicts the effect of an intervention through associative learning by the information processing devices 10 and 20, based on the third feature converted from the first feature, the result, and the intervention status. For example, the first prediction model training unit 13 may train a first prediction model that predicts the effect of an intervention based on the third feature converted from the first feature using the first input information and the predicted intervention status as training data, by machine learning with reference to a model obtained by integrating the first prediction model with a second prediction model trained by the information processing device 20. Note that the first prediction model and the second prediction model are local models in associative learning. For example, the information processing device 10 may use the first prediction model after training as a prediction model, or may use a model obtained by integrating the first prediction model and the second prediction model after training as a prediction model. The third feature will be described in detail below.

[0027] The information processing device 20 is an example of a second information processing device. The information processing device 20 is a device that can acquire a second feature representing a target and the status of intervention that may have affected an outcome related to the target, but cannot acquire the outcome. The second feature will be described in detail later.

[0028] The information processing device 20 includes a second acquisition unit 21, a second prediction unit 22, and a second prediction model training unit 23. The second acquisition unit 21 is an example of a configuration that realizes second acquisition means. The second prediction unit 22 is an example of a configuration that realizes second prediction means. The second prediction model training unit 23 is an example of a configuration that realizes second prediction model training means.

[0029] The second acquisition unit 21 acquires second feature quantities representing the target and the status of interventions that may have affected the results obtained for the target. Hereinafter, the information acquired by the second acquisition unit 21 will be referred to as second input information. The second input information includes feature quantities representing the target and the status of interventions that may have affected the results obtained for the target. It is desirable that the second input information include a set of the second feature quantities and the status of interventions for each of a plurality of targets.

[0030] The second prediction unit 22 predicts an outcome for an object based on a second feature amount representing the object. Specifically, the second prediction unit 22 predicts an outcome for the object based on a second feature amount for each of a plurality of objects included in the second input information. For example, the second prediction unit 22 may make a prediction using a model that predicts an outcome for the object based on the second feature amount for the object.

[0031] The second prediction model training unit 23 trains a prediction model that predicts the effect of the intervention through associative learning by the information processing devices 10 and 20 based on the third feature converted from the second feature, the result, and the status of the intervention. For example, the second prediction model training unit 23 may train a second prediction model that predicts the effect of the intervention based on the third feature converted from the second feature using the second input information and the predicted result as training data, by machine learning with reference to a model obtained by integrating the first prediction model trained by the information processing device 10 and the second prediction model. As described above, the first prediction model and the second prediction model are local models in associative learning. For example, the information processing device 20 may use the second prediction model after training as a prediction model, or may use a model obtained by integrating the first prediction model and the second prediction model after training as a prediction model. The third feature will be described in detail below.

[0032] (First feature, second feature, and third feature) The first feature amount obtainable by the information processing device 10 is at least partially different from the second feature amount obtainable by the information processing device 20. For example, if the target is a user, the first feature amount representing the target may be "gender, age, marital status," and the second feature amount may be "gender, age, deposit amount, loan amount." In this way, the first feature amount includes a unique feature amount (in this example, marital status), and the second feature amount includes a unique feature amount (in this example, deposit amount, loan amount, etc.). Furthermore, the first feature amount and the second feature amount may include a common feature amount (in this example, gender, age). Note that the first feature amount and the second feature amount may be completely different without including a common feature amount.

[0033] The third feature is a feature converted from the first feature and the second feature so that the feature distributions are similar in the same feature space. In other words, the third feature converted from the first feature and the third feature converted from the second feature have similar feature distributions. For example, the first feature may be converted into the third feature using a first conversion model. Also, for example, the second feature may be converted into the third feature using a second conversion model. The first conversion model and the second conversion model may be generated in advance.

[0034] (Associative Learning) Here, as a technique for training the prediction models by the first prediction model training unit 13 and the second prediction model training unit 23, for example, associative learning is adopted. In other words, the first prediction model and the second prediction model are each trained by associative learning. In associative learning, the "integrated model" is referred to as, for example, a global model. As described above, the first prediction model and the second prediction model are each referred to as, for example, a local model in associative learning. In other words, the first prediction model, the second prediction model, and the global model are trained as prediction models by associative learning.

[0035] In federated learning, the following steps are repeated: (i) the information processing device 10 trains a first prediction model by referring to a global model, and the information processing device 20 trains a second prediction model by referring to the global model; and (ii) the trained first prediction model and the trained second prediction model are integrated to generate a new global model. The training data used to train the first prediction model and the training data used to train the second prediction model do not need to be disclosed between the information processing device 10 and the information processing device 20.

[0036] (First prediction model) The first prediction model is a local model trained by the information processing device 10A to obtain, by associative learning, a model that predicts the effect of an intervention on a target based on a third feature converted from a first feature representing the target. The first prediction model may include, for example, a third prediction model that predicts an outcome in the presence of an intervention based on the third feature, and a fourth prediction model that predicts an outcome in the absence of the intervention based on the third feature. In this case, information obtained by subtracting the output of the fourth prediction model from the output of the third prediction model may be output from the first prediction model as the effect of the intervention.

[0037] If the "intervention status" includes only whether or not an intervention was performed, the input of the third prediction model and the fourth prediction model may be only the "third feature." If the "intervention status" includes other factors besides whether or not an intervention was performed, such as the type of intervention and the degree of intervention, the input of the third prediction model that predicts the outcome when an intervention was performed may include the intervention status in addition to the third feature.

[0038] For example, the first prediction model training unit 13 classifies each pair of a third feature value obtained by converting the first feature value included in the first input information and a result into either "with intervention" or "without intervention" based on the intervention status predicted by the first prediction unit 12. As a result, the third prediction model is trained using the pair of the third feature value and the result classified as "with intervention" as training data. In other words, the third prediction model is trained so that when the third feature value is input, a result in the case of intervention is output. Note that, as described above, if the intervention status includes other than the presence or absence of intervention, the third prediction model may be trained so that when the third feature value and the intervention status are input, a result in the case of intervention is output. Furthermore, the fourth prediction model is trained using the pair of the third feature value and the result classified as "without intervention" as training data. In other words, the fourth prediction model is trained so that when the third feature value is input, a result in the case of no intervention is output.

[0039] Furthermore, the first prediction model is trained with reference to the global model. "Training with reference to the global model" means, for example, training the first prediction model using the parameters of the global model as the initial parameters. For example, if the first prediction model includes a third prediction model and a fourth prediction model, the global model may include a first global model and a second global model, which will be described later. In this case, the third prediction model is trained based on the first global model, and the fourth prediction model is trained based on the second global model.

[0040] (Second forecast model) The second prediction model is a local model trained by the information processing device 20A to obtain, through associative learning, a model that predicts the effect of an intervention on a subject based on a third feature converted from a second feature representing the subject. The second prediction model may include, for example, a fifth prediction model that predicts an outcome with an intervention based on the third feature, and a sixth prediction model that predicts an outcome without the intervention based on the third feature. In this case, information obtained by subtracting the output of the sixth prediction model from the output of the fifth prediction model may be output from the second prediction model as the effect of the intervention.

[0041] If the "intervention status" includes only whether or not an intervention was performed, the input of the fifth prediction model and the sixth prediction model may be only the "third feature." If the "intervention status" includes other factors besides whether or not an intervention was performed, such as the type of intervention and the degree of intervention, the input of the fifth prediction model, which predicts the outcome when an intervention is performed, may include the intervention status in addition to the third feature.

[0042] For example, for each pair of a third feature converted from the second feature included in the second input information and an intervention status, the second prediction model training unit 23 classifies the third feature into either "with intervention" or "without intervention" based on the intervention status. As a result, a fifth prediction model is trained using a pair of a third feature classified as "with intervention" and a result predicted based on the third feature as training data. In other words, the fifth prediction model is trained so that when the third feature is input, a result in the case of intervention is output. Note that, as described above, if the intervention status includes other than the presence or absence of intervention, the fifth prediction model may be trained so that when the third feature and the intervention status are input, a result in the case of intervention is output. Furthermore, a sixth prediction model is trained using a pair of a third feature classified as "without intervention" and a result predicted based on the third feature as training data. In other words, the sixth prediction model is trained so that when the third feature is input, a result in the case of no intervention is output.

[0043] Furthermore, the second prediction model is trained based on the global model. "Trained based on the global model" means that the second prediction model is trained using the parameters of the global model as initial parameters. For example, if the second prediction model includes a fifth prediction model and a sixth prediction model, the global model may include a first global model and a second global model, which will be described later. In this case, the fifth prediction model is trained based on the first global model, and the sixth prediction model is trained based on the second global model.

