JP2022112651A - Depression symptom determination program - Google Patents

Abstract

To automatically and highly accurately determine a symptom of a depression of a subject.SOLUTION: A depression symptom determination program for determining a symptom of a depression of a subject causes a computer to execute: an information acquisition step of acquiring behavior pattern information about a behavior pattern of the subject; and a determination step of determining a symptom of a depression of the subject on the basis of the behavior pattern information acquired by the information acquisition step by referring to three or greater stages of relevance between behavior pattern information for reference about the past behavior pattern of the subject and a determination type of the symptom of the depression.SELECTED DRAWING: Figure 17

Description

The present invention relates to a depression symptom determination program for determining depression symptoms of a subject.

In recent years, the number of patients with depression is increasing. When falling into depression, even if the person is not aware of it, it may appear as a sign externally. If signs of possible depression can be detected in advance, various prescriptions can be given at that stage to avoid the risk of full-blown depression. However, in the past, the current situation is that no system has been proposed for automatically and highly accurately discriminating such signs of depression.

Therefore, the present invention has been devised in view of the above-mentioned problems, and its purpose is to provide a method for detecting depression that can automatically and highly accurately discriminate signs of depression in a subject. To provide a symptom discrimination program.

In order to solve the above-described problems, a depression symptom discrimination program according to the present invention is a depression symptom discrimination program that discriminates signs of depression of a subject, and includes behavior pattern information about the behavior pattern of the subject. With reference to the information acquisition step to be acquired, the reference behavior pattern information related to the past behavior pattern of the subject, and the degree of association of three or more levels with the discriminant type of the signs of depression, the information acquired by the information acquisition step. and a determination step of determining signs of depression of the subject based on the obtained behavior pattern information.

Even if there is no special skill or experience, it is possible to automatically and highly accurately discriminate signs of depression in a subject.

1 is a block diagram showing the overall configuration of a system to which the present invention is applied; FIG. It is a figure which shows the specific structural example of a search apparatus. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention. It is a figure for demonstrating the operation|movement of this invention.

Hereinafter, a depression symptom discrimination program to which the present invention is applied will be described in detail with reference to the drawings.

First Embodiment FIG. 1 is a block diagram showing the overall configuration of a depression symptom discrimination system 1 in which a depression symptom discrimination program to which the present invention is applied is implemented. A depression symptom discrimination system 1 includes an information acquisition unit 9 , a search device 2 connected to the information acquisition unit 9 , and a database 3 connected to the search device 2 .

The information acquisition unit 9 is a device for a person using this system to input various commands and information. The information acquisition unit 9 is not limited to a device for inputting text information, and may be configured by a device such as a microphone that can detect voice and convert it into text information. Further, the information acquisition unit 9 may be configured as an imaging device capable of capturing an image, such as a camera. The information acquisition unit 9 may be configured by a scanner having a function of recognizing a character string from a paper document. Moreover, the information acquisition part 9 may be integrated with the searching device 2 which will be described later. The information acquisition unit 9 outputs the detected information to the searching device 2 . Further, the information acquisition unit 9 may be configured by means for specifying position information by scanning map information. The information acquisition unit 9 also includes a temperature sensor, a humidity sensor, a flow rate sensor, and other sensors capable of specifying substances and physical properties. The information acquisition unit 9 may be configured by means for automatically retrieving character strings and data posted on sites on the Internet.

The database 3 accumulates various information necessary for discriminating symptoms of depression. The information necessary to discriminate signs of depression includes reference pronoun frequency information related to the frequency of pronouns in the text data, reference tone information related to the tone of voice, facial expression image information obtained by imaging the subject's facial expression, and actions. A data set with signs of depression discriminated against reference intent information related to intents that define the above, reference electroencephalogram information related to past electroencephalograms of subjects, reference attribute information related to subject attributes, etc. is stored.

That is, the database 3 stores such reference pronoun frequency information, reference tone information, facial expression image information, reference intent information, reference electroencephalogram information, reference attribute information, and symptoms of depression of the subject. are associated with each other and stored.

The search device 2 is composed of an electronic device such as a personal computer (PC), for example, but in addition to the PC, it is embodied in any other electronic device such as a mobile phone, a smartphone, a tablet terminal, a wearable terminal, etc. It may be one that is made into. A user can obtain a search solution by this search device 2 .

FIG. 2 shows a specific configuration example of the search device 2. As shown in FIG. This searching device 2 performs wired or wireless communication with a control unit 24 for controlling the entire searching device 2 and an operation unit 25 for inputting various control commands via operation buttons, keyboards, etc. A communication unit 26 for searching, an estimating unit 27 for making various judgments, and a storage unit 28, represented by a hard disk, for storing a program for performing a search to be executed are connected to the internal bus 21, respectively. . Further, the internal bus 21 is connected with a display unit 23 as a monitor for actually displaying information.

The controller 24 is a so-called central control unit for controlling each component implemented in the search device 2 by transmitting control signals via the internal bus 21 . In addition, the control unit 24 transmits commands for various controls through the internal bus 21 according to operations through the operation unit 25 .

The operation unit 25 is embodied by a keyboard or a touch panel, and a user inputs an execution command for executing a program. The operation unit 25 notifies the control unit 24 when the execution command is input by the user. Upon receiving this notification, the control unit 24 cooperates with each component including the estimation unit 27 to execute desired processing operations. The operation unit 25 may be embodied as the information acquisition unit 9 described above.

The estimation unit 27 estimates a search solution. The estimation unit 27 reads various information stored in the storage unit 28 and various information stored in the database 3 as necessary information in executing the estimation operation. This estimation unit 27 may be controlled by artificial intelligence. This artificial intelligence may be based on any known artificial intelligence technology.

The display unit 23 is composed of a graphic controller that creates a display image based on control by the control unit 24 . The display unit 23 is implemented by, for example, a liquid crystal display (LCD).

When the storage unit 28 is configured with a hard disk, predetermined information is written to each address based on the control by the control unit 24, and this information is read as necessary. The storage unit 28 also stores a program for executing the present invention. This program is read and executed by the control unit 24 .

The operation of the depression symptom discrimination system 1 configured as described above will be described.

The depression symptom discrimination system 1 is premised on forming a combination of reference pronoun frequency information and reference tone information, as shown in FIG. 3, for example.

The reference pronoun frequency information is information indicating how many pronouns are included in the text data when the voice spoken by the subject whose signs of depression are to be determined is converted into text data. For example, if the subject says, ``Tomorrow, I will go to Osaka by Shinkansen with Mr. Fujimoto by 13:00,'' and ``I will go to Osaka tomorrow, ', the former has a clearer meaning, while the latter has an unclear meaning. Patients with depression have a high proportion of pronouns in their own speech text data. By extracting this in units of text data, it is used as reference pronoun frequency information.

In order to actually quantify the frequency of pronouns in text data, it is possible to detect the volume of the entire text data by counting the number of clauses, words, case components, noun phrases, and characters in the text data. can be Then, the volume of pronouns contained in the entire text data is counted through the number of phrases, the number of words, the number of case components, the number of noun phrases, the number of characters, and the like. Then, the ratio of the volume of pronouns to the volume of the entire text data is detected as the frequency described above. It is premised that the units (number of clauses, number of words, number of case components, number of noun phrases, number of characters, etc.) for measuring the volume of these entire text data and pronouns are shared with each other.

