Information presentation system, information presentation method, and computer program

Abstract

This information presentation system (1) comprises: a prediction means (110) for predicting, on the basis of information relating to the health state of a subject, an item to be included in a care plan for the subject; an identification means (120) for identifying a feature amount that contributed to the prediction of the item; an extraction means (130) for extracting, on the basis of the predicted item and the identified feature amount, grounds for including the item in the care plan; and a presentation means (140) for presenting the predicted item and the grounds corresponding to the item. Such an information presentation system makes it possible to appropriately present information relating to a care plan.

Description

[Technical Field]

[0001] The present invention relates to the technical fields of an information presentation system, an information presentation method, and a computer program that present information related to a care plan. [Background technology]

[0002] Known systems of this type support the creation of care plans for elderly people, care recipients, etc. For example, Patent Document 1 discloses a technology for calculating the type of service and amount of intervention in a support plan to be applied to a care recipient based on information about the care recipient's health condition. Patent Document 2 discloses a technology for obtaining the probability that the level of care required will improve for each care plan and outputting a care plan with a high probability of improving the level of care required. Patent Document 3 discloses a technology for presenting standard care suited to the patient's symptoms and condition, thereby improving the quality of care and standardizing the content. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-046474 [Patent Document 2] International Publication No. 2018 / 030340 [Patent Document 3] Japanese Patent Application Publication No. 11-312199 Summary of the Invention [Problem to be solved by the invention]

[0004] When making a proposal regarding a care plan, if the basis for the proposal cannot be shown, the caregiver or care plan creator may question why such a proposal was made. In such a case, even if the proposal is appropriate, the caregiver or care plan creator may not be convinced of the proposal and may not adopt it. The technologies described in Patent Documents 1 to 3 do not take into account the above-mentioned situation, and there is room for improvement.

[0005] The present invention has been made in consideration of the above-mentioned problems, and an object of the present invention is to provide an information presentation system, an information presentation method, and a computer program that are capable of appropriately presenting information related to care plans. [Means for solving the problem]

[0006] One aspect of the information presentation system of the present invention comprises a prediction means for predicting items to be included in a care plan for a subject based on information regarding the subject's health condition that should be included in the care plan for the subject, an identification means for identifying features that contributed to the prediction of the items, an extraction means for extracting reasons for including the items in the care plan based on the predicted items and the identified features, and a presentation means for presenting the predicted items and the reasons corresponding to the items.

[0007] One aspect of the information presentation method of the present invention predicts items to be included in a care plan for a subject based on information regarding the subject's health condition, identifies features that contributed to the prediction of the items, extracts reasons for including the items in the care plan based on the predicted items and the identified features, and presents the predicted items and the reasons corresponding to the items.

[0008] One aspect of the computer program of the present invention operates a computer to predict items to be included in a care plan for a subject based on information about the subject's health condition, identify features that contributed to the prediction of the items, extract reasons for including the items in the care plan based on the predicted items and the identified features, and present the predicted items and the reasons corresponding to the items. [Effects of the Invention]

[0009] According to one aspect of each of the above-described information presentation system, information presentation method, and computer program, it is possible to appropriately present information for supporting the creation of a care plan. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing the overall configuration of an information presentation system according to a first embodiment. [Figure 2] 1 is a block diagram showing a hardware configuration of an information presentation system according to a first embodiment. [Figure 3] 4 is a flowchart showing the flow of operations of the information presentation system according to the first embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing the linking of reasons in a reason list. [Figure 5] FIG. 10 is a conceptual diagram showing a specific example of linking of grounds. [Figure 6] FIG. 2 is a diagram showing an example of presentation by the information presentation system according to the first embodiment. [Figure 7] FIG. 10 is a block diagram showing the overall configuration of an information presentation system according to a second embodiment. [Figure 8] 10 is a flowchart showing the flow of operations of the information presentation system according to the second embodiment. [Figure 9] FIG. 10 is a diagram showing an example of presentation by the information presentation system according to the second embodiment. [Figure 10] FIG. 10 is a block diagram showing the overall configuration of an information presentation system according to a third embodiment. [Figure 11] 10 is a flowchart showing the flow of operations of the information presentation system according to the third embodiment. [Figure 12] FIG. 11 is a diagram showing an example of presentation by the information presentation system according to the third embodiment. [Figure 13] 13 is a graph showing an example of calculation of a sort score in the information presentation system according to the fourth embodiment. [Figure 14] FIG. 10 is a diagram showing the relationship between sort scores and display orders. [Figure 15] FIG. 11 is a block diagram showing the overall configuration of an information presentation system according to a fifth embodiment. [Figure 16] FIG. 10 is a conceptual diagram showing a method for utilizing evidence after updating a prediction model. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of an information presentation system, an information presentation method, and a computer program will be described with reference to the drawings.

[0012] First Embodiment An information presentation system according to a first embodiment will be described with reference to FIGS.

[0013] (System Configuration) First, the configuration of an information presentation system according to a first embodiment will be described with reference to Fig. 1 and Fig. 2. Fig. 1 is a block diagram showing the overall configuration of the information presentation system according to the first embodiment. Fig. 2 is a block diagram showing the hardware configuration of the information presentation system according to the first embodiment.