[0044] (Global model) The global model is a model obtained by integrating the first prediction model and the second prediction model to generate, by associative learning, a model that predicts the effect of an intervention on a subject based on a third feature representing the subject. "Models are integrated" may mean, for example, that parameters defining each model are integrated. In other words, the global model is defined by the integrated parameters. Integrating parameters may mean, but is not limited to, taking the average of the parameters. Note that, when the information processing system 1 includes multiple information processing devices 10, the global model is a model obtained by integrating multiple first prediction models and multiple second prediction models. Also, when the information processing system 1 includes multiple information processing devices 20, the global model is a model obtained by integrating the first prediction model and multiple second prediction models.

[0045] For example, the global model may include a first global model in which the third prediction model and the fifth prediction model are integrated, and a second global model in which the fourth prediction model and the sixth prediction model are integrated. In this case, information obtained by subtracting the output of the second global model from the output of the first global model may be output from the global model as the effect of the intervention.

[0046] The global model is not limited to including the first global model and the second global model. For example, if the third prediction model and the fourth prediction model are linear models, the first prediction model training unit 13 may calculate the first prediction model defined by parameters obtained by subtracting the parameters of the fourth prediction model from the parameters of the third prediction model. Similarly, if the fifth prediction model and the sixth prediction model are linear models, the second prediction model training unit 23 may calculate the second prediction model defined by parameters obtained by subtracting the parameters of the sixth prediction model from the parameters of the fifth prediction model.

[0047] (Effects of Information Processing System 1) As described above, the information processing system 1 includes information processing devices 10 and 20, and the information processing device 10 is equipped with the above-mentioned first acquisition unit 11, first prediction unit 12, and first prediction model training unit 13, and the information processing device 20 is equipped with the above-mentioned second acquisition unit 21, second prediction unit 22, and second prediction model training unit 23.

[0048] Therefore, according to the information processing system 1, the information processing device 10 can obtain a prediction model (first prediction model or global model) that predicts the effect of an intervention on a subject from the third feature quantity related to the subject, without needing to know the second feature quantity and the status of the intervention on the subject, which the information processing device 10 cannot obtain, and without disclosing the first feature quantity and the results related to the subject, which the information processing device 10 has obtained, to the information processing device 20. Here, because the third feature quantity is convertible from the first feature quantity, in other words, the information processing device 10 can predict the effect of an intervention on the subject based on the first feature quantity representing the subject. Furthermore, the information processing device 20 can obtain a prediction model (second prediction model or global model) that predicts the effect of an intervention on the subject from the third feature quantity related to the subject, without needing to know the first feature quantity and the results related to the subject, which the information processing device 10 cannot obtain, and without disclosing the second feature quantity and the status of the intervention on the subject, which the information processing device 20 has obtained, to the information processing device 10. Here, because the third feature quantity is convertible from the second feature quantity, in other words, the information processing device 20 can predict the effect of an intervention on the subject based on the second feature quantity representing the subject. As a result, according to the information processing system 1, when the intervention status regarding a subject and the results obtained regarding the subject cannot be linked and obtained, and the features that can be obtained with the intervention status and the features that can be obtained with the results are different, the effect of the intervention can be predicted from each of the first feature and the second feature.

[0049] (Flow of information processing method S1) The flow of information processing method S1 will be described with reference to Fig. 2. For example, when the above-described information processing devices 10 and 20 each include at least one processor, the information processing system 1 executes information processing method S1. Fig. 2 is a flow diagram showing the flow of information processing method S1. As shown in Fig. 2, information processing method S1 includes a first acquisition process S11, a first prediction process S12, a first prediction model training process S13, a second acquisition process S21, a second prediction process S22, and a second prediction model training process S23.

[0050] In the first acquisition process S11, at least one processor (for example, the first acquisition unit 11) included in the information processing device 10 acquires a first feature representing an object and a result obtained regarding the object. In other words, first input information is acquired.

[0051] In the first prediction process S12, at least one processor (e.g., the first prediction unit 12) provided in the information processing device 10 predicts the status of intervention that could have affected the outcome related to the target based on a first feature representing the target included in the first input information.

[0052] In the first prediction model training process S13, at least one processor (e.g., first prediction model training unit 13) included in the information processing device 10 trains a prediction model that predicts the effect of an intervention by associative learning using the information processing devices 10 and 20, based on the third feature converted from the first feature, the result, and the intervention status. For example, the at least one processor uses the first input information and the predicted intervention status as training data and trains a first prediction model that predicts the effect of an intervention on a subject based on the third feature converted from the first feature representing the subject by machine learning, with reference to a model obtained by integrating the first prediction model and a second prediction model trained by the information processing device 20. Here, the third feature is a feature converted from the first feature and the second feature so that the feature distributions are similar in the same feature space.

[0053] In the second acquisition process S21, at least one processor (for example, the second acquisition unit 21) included in the information processing device 20 acquires a second feature representing the object and an intervention status related to the object. In other words, second input information is acquired.

[0054] In the second prediction process S22, at least one processor (for example, the second prediction unit 22) included in the information processing device 20 predicts a result related to the target based on a second feature amount representing the target included in the second input information.

[0055] In the second prediction model training process S23, at least one processor (e.g., second prediction model training unit 23) included in the information processing device 20 trains a prediction model that predicts the effect of the intervention by associative learning using the information processing devices 10 and 20, based on the third feature converted from the second feature, the result, and the status of the intervention. For example, the at least one processor uses the second input information and the predicted result as training data and trains a second prediction model that predicts the effect of the intervention on the subject based on the third feature converted from the second feature representing the subject by machine learning, with reference to a model obtained by integrating the second prediction model and the first prediction model trained by the information processing device 10. Here, the third feature is a feature converted from the first feature and the second feature so that the feature distributions are similar in the same feature space.

[0056] The information processing device 10 repeatedly executes at least the first prediction model training process S13. For example, the information processing device 10 may repeat a series of processes including the first prediction process S12 and the first prediction model training process S13, or may repeat the first prediction model training process S13 without repeating the first prediction process S12. The information processing device 20 repeatedly executes at least the second prediction model training process S23. For example, the information processing device 20 may repeat a series of processes including the second prediction process S22 and the second prediction model training process S23, or may repeat the second prediction model training process S23 without repeating the second prediction process S22.

[0057] In the first prediction model training process S13 and the second prediction model training process S23, a model obtained by integrating the first prediction model and the second prediction model after training in the previous processes S13 and S23 is referenced as a new global model. In the processes S13 and S23, the same new global model is referenced to train the first prediction model and the second prediction model, respectively. Note that the same initial global model is referenced in the initial first prediction model training process S13 and the initial second prediction model training process S23.

[0058] Note that the process of integrating the first prediction model and the second prediction model to generate a new global model may be performed by either the information processing device 10 or the information processing device 20. For example, when the information processing device 10 performs this process, the information processing device 10 may integrate the first prediction model after training on its own device and the second prediction model after training received from the information processing device 20 to generate a new global model. Furthermore, the information processing device 10 may transmit the new global model to the information processing device 20. When the information processing device 20 performs this process, the same description can be given by replacing the information processing devices 10 and 20 and the first prediction model and the second prediction model in the above description of when the information processing device 10 performs this process.

[0059] Furthermore, the process of integrating the first prediction model and the second prediction model to generate a new global model may be performed by a server (not shown) different from either of the information processing devices 10 and 20. In this case, the server may integrate the post-training first prediction model received from the information processing device 10 and the post-training second prediction model received from the information processing device 20 to generate a new global model and transmit the new global model to each of the information processing devices 10 and 20.

[0060] In this manner, (i) the information processing device 10 trains the first prediction model by referring to the global model, and the information processing device 20 trains the second prediction model by referring to the global model, and (ii) a model obtained by integrating the first prediction model and the second prediction model becomes a new global model. The repetition may be performed a predetermined number of times, or may be performed until a first prediction model, a second prediction model, or a global model with a predetermined accuracy is obtained.

[0061] (Effect of information processing method S1) As described above, the information processing method S1 includes the first acquisition process S11, the first prediction process S12, the first prediction model training process S13, the second acquisition process S21, the second prediction process S22, and the second prediction model training process S23. Therefore, the information processing method S1 can achieve the same effects as the information processing system 1.

[0062] (Configuration of information processing device 10) FIG. 3 is a block diagram showing a configuration of an information processing device 10. The information processing device 10 is an example of a configuration for realizing an information processing device according to an exemplary aspect of the present disclosure. As shown in FIG. 3, the information processing device 10 includes a first acquisition unit 11, a first prediction unit 12, and a first prediction model training unit 13. The first acquisition unit 11 is an example of a configuration for realizing acquisition means. The first prediction unit 12 is an example of a configuration for realizing prediction means. The first prediction model training unit 13 is an example of a configuration for realizing prediction model training means. The first feature is an example of a "feature representing an object." The second feature is an example of "another feature acquired about an object by another information processing device." The third feature is an example of a "post-conversion feature." Details of the first acquisition unit 11, the first prediction unit 12, and the first prediction model training unit 13 have been described above, and therefore will not be repeated.