In the present invention, when detecting this reference pronoun frequency information, input of the past voice of the subject is accepted. This input may be received via a microphone or the like. Then, the subject's voice is converted into text data and morphologically analyzed to extract pronouns contained in the text data. Pronouns are extracted by morphological analysis of phrases such as "that", "that", and "this". Morphological analysis is also used to extract phrase structures (case components, noun phrases, etc.).

The reference tone information is information about tone of voice extracted from past subjects. The tone of this sound indicates, for example, the pitch of the sound (the number of vibrations of sound waves per second, that is, the frequency), the sound itself, or the intensity of the sound. The tone of the voice may be analyzed by detecting its pitch and strength through a general voice detector.

The tone information for reference may be linked and linked with the text data in the pronoun frequency information for reference. For example, in the sentence "Tomorrow, I will go to Osaka with that and that," each noun phrase (case component) such as "tomorrow" and "that" is associated with a tone of voice. and may be used as reference tone information.

As input data, such reference pronoun frequency information and reference tone information are arranged side by side. An intermediate node 61 shown in FIG. 3 is a combination of reference pronoun frequency information as such input data and reference tone information. Each intermediate node 61 is further coupled to an output. In this output, discriminating types A to E of signs of depression are displayed. Each of the discriminative patterns of signs of depression indicates all types of signs of depression. The discrimination type of signs of depression is, for example, A for "no abnormality", B for "severe depression", and C for "preliminary group with signs of depression but not depression". In addition to this, the discriminative pattern of signs of depression may indicate the magnitude or degree of symptoms of depression.

Each combination (intermediate node) of the reference pronoun frequency information and the reference tone information is associated with the discriminative pattern of signs of depression as the output solution through three or more levels of association. . The pronoun frequency information for reference and the tone information for reference are arranged on the left side through this degree of association, and the discriminative types A, B, C, D, E, ... of signs of depression are arranged on the right side through the degree of association. are arranged in The degree of association indicates the degree of association between the reference pronoun frequency information and the reference tone information arranged on the left side and which depression symptom discrimination pattern is highly relevant. In other words, the degree of association is an index indicating whether each reference pronoun frequency information and reference tone information is highly likely to be associated with a discriminative pattern of signs of depression. It indicates the accuracy in selecting the discriminative pattern of signs of depression that is most likely to apply to the subject from the frequency information and the reference tone information. In the example of FIG. 3, w13 to w22 are shown as association degrees. These w13 to w22 are shown in 10 stages as shown in Table 1 below, and the closer to 10 points, the higher the degree of correlation between each combination as an intermediate node and the discrimination type of symptoms of depression as an output. Conversely, the closer to 1 point, the lower the degree of correlation between each combination as an intermediate node and the discriminative pattern of symptoms of depression as an output.

The search device 2 acquires in advance the degrees of association w13 to w22 of three or more stages shown in FIG. In other words, the search device 2 accumulates past data as to which of the reference pronoun frequency information, the reference tone information, and the discrimination pattern of the symptoms of depression in that case was suitable for determining the actual search solution. By analyzing these, the degree of association shown in FIG. 3 is created.

In the process of accumulating these data, past subjects who actually suffered from depression, past subjects who did not suffer from depression, and even those who did not suffer from depression, but in the preliminary group Pronoun frequency information for reference and tone information for reference are detected from the past subjects who have become. Along with this, the subject actually applies the results of discrimination by experts and doctors regarding signs of depression to a predetermined discrimination type, converts this into data, and the above-mentioned reference pronoun frequency A data set of information and reference tone information may be trained.

In the process of constructing this learning data, it is not limited to the case of actually extracting data from a subject. In the case of information, it is also possible to determine what kind of discrimination type of signs of depression is actually applied, convert it into data, and learn this data.

This analysis may be performed by artificial intelligence. In such a case, for example, when the reference pronoun frequency information P01 is the reference tone information P16, the discrimination pattern of the symptom of depression is analyzed from the past data. If there are many cases of A, the degree of association leading to A is set higher, and if there are many cases of B and few cases of A, the degree of association leading to B is set higher, and the degree of association leading to A is set higher. set lower. For example, in the example of the intermediate node 61a, it is linked to the outputs of the discriminant types A and B of the signs of depression, but the degree of association of w13 that leads to the discriminant type A of the signs of depression from the previous case is set to 7 points, The degree of association of w14 connected to the discrimination type B of signs of depression is set to 2 points.

Further, the degree of association shown in FIG. 3 may be composed of nodes of a neural network in artificial intelligence. That is, the weighting coefficients for the outputs of the nodes of this neural network correspond to the degrees of association described above. Moreover, it is not limited to a neural network, and may be composed of all decision-making factors that constitute artificial intelligence.

In the example of the degree of association shown in FIG. 3, the node 61b is a node of a combination of the tone information for reference P14 with the pronoun frequency information for reference P01, and the degree of association for the discrimination type C of signs of depression is w15, The degree of association of the discriminative type E of signs of depression is w16. The node 61c is a node of a combination of the reference tone information P15 and P17 for the reference pronoun frequency information P02. is w18.

Such a degree of association becomes learned data in terms of artificial intelligence. After such learned data is created, the above-described learned data will be used when actually performing a search for suggesting a discriminant pattern of signs of depression. In such a case, tone information is acquired in addition to pronoun frequency information from a new subject for whom a new discrimination pattern of signs of depression is proposed. In addition to such pronoun frequency information, the method of acquiring tone information is the same as the above-described reference pronoun frequency information and reference tone information.

Based on the pronoun frequency information and the tone information newly acquired in this way, the optimal depression symptom discrimination pattern is searched. In such a case, reference is made to the degree of association shown in FIG. 3 (Table 1), which has been acquired in advance. For example, when the newly acquired pronoun frequency information is the same as or similar to P02 and the tone information is the same or similar to P17, the node 61d associates This node 61d is associated with the discriminant type C of the symptom of depression with w19 and with the discriminant type D of the symptom of depression with the degree of association w20. In such a case, the discriminant type C of signs of depression with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the discrimination type D of signs of depression, which has a low degree of association but the association itself is recognized, may be selected as the optimum solution. . In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

Table 2 below shows examples of degrees of association w1 to w12 extending from the input.

Intermediate nodes 61 may be selected based on degrees of association w1 to w12 extending from this input. In other words, the greater the degree of association w1 to w12, the heavier the weight in selecting the intermediate node 61 may be. However, the degrees of association w1 to w12 may all have the same value, and the weighting in selecting the intermediate nodes 61 may all be the same.

FIG. 4 shows an example in which three or more degrees of association are set for combinations of the above-described reference pronoun frequency information and reference facial expression image information, and depression symptom discrimination patterns for the combinations. there is

The reference facial expression image information is information relating to the facial expression image of the subject from whom the reference pronoun frequency information is to be obtained. The facial expression image information for reference may be obtained by analyzing the image data obtained by imaging the facial expression of the subject with a camera, and extracting a characteristic portion for detecting the depression. . Assuming that a depressed patient sometimes shows a peculiar smile in facial expression, the presence or absence of the peculiar smile may be detected by analyzing the face image. Further, this facial expression image information for reference may be composed not only of a still image but also of a moving image. In the case of a moving image, it may be linked with the text data in the reference pronoun frequency information. For example, in the sentence ``Tomorrow, I will go to Osaka with that. may be associated with each other and used as reference facial expression image information. Such reference facial expression image information and facial expression image information acquisition method may use deep learning technology as necessary other than image analysis, automatically discriminate based on the feature amount of the analysis image, and convert it into data. .