[0014] 1, an information presentation system 1 according to the first embodiment is configured as a system that presents information used when creating a care plan for a subject. The information presentation system 1 is configured to include, as main components for realizing its functions, an item prediction unit 110, a feature identification unit 120, a reason extraction unit 130, and a presentation unit 140.

[0015] The item prediction unit 110 is configured to predict items to be included in a care plan for a subject using information indicating the subject's health condition. The "subject" refers to a person who is the target of care, such as a person requiring nursing care or assistance. The "information indicating the subject's health condition" refers to information acquired during an assessment (information collection) for creating a care plan. The information indicating the subject's health condition may include various information about the subject, such as basic information such as the subject's height and weight, as well as information about specific symptoms, actions the subject can perform, and medical history. The item prediction unit 110 predicts items related to a care plan appropriate for the subject based on such information. The item prediction unit 110 may predict items that serve as goals for the subject, such as "being able to walk around the house," "being able to enjoy shopping and interacting with friends," "being able to engage in outdoor activities," and "being able to walk without using a cane." Such items correspond to "needs," which will be described later. The item prediction unit 110 may also be configured to predict multiple items. In this case, the item prediction unit 110 may have a function of selecting an item that is particularly suitable for the subject from among the multiple predicted items. Note that the item prediction unit 110 may predict an item using, for example, a prediction model that has been machine-learned in advance. The machine learning of the prediction model can be performed using, for example, information indicating the subject's past health condition, information regarding past care plans, etc.

[0016] The feature amount identifying unit 120 is configured to be able to identify feature amounts that contributed to the prediction in the item prediction unit 110. More specifically, the feature amount identifying unit 120 is configured to be able to identify feature amounts that contributed to the prediction based on the prediction result of the item prediction unit 110. Note that the "feature amount" here refers to a parameter that can be calculated from information indicating the subject's health condition, and is used as an input to the item prediction unit 110. The feature amount identifying unit 120 may be configured to identify only feature amounts that contribute significantly among multiple types of feature amounts used for prediction.

[0017] The basis extraction unit 130 is configured to extract the basis for including the predicted item in the care plan (in other words, the reason why the item was predicted) based on the item predicted by the item prediction unit 110 and the feature identified by the feature identification unit 120. The basis extraction unit 130 extracts the basis according to the predicted item and the identified feature from a basis list 200 in which a plurality of basis are stored in advance. Note that the basis list 200 stores a plurality of basis linked to the item and the feature. Therefore, once the predicted item and the identified feature are known, the basis extraction unit 130 can easily extract the basis by searching the basis list 200 using the item and the feature as conditions.

[0018] The presentation unit 140 is configured to be able to present the items predicted by the item prediction unit 110 and the grounds extracted by the grounds extraction unit 130. The presentation unit 140 is configured as a terminal operated by, for example, a care plan creator or a caregiver who creates a care plan, and presents the predicted items and the extracted grounds as information to support the creation of the care plan. More specifically, the presentation unit 140 presents the predicted items and the extracted grounds by displaying them on a display of a personal computer, smartphone, tablet, or the like. Note that the presentation unit 140 may be configured to be able to present information other than the items and grounds.

[0019] 2, the information presentation system 1 according to the first embodiment includes a CPU (Central Processing Unit) 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, and a storage device 14. The information presentation system 1 may further include an input device 15 and an output device 16. The CPU 11, RAM 12, ROM 13, storage device 14, input device 15, and output device 16 are connected via a data bus 17.

[0020] The CPU 11 loads a computer program. For example, the CPU 11 may load a computer program stored in at least one of the RAM 12, the ROM 13, and the storage device 14. For example, the CPU 11 may load a computer program stored in a computer-readable storage medium using a storage medium reading device (not shown). The CPU 11 may acquire (i.e., load) the computer program from a device (not shown) located outside the information presentation system 1 via a network interface. The CPU 11 controls the RAM 12, the storage device 14, the input device 15, and the output device 16 by executing the loaded computer program. In particular, in this embodiment, when the CPU 11 executes the loaded computer program, a functional block is realized within the CPU 11 for predicting items to be suggested and presenting them together with the reasons for the prediction (see FIG. 1).

[0021] The RAM 12 temporarily stores computer programs executed by the CPU 11. The RAM 12 temporarily stores data that is temporarily used by the CPU 11 while the CPU 11 is executing the computer programs. The RAM 12 may be, for example, a D-RAM (Dynamic RAM).

[0022] The ROM 13 stores computer programs executed by the CPU 11. The ROM 13 may also store fixed data. The ROM 13 may be, for example, a P-ROM (Programmable ROM).

[0023] The storage device 14 stores data that is to be saved long-term by the information presentation system 1. The storage device 14 may operate as a temporary storage device for the CPU 11. The storage device 14 may include, for example, at least one of a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and a disk array device.