[0063] (Effects of the information processing device 10) As described above, the information processing device 10 is configured to include the first acquisition unit 11, the first prediction unit 12, and the first prediction model training unit 13. Therefore, the information processing device 10 can obtain a prediction model (first prediction model or global model) that predicts the effect of an intervention on a target from a third feature representing the target, without needing to know the second feature and the status of the intervention on the target, which the device itself cannot acquire, and without disclosing the first feature and the results on the target acquired by the device itself to the outside. Here, since the third feature can be converted from the first feature, in other words, the information processing device 10 can predict the effect of an intervention from the first feature representing the target.

[0064] (Flow of information processing method S10) The flow of the information processing method S10 will be described with reference to FIG. 4. For example, when the above-described information processing device 10 includes at least one processor, the information processing device 10 executes the information processing method S10. FIG. 4 is a flow diagram showing the flow of the information processing method S10. As shown in FIG. 4, the information processing method S10 includes a first acquisition process S11 (an example of an acquisition process), a first prediction process S12 (an example of a prediction process), and a first prediction model training process S13 (an example of a prediction model training process). Details of the first acquisition process S11, the first prediction process S12, and the first prediction model training process S13 have been described above, and therefore will not be described repeatedly. Note that the at least one processor repeatedly executes at least the first prediction model training process S13. For example, the at least one processor may repeat a series of processes including the first prediction process S12 and the first prediction model training process S13, or may repeat the first prediction model training process S13 without repeating the first prediction process S12.

[0065] (Effect of information processing method S10) As described above, the information processing method S10 employs a configuration including the above-described first acquisition process S11, first prediction process S12, and first prediction model training process S13. Therefore, the information processing method S10 can achieve the same effects as the information processing device 10.

[0066] (Configuration of information processing device 20) FIG. 5 is a block diagram showing a configuration of the information processing device 20. The information processing device 20 is an example of a configuration for realizing an information processing device according to an exemplary aspect of the present disclosure. As shown in FIG. 5, the information processing device 20 includes a second acquisition unit 21, a second prediction unit 22, and a second prediction model training unit 23. The second acquisition unit 21 is an example of a configuration for realizing acquisition means. The second prediction unit 22 is an example of a configuration for realizing prediction means. The second prediction model training unit 23 is an example of a configuration for realizing prediction model training means. The first feature is an example of "another feature acquired for the object by another information processing device." The second feature is an example of "a feature representing the object." The third feature is an example of "a feature after conversion." Details of the second acquisition unit 21, the second prediction unit 22, and the second prediction model training unit 23 have been described above, and therefore will not be repeated.

[0067] (Effects of the information processing device 20) As described above, the information processing device 20 is configured to include the second acquisition unit 21, the second prediction unit 22, and the second prediction model training unit 23. Therefore, the information processing device 20 can obtain a prediction model (second prediction model or global model) that predicts the effect of an intervention on a target from the third feature value related to the target, without needing to know the first feature value and the results obtained for the target, which the device itself cannot acquire, and without disclosing the second feature value and the intervention status for the target, which the device itself acquired. Here, since the third feature value can be converted from the second feature value, in other words, the information processing device 20 can predict the effect of an intervention from the second feature value representing the target.

[0068] (Flow of information processing method S20) The flow of the information processing method S20 will be described with reference to FIG. 6. For example, when the above-described information processing device 20 includes at least one processor, the information processing device 20 executes the information processing method S20. FIG. 6 is a flow diagram showing the flow of the information processing method S20. As shown in FIG. 6, the information processing method S20 includes a second acquisition process S21 (an example of an acquisition process), a second prediction process S22 (an example of a prediction process), and a second prediction model training process S23 (an example of a prediction model training process). The details of the second acquisition process S21, the second prediction process S22, and the second prediction model training process S23 have been described above, and therefore will not be described repeatedly. Note that the at least one processor repeatedly executes at least the second prediction model training process S23. For example, the at least one processor may repeat a series of processes including the second prediction process S22 and the second prediction model training process S23, or may repeat the second prediction model training process S23 without repeating the second prediction process S22.

[0069] (Effect of information processing method S20) As described above, the information processing method S20 includes the second acquisition process S21, the second prediction process S22, and the second prediction model training process S23. Therefore, the information processing method S20 can achieve the same effects as the information processing device 20.

[0070] Second Exemplary Embodiment A second exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs. Furthermore, each technology shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs.

[0071] (Outline of Information Processing System 1A) The information processing system 1A is configured similarly to the information processing system 1, and is also configured as follows: In the information processing system 1A, the information processing devices 10A and 20A cooperate to train a first conversion model that converts a first feature quantity representing an object into a third feature quantity and a second conversion model that converts a second feature quantity representing the object into the third feature quantity. In the information processing system 1A, a result prediction model trained by the information processing device 10A, which can acquire results related to the object, and an intervention prediction model trained by the information processing device 20A, which can acquire the status of intervention related to the object, are exchanged between the information processing devices 10A and 20A.

[0072] 7 is a diagram showing a schematic overview of the information processing system 1A. Note that, hereinafter, a subscript (e.g., i) shown in FIG. 7 will be written with an underscore next to the character, such as "_i." Also, a tilde symbol (~) placed above a character (e.g., x) will be written with the character followed by the tilde symbol, such as "x~." Also, a hat symbol (^) placed above a character (e.g., t) will be written with the character followed by the hat symbol, such as "t^."

[0073] 7, an information processing device 10A is a device capable of acquiring a first feature x_i representing an object and a result y_i related to the object. N sets (N is a natural number equal to or greater than 2, i=1, 2, ..., N) of first feature x_i and result y_i are input to the information processing device 10A as first input information. An information processing device 20A is a device capable of acquiring second feature x~_i related to an object and an intervention status t_i related to the object. M sets (M is a natural number equal to or greater than 2) of second feature x~_i and intervention status t_i are input to the information processing device 20A as second input information.

[0074] The first feature x_i and the second feature x~_i include at least unique features different from each other. Furthermore, the first feature x_i and the second feature x~_i may include a common feature. Furthermore, the first feature x_i and the second feature x~_i are information that is not disclosed to each other. Furthermore, the first feature x_i and the second feature x~_i are not necessarily features related to the same object (for example, the same user).

[0075] The information processing device 10A trains, by machine learning, a first conversion model "F" that converts the feature x_i included in the first input information into a third feature. The information processing device 20A trains, by machine learning, a first conversion model "G" that converts the feature x~_i included in the second input information into a third feature. Here, the training of the first conversion model "F" and the training of the second conversion model "G" are performed in cooperation under the constraint that the distributions of the third feature to be output are made close to each other.

[0076] Here, for example, specific examples of a method for approximating the distribution of the third feature amount include a method of exchanging statistical information and a method using adversarial learning. In the method of exchanging statistical information, the information processing devices 10A and 20A (a first conversion model training unit 15 and a second conversion model training unit 25 described later) each calculate and exchange statistical information on the third feature amount. Examples of statistical information include, but are not limited to, a mean and a covariance. Furthermore, the information processing device 10A trains the first conversion model so as to reduce the difference in the statistical information (e.g., a difference in the mean and a difference in the covariance) by including a term corresponding to the difference in the statistical information in a loss function. Similarly, the information processing device 20A trains the second conversion model so as to reduce the difference in the statistical information by including a term corresponding to the difference in the statistical information in a loss function. The difference in the statistical information is the difference between the statistical information calculated by the information processing device 10A and the statistical information calculated by the information processing device 20A. For example, the difference in the mean is the difference between the mean calculated by the information processing device 10A and the mean calculated by the information processing device 20A. Furthermore, for example, the difference in covariance is the difference between the covariance calculated by the information processing device 10A and the covariance calculated by the information processing device 20A.

[0077] In the adversarial learning method, the information processing devices 10A and 20A cooperate to train a discrimination model that discriminates whether the third feature has been converted from the first feature or the second feature. The information processing device 10A trains the first conversion model to output a third feature that causes the discrimination model to make an erroneous discrimination. The information processing device 20A trains the second conversion model to output a third feature that causes the discrimination model to make an erroneous discrimination. Note that the method for approximating the distribution of the third feature is not limited to the above-described method.

[0078] Furthermore, the information processing device 10A uses a third feature F(x_i) obtained by converting the first feature x_i included in the first input information using the first conversion model "F" and the result y_i included in the first input information as training data, and trains a result prediction model "Y" so that when F(x_i) is input, y_i is output.

[0079] Furthermore, the information processing device 20A uses as training data the third feature G(x~_i) obtained by converting the second feature x~_i included in the second input information using the second conversion model "G" and the intervention status t_i included in the second input information, and trains the intervention prediction model "T" so that t_i is output when G(x~_i) is input. The outcome prediction model "Y" and the intervention prediction model "T" are exchanged between the information processing devices 10A and 20A.