In the example of FIG. 4, it is assumed that the input data are, for example, reference pronoun frequency information P01 to P03 and reference expression image information P18 to P21. The intermediate node shown in FIG. 5 is a combination of the pronoun frequency information for reference and the facial expression image information for reference as such input data. Each intermediate node is also connected to an output. In this output, the discriminating pattern of symptoms of depression is displayed as the output solution.

Each combination (intermediate node) of the reference pronoun frequency information and the reference facial image information is associated with the discriminative pattern of signs of depression as the output solution through three or more levels of association. . The pronoun frequency information for reference and the facial expression image information for reference are arranged on the left side through the degree of association, and the discriminating pattern of signs of depression is arranged on the right side through the degree of association. The degree of association indicates the degree of high association between the reference pronoun frequency information and the reference facial expression image information arranged on the left side and the discrimination pattern of signs of depression. In other words, the degree of association is an index indicating whether each of the reference pronoun frequency information and the reference facial expression image information is likely to be linked to any type of depression symptom discrimination, and is an index indicating whether each reference pronoun frequency information and the reference facial expression image information are highly likely to be associated with each of the reference pronoun frequency information. This indicates the accuracy in selecting the most probable discriminative pattern of each symptom of depression from the facial expression image information for reference. In addition to the pronoun frequency information, the search solution changes depending on the state of the actual facial expression image. Therefore, the combination of the reference pronoun frequency information and the reference facial expression image information is used to search for the optimum depression symptom discrimination type.

In the example of FIG. 4, w13 to w22 are shown as association degrees. These w13 to w22 are shown in 10 stages as shown in Table 1. The closer to 10 points, the higher the degree of correlation between each combination as an intermediate node and the output. The closer it is, the lower the degree of correlation between each combination as an intermediate node and the output.

The search device 2 acquires in advance three or more degrees of association w13 to w22 shown in FIG. In other words, the search device 2 determines which of the reference pronoun frequency information and the reference facial expression image information, as well as the depression symptom discrimination type in that case, is preferable in determining the actual search solution, and the past data are accumulated, and the degree of association shown in FIG. 4 is created by analyzing these.

This analysis may be performed by artificial intelligence. In such a case, for example, in the case of the reference pronoun frequency information P01 and the reference expression image information P20, the discrimination pattern of the signs of depression is analyzed from the past data. For example, in the example of the intermediate node 61a, it is linked to the outputs of the discriminant types A and B of the signs of depression, but the degree of association of w13 that leads to the discriminant type A of the signs of depression from the previous case is set to 7 points, The degree of association of w14 connected to the discrimination type B of signs of depression is set to 2 points.

In the example of the degree of association shown in FIG. 4, the node 61b is a node of a combination of the reference pronoun frequency information P01 and the facial expression image information for reference P18, and the degree of association for the discrimination type C of signs of depression is w15. , the degree of association of the discriminant type E of signs of depression is w16. The node 61c is a node of a combination of the reference pronoun frequency information P02 and the facial expression image information for reference P19 and P21. The association degree of D is w18.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually giving advice. In such a case, in addition to the pronoun frequency information described above, facial expression image information regarding the subject whose signs of depression are to be examined for discrimination patterns is newly acquired. The facial expression image information corresponds to reference facial expression image information.

Based on the pronoun frequency information and facial expression image information newly acquired in this way, the credibility is searched. In such a case, reference is made to the degrees of association shown in FIG. 4 (Table 1) that have been acquired in advance. For example, when the newly acquired pronoun frequency information is the same as or similar to P02 and the facial expression image information is P21, the node 61d is associated via the degree of association, This node 61d is associated with the discriminant type C of the symptom of depression with w19 and with the discriminant type D of the symptom of depression with the degree of association w20. In such a case, the discriminant type C of signs of depression with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the discrimination type D of signs of depression, which has a low degree of association but the association itself is recognized, may be selected as the optimum solution. . In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

As an alternative to the reference pronoun frequency information, the reference intent information described below may be used. This reference intent information is information managed in units of processing operations contained in text data, and defines an action name.

Intents usually define actions that specify business processes (processing operations). For example, all actions such as "throw in trash", "eat rice", "watch TV", "go shopping", "ride train", "listen to music", etc. are defined as intents.

Morphologically analyze the text data and assign intents to each of them. This intent assignment refers to an intent table created and saved in advance.

The intent table defines which intent includes the morphologically analyzed wording. For example, if the intent is "go shopping", the phrases included in the morphological analysis include "go shopping", "go shopping", "go to run errands", "go shopping", and "procure". It includes various things such as "coming". Similarly, if the intent is "take a train", the phrases included in the morphological analysis include "take the Yamanote Line", "take the Chuo Line", "use the train", "use the train", etc. includes things.

In the intent table, various sentences that have been morphologically analyzed are linked to each intent and recorded. By reading this, it is possible to assign an intent to each sentence that has been morphologically analyzed. becomes.

As shown in FIG. 5, a combination of the reference intent information consisting of each intent and the reference facial expression image information and the discriminative pattern of the signs of depression as output data are shown in the intermediate node 61. They are related via the degree of association and learned.

Then, intent information and facial expression image information are newly extracted from the subject, and symptoms of depression are analyzed as a search solution using the corresponding reference intent information.

The combination of the reference intent information and the reference tone information and the discriminative pattern of the signs of depression as the output data are associated with each other through the degree of association of the intermediate node 61 and learned. When intent information and tone information are newly input from the subject, it is also possible to search for a search solution in the same way.

FIG. 6 shows that in addition to the above-mentioned reference pronoun frequency information, reference tone information, and further reference electroencephalogram information, three or more levels of correlation between the combination and the depression symptom discrimination pattern are shown. A set example is shown.

The reference electroencephalogram information is information relating to the subject's electroencephalogram. A subject's electroencephalogram can be measured from a commercially available electroencephalograph. By combining such reference electroencephalogram information, it may be possible to grasp signs of depression, so this is added as an explanatory variable. This electroencephalogram information for reference may be composed of information capturing chronological changes. In such a case, the text data in the reference pronoun frequency information may be interlocked and linked. For example, in the sentence "Tomorrow, I will go to Osaka with that and that," the time-series changes in brain waves for each noun phrase (case component) such as "tomorrow" and "that" may be linked and used as reference pronoun frequency information.

In such a case, as shown in FIG. 6, the degree of association can be obtained by using a set of combinations of reference pronoun frequency information, reference tone information, and reference electroencephalogram information as intermediate nodes 61a to 61e in the same manner as described above. to be expressed.

For example, in FIG. 6, the node 61c is associated with the reference pronoun frequency information P02 with the degree of association w3, with the reference tone information P15 with the degree of association w7, and with the reference electroencephalogram information W with the degree of association w11. Similarly, the node 61e is associated with the reference pronoun frequency information P03 with the degree of association w5, with the reference tone information P15 with the degree of association w8, and with the reference electroencephalogram information V with the degree of association w10.

Similarly, when such a degree of association is set, signs of depression are discriminated based on pronoun frequency information, tone information, and electroencephalogram information newly acquired from a subject to be examined.