[0024] The input device 15 is a device that receives input instructions from a user of the information presentation system 1. The input device 15 may include, for example, at least one of a keyboard, a mouse, and a touch panel. More specifically, the input device 15 may include a smartphone, a tablet, a personal computer, etc.

[0025] The output device 16 is a device that outputs information related to the information presentation system 1 to the outside. For example, the output device 16 may be a display device that can display information related to the information presentation system 1. More specifically, the output device 16 may be a display of a smartphone, a tablet, a personal computer, or the like.

[0026] (Operation description) Next, the flow of operations of the information presentation system 1 according to the first embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart showing the flow of operations of the information presentation system according to the first embodiment.

[0027] 3, during operation of the information presentation system 1 according to the first embodiment, the item prediction unit 110 first acquires information about the health condition of the subject (step S11). Then, based on the input information, the item prediction unit 110 predicts items to be included in the care plan for the subject (step S12).

[0028] Next, the feature identifying unit 120 identifies the feature that contributed to the prediction (step S13). Then, the basis extracting unit 130 extracts the basis for including the item in the care plan based on the item predicted by the item predicting unit 110 and the feature identified by the feature identifying unit 120 (step S14).

[0029] Thereafter, the presentation unit 140 presents the items predicted by the item prediction unit 110 and the grounds extracted by the grounds extraction unit 130 (step S15). A specific presentation example here will be described in detail later.

[0030] (Method of extracting evidence) Next, a method for extracting grounds by the grounds extraction unit 130 will be specifically described with reference to Fig. 4 to Fig. 6. Fig. 4 is a conceptual diagram showing linking of grounds in a grounds list. Fig. 5 is a conceptual diagram showing a specific example of linking of grounds. Fig. 6 is a diagram showing an example of presentation by the information presentation system according to the first embodiment.

[0031] As shown in FIG. 4 , the basis list stores multiple bases linked to needs and explanatory variables corresponding to those needs. The “needs” correspond to items predicted by the item prediction unit 110 and are information indicating what the subject wants to do, what they hope for, what they are struggling with, factors that hinder the user's independence, etc. In addition to the above needs, information corresponding to items predicted by the item prediction unit 110 also includes “long-term goals,” “short-term goals,” “service content,” and “service type.” Here, the “long-term goals” are goals set to resolve needs and require a relatively long time to achieve. The “short-term goals” are goals required to achieve the long-term goals and require a relatively short time to achieve. The “service content” refers to the content of the service for achieving the short-term goals. The “service type” refers to the service actually provided to implement the service content. The “explanatory variables” are variables (coefficients) used to predict needs. A feature can be calculated by adding personal information about the subject (i.e., the “information about the subject's health condition” described above) to the explanatory variables. For example, if needs are "Y," explanatory variables are "a1, a2, a3, ...," and information about the subject's health condition is "x1, x2, x3, ...," the prediction formula for needs Y can be expressed as "Y = a1 x1 + a2 x2 + a3 x3 + ...." Here, three explanatory variables are set for needs A. This indicates that subjects with the feature quantities of explanatory variables (1), (2), and (3) are more likely to meet needs A. Therefore, when the feature quantities of explanatory variables (1), (2), and (3) are calculated from information indicating the subject's health condition, items corresponding to needs A are predicted as items to be included in the care plan.

[0032] The grounds list stores grounds (1) to (5) so as to be linked to explanatory variables (1), (2), and (3) corresponding to need A, as well as combinations thereof. Specifically, grounds (1) are linked to explanatory variable (1). Grounds (2) are linked to the combination of explanatory variables (1) and (2). Grounds (3) are linked to explanatory variable (2). Grounds (4) are linked to the combination of explanatory variables (2) and (3). Grounds (5) are linked to explanatory variable (3). In other words, the grounds list stores causal relationships between needs predicted by the item prediction unit 110 and their grounds by linking them to explanatory variables. Storing multiple grounds in this way makes it possible to easily search for grounds from combinations of needs and features (i.e., values ​​obtained by adding the subject's state to explanatory variables).

[0033] As shown in FIG. 5, for example, assume that there are explanatory variables such as "has heart disease," "can walk," and "can take a bath," and a need such as "want to live without anxiety." In the evidence list, the explanatory variable "has heart disease" is linked to the evidence "risk of recurrence," the combination of the explanatory variables "has heart disease" and "can walk" is linked to the evidence "does not know what pace to walk at to stabilize the condition," and the explanatory variable "can take a bath" is linked to the evidence "does not know what to pay attention to." In this case, if the item "want to live without anxiety" is predicted from information about the subject's health condition, and the features contributing to the prediction reveal that "has heart disease," "can walk," and "cannot take a bath," the evidence extraction unit 130 extracts the evidence "risk of recurrence" and "does not know what pace to walk at to stabilize the condition." The list of reasons also includes the reason "I don't know what to pay attention to," but since this subject "cannot take a bath," the reason "I don't know what to pay attention to" corresponding to the explanatory variable "can take a bath" is not extracted.