[0080] The information processing device 10A calculates "T(F(x_i))" using the trained first conversion model "F" and the intervention prediction model "T" obtained by exchange, and assigns it to the first input information as a pseudo label "t^_i" indicating the intervention status. As a result, N sets of triples, each consisting of a first feature x_i representing the target, a pseudo label t^_i, and a result y_i, are obtained.

[0081] The information processing device 20A calculates "Y(G(x~_i))" using the trained second conversion model "G" and the result prediction model "Y" obtained by exchange, and assigns it to the second input information as a pseudo label "y^_i" indicating the result. As a result, M sets of triples are obtained: the second feature x~_i representing the target, the intervention status t^_i, and the pseudo label y_i indicating the result.

[0082] The information processing devices 10A and 20A can each use triples as training data, and as a result, can generate a prediction model "u(z)" by associative learning. The prediction model u(z) is a model that takes a third feature "z" representing the target as input and outputs the effect of the intervention "u(z)."

[0083] FIG. 8 is a diagram schematically illustrating the relationship between the first conversion model, the first prediction model, the outcome prediction model, the second conversion model, the second prediction model, and the intervention prediction model. As shown in FIG. 8, the first conversion model receives a first feature value obtainable by the information processing device 10A as an input and outputs a third feature value. The outcome prediction model receives the third feature value as an input and outputs a result. The first prediction model receives the third feature value as an input and outputs the effect of the intervention. Furthermore, the second conversion model receives a second feature value obtainable by the information processing device 20A as an input and outputs the third feature value. The intervention prediction model receives the third feature value as an input and outputs the status of the intervention. The second prediction model receives the third feature value as an input and outputs the effect of the intervention. Associative learning is performed using the first prediction model and the second prediction model as local models. Furthermore, the outcome prediction model and the intervention prediction model are exchanged between the information processing devices 10A and 20A and are used to train the first prediction model and the second prediction model.

[0084] (Configuration of information processing system 1A) The configuration of the information processing system 1A will be described with reference to FIG. 9. FIG. 9 is a block diagram showing the configuration of the information processing system 1A. The information processing system 1A includes information processing devices 10A and 20A. The information processing device 10A includes a result prediction model training unit 14, a first conversion model training unit 15, and a global model generation unit 19 in addition to the first acquisition unit 11, the first prediction unit 12, and the first prediction model training unit 13 included in the information processing device 10. The information processing device 20A includes an intervention prediction model training unit 24 and a second conversion model training unit 25 in addition to the second acquisition unit 21, the second prediction unit 22, and the second prediction model training unit 23 included in the information processing device 20. The result prediction model training unit 14 is an example of a configuration realizing result prediction model training means. The first conversion model training unit 15 is an example of a configuration realizing first conversion model training means. The intervention prediction model training unit 24 is an example of a configuration realizing intervention prediction model training means. The second conversion model training unit 25 is an example of a configuration that realizes a second conversion model training means.

[0085] The first conversion model training unit 15 trains a first conversion model that converts a first feature into a third feature. For example, the first feature included in the first input information is used as training data to train the first conversion model. The second conversion model training unit 25 trains a second conversion model that converts a second feature into a third feature. For example, the second feature included in the second input information is used as training data to train the second conversion model. Furthermore, the training of the first conversion model and the training of the second conversion model are performed in cooperation under the constraint that the distribution of the output third feature be close. Specific examples of techniques for approximating the distribution of the third feature have been described above, and therefore details will not be repeated.

[0086] The result prediction model training unit 14 trains a result prediction model that predicts an outcome related to an object based on a third feature representing the object. For example, the result prediction model training unit 14 may use first input information as training data and convert the first feature included in the first input information into a third feature using a first conversion model, thereby training a result prediction model by machine learning that predicts an outcome related to the object based on the third feature representing the object. In other words, when the third feature converted from the first feature included in the first input information is input, the result prediction model is trained so that the result included in the first input information is output. Furthermore, the result prediction model training unit 14 provides the result prediction model to the information processing device 20A.

[0087] The intervention prediction model training unit 24 trains an intervention prediction model that predicts the intervention status of a target based on a third feature representing the target. For example, the intervention prediction model training unit 24 may use second input information as training data and convert the second feature included in the second input information into a third feature using a second conversion model, thereby training an intervention prediction model by machine learning that predicts the intervention status of the target based on the third feature representing the target. In other words, when the third feature converted from the second feature included in the second input information is input, the intervention prediction model is trained so that the intervention status included in the second input information is output. Furthermore, the intervention prediction model training unit 24 provides the intervention prediction model to the information processing device 10A.

[0088] The first prediction unit 12 is configured similarly to the first prediction unit 12 included in the information processing device 10, and is also configured as follows: The first prediction unit 12 predicts the intervention status for a target using the first conversion model trained by the first conversion model training unit 15 and the intervention prediction model provided by the information processing device 20A. For example, the first prediction unit 12 converts first feature quantities representing each of the multiple targets included in the first input information into third feature quantities using the first conversion model, and inputs the third feature quantities into the intervention prediction model, thereby acquiring the intervention status output from the intervention prediction model.

[0089] The second prediction unit 22 is configured similarly to the second prediction unit 22 included in the information processing device 20, and is also configured as follows: The second prediction unit 22 predicts a result related to an object using the second conversion model trained by the second conversion model training unit 25 and a result prediction model provided by the information processing device 10A. For example, the second prediction unit 22 converts second feature quantities representing each of the multiple objects included in the second input information into third feature quantities using the second conversion model, and inputs the third feature quantities into the result prediction model, thereby obtaining a result output from the result prediction model.

[0090] Here, the training of the first transformation model, the training of the result prediction model, and the training of the prediction model are performed independently of each other. In other words, the training of the first transformation model, the training of the result prediction model, and the training of the first prediction model, which is a local model in the associative learning for generating the prediction model, are performed independently of each other. This allows, for example, the training of the first transformation model and the result prediction model to be completed before the training of the first prediction model begins. Furthermore, the trained result prediction model can be provided to the information processing device 20A before the training of the second prediction model begins.

[0091] Furthermore, the training of the second transformation model, the training of the intervention prediction model, and the training of the prediction model are performed independently of each other. In other words, the training of the second transformation model, the training of the intervention prediction model, and the training of the second prediction model, which is a local model in the associative learning for generating the prediction model, are performed independently of each other. This allows, for example, the training of the second transformation model and the intervention prediction model to be completed before the training of the second prediction model begins. Furthermore, the trained intervention prediction model can be provided to the information processing device 10A before the training of the first prediction model begins.

[0092] As a result, before starting training of the first prediction model, the information processing device 10A can accurately predict the "intervention situation" required for the training using the trained first conversion model and the trained intervention prediction model. Also, before starting training of the second prediction model, the information processing device 20A can predict the "result" required for the training using the trained second conversion model and the trained result prediction model.

[0093] The global model generation unit 19 generates an initial global model and provides it to the first prediction model training unit 13 and the second prediction model training unit 23. The initial global model is defined by initial parameters. The global model generation unit 19 also generates a new global model by integrating the first prediction model and the second prediction model and provides it to the first prediction model training unit 13 and the second prediction model training unit 23.

[0094] (Flow of information processing method S1A) The flow of information processing method S1A will be described with reference to Fig. 10. For example, when the above-described information processing devices 10A and 20A each include at least one processor, the information processing system 1A executes information processing method S1A. Fig. 10 is a flow diagram showing the flow of information processing method S1A. As shown in Fig. 10, information processing method S1A includes steps S101 to S109 executed by information processing device 10A and steps S201 to S206 executed by information processing device 20A.

[0095] In step S101, the first acquisition unit 11 acquires first input information including a first feature amount representing an object and a result related to the object. Step S101 is an example of a first acquisition process.

[0096] In step S201, the second acquisition unit 21 acquires second input information including a second feature representing the target and the status of intervention related to the target. Step S201 is an example of a second acquisition process. The execution order of steps S101 and S201 is not limited to this order and may be any order. Note that "the execution order of multiple steps is any order" includes executing each step in any order, executing some or all of each step in parallel, etc.

[0097] In step S102, the first conversion model training unit 15 trains the first conversion model. Step S102 is an example of a first conversion model training process. In step S202, the second conversion model training unit 25 trains the second conversion model. Step S202 is an example of a second conversion model training process. The training of the first conversion model and the training of the second conversion model are performed in cooperation under the constraint that the distributions of the third feature amounts to be output are made close to each other. Therefore, steps S102 and S202 are performed in parallel.