In order to discriminate the discriminative pattern of the signs of depression, reference is made to the degree of association shown in FIG. 6 acquired in advance. For example, it can be specified that the pronoun frequency information is identical or similar to the reference pronoun frequency information P02, the acquired tone information is identical or similar to the reference tone information P15, and the acquired electroencephalogram information is the electroencephalogram information for reference. If W can be specified, the combination is associated with a node 61c, and this node 61c has a degree of association w17 for the discriminant type B of signs of depression and a discriminant type D for signs of depression. They are associated with a degree of association w18. Based on w17 and w18 as a result of such a degree of association, the discriminant type of signs of depression is actually obtained from the new pronoun frequency information, tone information, and electroencephalogram information.

A buy search can be performed in the same way when referring intent information is used instead of referring pronoun frequency information.

FIG. 7 shows that, in addition to the reference pronoun frequency information and the reference tone information, the combination of the reference attribute information and the depression symptom discrimination type for the combination have three or more levels of association. A set example is shown.

Reference attribute information is information indicating attributes of a subject. Attributes of subjects include age, gender, occupation, current social activities, behaviors and behaviors related to depression from the past to the present, various diseases other than depression, etc. It also includes information about

In such a case, as shown in FIG. 7, the degree of relevance is obtained by using a set of combinations of reference pronoun frequency information, reference tone information, and reference attribute information as intermediate nodes 61a to 61e in the same manner as described above. to be expressed.

For example, in FIG. 7, the node 61c is associated with the reference pronoun frequency information P02 with the degree of association w3, with the reference tone information P15 with the degree of association w7, and with the reference attribute information W with the degree of association w11. Similarly, the node 61e is associated with the reference pronoun frequency information P03 with the degree of association w5, with the reference tone information P15 with the degree of association w8, and with the reference attribute information V with the degree of association w10.

Similarly, when such a degree of association is set, determination is made based on pronoun frequency information, tone information, and attribute information newly acquired from the subject.

In order to discriminate the discriminant type of depression, the degree of association shown in FIG. 7 acquired in advance is referred to. For example, it can be specified that the pronoun frequency information is identical or similar to the reference pronoun frequency information P02, the acquired tone information is identical or similar to the reference tone information P15, and the acquired attribute information is the reference attribute information. If W can be specified, the combination is associated with a node 61c, and this node 61c is associated with the discriminant type B with a degree of association w17 and with the discriminant type D with a degree of association w18. As a result of such degree of association, based on w17 and w18, a new discriminant type of the subject is actually obtained based on the new pronoun frequency information, tone information, and attribute information. .

Further, as shown in FIG. 8, reference information U is composed of reference pronoun frequency information, reference tone information, expression image information, reference intent information, reference electroencephalogram information, and reference attribute information. Reference pronoun frequency information, reference tone information, facial expression image information, reference intent information, reference electroencephalogram information, and reference attribute information, which are combined with reference information U to form a degree of association, are used as reference information V. You may make it discriminate|determine based on the association degree of the combination of. The output solution corresponds to the classification type of each symptom of depression described above.

At this time, the output obtained for the reference information U may be used as input data as it is, and may be associated with the output via the intermediate node 61 in combination with the reference information V. FIG. For example, after providing an output solution for the reference information U, this may be used as an input as it is, and the degree of association with other reference information V may be used to search for the output.

It should be noted that the present invention is not limited to the case of searching for a discriminant pattern as a search solution, but as shown in FIG. can be output. After verifying in advance which prescription is effective for which discriminant type, the effective prescription is tied to each discriminant type. Then, in the same manner as described above, the discriminant pattern may be searched, and the prescription linked to the searched discriminant pattern may be output together with the discriminant pattern or as a substitute for the discriminant pattern. As an alternative to the discriminant pattern, the prescription itself may be learned as a data set together with the above-described reference information. As a result, when the input data obtained from the subject is input, a more effective prescription is directly output.

FIG. 9 shows an example in which the degree of association is formed by combining the reference pronoun frequency information and the reference tone information. As for the degree of association as input data, it goes without saying that the prescription itself may be similarly learned as a data set with the above-described reference information.

In the above-mentioned degree of relevance, the degree of relevance is expressed by a 10-level evaluation, but it is not limited to this, and it may be expressed by a degree of relevance of 3 or more stages. For example, 100 steps or 1000 steps may be used. On the other hand, this degree of association does not include those expressed in two stages, that is, whether or not they are associated with each other, either 1 or 0.

According to the present invention configured as described above, anyone can easily search for a depression discrimination type without special skills or experience. Further, according to the present invention, it is possible to judge the search solution with a higher degree of accuracy than a human being does. Furthermore, by configuring the degree of association described above with artificial intelligence (neural network, etc.) and making it learn, it is possible to further improve the discrimination accuracy.

Since there are many cases where the above-described input data and output data are not exactly the same during the learning process, information obtained by classifying these input data and output data according to type may be used. In other words, the information P01, P02, . . . P15, 16, . A data set may be created between the data and the output data for learning.

Moreover, according to the present invention, it is characterized in that the optimum solution search is performed through the degree of association set to three or more stages. The degree of association can be described by a numerical value of, for example, 0 to 100% in addition to the 10 stages described above, but is not limited to this, and can be described by a numerical value of 3 or more stages. may be configured.

Based on such a degree of association represented by a numerical value of three or more levels, by determining the credibility with higher credibility and less misidentification, there are multiple candidates for the possibility of search solutions. It is also possible to search and display in descending order of the degree of association.

In addition to this, according to the present invention, it is possible to make a judgment without overlooking even a very low output discrimination result such as a correlation degree of 1%. Remind the user that even discrimination results with an extremely low degree of association are connected as slight signs, and that once in dozens or hundreds of times, the discrimination results may be useful. be able to.

Furthermore, according to the present invention, there is an advantage that a search policy can be determined by setting thresholds by performing a search based on three or more degrees of association. If the threshold value is lowered, even if the degree of association is 1%, it can be picked up without omission. be. On the other hand, if the threshold is set high, there is a high possibility that the optimal search solution can be detected with a high probability. Sometimes the solution is overlooked. It is possible to decide which one to place emphasis on based on the way of thinking of the user side and the system side, and it is possible to increase the degree of freedom in selecting such points to place emphasis on.

Furthermore, in the present invention, the degree of association described above may be updated. This update may reflect information provided via a public communication network such as the Internet, for example. When pronoun frequency information, tone information, facial expression image information, intent information, electroencephalogram information, and knowledge, information, and data relating to attribute information are acquired, the degree of association is increased or decreased accordingly.

In other words, this update corresponds to learning in terms of artificial intelligence. Since new data is acquired and reflected in the learned data, it can be said that it is a learning act.

In addition to updating the degree of association based on information that can be obtained from the public communication network, the system side or the user side based on the contents of research data, papers, conference presentations, newspaper articles, books, etc. by experts It may be updated manually or automatically. Artificial intelligence may be used in these update processes.

Also, the process of initially building a trained model and the above-described updating may use not only supervised learning but also unsupervised learning, deep learning, reinforcement learning, and the like. In the case of unsupervised learning, instead of loading and learning datasets of input and output data, learning is performed by loading information corresponding to the input data, from which the degree of association related to the output data is self-formed. You can let it run.