[0034] As shown in FIG. 6, in the case of FIG. 5 described above, the presentation unit 140 presents the item "I want to live without anxiety" along with two reasons for the item, "There is a risk of recurrence" and "I don't know what pace I need to walk to stabilize my condition." The item and the reasons do not necessarily need to be presented simultaneously on the same screen. For example, only the item may be displayed in the initial state, and the reasons may be displayed when an operation to display the reasons is performed. Also, for convenience of explanation, only one item is displayed here, but if multiple items are predicted, multiple items may be presented simultaneously. In that case, the reasons may be presented for each item.

[0035] (Technical Effects) Next, the technical effects obtained by the information presentation system 1 according to the first embodiment will be described.

[0036] As described in Figures 1 to 6, the information presentation system 1 according to the first embodiment presents items to be included in a care plan for a subject and the reasons for each item. Therefore, a caregiver or other person who is presented with this information can create a care plan with confidence in the predicted items. In other words, because the causal relationship between the predicted items and their reasons is clearly shown, a caregiver or other person can understand the reasons why the items were presented and then create an appropriate care plan.

[0037] Second Embodiment Next, an information presentation system according to a second embodiment will be described with reference to Figures 7 to 9. The second embodiment differs from the first embodiment in only some of its configurations and operations, and the remaining parts are generally the same. Therefore, the following will describe only the parts that are different from the first embodiment already described, and will omit a description of other overlapping parts as appropriate.

[0038] (System Configuration) First, the configuration of an information presentation system 1 according to the second embodiment will be described with reference to Fig. 7. Fig. 7 is a block diagram showing the overall configuration of the information presentation system according to the second embodiment. Note that in Fig. 7, the same components as those shown in Fig. 1 are denoted by the same reference numerals.

[0039] As shown in FIG. 7, the information presentation system 1 according to the second embodiment further includes a graph creation unit 150 and a reason addition unit 160 in addition to the configuration of the first embodiment (see FIG. 1).

[0040] The graph creation unit 150 is configured to be able to create a graph showing the feature amounts based on the feature amounts identified by the feature amount identification unit 120. Specifically, the graph creation unit 150 is configured to be able to create a graph showing scores obtained by quantifying the feature amounts, a graph showing the contribution rate of the feature amounts to prediction, etc. The graph created by the graph creation unit 150 is output to the presentation unit 140 and displayed together with the items and the reasons.

[0041] The basis adding unit 160 is configured to be able to add a new basis to the basis list 200. More specifically, the basis adding unit 160 can add a new basis to the basis list 200 by using feedback information (e.g., an evaluation of the presented basis by the caregiver) after the presentation by the presenting unit 140. The specific process for adding a basis will be described in detail below.

[0042] (Operation description) Next, the flow of operations of the information presentation system 1 according to the second embodiment will be described with reference to Fig. 8. Fig. 8 is a flowchart showing the flow of operations of the information presentation system according to the second embodiment. Note that in Fig. 8, the same processes as those shown in Fig. 3 are denoted by the same reference numerals.

[0043] As shown in FIG. 8, when the information presentation system 1 according to the second embodiment operates, first, the processes of steps S11 to S14 are executed, similarly to the first embodiment.

[0044] Thereafter, in the second embodiment, the graph creation unit 150 creates a graph using the feature amounts identified by the feature amount identification unit 120 (step S21). Note that the processing of step S21 may be executed immediately when the feature amounts are identified. That is, the processing of step S21 may be executed before the processing of extracting the basis in step S14 is executed, or may be executed simultaneously in parallel with the processing of step S14.

[0045] Next, the presentation unit 140 presents the items predicted by the item prediction unit 110, the grounds extracted by the grounds extraction unit 130, and the graph created by the graph creation unit (step S22). Note that the items, grounds, and graphs do not necessarily need to be presented on the same screen of the presentation unit 140. For example, the care plan creator may operate the presentation unit 140 to switch between a state in which the items are displayed, a state in which the grounds are displayed, and a state in which the graph is displayed.

[0046] Next, the basis adding unit 160 acquires feedback information on the presented basis (step S23). The "feedback information" is information indicating the validity of the basis presented for the predicted item, and is input, for example, by the person to whom the basis is presented (for example, a caregiver or a care plan creator) who has received the presentation from the presenting unit 140. The basis adding unit 160 uses the acquired feedback information to determine whether or not a convincing basis has been presented by the presenting unit 140 (step S24). For example, the basis adding unit 160 uses evaluation information on the basis by the caregiver or the care plan creator acquired as feedback information to determine whether or not a convincing basis has been presented.

[0047] If it is determined that a satisfactory basis has been presented (step S24: YES), the subsequent processes are omitted and the series of operations ends. On the other hand, if it is determined that a satisfactory basis has not been presented (step S24: NO), the basis adding unit 160 executes a process of adding a new basis to the basis list 200 (step S25). Note that the new basis may be newly input by a caregiver, a care plan creator, or the like who is not satisfied with the presented basis. Alternatively, the new basis may be a partial modification of an existing basis.

[0048] (Display example) Next, a specific display example in the information presentation system 1 according to the second embodiment will be described with reference to Fig. 9. Fig. 9 is a diagram showing a presentation example by the information presentation system according to the second embodiment.