[0098] In step S103, the result prediction model training unit 14 converts the first feature included in the first input information into a third feature using the first conversion model. The result prediction model training unit 14 also trains the result prediction model so that when the third feature is input, the result included in the first input information is output. The result prediction model training unit 14 also transmits the trained result prediction model to the information processing device 20A. Step S103 is an example of a result prediction model training process.

[0099] In step S203, the intervention prediction model training unit 24 converts the second feature included in the second input information into a third feature using the second conversion model. The intervention prediction model training unit 24 also trains the intervention prediction model so that the intervention status included in the second input information is output when the third feature is input. The intervention prediction model training unit 24 also transmits the trained intervention prediction model to the information processing device 10A. Step S203 is an example of an intervention prediction model training process. The execution order of steps S103 and S203 is not limited to this order and can be any order.

[0100] In step S104, the first prediction unit 12 converts the first feature included in the first input information into a third feature using the first conversion model trained in step S102. The first prediction unit 12 then inputs the converted third feature into the intervention prediction model received from the information processing device 20A in step S203, thereby predicting the intervention status for the target indicated by the third feature. This assigns a pseudo label indicating the predicted intervention status to the first feature representing each of the multiple targets included in the first input information. Step S104 is an example of the first prediction process.

[0101] In step S204, the second prediction unit 22 converts the second feature included in the second input information into a third feature using the second conversion model trained in step S202. The second prediction unit 22 then inputs the converted third feature into the result prediction model received from the information processing device 10A in step S103, thereby predicting the outcome of the object indicated by the third feature. This assigns a pseudo label indicating the predicted outcome to the second feature representing each of the multiple objects included in the second input information. Step S204 is an example of a second prediction process. The execution order of steps S104 and S204 is not limited to this order and may be any order.

[0102] In step S105, the global model generation unit 19 generates an initial global model. In other words, the global model generation unit 19 sets initial parameters that define the global model. Step S105 may be executed before step S106 is executed, and is not necessarily executed after step S104.

[0103] In step S106, the global model generation unit 19 transmits the global model to the information processing device 20A.

[0104] In step S107, the first prediction model training unit 13 trains the first prediction model by referring to the global model, using the first input information and the pseudo-label indicating the intervention status as training data. Step S107 is an example of a first prediction model training process. The details of the training of the first prediction model are as described in the first exemplary embodiment, and therefore will not be repeated.

[0105] In step S107, the first conversion model may be retrained in parallel with the training of the first prediction model. For example, a model connected to input the output of the first conversion model to the first prediction model is trained so that the effect of an intervention is output when the first feature is input, thereby training the first prediction model and retraining the first conversion model at the same time. The retraining of the first conversion model is performed in cooperation with the retraining of the second conversion model (described later) under the constraint of approximating the distribution of the output third feature.

[0106] In step S205, the second prediction model training unit 23 trains the second prediction model by referring to the global model, using the second input information and pseudo labels indicating the results as training data. Step S205 is an example of a second prediction model training process. The details of the training of the second prediction model are the same as those described in the first exemplary embodiment, and therefore will not be repeated.

[0107] In step S205, the second conversion model may be retrained in parallel with the training of the second prediction model. For example, a model connected to input the output of the second conversion model to the second prediction model is trained so that the effect of the intervention is output when the second feature is input, thereby training the second prediction model and retraining the second conversion model at the same time. The retraining of the second conversion model is performed in cooperation with the above-mentioned retraining of the first conversion model under the constraint that the distribution of the output third feature is made closer.

[0108] The second prediction model training unit 23 transmits the trained second prediction model to the information processing device 10A. The execution order of steps S107 and S205 is not limited to this order and may be any order.

[0109] In step S108, the global model generation unit 19 generates a new global model by integrating the first prediction model after training in step S107 and the second prediction model received from the information processing device 20A in step S205.

[0110] In step S109, information processing device 10A determines whether to end the associative learning. If it is determined not to end the associative learning, information processing device 10A repeats the processing from step S106. Note that information processing device 10A may determine whether to end the associative learning based on whether the number of repetitions has reached a predetermined number, or may determine based on whether the accuracy of the first prediction model (or global model) has exceeded a threshold. However, the viewpoint for determining whether to end the associative learning is not limited to these examples.

[0111] The global model transmitted to the information processing device 20A in the next step S106 is a new global model generated in the previous step S108 by integrating the first and second prediction models. In addition, in the next step S107, the first prediction model is trained with reference to the "new global model obtained by integrating the first and second prediction models." Note that in each repeated step S107 (first prediction model training process), the pseudo label indicating the intervention status assigned in advance in step S104 is referenced.

[0112] In step S206, information processing device 20A determines whether or not to terminate the associative learning. If it is determined not to terminate, information processing device 20A repeats the processing from step S205. Note that information processing device 20A may determine whether or not to terminate the associative learning based on whether or not the number of repetitions has reached a predetermined number, or may determine based on whether or not the accuracy of the second prediction model (or global model) has exceeded a threshold. However, the viewpoint for determining whether or not to terminate the associative learning is not limited to these examples.

[0113] In the next step S205, the second prediction model is trained with reference to the "new global model obtained by integrating the first prediction model and the second prediction model" received from the information processing device 10A. Note that in each repeated step S205 (second prediction model training process), the pseudo label indicating the result previously assigned in step S204 is referenced.

[0114] If it is determined in step S109 or S206 that the process is to end, the information processing method S1A ends. This allows the information processing device 10A to obtain a first prediction model (or a global model) that predicts the effect of an intervention on a subject based on a third feature quantity representing the subject. As a result, the information processing device 10A can predict the effect of an intervention on a subject based on the first feature quantity representing the subject by using the first transformation model and the first prediction model (or the global model). Furthermore, the information processing device 20A can obtain a second prediction model (or a global model) that predicts the effect of an intervention on a subject based on the third feature quantity representing the subject. As a result, the information processing device 20A can predict the effect of an intervention on a subject based on the second feature quantity representing the subject by using the second transformation model and the second prediction model (or the global model).

[0115] (Advantages of this exemplary embodiment) As described above, in the information processing system 1A, the information processing device 10A further includes a first conversion model training unit 15 that trains a first conversion model that converts a first feature into a third feature, and an outcome prediction model training unit 14 that trains an outcome prediction model that predicts an outcome for an object based on the third feature representing the object. The information processing device 20A further includes a second conversion model training unit 25 that trains a second conversion model that converts a second feature into the third feature, and an intervention prediction model training unit 24 that trains an intervention prediction model that predicts an intervention status for the object based on the third feature representing the object. The information processing system 1A is configured such that the first prediction unit 12 predicts an intervention status for the object using the first conversion model and the intervention prediction model, and the second prediction unit 22 predicts an outcome for the object using the second conversion model and the outcome prediction model. Therefore, according to the information processing system 1A, in addition to the effects achieved by the information processing system 1, the information processing device 10A that cannot acquire the status of an intervention related to a target can accurately predict the status of the intervention by using the intervention prediction model trained by the information processing device 20A that can acquire the status of the intervention and the first conversion model trained by the information processing device 10A itself. Also, the information processing device 20A that cannot acquire a result related to a target can accurately predict the result by using the result prediction model trained by the information processing device 10A that can acquire the result and the second conversion model trained by the information processing device 10A itself.

[0116] Furthermore, in the information processing system 1A, the first conversion model training unit 15 and the second conversion model training unit 25 exchange statistical information of the third feature and train the first conversion model and the second conversion model so as to reduce the difference by including a term corresponding to the difference in the statistical information in the loss function. Therefore, according to the information processing system 1A, the feature distributions of the third feature converted from the first feature and the third feature converted from the second feature can be accurately made similar, and associative learning of a prediction model that predicts the effect of an intervention from the third feature can be accurately performed.

[0117] Furthermore, in the information processing system 1A, the first conversion model training unit 15 and the second conversion model training unit 25 cooperatively train a discrimination model that identifies whether the third feature value was converted from the first feature value or the second feature value, and train the first conversion model and the second conversion model to output a third feature value that causes the discrimination model to make an erroneous discrimination. Therefore, according to the information processing system 1A, the feature distributions of the third feature value converted from the first feature value and the third feature value converted from the second feature value can be accurately made similar, and associative learning of a prediction model that predicts the effect of an intervention from the third feature value can be accurately performed.

[0118] Furthermore, the information processing system 1A is configured such that the training of the first conversion model, the training of the outcome prediction model, and the training of the prediction model are performed independently of one another, and the training of the second conversion model, the training of the intervention prediction model, and the training of the prediction model are performed independently of one another. Therefore, according to the information processing system 1A, in addition to the effects achieved by the information processing system 1, associative learning for generating a prediction model (first prediction model, second prediction model, or global model) that predicts the effect of an intervention on a subject based on a third feature representing the subject can be started using as training data the intervention status and results accurately predicted by the trained outcome prediction model and intervention prediction model, resulting in the effect of rapid convergence.