Second Embodiment In the second embodiment, the discrimination pattern of signs of depression is discriminated only from the reference pronoun frequency information. For example, as shown in FIG. 10, three or more degrees of association between the reference pronoun frequency information acquired in the past and the discriminant pattern of the signs of depression actually discriminated in the past are used.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly discriminating signs of depression. In such a case, pronoun frequency information is newly acquired. The acquisition method is the same as in the first embodiment.

Based on the pronoun frequency information newly acquired in this way, the discriminative pattern of the signs of depression is discriminated. In such a case, reference is made to the degree of association shown in FIG. 10, which has been acquired in advance. A specific method for estimating the discriminant type of depression symptoms is the same as that in the first embodiment, and thus description thereof is omitted below.

Further, in the second embodiment, the discrimination pattern of signs of depression may be discriminated only from the reference intent information. In such a case, for example, as shown in FIG. 11, three or more degrees of association between reference intent information acquired in the past and the discrimination type of signs of depression actually discriminated in the past are used.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly discriminating signs of depression. In such a case, intent information is newly acquired. The acquisition method is the same as in the first embodiment.

Based on the intent information newly acquired in this way, the discrimination type of the sign of depression is discriminated. In such a case, reference is made to the degrees of association shown in FIG. 11 that have been acquired in advance. A specific method for estimating the discriminant type of depression symptoms is the same as that in the first embodiment, and thus description thereof is omitted below.

Further, in the second embodiment, the discrimination pattern of signs of depression may be discriminated only from the reference tone information. In such a case, for example, as shown in FIG. 12, three or more degrees of association between the reference tone information acquired in the past and the discrimination pattern of signs of depression actually discriminated in the past are used.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly discriminating signs of depression. In such a case, tone information is newly acquired. The acquisition method is the same as in the first embodiment.

Based on the tone information newly acquired in this way, the discrimination pattern of signs of depression is discriminated. In such a case, the degree of association shown in FIG. 12 acquired in advance is referred to. A specific method for estimating the discriminant type of depression symptoms is the same as that in the first embodiment, and thus description thereof is omitted below.

Similarly, in the second embodiment, the search solution is not limited to searching for the discriminant pattern, but by learning in advance the prescription corresponding to the discriminant pattern, the prescription is output as the search solution. Of course, it is also possible to do so.

In addition, both the first embodiment and the second embodiment are not limited to the embodiments described above. For example, as shown in FIG. may be used. In such a case, a solution search is performed based on three or more degrees of association with the discriminative pattern of signs of depression according to newly acquired information. The basic reference information is, for example, reference pronoun frequency information or the like, but is not limited to this, and any reference information (reference pronoun frequency information, reference tone information for use, facial expression image information, intent information for reference, electroencephalogram information for reference, attribute information for reference, etc.) can also be applied.

In these cases, similarly, when information corresponding to reference information used as learning data is input, solution search is performed based on the above-described method.

The search solution obtained through the degree of association may be further modified or weighted based on other reference information.

The other reference information referred to here corresponds to any reference information other than the basic reference information when any of the reference information described above is used as the basic reference information.

For example, in certain reference tone information P14, which is one of other reference information, it is assumed that B was frequently identified as the identification type of signs of depression in the past. When the tone information corresponding to such reference tone information P14 is newly acquired, the search solution B as the discrimination pattern of the signs of depression is weighted. It is set in advance so that a process for connecting to the search solution B as the discrimination type of is performed.

For example, other reference information G is an analysis result that suggests a search solution C as a discrimination type of signs of depression, and reference information F is a search as a discrimination type of signs of depression. Assume that the analysis result suggests the solution D. After the setting with the reference information in this way, if the actually obtained information is the same as or similar to the reference information G, the weight of the search solution C as the discrimination type of the signs of depression is increased. process. On the other hand, when the actually acquired information is the same as or similar to the reference information F, processing is performed to increase the weight of the search solution D as the type of discrimination of signs of depression. In other words, the degree of association itself leading to the discriminative pattern of signs of depression may be controlled based on the reference information FH. Alternatively, after determining the discriminative pattern of the signs of depression based only on the degree of association described above, the obtained search solution may be corrected based on the reference information FH. In the latter case, it is necessary to reflect what is designed on the system side each time as to how to modify the discrimination pattern of signs of depression as a search solution based on the reference information FH. Become.

The reference information is not limited to any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the more the case leads to the discriminant pattern with signs of depression suggested by the reference information, the higher the discriminant pattern as the search solution obtained through the degree of association may be corrected. .

Similarly, as shown in FIG. 14, even when forming the degree of association with the discriminant pattern of signs of depression for a combination of reference information that serves as a keynote and other reference information, The reference information is any reference information (reference pronoun frequency information, reference tone information, expression image information, reference intent information, reference electroencephalogram information, reference attribute information, etc.) in the first and second embodiments. etc.) are also applicable. Other reference information includes any reference information in the first and second embodiments other than the basic reference information.

At this time, if the basic reference information is the reference pronoun frequency information, the other reference information includes any reference information in the first embodiment and the second embodiment.

In such a case as well, by performing a solution search in the same way, it is possible to estimate the discriminant pattern of signs of depression. At this time, as shown in FIG. 13 described above, for the search solution obtained through the degree of association, through other reference information (reference information F, G, H, etc.), discrimination of signs of depression The type may be modified.

Also in the second embodiment, the degree of association may be learned by combining not only one piece of other reference information but also two or more pieces of reference information.

As the search solution described above, a prescription for depression may be searched as a search solution in place of the discriminating type of symptoms of depression. In such a case, search solutions can be similarly obtained by preparing data associated with prescriptions for depression through three or more levels of association with the combination of the above-described basic reference information and other reference information. can be explored.

Third Embodiment In the third embodiment, as shown in FIGS. 15 and 16, reference information for reference when using three or more levels of degrees of association between reference information as a keynote and discrimination patterns of signs of depression. Examples of various variation deployments of are explained.

An example of the basic reference information is reference magnetoencephalogram information obtained by past magnetoencephalogram examinations of subjects. This reference magnetoencephalogram information may be composed of image data obtained by MEG (magnetoencephalography), or may be composed of MRI data obtained by scanning the brain. The magnetoencephalogram information for reference may further be composed of data obtained by extracting characteristic portions of these image data using well-known deep learning technology. Since it is considered that there is a correlation between the degree of depression and the magnetoencephalogram information, the degree of association described above is constructed in advance by learning a data set in which these are associated with each other.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly judging signs of depression. In such a case, new magnetoencephalogram information is acquired.

The newly obtained magnetoencephalogram information is obtained from a subject whose symptoms of depression are to be newly determined, and the type and method of obtaining the information are the same as the reference magnetoencephalogram information described above. A specific solution search method is the same as in the first and second embodiments, and therefore description thereof is omitted below.

An example of the basic reference information is reference meal content information relating to the past meal content of the subject. This reference meal content information includes the details of meals actually ingested by the subject in the past (menus, etc.), meal amounts, meal times, time intervals for taking three meals, nutrients and calorie intake. This reference meal content may be obtained by dividing it into periods such as one day, one week, and one month.

Since it is considered that there is a correlation between the degree of depression and the information about the meal content, the degree of association described above is constructed in advance by learning a data set in which these are associated with each other.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly judging signs of depression. In such a case, the meal content information is newly acquired.