[0049] As shown in FIG. 9, in the information presentation system 1 according to the second embodiment, in addition to the display example of the first embodiment (see FIG. 6), buttons for "Display graph" and "Add new reason" are displayed.

[0050] Here, if you press "Display graph," the graph created by the graph creation unit 150 will be displayed. Therefore, if you want to know information about the feature (for example, a score that quantifies the feature, or the contribution rate of the feature), you can press "Display graph" to display the graph. Also, if you press "Add new reason," a screen for inputting new reason will be displayed. Therefore, if you are not satisfied with the reason presented, you can press "Add new reason" to add new reason.

[0051] (Technical Effects) Next, the technical effects obtained by the information presentation system 1 according to the second embodiment will be described.

[0052] 7 to 9, in the information presentation system 1 according to the second embodiment, information on feature quantities is presented in addition to the items and the grounds. Therefore, compared to the case where only the items and the grounds are displayed, more information on the prediction of items is presented. Therefore, when presented with this information, caregivers, care plan creators, etc. can be more convinced of the predicted items and create an appropriate care plan.

[0053] In the second embodiment, if a satisfactory item is not displayed, a new item can be added. This increases the number of grounds stored in the grounds list, making it possible to present more appropriate items for subsequent predictions.

[0054] Third Embodiment Next, an information presentation system according to a third embodiment will be described with reference to Figures 10 to 12. The third embodiment differs only in part of the configuration and operation from the first and second embodiments described above, and the remaining parts are generally the same. Therefore, the following will describe only the parts that are different from the first and second embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0055] (System Configuration) First, the configuration of the information presentation system 1 according to the third embodiment will be described with reference to Fig. 10. Fig. 10 is a block diagram showing the overall configuration of the information presentation system according to the third embodiment. Note that in Fig. 10, the same components as those shown in Fig. 7 are denoted by the same reference numerals.

[0056] 10, the information presentation system 1 according to the third embodiment further includes a basis evaluation unit 170 in addition to the configuration of the second embodiment (see FIG. 7). Also, the basis list 200 is stored separately as a regular list 210 and a candidate list 220.

[0057] The basis evaluation unit 170 is configured to be able to evaluate the basis stored in the regular list 210 and the candidate list 220. The basis evaluation unit 170 is configured to be able to acquire evaluation information for the basis stored in the regular list 210 and the candidate list 220, for example, based on feedback information after the basis is presented, and output the evaluation result.

[0058] Here, the regular list 210 stores grounds that satisfy a predetermined evaluation criterion. On the other hand, the candidate list 220 stores grounds that do not satisfy the predetermined evaluation criterion. The "predetermined evaluation criterion" here refers to a criterion (e.g., a threshold) for determining whether a ground is to be stored in the regular list 210 or the candidate list 220, and a reference value is set in advance as appropriate. Both the grounds stored in the regular list 210 and the grounds stored in the candidate list 220 are targets for extraction by the grounds extraction unit 130. However, the grounds stored in the regular list 210 may be set to be more easily extracted than the grounds stored in the candidate list 220. Alternatively, the grounds stored in the regular list 210 may be presented as being more reliable than the grounds stored in the candidate list 220 (for example, displayed in a display manner that indicates that they are more reliable).

[0059] The basis evaluation unit 170 is configured to be able to switch the basis stored in the regular list 210 and the candidate list 220 according to the evaluation result. Furthermore, the basis evaluation unit 170 is configured to be able to delete the basis stored in the candidate list 220 according to the evaluation result. Specifically, the basis evaluation unit 170 can delete from the candidate list 220 a basis that has reached a predetermined deletion criterion. The "predetermined deletion criterion" here is a criterion for determining whether or not to delete a basis, and a criterion value is set in advance as appropriate.

[0060] (Operation description) Next, the flow of operations of the information presentation system 1 according to the third embodiment will be described with reference to Fig. 11. Fig. 11 is a flowchart showing the flow of operations of the information presentation system according to the third embodiment. In Fig. 11, the same processes as those shown in Fig. 8 are denoted by the same reference numerals.

[0061] As shown in FIG. 11, when the information presentation system 1 according to the third embodiment operates, first, the processes of steps S11 to S14 and then steps S21 to S25 are executed, similarly to the second embodiment.

[0062] Thereafter, particularly in the third embodiment, the basis evaluation unit 170 acquires evaluation information of the basis presented by the presentation unit 140 (step S31). Note that if the feedback information in step S23 includes evaluation information of the presented basis, step S31 may be omitted and the feedback information acquired in step S23 may be used. Then, the basis evaluation unit 170 performs evaluation using the acquired evaluation information and replaces the basis stored in the regular list 210 and the candidate list 220 (step S32).

[0063] Specifically, the basis evaluation unit 170 moves a basis that meets the predetermined evaluation criteria as a result of the evaluation (for example, a basis that has received a good evaluation) from the candidate list 220 to the regular list 210. Also, the basis evaluation unit 170 moves a basis that no longer meets the predetermined evaluation criteria as a result of the evaluation (for example, a basis that has received a bad evaluation) from the regular list 210 to the candidate list 220. Furthermore, the basis evaluation unit 170 deletes from the candidate list 220, among the reasons stored in the candidate list 220, a basis that meets the predetermined deletion criteria (for example, a basis that has received an extremely bad evaluation). Note that the basis evaluation unit 170 may delete from the regular list 210 a basis that meets the predetermined deletion criteria, even if it is stored in the regular list 210.