[0119] [Variation 1] The above-described information processing system 1A can be further modified as follows: The first conversion model training unit 15, the result prediction model training unit 14, and the first prediction model training unit 13 train the first conversion model, the result prediction model, and the prediction model in parallel while sharing the output from the first conversion model as input to the result prediction model and the prediction model. In other words, the first conversion model, the result prediction model, and the first prediction model are trained in parallel while sharing the output from the first conversion model as input to the result prediction model and the first prediction model, which is a local model in associative learning for generating the prediction model.

[0120] Furthermore, the second transformation model training unit 25, the intervention prediction model training unit 24, and the second prediction model training unit 23 train the second transformation model, the intervention prediction model, and the prediction model in parallel while sharing the output from the second transformation model as an input to the intervention prediction model and the prediction model. In other words, the second transformation model, the intervention prediction model, and the second prediction model are trained in parallel while sharing the output from the second transformation model as an input to the intervention prediction model and the second prediction model, which is a local model in the associative learning for generating the prediction model.

[0121] For example, the first transformation model, outcome prediction model, and first prediction model shown in FIG. 8 are trained in parallel in the information processing device 10A. The second transformation model, intervention prediction model, and second prediction model are trained in parallel in the information processing device 20A. Furthermore, since the first prediction model and the second prediction model are the targets of associative learning, a global model is obtained by integrating the first prediction model and the second prediction model. In the next cycle, the first transformation model and outcome prediction model trained in the previous cycle, and the first prediction model to which the global model is applied, are trained in parallel. Furthermore, the second transformation model and intervention prediction model trained in the previous cycle, and the second prediction model to which the global model is applied, are trained in parallel. Then, the process of integrating the first prediction model and the second prediction model is repeated.

[0122] In this modification, information processing method S1B is executed instead of information processing method S1A shown in Fig. 10. Fig. 11 is a flow diagram showing the flow of information processing method S1B. As shown in Fig. 11, information processing method S1B includes steps S151 to S158 executed by information processing device 10A and steps S251 to S256 executed by information processing device 20A.

[0123] In step S151, the first acquisition unit 11 acquires first input information. Step S151 is the same as step S101 described above.

[0124] In step S251, the second acquiring unit 21 acquires second input information. Step S251 is the same as step S201 described above. The execution order of steps S151 and S251 is not limited to this order and may be any order.

[0125] In step S152, the global model generation unit 19 generates an initial global model. Step S152 is similar to the above-mentioned step S105. Step S152 may be executed before step S153 is executed, and does not necessarily have to be executed after step S151.

[0126] In step S153, the global model generation unit 19 transmits the global model to the information processing device 20 A. Step S153 is the same as step S105 described above.

[0127] In step S154, the first conversion model training unit 15, the result prediction model training unit 14, and the first prediction model training unit 13 of the information processing device 10A train the first conversion model, the result prediction model, and the first prediction model in parallel while sharing the output of the first conversion model as input to the first prediction model and the result prediction model. Among these, the first prediction model is trained with reference to the global model. Furthermore, the first input information and pseudo-labels indicating the intervention status are used as training data for training these models in parallel. A known multitask learning method can be used for this parallel training process.

[0128] Furthermore, among the trainings performed in parallel in step S154, training of the first prediction model requires a pseudo label indicating the intervention status, but the intervention prediction model required to assign the pseudo label has not yet been obtained when step S154 is performed for the first time. In this case, the pseudo label may be assigned using any intervention prediction model. Note that pseudo labels when step S154 is performed for the second time or later will be described later. Furthermore, in the first execution of step S154, training of the first prediction model may be omitted, and only training of the first transformation model and outcome prediction model may be performed.

[0129] In step S252, the second conversion model training unit 25, the intervention prediction model training unit 24, and the second prediction model training unit 23 of the information processing device 20A train the second conversion model, the intervention prediction model, and the second prediction model in parallel while sharing the output of the second conversion model as input to the second prediction model and the intervention prediction model. Among these, the second prediction model is trained with reference to the global model. Furthermore, pseudo labels indicating the second input information and the results are used as training data for training these models in parallel. A known multitask learning method can be used for this parallel training process.

[0130] Furthermore, among the training steps performed in parallel in step S252, training of the second prediction model requires a pseudo label indicating the result, but the result prediction model required to assign the pseudo label has not yet been obtained when step S252 is performed for the first time. In this case, the pseudo label may be assigned using any result prediction model. Furthermore, in the first execution of step S252, training of the second prediction model may be omitted, and only training of the second transformation model and the intervention prediction model may be performed. Note that pseudo labels when step S252 is performed for the second time or later will be described later. The execution order of steps S154 and S252 is not limited to this order and may be any order.

[0131] In step S155, the result prediction model training unit 14 of the information processing device 10A transmits the trained result prediction model to the information processing device 20A.

[0132] In step S253, the intervention prediction model training unit 24 of the information processing device 20A transmits the trained intervention prediction model to the information processing device 10A. The execution order of steps S155 and S253 is not limited to this order and may be any order.

[0133] In step S156, the first prediction unit 12 of the information processing device 10A assigns pseudo labels indicating the intervention status to the first features representing each of the multiple targets included in the first input information, using the trained first conversion model and the received intervention prediction model. The pseudo labels assigned in this step are referred to when training the first prediction model in the next step S154.

[0134] In step S254, the second prediction unit 22 of the information processing device 20A assigns pseudo labels indicating results to second features representing each of the multiple targets included in the second input information using the trained second conversion model and the received result prediction model. The pseudo labels assigned in this step are referenced when training the second prediction model in the next step S252. The execution order of steps S156 and S254 is not limited to this order and can be any order.

[0135] In step S255, the second prediction model training unit 23 of the information processing device 20A transmits the trained second prediction model to the information processing device 10A.

[0136] In step S157, the global model generation unit 19 generates a global model that integrates the trained first prediction model and the received second prediction model.

[0137] In step S158, information processing device 10A determines whether to end the associative learning. A specific example of determining whether to end the associative learning is the same as in step S109, and therefore detailed description will not be repeated. If it is determined not to end, information processing device 10A repeats the processing from step S153.

[0138] The global model transmitted to the information processing device 20A in the next step S153 is a new global model generated in the previous step S157 by integrating the first prediction model and the second prediction model. Furthermore, in the next step S154, the new global model becomes the first prediction model at the start of training. Furthermore, the first transformation model trained in the previous step S154 becomes the first transformation model at the start of training. Furthermore, the result prediction model trained in the previous step S154 becomes the result prediction model at the start of training. The first transformation model, the result prediction model, and the first prediction model are trained in parallel. Furthermore, the pseudo labels assigned in the previous step S156 are referenced during the training.

[0139] In step S256, information processing device 20A determines whether to end the associative learning. A specific example of determining whether to end the associative learning is the same as in step S206, and therefore detailed description will not be repeated. If it is determined not to end, information processing device 20A repeats the processing from step S252.

[0140] In the next step S252, the "new global model reflecting the first prediction model and the second prediction model" received from the information processing device 10A becomes the second prediction model at the start of training. Also, the second converted model trained in the previous step S252 becomes the second converted model at the start of training. Also, the intervention prediction model trained in the previous step S252 becomes the intervention prediction model at the start of training. Then, training of the second converted model, the intervention prediction model, and the second prediction model is performed in parallel. Also, in this training, the pseudo label assigned in the previous step S254 is referenced.

[0141] If it is determined in step S158 or S256 that the process is to end, the information processing method S1B ends. This allows the information processing device 10A to obtain a first prediction model (or a global model) that predicts the effect of an intervention on a subject based on a third feature quantity representing the subject. Furthermore, the information processing device 10A can predict the effect of an intervention on a subject from the first feature quantity representing the subject by using the first transformation model and the first prediction model (or the global model). Furthermore, the information processing device 20A can obtain a second prediction model (or a global model) that predicts the effect of an intervention on a subject based on the third feature quantity representing the subject. Furthermore, the information processing device 20A can predict the effect of an intervention on a subject from the second feature quantity representing the subject by using the second transformation model and the second prediction model (or the global model).

[0142] (Effects of this modified example) In this modified example, the first conversion model training unit 15, the outcome prediction model training unit 14, and the first prediction model training unit 13 train the first conversion model, the outcome prediction model, and the prediction model in parallel while sharing the output from the first conversion model as input to the outcome prediction model and the prediction model. The second conversion model training unit 25, the intervention prediction model training unit 24, and the second prediction model training unit 23 train the second conversion model, the intervention prediction model, and the prediction model in parallel while sharing the output from the second conversion model as input to the intervention prediction model and the prediction model. This configuration is adopted. The information processing device 10A thus achieves knowledge transfer between the task of predicting the effect of an intervention and the task of predicting an outcome, thereby improving the performance of the prediction model and the outcome prediction model. It also achieves the effect of obtaining a first conversion model that contributes to improving the performance of the prediction model and the outcome prediction model. The information processing device 20A also achieves knowledge transfer between the task of predicting the effect of an intervention and the task of predicting the intervention status, thereby improving the performance of the prediction model and the intervention prediction model. Another effect is that a second conversion model can be obtained that contributes to improving the performance of the prediction model and the intervention prediction model.

