Device and method

Abstract

A device 1 is provided with: an acquisition unit (11) that acquires reaction information pertaining to reactions of one or more users to one piece of information, and cognitive information pertaining to a cognitive bias of each of the users; and a determination unit (12) that, on the basis of the reaction information and the cognitive information, determines a cognitive bias that tends to be possessed by a user who reacts to the piece of information. The determination unit (12) may determine the cognitive bias that tends to be possessed by a user who reacts to the piece of information on the basis of the degree of each of one or more cognitive biases possessed by each of the users who have reacted to the piece of information.

Description

Apparatus and method

[0001] One aspect of the present disclosure relates to an apparatus and method for determining cognitive biases that a user tends to have in responding to information.

[0002] The following Patent Document 1 discloses a method for determining a measure of a user's cognitive bias or emotional state according to the degree of correspondence between the user's facial expression and an emotional prompt.

[0003] Special Publication No. 2022-506651

[0004] While the above methods determine a measure of a user's cognitive biases, they cannot determine, for example, the cognitive biases that a user is likely to have when responding to information. Therefore, it is desirable to determine the cognitive biases that a user is likely to have when responding to information.

[0005] An apparatus according to one aspect of the present disclosure includes an acquisition unit that acquires reaction information regarding the reactions of one or more users to a piece of information and cognitive information regarding cognitive biases possessed by each of the users, and a determination unit that determines cognitive biases that users who react to a piece of information tend to have based on the reaction information and the cognitive information.

[0006] In this aspect, the cognitive bias that a user who responds to a piece of information tends to have is determined based on the reaction information and the cognitive information. That is, the cognitive bias that a user who responds to the information tends to have can be determined.

[0007] According to one aspect of the present disclosure, it is possible to determine the cognitive biases that a user tends to have in responding to information.

[0008] 1 is a diagram illustrating an example of a functional configuration of a device according to an embodiment; FIG. 2 is a matrix diagram illustrating an example of what the device according to an embodiment can achieve depending on the presence or absence of a label and the presence or absence of intervention history; FIG. 3 is a diagram illustrating an example of an overall view of processing of the device according to an embodiment; FIG. 4 is a diagram illustrating an example of a table of content information; FIG. 5 is a diagram illustrating an example of a table (part 1) of user response information; FIG. 6 is a diagram illustrating an example of a table of user cognitive tendency information; FIG. 7 is a diagram illustrating an example of a table (part 2) of user response information; FIG. 8 is a diagram illustrating an example of a table of content cognitive tendency information; FIG. 9 is a diagram illustrating an example of a table of content cognitive bias information (part 1); FIG. 10 is a diagram illustrating an example of a table of content cognitive bias information (part 2); FIG. 11 is a diagram illustrating an example of a table of content cognitive bias information (part 3); FIG. 12 is a diagram illustrating an example of a table of content cognitive bias information (part 4); FIG. 13 is a diagram illustrating an example of a table of a token score dictionary; FIG. 14 is a diagram illustrating an example of a table of score information by token cognitive bias; FIG. 15 is a diagram illustrating an example of a table (part 3) of user response information; A flowchart illustrating an example of processing (part 1) executed by the device according to an embodiment; A flowchart illustrating an example of processing (part 2) executed by the device according to an embodiment; A diagram illustrating an example of the hardware configuration of a computer used in the device according to an embodiment.

[0009] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicate explanations will be omitted. Furthermore, the embodiments of the present disclosure in the following description are specific examples of the present invention, and the present invention is not limited to these embodiments unless otherwise specified to limit the present invention.

[0010] Device 1 is a computer that determines the cognitive biases that a user tends to have in responding to information.

[0011] Information is information about the content or circumstances of something. Information may be a sentence, a paragraph, a message, a statement, a video, a picture, a sound, a scent, or the like. In this embodiment, advertising statements are used as an example of information, but are not limited to this. In this embodiment, advertisements or advertising statements refer to advertising statements that can be handled electronically via a smartphone or the like, but are not limited to this.

[0012] A response is a user's behavior in response to a certain action, such as whether or not the user opened a message (text, push notification) from an advertisement, or whether or not the user actually took action or made a purchase.

[0013] Cognitive bias refers to a cognitive bias or tendency due to preconceptions such as the surrounding environment, past experiences, or intuition. People (users) need to make various decisions in their daily lives, and it is difficult to think logically about everything. Therefore, decisions are made based on this cognitive bias almost unconsciously. Cognitive bias varies from person to person, with cognitive tendencies (the strength of cognitive bias) differing from person to person. In this embodiment, person or individual may be replaced with user as appropriate.