[0064] (Display example) Next, a specific display example in the information presentation system 1 according to the third embodiment will be described with reference to Fig. 12. Fig. 12 is a diagram showing a presentation example by the information presentation system according to the third embodiment.

[0065] 12, in the information presentation system 1 according to the third embodiment, an "OK" button and an "NG" button are displayed in addition to the display example of the second embodiment (see FIG. 9). The "OK" button and the "NG" button are displayed for each reason.

[0066] Here, when the "OK" button is pressed, information indicating that the basis has received a good evaluation is output to the basis evaluation unit 170. On the other hand, when the "NG" button is pressed, information indicating that the basis has received a bad evaluation is output to the basis evaluation unit 170. Note that here, the evaluation is performed using two options, "OK" or "NG," but evaluation may be possible using multiple levels, such as three or five levels. Alternatively, it may be possible to input a score for the basis.

[0067] (Technical Effects) Next, the technical effects obtained by the information presentation system 1 according to the third embodiment will be described.

[0068] 10 to 12, in the information presentation system 1 according to the third embodiment, the presented grounds are replaced or deleted depending on the evaluation results of the grounds. This makes it possible to make highly rated grounds easier to extract, while making it possible to make low-rated grounds more difficult to extract or to prevent them from being extracted at all. As a result of such evaluation of the grounds, the grounds stored in the regular list 210 and the candidate list 220 become more appropriate, and each time an evaluation is performed, higher quality grounds are presented.

[0069] <Fourth embodiment> Next, an information presentation system according to a fourth embodiment will be described with reference to Fig. 13 and Fig. 14. The fourth embodiment differs from the first to third embodiments in only some of its configurations and operations, and the remaining parts are generally the same. Therefore, the following description will focus on the parts that are different from the first to third embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0070] (Calculation of sort score) First, a process for calculating a sort score executed in the information presentation system 1 according to the fourth embodiment will be described with reference to Fig. 13. Fig. 13 is a graph showing an example of calculation of a sort score in the information presentation system according to the fourth embodiment.

[0071] As shown in FIG. 13 , in the information presentation system 1 according to the fourth embodiment, before the presentation unit 140 presents the evidence, a sort score for changing the display order of the evidence is calculated. The sort score can be calculated from the contribution rate of the explanatory variable corresponding to the evidence to the prediction. More specifically, the sort score can be calculated as the product of the contribution rate of the explanatory variable and the actual score of the explanatory variable (i.e., the score of the feature calculated from information related to the subject's health condition). When there are evidences corresponding to multiple explanatory variables, the average value of the sort scores calculated for each of the multiple explanatory variables can be used.

[0072] Note that the method for calculating the sort score here is merely an example, and the sort score may be calculated from other parameters. For example, the contribution rate of the explanatory variable may be used as the sort score as is, or the value obtained by multiplying the contribution rate of the explanatory variable by another parameter may be used as the sort score.

[0073] (Order of evidence display) Next, the display order of the grounds based on the sort score will be specifically described with reference to Fig. 14. Fig. 14 is a diagram showing the relationship between the sort score and the display order. Note that the sort score shown in Fig. 14 corresponds to the sort score calculated in Fig. 13.

[0074] Assume that a sort score has been calculated for each of the grounds (1) to (7) corresponding to the explanatory variables (1) to (5) as shown in Figure 14. Specifically, the sort score for grounds (1) is "1.6", the sort score for grounds (2) is "2.1", the sort score for grounds (3) is "2.6", the sort score for grounds (4) is "2.5", the sort score for grounds (5) is "2.4", the sort score for grounds (6) is "0.5", and the sort score for grounds (7) is "1".

[0075] In this case, the presentation unit 140 rearranges the displayed reasons in descending order of sort score. Therefore, the display order of the reasons is: reason (3), reason (4), reason (5), reason (2), reason (1), reason (7), and reason (6). Note that if there are reasons with the same sort score, the display order of the reasons may be determined taking into consideration parameters other than the sort score. For example, the reason with the lowest number may simply be displayed at the top, or the display order may be determined using different sort scores calculated using different formulas.

[0076] (Technical Effects) Next, the technical effects obtained by the information presentation system 1 according to the fourth embodiment will be described.

[0077] 13 and 14, in the information presentation system 1 according to the fourth embodiment, the display order of the grounds is determined according to the sort score. In particular, since the sort score is calculated from the contribution rate of the explanatory variable corresponding to the grounds to the prediction, more reliable grounds are displayed at the top. Therefore, compared to the case where the display order of the grounds is not changed, it is possible to present the grounds in a more appropriate state.