The newly obtained meal content information is obtained from a subject whose signs of depression are to be newly determined, and the type and acquisition method of the information are the same as those of the reference meal content information described above. A specific solution search method is the same as in the first and second embodiments, and therefore description thereof is omitted below.

An example of the basic reference information is reference sleep information relating to past sleep states of the subject. This reference sleep information is all information related to sleep actually performed by the subject in the past. Contains any data related to Since depression patients have data such as sleep fragmentation and frequent awakenings, the above-mentioned degree of association is constructed in advance by learning a data set in which these are associated with each other.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly judging signs of depression. In such a case, sleep information is newly acquired.

The newly acquired sleep information is acquired from a subject whose signs of depression are to be newly determined, and the type and acquisition method of the information are the same as those of the reference meal content information described above. A specific solution search method is the same as in the first and second embodiments, and therefore description thereof is omitted below.

An example of the basic reference information is reference exercise information relating to the past exercise state of the subject. This reference exercise information is all kinds of information related to the exercise that the subject actually performed in the past, and includes, for example, the number of steps per unit time, the time and number of times of going out, the distance walked, the distance run, and the like. good too. Also, the reference exercise information may be composed of information obtained by measuring arm swing, leg movement, walking speed, and the like through an acceleration sensor actually worn by the subject. Also, the reference exercise information may indicate a heart rate detected by a heart rate monitor worn on the body, or an actual range of activity via position information detected by GPS or the like.

Since depression patients are considered to have a correlation with the amount of exercise, the above-mentioned degree of association is constructed in advance by learning a data set in which these are associated with each other.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly judging signs of depression. In such a case, exercise information is newly acquired.

The newly acquired exercise information is obtained from a subject whose signs of depression are to be newly determined, and the type and acquisition method of the information are the same as those of the reference exercise information described above. A specific solution search method is the same as in the first and second embodiments, and therefore description thereof is omitted below.

An example of basic reference information is reference life time information related to past life time zones of subjects. This reference life time information is all information related to the life time period actually used by the subject in the past. The actual waking time and sleep time may be detected from the usage time of electricity in the room. It is also possible to detect which room and how long the user has stayed through a door open/close sensor. The usage time of electricity may be detected via an electricity usage meter installed in a house, or may be detected via an electricity meter installed in a so-called smart house or the like.

Since depression patients are considered to be correlated with their daily life, the above-mentioned degree of association is constructed in advance by learning a data set in which these are associated with each other.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly judging signs of depression. In such a case, the usage time information is newly acquired.

The newly acquired time-use information is obtained from a subject whose signs of depression are to be newly determined, and the type and acquisition method of the information are the same as the reference-use time-use information described above. A specific solution search method is the same as in the first and second embodiments, and therefore description thereof is omitted below.

Examples of basic reference information include reference operation information related to past various operations in the subject's home. This reference operation information includes the electric appliances (TV, air conditioner, PC, VCR, vacuum cleaner, refrigerator, washing machine), lighting switches, bath gas switches, system kitchens, etc. that the past subject actually had in the house. Anything that may be operated by any resident of the house, such as the operation of a window that opens and closes with a push button, such as an operation button or lever of a house. These reference operation information may be detected through IoT sensors installed on push buttons such as electric appliances, lighting switches in the house, gas switches in baths, operation buttons and levers in system kitchens, and the like. It may be detected via an electric meter installed in a so-called smart house or the like.

Depressive patients are thought to have correlations with the frequency of pressing mistakes, pressing time, and pressing intensity when operating buttons, etc. The degree of association is constructed in advance.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly judging signs of depression. In such a case, operation information is newly acquired.

The newly acquired operation information is acquired from a subject whose signs of depression are to be newly determined, and the type and acquisition method of the information are the same as those of the reference operation information described above. A specific solution search method is the same as in the first and second embodiments, and therefore description thereof is omitted below.

An example of the basic reference information is reference line-of-sight image information relating to past movements of the line of sight of the subject. This line-of-sight image information for reference is obtained by imaging the past line-of-sight of the examinee with respect to the questions set. When performing image analysis of the line of sight, deep learning technology may be used to automatically discriminate based on the feature amount of the analysis image and convert it into data. Also, an infrared camera may be used to detect the movement of the subject's line of sight to a high degree.

Examples of questions to be asked include, for example, displaying figures of various shapes at the same time and counting how many of the same shapes exist, analyzing the line of sight when moving the mark displayed on the screen, or It may be a question that tests spatial cognitive ability, judgment ability, etc., such as a question that makes you look for mistakes.

Depressive patients are considered to have characteristic gaze movements in response to such problems. .

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly judging signs of depression. In such a case, line-of-sight image information is newly acquired.

The newly acquired operation information is an image of the movement of the line of sight for the question posed to the subject who newly discriminates signs of depression, and the type and acquisition method of the information are the same as the reference operation described above. Similar to information. A specific solution search method is the same as in the first and second embodiments, and therefore description thereof is omitted below.

An example of the basic reference information is reference conversation volume information relating to the conversation volume per unit time. The unit time may be any time unit such as 1 minute, 10 minutes, 60 minutes, 3 hours, and a day. The amount of conversation may simply be a value obtained by dividing the length of time during which voice is emitted, that is, the length of time when voice exceeding a predetermined volume is detected, divided by the unit time. In addition, when the subject's voice is converted to text data, the amount of conversation is quantified by each part of speech (verb, adjective, object, pronoun, adverb, etc.) in the text data, and the amount of the part of speech per unit time may be configured with Also, the volume of conversation may be detected by converting speech into text data and counting the number of clauses, words, case components, noun phrases, and characters to detect the volume of the entire text data. Then, the volume of the entire text data per unit time may be used as the amount of conversation. It is premised that the units (number of clauses, number of words, number of case components, number of noun phrases, number of characters, etc.) for measuring the volume of these entire text data and pronouns are shared with each other.

Since it is conceivable that the degree of symptoms of a depressed patient is related to the amount of such conversation, the degree of association described above is constructed in advance by learning a data set in which these are associated with each other.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly judging signs of depression. In such a case, conversation volume information is newly acquired.

For newly acquired information on the amount of conversation, the amount of conversation per unit time is calculated in the same manner as described above by converting the voice of the subject whose signs of depression are to be newly determined into text data. A specific solution search method is the same as in the first and second embodiments, and therefore description thereof is omitted below.

Moreover, the first to third embodiments are not limited to the above-described embodiments. For example, as shown in FIG. may be used. In such a case, a solution search is performed based on three or more degrees of association with the discriminative pattern of signs of depression according to newly acquired information. The basic reference information is, for example, reference pronoun frequency information or the like, but is not limited to this, and any reference information (reference Pronoun frequency information, tone information for reference, facial expression image information, intent information for reference, electroencephalogram information for reference, attribute information for reference, magnetoencephalogram information for reference, meal content information for reference, sleep information for reference, driving information for reference , reference operation information, reference line-of-sight image information, reference conversation volume information, reference life time information, etc.) are also applicable.

In these cases, similarly, when information corresponding to reference information used as learning data is input, solution search is performed based on the above-described method.

The search solution obtained through the degree of association may be further modified or weighted based on other reference information.

The other reference information referred to here corresponds to any reference information other than the basic reference information when any of the reference information described above is used as the basic reference information.