[0014] Types of cognitive bias include conformity bias, scarcity bias, gain preference, loss aversion bias, and time pressure. Conformity bias means that people with a strong tendency to this bias tend to act or think in the same way as others. Scarcity bias means that people with a strong tendency to this bias are more likely to be attracted to things that are rare. Gain preference means that people with a strong tendency to this bias prefer to gain profits. Loss aversion bias means that people with a strong tendency to this bias are more likely to feel sadness from losses than joy from gains. Time pressure means that people with a strong tendency to this bias are more likely to concentrate when they feel time constraints such as deadlines or time limits.

[0015] 1 is a diagram illustrating an example of the functional configuration of an apparatus 1 according to an embodiment. As illustrated in FIG. 1, the apparatus 1 includes a storage unit 10, an acquisition unit 11 (acquisition unit), a determination unit 12 (determination unit), an output unit 13 (output unit), an extraction unit 14, and an update unit 15.

[0016] Each functional block of the device 1 is assumed to function within the device 1, but this is not limited to this. For example, some of the functional blocks of the device 1 may function in a computer device different from the device 1, connected to the device 1 through a network, while appropriately sending and receiving information with the device 1. Furthermore, some functional blocks of the device 1 may be omitted, multiple functional blocks may be integrated into one functional block, or one functional block may be separated into multiple functional blocks.

[0017] The storage unit 10 stores any information used in calculations and the like in the device 1, as well as the results of calculations in the device 1. The information stored by the storage unit 10 may be referenced by each function of the device 1 as appropriate.

[0018] Before describing the remaining functions of the device 1 shown in FIG. 1, the background, challenges, purpose and overview of the device 1 will now be described.

[0019] As background, it is known that when requesting something from someone or intervening in an advertising message (wording), the appeal effect can be increased by taking cognitive bias into consideration. In this embodiment, intervention refers to sending a message such as an advertisement to a user, but is not limited to this. For example, since many people generally have a strong conformity bias that makes them prone to behaving in the same way as others, a message such as "Many people use this service" is effective. Messages that take cognitive bias into consideration are usually designed in advance based on knowledge from behavioral economics or psychology.

[0020] Because each individual has different cognitive tendencies, more effective interventions can be achieved by providing tailored wording to suit each individual's cognitive tendencies (personalizing the wording). For example, by providing wording that takes into account conformity bias for people with a strong tendency toward conformity bias, wording that takes into account scarcity bias for people with a strong tendency toward scarcity bias, and wording that takes into account gain preference for people with a strong gain preference, it is possible to expect an improvement in overall effectiveness.

[0021] Personalization of messages may be achieved by machine learning using messages that take specific cognitive biases into account, i.e., messages labeled as cognitive biases, and data on the results of interventions. In this embodiment, the term "label" may be replaced with "cognitive bias" or "cognitive bias label." The intervention results here refer to whether or not a user responded to the message. For example, this refers to whether or not the user opened the message, or whether or not the user actually took action or made a purchase. The machine learning model constructed by the above-described machine learning can be used in services or situations such as web advertising, product recommendations through the push notification function of various apps, encouraging users to view news articles, and encouraging purchases.

[0022] Therefore, one of the objectives of the device 1 may be to secure a large amount of learning data for personalizing the wording.

[0023] Building machine learning models requires a large amount of training data, but there are not many messages that have been explicitly labeled with cognitive biases based on knowledge from behavioral economics or psychology. To address this issue, it would be meaningful to retroactively label common advertising copy that has intervention results with cognitive biases (corresponding to (1) below).

[0024] The world is filled with a huge amount of advertising, and many of them use psychological techniques to consciously or unconsciously encourage people to take action, so advertising copy can be placed within the framework of behavioral economics (i.e., labeled as a cognitive bias). An example of a psychological technique is using the phrase "limited time only" to enhance the appeal, in accordance with the law of scarcity, which is that scarce items are perceived as valuable.

[0025] However, since most data is accumulated without being labeled for cognitive biases, it cannot be used as training data for personalizing wording. Also, it is not realistic to manually label a huge amount of advertising data.

[0026] Therefore, the device 1 assigns a cognitive bias label to the advertising copy based on intervention results, such as "for what cognitive tendencies each advertisement was effective" (corresponding to (1) described below).

[0027] Note that the above labels are based on the premise that there is a history of intervention, so newly created wording cannot be labeled.