[0078] Fifth Embodiment Next, an information presentation system according to a fifth embodiment will be described with reference to Fig. 15 and Fig. 16. The fifth embodiment differs from the first to fourth embodiments in only some of its configurations and operations, and other parts are generally similar. Therefore, the following description will focus on parts that differ from the first to fourth embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0079] (System Configuration) First, the configuration of an information presentation system 1 according to the fifth embodiment will be described with reference to Fig. 15. Fig. 15 is a block diagram showing the overall configuration of the information presentation system according to the fifth embodiment. Note that in Fig. 15, the same components as those shown in Fig. 10 are denoted by the same reference numerals.

[0080] As shown in FIG. 15, the information presentation system 1 according to the fifth embodiment further includes a model update unit 180 in addition to the configuration of the third embodiment (see FIG. 10).

[0081] The model update unit 180 is configured to be able to update the prediction model used by the item prediction unit 110. Specifically, the model update unit 180 is configured to be able to update the prediction model by machine learning using information on the subject's health condition and correct answer data for items to be presented to the subject. The correct answer data can be acquired from feedback information after the items are presented. For example, if the presented items are determined to be appropriate by a caregiver, a care plan creator, or the like, the information at that time can be used as correct answer data. Note that existing technologies can be appropriately adopted for machine learning using correct answer data, and therefore a detailed description thereof will be omitted here.

[0082] (List of grounds after model update) Next, the basis list after the prediction model is updated will be described with reference to Fig. 16. Fig. 16 is a conceptual diagram showing how to use the basis after the prediction model is updated.

[0083] As shown in Figure 16, suppose a prediction model that predicts need A from explanatory variables (1), (2), and (3) and predicts need B from explanatory variables (1), (2), and (4) is updated to a prediction model that predicts need A from explanatory variables (1), (3), and (4). In this case, because the combinations of explanatory variables and needs are changed, the basis associated with these combinations can no longer be used as is.

[0084] However, even when a prediction model is updated, it is possible to use some of the evidence before the update as is. For example, if there is an unchanged combination of explanatory variables and needs, that evidence can be used in the same way as before the update. Specifically, since the combination of explanatory variable (1) and need A and the combination of explanatory variable (3) and need A have not changed before and after the update, evidence (1) linked to the combination of explanatory variable (1) and need A and evidence (5) linked to the combination of explanatory variable (3) and need A can be used as is.

[0085] Furthermore, grounds associated with needs of the same category and grounds associated with explanatory variables of the same category can be left as candidate grounds (i.e., grounds stored in the candidate list 220). For example, if need A and need B are needs of the same category, and explanatory variables (1) and (3) are explanatory variables of the same category, then it is possible to leave grounds (2), (4), (7), (8), (9), and (10) as candidate grounds. Note that, as described in the third embodiment, the grounds left as candidate grounds can be moved to the regular list 210 or deleted from the candidate list 220 based on subsequent evaluation.

[0086] (Technical Effects) Next, the technical effects obtained by the information presentation system 1 according to the fifth embodiment will be described.

[0087] 15 and 16, in the information presentation system 1 according to the fifth embodiment, the prediction model is updated, making it possible to predict more appropriate items. Furthermore, when the prediction model is updated, some of the grounds can be reused (i.e., it is not necessary to re-store all of the grounds by linking them to explanatory variables and needs from the beginning), which significantly reduces the effort required when updating the prediction model.

[0088] <Additional Notes> The following additional notes are provided regarding the above-described embodiment.

[0089] (Appendix 1) The information presentation system described in Appendix 1 is an information presentation system characterized by comprising: a prediction means for predicting items to be included in a care plan for a subject based on information about the subject's health condition; an identification means for identifying features that contributed to the prediction of the items; an extraction means for extracting reasons for including the items in the care plan based on the predicted items and the identified features; and a presentation means for presenting the predicted items and the reasons corresponding to the items.

[0090] (Appendix 2) The information presentation system described in Appendix 2 is the information presentation system described in Appendix 1, characterized in that the extraction means extracts reasons corresponding to the item from a list in which reasons for including the item in the care plan are linked to the item and the feature and stored.

[0091] (Appendix 3) The information presentation system described in Appendix 3 is the information presentation system described in Appendix 2, further comprising an addition means for adding new grounds to the list based on feedback information obtained after presentation by the presentation means.

[0092] (Appendix 4) The information presentation system described in Appendix 4 is the information presentation system described in Appendix 3, characterized in that the feedback information is information indicating the validity of the basis extracted for the predicted item.

[0093] (Appendix 5) The information presentation system described in Appendix 5 is the information presentation system described in Appendix 3 or 4, characterized in that the list includes a regular list including the grounds that satisfy predetermined evaluation criteria and a candidate list including the grounds that do not satisfy the predetermined evaluation criteria, and the adding means adds new grounds to the candidate list.

[0094] (Appendix 6) The information presentation system described in Appendix 6 is the information presentation system described in Appendix 5, further comprising an evaluation means for replacing the grounds stored as the list based on an evaluation result of whether or not the grounds satisfy the predetermined evaluation criteria.

[0095] (Appendix 7) The information presentation system described in Appendix 7 is the information presentation system described in Appendix 6, characterized in that the evaluation means deletes from the candidate list those grounds included in the candidate list that meet predetermined deletion criteria.