For example, in certain reference time-use information P14, which is one of the other reference information, it is assumed that B was frequently identified as the identification type of signs of depression in the past. When the tone information corresponding to the reference time-use information P14 is newly acquired, the search solution B as the discrimination type of the signs of depression is weighted. It is set in advance so that a process leading to the search solution B as the symptom discrimination type is performed.

For example, other reference information G is an analysis result that suggests a search solution C as a discrimination type of signs of depression, and reference information F is a search as a discrimination type of signs of depression. Assume that the analysis result suggests the solution D. After the setting with the reference information in this way, if the actually obtained information is the same as or similar to the reference information G, the weight of the search solution C as the discrimination type of the signs of depression is increased. process. On the other hand, when the actually acquired information is the same as or similar to the reference information F, processing is performed to increase the weight of the search solution D as the type of discrimination of signs of depression. In other words, the degree of association itself leading to the discriminative pattern of signs of depression may be controlled based on the reference information FH. Alternatively, after determining the discriminative pattern of the signs of depression based only on the degree of association described above, the obtained search solution may be corrected based on the reference information FH. In the latter case, it is necessary to reflect what is designed on the system side each time as to how to modify the discrimination pattern of signs of depression as a search solution based on the reference information FH. Become.

The reference information is not limited to any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the more the case leads to the discriminant pattern with signs of depression suggested by the reference information, the higher the discriminant pattern as the search solution obtained through the degree of association may be corrected. .

Similarly, as shown in FIG. 14, even when forming the degree of association with the discriminant pattern of signs of depression for a combination of reference information that serves as a keynote and other reference information, The reference information is any reference information (reference pronoun frequency information, reference tone information, facial expression image information, reference intent information, reference electroencephalogram information, reference attribute information, etc.) in the first to third embodiments. , magnetoencephalogram information for reference, meal content information for reference, sleep information for reference, driving information for reference, operation information for reference, line-of-sight image information for reference, conversation volume information for reference, life time information for reference, etc.) can also be applied. is. Other reference information includes any reference information in the first and second embodiments other than the basic reference information.

At this time, if the basic reference information is the reference magnetoencephalogram information, the other reference information includes any reference information in the first to third embodiments other than this.

In such a case as well, by performing a solution search in the same way, it is possible to estimate the discriminant pattern of signs of depression. At this time, as shown in FIG. 13 described above, for the search solution obtained through the degree of association, through other reference information (reference information F, G, H, etc.), discrimination of signs of depression The type may be modified.

Also in the third embodiment, the degree of association may be learned by combining not only one piece of other reference information but also two or more pieces of reference information.

As the search solution described above, a prescription for depression may be searched as a search solution in place of the discriminating type of symptoms of depression. In such a case, search solutions can be similarly obtained by preparing data associated with prescriptions for depression through three or more levels of association with the combination of the above-described basic reference information and other reference information. can be explored.

Fourth Embodiment In the fourth embodiment, the discrimination type of signs of depression is discriminated only from the behavior pattern information for reference. For example, as shown in FIG. 17, three or more degrees of association between reference behavior pattern information acquired in the past and the discriminant type of signs of depression actually discriminated in the past are used.

The reference behavioral pattern information referred to here is all information relating to past behavioral patterns of the subject. This behavior pattern may be typified in advance. Any pattern of behavior may be categorized, such as acting suspiciously, nodding, going back and forth in the same place, and immediately returning to the place previously visited. This reference action pattern information may be obtained by applying an image obtained by picking up a past action of the subject to the above-described action pattern categorized in advance. In such a case, it may be obtained by analyzing the acquired moving image or still image. In addition to image analysis, deep learning technology may be used as necessary to automatically determine based on the feature amount of the analysis image and convert it into data.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually newly discriminating signs of depression. In such a case, behavior pattern information is newly acquired from a new subject. The acquisition method is the same as that for reference behavior pattern information.

Based on the behavior pattern information newly acquired in this way, the discriminative pattern of the signs of depression is discriminated. In such a case, reference is made to the degree of association shown in FIG. 17 acquired in advance. A specific method for estimating the discriminant type of depression symptoms is the same as that in the first embodiment, and thus description thereof is omitted below.

Further, FIG. 18 shows an example in which three or more degrees of association are set between the combination of the reference behavior pattern information and the reference situation information described above and the discrimination pattern of signs of depression for the combination. there is

The reference situation information is any information about past situations in which the subject has behaved. The situation here refers to the circumstances surrounding the behavior of the subject. brightness and weather in the environment, sounds and noises in the surroundings, whether the surroundings are neat and tidy, or if the environment is messy, to what extent It may also indicate whether the person is in a situation where another person is helping, lending a hand, or interfering with the person, or whether the person is being talked to by another person.

The current situation for acquiring the reference situation information may be obtained by taking an image of the surroundings of the subject and analyzing the image. Each situation may be categorized in advance, and reference situation information may be obtained by applying an analyzed image to each categorization. In addition to image analysis, deep learning technology may be used as necessary to automatically determine based on the feature amount of the analysis image and convert it into data.

In the example of FIG. 18, it is assumed that the input data are behavior pattern information for reference P01 to P03 and situation information for reference P18 to 21, for example. An intermediate node shown in FIG. 18 is a combination of reference behavior pattern information as input data and reference situation information. Each intermediate node is also connected to an output. In this output, the discriminating pattern of symptoms of depression is displayed as the output solution.

Each combination (intermediate node) of the behavior pattern information for reference and the situation information for reference is associated with the discriminative pattern of signs of depression as the output solution through three or more degrees of association. The action pattern information for reference and the situation information for reference are arranged on the left side through the degree of association, and the discriminative pattern of signs of depression is arranged on the right side through the degree of association.

The search device 2 acquires in advance three or more degrees of association w13 to w22 shown in FIG. In other words, the search device 2, in determining the actual search solution, the reference behavior pattern information and the reference situation information, as well as the past data as to which of the discrimination patterns of signs of depression was preferable in that case. By accumulating and analyzing these, the degree of association shown in FIG. 18 is created. This analysis may be performed by artificial intelligence.

In the example of the degree of association shown in FIG. 18, the node 61b is a node of a combination of the reference situation information P18 with respect to the reference behavior pattern information P01, and the degree of association of the depression symptom discrimination type C is w15, The degree of association of the discriminative type E of signs of depression is w16. The node 61c is a node of a combination of the reference situation information P19 and P21 with respect to the reference behavior pattern information P02. is w18.

Such a degree of association becomes learned data in terms of artificial intelligence. After creating such learned data, the above-described learned data will be used when actually searching for a solution. In such a case, in addition to the behavior pattern information described above, situation information regarding the subject to be tested for the discriminative pattern of signs of depression is newly acquired. The situation information corresponds to the reference situation information.

Based on the behavior pattern information and the situation information newly acquired in this way, the credibility is searched. In such a case, reference is made to the degrees of association shown in FIG. 18 (Table 1) that have been acquired in advance. For example, when the newly acquired action pattern information is the same as or similar to P02 and the situation information is P21, the node 61d is associated via the degree of association, and this The node 61d is associated with the discriminant type C of the symptom of depression with w19 and with the discriminant type D of the symptom of depression with the degree of association w20. In such a case, the discriminant type C of signs of depression with the highest degree of association is selected as the optimum solution. However, it is not essential to select the one with the highest degree of association as the optimum solution, and the discrimination type D of signs of depression, which has a low degree of association but the association itself is recognized, may be selected as the optimum solution. . In addition, it is of course possible to select an output solution that is not connected by an arrow, and any other priority may be used as long as it is based on the degree of association.