[0143] [Other Modifications] The global model generation unit 19 may be included in the information processing device 20A instead of being included in the information processing device 10A, or may be included in a device different from either the information processing device 10A or 20A. In this modification, the information processing system 1A also achieves the above-described effects.

[0144] [Application example] 12 is a diagram schematically illustrating an application example in which a sales promotion effect due to advertisement display is predicted using the information processing systems 1 and 1A. For example, an advertiser requests one or more advertisement distribution platforms to distribute advertisements in order to promote product purchases.

[0145] In this case, as shown in FIG. 12, the advertiser server managed by the advertiser can acquire the gender and age (an example of a first feature) of a user (A, B, C, ...) (an example of a target) and whether or not the user has made a purchase (an example of a result). The ad delivery server managed by the ad delivery platform can acquire the user's gender and marital status (an example of a second feature) and whether or not an advertisement has been displayed on the user terminal (A, B, C, ...) used by the user (an example of an intervention status). However, due to privacy protection and other considerations, the advertiser server and the ad delivery server cannot mutually disclose whether or not a user has made a purchase or whether or not an advertisement has been displayed to the user. This makes it difficult to link whether or not an advertisement has been displayed to the user and whether or not the user has made a purchase. Furthermore, while the user's "gender" can be acquired by both the advertiser server and the ad delivery server, only one can acquire the "age" and "marital status." In other words, some of the features that the advertiser server and the ad delivery server can acquire about the user are different. Therefore, an advertiser server is applied as an example of the information processing devices 10 and 10A, and an advertisement delivery server is applied as an example of the information processing devices 20 and 20A. This allows the advertiser server to generate a prediction model that predicts the effect of advertisement display (an example of the effect of intervention) based on the gender and age of the user. Furthermore, the advertisement delivery server can generate a prediction model that predicts the effect of advertisement display (an example of the effect of intervention) based on the gender and marital status of the user.

[0146] According to this application example, an advertiser can cooperate with an advertisement distribution platform to generate a prediction model for predicting sales promotion effects. In this case, the advertiser does not need to know whether an advertisement was displayed to users who purchased a product, nor does it need to disclose whether the user purchased a product, and further, it does not need to match user characteristics to be acquired with the advertisement distribution platform. As a result, the advertiser can use the prediction model to predict the sales promotion effects of advertisement display based on user characteristics, and can request the advertisement distribution platform to distribute advertisements preferentially to users with the characteristics that will be most effective.

[0147] Furthermore, according to this application example, the advertising distribution platform can cooperate with advertisers to generate a prediction model for predicting sales promotion effects. In this case, the advertising distribution platform does not need to know whether users who viewed a product advertisement purchased the product, nor does it need to disclose whether an advertisement was displayed, nor does it need to match user characteristics to be acquired with the advertiser. As a result, the advertising distribution platform can predict the sales promotion effect of the advertisement display based on the user characteristics, and can preferentially deliver advertisements based on the effect. This can, for example, be expected to increase incentives from advertisers.

[0148] [Software implementation example] Some or all of the functions of the information processing devices 10, 10A, 20, 20A (hereinafter also referred to as "the above-mentioned devices") that make up the information processing systems 1, 1A may be realized by hardware such as an integrated circuit (IC chip), or by software.

[0149] In the latter case, each of the above devices is realized by, for example, a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 13. Figure 13 is a block diagram showing the hardware configuration of computer C that functions as each of the above devices.

[0150] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to operate as each of the above-mentioned devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above-mentioned devices.

[0151] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0152] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0153] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0154] Furthermore, the functions of each of the devices may be realized by a single processor provided in a single computer, by multiple processors provided in a single computer working in cooperation, or by multiple processors provided in each of multiple computers working in cooperation. Furthermore, the programs for causing each of the devices to realize the functions may be stored in a single memory provided in a single computer, or may be distributed and stored in multiple memories provided in a single computer, or may be distributed and stored in multiple memories provided in each of multiple computers.

[0155] [Appendix 1] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0156] (Appendix 1) a first information processing device and a second information processing device; The first information processing device a first acquisition means for acquiring a first feature representing an object and a result obtained regarding the object; a first prediction means for predicting a state of an intervention that may have influenced the outcome based on the first feature amount; a first prediction model training means for training a prediction model that predicts an effect of the intervention by associative learning using the first information processing device and the second information processing device, based on a third feature amount converted from the first feature amount, the result, and a status of the intervention; The second information processing device a second acquisition means for acquiring a second feature representing the object and a status of the intervention; a second prediction means for predicting the result based on the second feature amount; a second prediction model training means for training the prediction model by the associative learning based on the third feature converted from the second feature, the result, and the intervention status; the third feature is a feature converted from the first feature and the second feature so that the feature distributions are similar in the same feature space; Information processing system.

[0157] (Appendix 2) The first information processing device a first transformation model training means for training a first transformation model that transforms the first feature amount into the third feature amount; and a result prediction model training means for training a result prediction model that predicts the result from the third feature amount, The second information processing device a second transformation model training means for training a second transformation model that transforms the second feature amount into the third feature amount; an intervention prediction model training means for training an intervention prediction model that predicts the intervention status from the third feature amount; the first prediction means predicts the intervention status using the first transformation model and the intervention prediction model; the second prediction means predicts the result using the second transformation model and the result prediction model. 10. The information processing system of claim 1.

[0158] (Appendix 3) the first transformation model training means and the second transformation model training means exchange statistical information of the third feature amount and train the first transformation model and the second transformation model so that the difference between the statistical information is reduced by including a term corresponding to the difference between the statistical information in a loss function. 10. The information processing system of claim 1.

[0159] (Appendix 4) the first transformation model training means and the second transformation model training means cooperatively train a discriminative model that identifies whether the third feature quantity is converted from the first feature quantity or the second feature quantity, and train the first transformation model and the second transformation model to output a third feature quantity that causes the discriminative model to make an erroneous classification. 10. The information processing system of claim 1.

[0160] (Appendix 5) the training of the first transformation model, the training of the outcome prediction model, and the training of the prediction model are performed independently of each other; The training of the second transformation model, the training of the intervention prediction model, and the training of the prediction model are performed independently of each other. 10. The information processing system of claim 2.

[0161] (Appendix 6) the first transformation model training means, the result prediction model training means, and the first prediction model training means train the first transformation model, the result prediction model, and the prediction model in parallel while sharing an output from the first transformation model as an input to the result prediction model and the prediction model; the second transformation model training means, the intervention prediction model training means, and the second prediction model training means train the second transformation model, the intervention prediction model, and the prediction model in parallel while sharing an output from the second transformation model as an input to the intervention prediction model and the prediction model. 10. The information processing system of claim 2.

[0162] (Appendix 7) an acquisition means for acquiring features representing an object and results obtained regarding the object; a prediction means for predicting an intervention status that may have affected the outcome based on the feature amount; and a prediction model training means for training a prediction model that predicts an effect of the intervention by associative learning between the device itself and another information processing device that can acquire the intervention status, based on the converted feature values ​​converted from the feature values, the result, and the intervention status, the transformed feature is a feature that has been transformed from the feature and another feature acquired about the target by the other information processing device so that the feature distributions in the same feature space are similar; Information processing device.

[0163] (Appendix 8) an acquisition means for acquiring features representing a subject and a status of intervention that may have influenced the results obtained for the subject; a prediction means for predicting the result based on the feature amount; and second prediction model training means for training a prediction model that predicts an effect of the intervention by associative learning between the device itself and another information processing device that can acquire the result, based on the converted feature values ​​converted from the feature values, the result, and the intervention status, the transformed feature is a feature that has been transformed from the feature and another feature acquired about the target by the other information processing device so that the feature distributions in the same feature space are similar; Information processing device.

[0164] (Appendix 9) An information processing method executed by an information processing system including a first information processing device and a second information processing device, a first acquisition process in which at least one processor included in the first information processing device acquires a first feature representing an object and a result obtained regarding the object; a first prediction process in which at least one processor included in the first information processing device predicts a state of an intervention that may have affected the outcome based on the first feature amount; a first prediction model training process in which at least one processor included in the first information processing device trains a prediction model that predicts the effect of the intervention through federated learning by the first information processing device and the second information processing device, based on third feature amounts converted from the first feature amounts, the result, and the intervention status; a second acquisition process in which at least one processor included in the second information processing device acquires a second feature representing an object and a status of the intervention; a second prediction process in which at least one processor included in the second information processing device predicts the result based on the second feature amount; a second prediction model training process, performed by at least one processor included in the second information processing device, to train the prediction model by the associative learning based on the third feature amount converted from the second feature amount, the result, and the intervention status; the third feature is a feature converted from the first feature and the second feature so that the feature distributions are similar in the same feature space; Information processing methods.