[0028] When messages (wording) that take cognitive bias into account are created manually, there is a possibility that cognitive bias labels will be assigned based on subjective interpretation. In business situations, it is expected that messages will be prepared by non-experts in behavioral economics or psychology. In such cases, a message about a specific cognitive bias may actually be linked to other cognitive biases rather than that specific bias.

[0029] To address this issue, the device 1 mechanically assigns labels to newly created phrases, rather than manually (corresponding to (2) and (2') described below). Specifically, it compares unlabeled phrases with phrases to which cognitive bias labels have been assigned, and determines which label phrase the phrase is closest to (not based on intervention records).

[0030] Furthermore, after assigning the label, the device 1 actually performs an intervention and updates the label based on the results (corresponding to (1') described below). It may be impossible to truly know whether the wording associated with the cognitive bias label is actually effective for people with a strong cognitive bias without actually performing the intervention. In other words, the accuracy of assigning cognitive bias may be better with a method based on intervention results than with a method not based on intervention results. The device 1 actually performs an intervention using the mechanically labeled wording, and updates the label using a method based on intervention results when the intervention results are accumulated (corresponding to (1') described below).

[0031] 2 is a matrix diagram showing an example of what the device 1 can achieve depending on whether a label is present and whether a history of intervention is present. In the case of an unlabeled word and a history of intervention, the device 1 can assign a label based on the history of intervention (referred to as "(1)" in this embodiment as appropriate). In the case of a labeled word and a history of intervention, the device 1 can reassign the label based on the history of intervention (referred to as "(1')" in this embodiment as appropriate). In the case of an unlabeled word and no history of intervention, the device 1 can assign a label that is not subjective (referred to as "(2)" in this embodiment as appropriate). In the case of a labeled word and no history of intervention, the device 1 can reassign a label that is not subjective (referred to as "(2')" in this embodiment as appropriate).

[0032] (1) labels statements that have not been labeled as cognitive biases based on intervention records. The accuracy of (1) is relatively high. (2) labels statements that have not been labeled as cognitive biases and have no intervention records. The accuracy of (2) is relatively medium.

[0033] Fig. 3 is a diagram showing an example of an overall picture of the processing of the device 1. First, starting from the left side of Fig. 3, the device 1 uses a large amount of past advertising data (unlabeled, with intervention history) to determine (the label of) a cognitive bias that users who respond to each piece of advertising data tend to have based on the intervention history (corresponding to (1)), and mechanically labels each piece of advertising data with the label of the determined cognitive bias.

[0034] Next, the process will be described from top to bottom in Figure 3. If the user has knowledge of behavioral economics or psychology, the user manually labels a newly created, unlabeled unknown phrase. On the other hand, if the user does not have knowledge of behavioral economics or psychology, the device 1 determines (the label of) a cognitive bias that users who respond to the unknown phrase tend to have, without based on intervention history (corresponding to (2)), and mechanically labels the unknown phrase with the label of the determined cognitive bias. Note that, for unknown phrases manually labeled by the user, the device 1 may also determine (the label of) a cognitive bias that users who respond to the unknown phrase tend to have, without based on intervention history (corresponding to (2')), and mechanically label the unknown phrase with the label of the determined cognitive bias (updating the manually assigned label).

[0035] Intervention is performed on phrases that have been manually or mechanically labeled as described above. For phrases for which intervention has been performed, the device 1 determines (the label of) the cognitive bias that users who respond to the phrase tend to have based on the intervention record (corresponding to (1')), and mechanically labels the phrase with the label of the determined cognitive bias. For phrases that have been mechanically labeled, the device 1 updates the label based on the record (repeats the processing after the intervention described above).

[0036] [Details of (1)] Each function of the device 1 shown in FIG. 1 for realizing (1) will be described.

[0037] The acquisition unit 11 acquires reaction information regarding reactions of one or more users to a piece of information and cognitive information regarding cognitive biases possessed by each of the users. The reaction information may be information regarding whether or not the user reacted to a piece of information. The cognitive information may be information regarding the degree of each of one or more cognitive biases possessed by the user.

[0038] The acquisition unit 11 may acquire the reaction information and the recognition information from the storage unit 10 where they are stored in advance, or may acquire them from another device via a network. The acquisition unit 11 may output the acquired reaction information and recognition information to the determination unit 12, or may have the storage unit 10 store them.

[0039] The determination unit 12 determines a cognitive bias that a user who reacts to a piece of information tends to have, based on the reaction information and the cognitive information input from the acquisition unit 11 or stored by the storage unit 10. The determination unit 12 may determine a cognitive bias that a user who reacts to a piece of information tends to have, based on the degree of each of one or more cognitive biases that each user who reacted to the piece of information has.