Also in the fourth embodiment, as shown in FIG. 13, three or more degrees of association may be used between the reference information serving as the keynote and the discriminative pattern of the signs of depression. In such a case, a solution search is performed based on three or more degrees of association with the discriminative pattern of signs of depression according to newly acquired information. The basic reference information is, for example, reference behavior pattern information, etc., but is not limited to this, and any reference information (reference Pronoun frequency information, tone information for reference, facial expression image information, intent information for reference, electroencephalogram information for reference, attribute information for reference, magnetoencephalogram information for reference, meal content information for reference, sleep information for reference, driving information for reference , reference operation information, reference line-of-sight image information, reference conversation amount information, reference use time information, reference situation information, etc.) are also applicable.

In these cases, similarly, when information corresponding to reference information used as learning data is input, solution search is performed based on the above-described method.

The search solution obtained through the degree of association may be further modified or weighted based on other reference information.

The other reference information here means any reference information (reference pronoun frequency information, reference pronoun frequency information, Tone information for reference, Facial expression image information, Intent information for reference, EEG information for reference, Attribute information for reference, MEG information for reference, Diet information for reference, Sleep information for reference, Driving information for reference, Operation for reference information, line-of-sight image information for reference, amount of conversation for reference, time spent information for reference, situation information for reference, behavior pattern information for reference, etc.).

The reference information is not limited to any one type, and the solution search may be performed based on two or more types of reference information. Similarly, in such a case, the more the case leads to the discriminant pattern with signs of depression suggested by the reference information, the higher the discriminant pattern as the search solution obtained through the degree of association may be corrected. .

Similarly, as shown in FIG. 14, even when forming the degree of association with the discriminant pattern of signs of depression for a combination of reference information that serves as a keynote and other reference information, If the reference information is action pattern information for reference, the other information for reference is any reference information other than the basic reference information (reference pronoun frequency information, reference tone information, facial expression image information, etc.). , reference intent information, reference electroencephalogram information, reference attribute information, reference magnetoencephalogram information, reference meal content information, reference sleep information, reference driving information, reference operation information, reference gaze image information, conversation volume information for reference, time spent information for reference, situation information for reference, behavior pattern information for reference, etc.). The underlying reference information may be reference situation information.

In such a case as well, by performing a solution search in the same way, it is possible to estimate the discriminant pattern of signs of depression. At this time, as shown in FIG. 13 described above, for the search solution obtained through the degree of association, through other reference information (reference information F, G, H, etc.), discrimination of signs of depression The type may be modified.

Also in the fourth embodiment, the degree of association may be learned by combining not only one piece of other reference information but also two or more pieces of reference information.

As the search solution described above, a prescription for depression may be searched as a search solution in place of the discriminating type of symptoms of depression. In such a case, search solutions can be similarly obtained by preparing data associated with prescriptions for depression through three or more levels of association with the combination of the above-described basic reference information and other reference information. can be explored.

1 depression symptom discrimination system 2 search device 21 internal bus 23 display unit 24 control unit 25 operation unit 26 communication unit 27 estimation unit 28 storage unit 61 node

Claims (9)

In a depression sign discrimination program for discriminating signs of depression in a subject,
an information acquisition step of acquiring behavioral pattern information about the behavioral pattern of the subject;
Based on the behavioral pattern information obtained by the information obtaining step, with reference to the reference behavioral pattern information related to the past behavioral pattern of the subject and the degree of association of three or more levels with the discriminative type of the signs of depression, and a discrimination step of discriminating signs of depression in a subject. The information acquisition step acquires the behavior pattern information by applying an image obtained by capturing the behavior of the subject to behavior patterns categorized in advance,
2. The depressive symptoms according to claim 1, wherein the discrimination step obtains the reference behavioral pattern information by applying an image obtained by picking up past behaviors of the subject to the behavioral patterns categorized in advance. discrimination program. The information acquisition step further acquires situation information related to the situation in which the subject behaves,
In the determination step, a combination having the reference behavior pattern information and the reference situation information related to the past behavioral situations of the subject and three or more levels of association with the discrimination type of the signs of depression. and causing a computer to execute a discrimination step of discriminating signs of depression of the subject based on the behavior pattern information acquired by the information acquisition step and the situation information. 1. Depressive symptom discrimination program according to 1. a receiving step of receiving voice input from the subject;
an extracting step of converting the speech received by the receiving step into text data and morphologically analyzing the text data to extract pronouns contained in the text data;
The information acquisition step further acquires pronoun frequency information regarding the frequency of the pronouns extracted by the extraction step in the text data,
In the determination step, three or more degrees of association between combinations having the reference behavior pattern information and the reference pronoun frequency information related to the frequency of pronouns in the text data and the discrimination pattern of the signs of depression are referred to. 2. The program for discriminating signs of depression according to claim 1, wherein the signs of depression of the subject are discriminated based on the behavior pattern information and the pronoun frequency information acquired in the information acquisition step. further comprising a receiving step for receiving voice input from the subject;
In the information acquisition step, an information acquisition step of acquiring tone information relating to the tone of the voice received in the reception step;
In the determination step, the information acquisition step refers to three or more degrees of association between a combination having the reference behavior pattern information and the reference tone information related to the tone of voice and the discrimination pattern of signs of depression. 2. The program for discriminating signs of depression according to claim 1, discriminating signs of depression of the subject based on the behavior pattern information and the tone information acquired by the program. a receiving step of receiving voice input from the subject;
In the information obtaining step, the voice received in the receiving step is converted into text data and subjected to morphological analysis to obtain intent information relating to an intent that defines an action specifying a processing operation included in the text data. and get more
In the determination step, the combination having the reference behavior pattern information and the reference intent information related to the intent specifying the action specifying the processing operation, and the degree of association in three or more stages with the discrimination pattern of the signs of depression. and discriminating a symptom of depression of the subject based on the behavior pattern information and the intent information acquired in the information acquisition step. . The information acquisition step further acquires situation information related to the situation in which the subject behaves,
The determination step refers to the degree of association, and the degree of association between the reference behavioral pattern information corresponding to the behavioral pattern information acquired by the information acquisition step and the discrimination type of signs of depression is higher than three levels. 2. The program for discriminating symptoms of depression according to claim 1, wherein the symptom of depression of the subject is discriminated based on the obtained situation information while giving priority to the situation. a receiving step of receiving voice input from the subject;
an extracting step of converting the speech received by the receiving step into text data and morphologically analyzing the text data to extract pronouns contained in the text data;
The information acquisition step further acquires pronoun frequency information regarding the frequency of the pronouns extracted by the extraction step in the text data,
The determination step refers to the degree of association, and the degree of association between the reference behavioral pattern information corresponding to the behavioral pattern information acquired by the information acquisition step and the discrimination type of signs of depression is higher than three levels. 2. The program for discriminating symptoms of depression according to claim 1, wherein the symptom of depression of the subject is discriminated based on the obtained pronoun frequency information while prioritizing the subject. The depression symptom discrimination program according to any one of claims 1 to 8, wherein the discrimination step uses the degree of association corresponding to a weighting coefficient of each output of a neural network node in artificial intelligence. .

Images