[0165] (Appendix 10) an acquisition process in which at least one processor included in the information processing device acquires features representing an object and results obtained regarding the object; a prediction process in which the at least one processor predicts intervention conditions that may have affected the outcome based on the features; a prediction model training process in which the at least one processor trains a prediction model that predicts an effect of the intervention by associative learning with the information processing device itself and another information processing device that can acquire the intervention status, based on the converted feature values ​​converted from the feature values, the result, and the intervention status, the transformed feature is a feature that has been transformed from the feature and another feature acquired about the target by the other information processing device so that the feature distributions in the same feature space are similar; Information processing methods.

[0166] (Appendix 11) an acquisition process in which at least one processor included in the information processing device acquires features representing the object and a status of intervention that may have influenced the results obtained regarding the object; a prediction process in which the at least one processor predicts the outcome based on the feature amount; a prediction model training process in which the at least one processor trains a prediction model that predicts an effect of the intervention by associative learning with the information processing device itself and another information processing device that can acquire the result, based on the converted feature values ​​converted from the feature values, the result, and a status of the intervention, the transformed feature is a feature that has been transformed from the feature and another feature acquired about the target by the other information processing device so that the feature distributions in the same feature space are similar; Information processing methods.

[0167] (Appendix 12) An information processing program that causes at least one processor included in the information processing device described in Supplementary Note 7 to execute the acquisition process, the prediction process, and the prediction model training process.

[0168] (Appendix 13) An information processing program that causes at least one processor included in the information processing device described in Supplementary Note 8 to execute the acquisition process, the prediction process, and the prediction model training process.

[0169] (Appendix 14) a first information processing device and a second information processing device; The first information processing device includes at least one processor, and the at least one processor a first acquisition process for acquiring a first feature representing an object and a result obtained regarding the object; a first prediction process for predicting a state of an intervention that may have affected the outcome based on the first feature amount; a first prediction model training process for training a prediction model that predicts the effect of the intervention by federated learning using the first information processing device and the second information processing device, based on third feature amounts converted from the first feature amounts, the result, and the intervention status; The second information processing device includes at least one processor, and the at least one processor a second acquisition process for acquiring a second feature representing the target and a status of the intervention; a second prediction process for predicting the result based on the second feature amount; a second prediction model training process for training the prediction model by the associative learning based on the third feature converted from the second feature, the result, and the intervention status; the third feature is a feature converted from the first feature and the second feature so that the feature distributions are similar in the same feature space; Information processing system.

[0170] The first information processing device may further include a memory. Furthermore, the memory may store a program for causing the at least one processor included in the first information processing device to execute each of the processes. Furthermore, the second information processing device may further include a memory. Furthermore, the memory may store a program for causing the at least one processor included in the second information processing device to execute each of the processes. [Explanation of symbols]

[0171] 1. 1A Information Processing System 10, 10A, 20, 20A Information processing equipment 11 First acquisition part 12 First Prediction Section 13 First Prediction Model Training Department 14. Outcome Prediction Model Training Department 15 1st Conversion Model Training Department 19 Global Model Generation Unit 21 Second acquisition part 22 Second Prediction Section 23 Second Prediction Model Training Department 24 Intervention Prediction Model Training Department 25 Second Conversion Model Training Department C1 processor C2 Memory

Claims

1. a first information processing device and a second information processing device; The first information processing device a first acquisition means for acquiring a first feature representing an object and a result obtained regarding the object; a first prediction means for predicting a state of an intervention that may have influenced the outcome based on the first feature amount; a first prediction model training means for training a prediction model that predicts an effect of the intervention by associative learning using the first information processing device and the second information processing device, based on a third feature amount converted from the first feature amount, the result, and a status of the intervention; The second information processing device a second acquisition means for acquiring a second feature representing the object and a status of the intervention; a second prediction means for predicting the result based on the second feature amount; a second prediction model training means for training the prediction model by the associative learning based on the third feature amount converted from the second feature amount, the result, and the intervention status; the third feature amount is a feature amount converted from the first feature amount and the second feature amount so that the feature amount distributions are similar in the same feature amount space; Information processing system.

2. The first information processing device a first transformation model training means for training a first transformation model that transforms the first feature amount into the third feature amount; and a result prediction model training means for training a result prediction model that predicts the result from the third feature amount, The second information processing device a second transformation model training means for training a second transformation model that transforms the second feature quantity into the third feature quantity; an intervention prediction model training means for training an intervention prediction model that predicts the intervention status from the third feature amount; the first prediction means predicts the intervention status using the first transformation model and the intervention prediction model; the second prediction means predicts the result using the second transformation model and the result prediction model. The information processing system according to claim 1 .

3. the first transformation model training means and the second transformation model training means exchange statistical information of the third feature amount and train the first transformation model and the second transformation model so that the difference between the statistical information is reduced by including a term corresponding to the difference between the statistical information in a loss function. The information processing system according to claim 2 .

4. the first transformation model training means and the second transformation model training means cooperatively train a discriminative model that identifies whether the third feature quantity is converted from the first feature quantity or the second feature quantity, and train the first transformation model and the second transformation model to output a third feature quantity that causes the discriminative model to make an erroneous classification. The information processing system according to claim 2 .

5. the training of the first transformation model, the training of the outcome prediction model, and the training of the prediction model are performed independently of each other; the training of the second transformation model, the training of the intervention prediction model, and the training of the prediction model are performed independently of each other; The information processing system according to claim 2 .

6. the first transformation model training means, the result prediction model training means, and the first prediction model training means train the first transformation model, the result prediction model, and the prediction model in parallel while sharing an output from the first transformation model as an input to the result prediction model and the prediction model; the second transformation model training means, the intervention prediction model training means, and the second prediction model training means train the second transformation model, the intervention prediction model, and the prediction model in parallel while sharing an output from the second transformation model as an input to the intervention prediction model and the prediction model. The information processing system according to claim 2 .

7. an acquisition means for acquiring features representing an object and results obtained regarding the object; a prediction means for predicting an intervention status that may have affected the outcome based on the feature amount; and a prediction model training means for training a prediction model that predicts an effect of the intervention by associative learning between the device itself and another information processing device that can acquire the intervention status, based on the converted feature values ​​converted from the feature values, the result, and the intervention status, the transformed feature is a feature that has been transformed from the feature and another feature acquired about the target by the other information processing device so that the feature distributions in the same feature space are similar; Information processing device.

8. an acquisition means for acquiring features representing a subject and a status of intervention that may have influenced the results obtained for the subject; a prediction means for predicting the result based on the feature amount; and second prediction model training means for training a prediction model that predicts an effect of the intervention by associative learning between the device itself and another information processing device that can acquire the result, based on the converted feature values ​​converted from the feature values, the result, and the intervention status, the transformed feature is a feature that has been transformed from the feature and another feature acquired about the target by the other information processing device so that the feature distributions in the same feature space are similar; Information processing device.

9. An information processing method executed by an information processing system including a first information processing device and a second information processing device, a first acquisition process in which at least one processor included in the first information processing device acquires a first feature representing an object and a result obtained regarding the object; a first prediction process in which at least one processor included in the first information processing device predicts a state of an intervention that may have affected the outcome based on the first feature amount; a first prediction model training process in which at least one processor included in the first information processing device trains a prediction model that predicts the effect of the intervention through federated learning by the first information processing device and the second information processing device, based on third feature amounts converted from the first feature amounts, the result, and the intervention status; a second acquisition process in which at least one processor included in the second information processing device acquires a second feature amount representing a target and a status of the intervention; a second prediction process in which at least one processor included in the second information processing device predicts the result based on the second feature amount; a second prediction model training process, performed by at least one processor included in the second information processing device, to train the prediction model by the associative learning based on the third feature amount converted from the second feature amount, the result, and a status of the intervention; The information processing method, wherein the third feature is a feature converted from the first feature and the second feature so that the feature distributions are similar in the same feature space.

10. an acquisition process in which at least one processor included in the information processing device acquires features representing an object and results obtained regarding the object; a prediction process in which the at least one processor predicts intervention conditions that may have affected the outcome based on the features; a prediction model training process in which the at least one processor trains a prediction model that predicts an effect of the intervention by associative learning with the information processing device itself and another information processing device that can acquire the intervention status, based on the converted feature values ​​converted from the feature values, the result, and the intervention status, the transformed feature is a feature that has been transformed from the feature and another feature acquired about the target by the other information processing device so that the feature distributions in the same feature space are similar; Information processing methods.

Images