[0040] The determination unit 12 may output the determination result to the output unit 13 or may store the result in the storage unit 10 .

[0041] The output unit 13 outputs a piece of information in association with a cognitive bias that the determination unit 12 has determined that a user who reacts to the piece of information is likely to have. More specifically, the output unit 13 outputs a piece of information in association with a cognitive bias that the determination unit 12 has determined that a user who reacts to the piece of information is likely to have, based on the determination result input from the determination unit 12 or stored by the storage unit 10. Associating a cognitive bias with a piece of information means, for example, assigning a cognitive bias label to the piece of information.

[0042] From another perspective, the acquisition unit 11 acquires the intervention result for each word. At this point, it does not matter whether a cognitive bias is associated with the word. The determination unit 12 determines and updates the cognitive bias based on the intervention record. The determination unit 12 makes a determination based on the cognitive tendencies of people who are responding.

[0043] The determination unit 12 in (1) is intended to assign cognitive bias to wording that has a history of intervention. There are a large number of advertising copy and intervention results that do not take cognitive bias based on psychology or behavioral economics into account, and cognitive bias is assigned to them. The wording determines which cognitive tendencies, such as conformity, scarcity, gain, loss, and time pressure, users were likely to respond to. There are no particular limitations on the labeling method, but as a specific example, a method of labeling the advertising copy based on the cognitive tendencies of a group of users who are likely to respond to each advertisement will be described below. The response (conversion) here refers to whether the push notification was opened or whether a purchase was made after intervention, etc.

[0044] The storage unit 10 stores content information related to advertisement copy in advance. Fig. 4 is a diagram showing an example of a table of content information. As shown in the example table in Fig. 4, the content information corresponds to a content_id, which is identification information for identifying an advertisement copy, and a content, which is the content of the advertisement copy.

[0045] The storage unit 10 stores user reaction information (reaction information) related to the intervention results in advance. FIG. 5 is a diagram showing an example table (part 1) of user reaction information. As shown in the example table shown in FIG. 5, the user reaction information corresponds to a user_id, which is identification information for identifying a user, the above-mentioned content_id, and a conversion, which indicates whether the user responded to the advertisement copy identified by the content_id (True) or not (False). For example, the first record in the example table shown in FIG. 5 indicates that a user with a user_id of "u001" responded (conversion is "True") to a content_id of "c01" (according to the example table shown in FIG. 4, the content of the advertisement copy is "Chocolate that many people buy").

[0046] The storage unit 10 pre-stores user cognitive tendency information (cognitive information) related to cognitive biases possessed by the user. The user cognitive tendency information may be information including cognitive tendencies, which are the strength (degree) of each of one or more cognitive biases possessed by the user. FIG. 6 is a diagram showing an example table of user cognitive tendency information. As shown in the example table in FIG. 6, the above-mentioned user_id corresponds to a cognitive tendency A related to the cognitive bias "synchronization," a cognitive tendency B related to the cognitive bias "limitation," a cognitive tendency C related to the cognitive bias "gain," and the like (other cognitive tendencies may also be associated). Each cognitive tendency is expressed in the range from "0" to "1," with values ​​closer to "0" indicating the absence (weaker) of the cognitive tendency and values ​​closer to "1" indicating the presence (stronger) of the cognitive tendency.

[0047] As with the user cognitive tendency information described above, it is assumed that the cognitive tendencies of some or all users have already been obtained. Cognitive tendencies can be obtained by conducting a survey, or based on the intervention effects of specific bias wording designed based on behavioral economics. Cognitive tendencies (each bias) are expressed in the range of "0" to "1" (using known technology) based on the results of a behavioral economics survey or intervention results of specific cognitive bias wording.

[0048] The determination unit 12 first extracts only the records (logs) of users who responded to each advertisement copy. Specifically, the determination unit 12 acquires only records for which the conversion is "True" (for each content_id) from the example table of user response information shown in FIG. 5. FIG. 7 is a diagram showing an example table (part 2) of user response information. FIG. 7 is an example table in which only records for which the conversion is "True" are extracted from the example table of user response information shown in FIG. 5.

[0049] The determination unit 12 then calculates the average value of the cognitive tendency of a group of users who are likely to respond to each advertisement copy. The "users who are likely to respond" here refers to users for whom at least one of the content_ids is set to True.