[0096] (Appendix 8) The information presentation system described in Appendix 8 is the information presentation system described in any one of Appendixes 1 to 7, characterized in that the presentation means sorts and presents the extracted grounds based on a score calculated from the contribution rate of the identified feature to the prediction.

[0097] (Appendix 9) The information presentation system described in Appendix 9 is the information presentation system described in any one of Appendixes 1 to 8, characterized in that the presentation means presents at least one of the feature and the contribution rate of the feature to the prediction in addition to the predicted item and the extracted basis.

[0098] (Appendix 10) The information presentation system described in Appendix 10 is the information presentation system described in any one of Appendixes 1 to 9, characterized in that the prediction means predicts items to be included in the care plan of the subject using a pre-prepared prediction model.

[0099] (Appendix 11) The information presentation system described in Appendix 11 is the information presentation system described in Appendix 10, further comprising an update means for updating the prediction model based on information regarding the subject's health condition used for the prediction and the care plan created based on the items presented by the presentation means.

[0100] (Appendix 12) The information presentation method described in Appendix 12 is an information presentation method characterized by predicting items to be included in a care plan for a subject based on information about the subject's health condition, identifying features that contributed to the prediction of the items, extracting reasons for including the items in the care plan based on the predicted items and the identified features, and presenting the predicted items and the reasons corresponding to the items.

[0101] (Appendix 13) The computer program described in Appendix 13 is a computer program characterized by operating a computer to predict items to be included in a care plan for a subject based on information about the subject's health condition, identify features that contributed to the prediction of the items, extract reasons for including the items in the care plan based on the predicted items and the identified features, and present the predicted items and the reasons corresponding to the items.

[0102] The present invention can be modified as appropriate within the scope that does not contradict the gist or idea of ​​the invention that can be read from the claims and the entire specification, and information presentation systems, information presentation methods, and computer programs that involve such modifications are also included in the technical idea of ​​the present invention. [Explanation of symbols]

[0103] 1 Information presentation system 110 Item Prediction Section 120 Feature Identification Unit 130 Basis Extraction Unit 140 Presentation section 150 Graph Creation Department 160 Additional grounds 170 Basis Evaluation Section 180 Model Update Department 200 List of Reasons 210 Official List 220 candidate list

Claims

1. A prediction means for predicting items to be included in a care plan for a subject based on information about the subject's health condition; An identification means for identifying a feature that contributed to the prediction of the item; an extraction means for extracting, based on the predicted item and the identified feature, a reason for including the item in the care plan from a list in which the reason for including the item in the care plan is linked to the item and the feature and stored; a presentation means for presenting the predicted items and the grounds corresponding to the items; adding means for adding new grounds to the list based on feedback information obtained after the presentation by the presenting means; Equipped with the list includes a regular list including the evidence that satisfies a predetermined evaluation criterion determined based on a predetermined threshold, and a candidate list including the evidence that does not satisfy the predetermined evaluation criterion; the adding means adds the new ground to the candidate list. An information presentation system comprising:

2. 2. The information presentation system according to claim 1, wherein the feedback information is information indicating the validity of the basis extracted for the predicted item.

3. The information presentation system according to claim 1, further comprising an evaluation means for replacing the grounds stored as the list based on an evaluation result of whether or not the grounds satisfy the predetermined evaluation criteria.

4. 4. The information presentation system according to claim 3, wherein the evaluation means deletes from the candidate list any of the grounds included in the candidate list that satisfy a predetermined deletion criterion.

5. 5. The information presentation system according to claim 1, wherein the presentation means sorts and presents the extracted grounds based on a score calculated from a contribution rate of the identified feature to the prediction.

6. At least one computer predicting items to be included in a care plan for the subject based on information regarding the subject's health status; Identifying features that contributed to the prediction of the item; Based on the predicted item and the identified feature amount, extracting a reason for including the item in the care plan from a list in which the reason for including the item in the care plan is linked to the item and the feature amount and stored; Presenting the predicted items and the grounds according to the items; adding new grounds to the list based on feedback information obtained after the presentation; the list includes a regular list including the evidence that satisfies a predetermined evaluation criterion determined based on a predetermined threshold, and a candidate list including the evidence that does not satisfy the predetermined evaluation criterion; When adding the grounds, add the new grounds to the candidate list. An information presentation method comprising:

7. predicting items to be included in a care plan for the subject based on information regarding the subject's health status; Identifying features that contributed to the prediction of the item; Based on the predicted item and the identified feature amount, extracting a reason for including the item in the care plan from a list in which the reason for including the item in the care plan is linked to the item and the feature amount and stored; Presenting the predicted items and the grounds according to the items; adding new grounds to the list based on feedback information obtained after the presentation; the list includes a regular list including the evidence that satisfies a predetermined evaluation criterion determined based on a predetermined threshold, and a candidate list including the evidence that does not satisfy the predetermined evaluation criterion; When adding the grounds, add the new grounds to the candidate list. A computer program that causes a computer to operate in such a manner.

Images