[0050] The determination unit 12 may generate content cognitive tendency information in which, for each advertising copy, an average value of the cognitive tendency for each cognitive bias of a group of users who are likely to respond to the advertising copy is associated with the advertising copy. FIG. 8 is a diagram showing an example table of content cognitive tendency information. As shown in the example table shown in FIG. 8, the above-mentioned content_id is associated with an average cognitive tendency A, which is the average value of the cognitive tendency A related to the cognitive bias "conformity" of each of one or more users who responded to the advertising copy identified by the content_id; an average cognitive tendency B, which is the average value of the cognitive tendency B related to the cognitive bias "limitation" of each of the one or more users; and an average cognitive tendency C, which is the average value of the cognitive tendency C related to the cognitive bias "gain" of each of the one or more users. The determination unit 12 generates the example table of content cognitive tendency information shown in FIG. 8 based on the example table of user cognitive tendency information (cognition information) shown in FIG. 6 and the example table of user response information (reaction information) shown in FIG. 7 (or the example table of user response information (reaction information) shown in FIG. 5).

[0051] The determination unit 12 then determines the cognitive tendency with the highest average value in the content cognitive tendency information shown in FIG. 8 as the label of the advertising copy (content). The determination unit 12 may generate content cognitive bias information in which the determined label is associated with each advertising copy. FIG. 9 is a diagram showing an example table of content cognitive bias information (part 1). As shown in the example table of FIG. 9, the above-mentioned content_id, the above-mentioned content, and the cognitive bias, which is the label determined by the determination unit 12 for the advertising copy identified by the content_id, are associated with each other. FIG. 10 is a diagram showing an example table of content cognitive bias information (part 2). As shown in the example table of FIG. 10, the above-mentioned content_id is associated with the cognitive bias, which is the label determined by the determination unit 12 for the advertising copy identified by the content_id.

[0052] [Details of (2)] Each function of the device 1 shown in FIG. 1 for realizing (2) will be described.

[0053] The acquiring unit 11 may further acquire another piece of information different from the piece of information and feature information regarding the features of information to which users with each cognitive bias tend to respond, for each cognitive bias. The feature information may be information regarding the frequency of appearance of each element constituting the information to which users with each cognitive bias tend to respond, for each cognitive bias.

[0054] The acquisition unit 11 may acquire the other information and the characteristic information from the storage unit 10 where they are stored in advance, or may acquire them from another device via a network. The acquisition unit 11 may output the acquired other information and the characteristic information to the determination unit 12, or may cause the storage unit 10 to store them.

[0055] The determination unit 12 may further determine a cognitive bias that a user who reacts to the other piece of information tends to have, based on the other piece of information and the feature information input from the acquisition unit 11 or stored by the storage unit 10. The determination unit 12 may determine a cognitive bias that a user who reacts to the other piece of information tends to have, based on each element constituting the other piece of information and the feature information.

[0056] The determination unit 12 may output the determination result to the output unit 13 or may store the result in the storage unit 10 .

[0057] The judgment unit 12 may re-judge the cognitive bias that a user tends to have when reacting to another piece of information, based on the reaction information and cognitive information obtained for the other piece of information whose cognitive bias has been judged (by the judgment unit 12).

[0058] The output unit 13 may output another piece of information in association with the cognitive bias that the determination unit 12 has determined that a user who reacts to the other piece of information is likely to have. More specifically, based on the determination result (by the determination unit 12) input from the determination unit 12 or stored by the storage unit 10, the output unit 13 outputs another piece of information in association with the cognitive bias that the determination unit 12 has determined that a user who reacts to the other piece of information is likely to have.

[0059] From another perspective, the determination unit 12 determines cognitive bias by focusing on the wording itself. Words are collected for each specific cognitive bias, and the determination unit 12 makes a determination based on the characteristics that appear in the wording itself to which the cognitive bias is linked. For example, the determination unit 12 makes a determination based on the type of tokens (words or characters) that appear frequently for each cognitive bias. Next, (1) is executed based on the actual intervention results to assign a cognitive bias. Since cognitive bias determination based on performance is more accurate, a label is obtained based on new data. In other words, (1) is executed in a loop.

[0060] The storage unit 10 stores in advance an example table of content perception bias information shown in Fig. 11. Fig. 11 is a diagram showing an example table of content perception bias information (part 3).

[0061] The extraction unit 14 extracts what characteristics appear in the wording of each cognitive bias. There are no particular limitations on the characteristics and the method for extracting them, but specific examples will be described below. The characteristics here refer to what tokens appear for each cognitive bias when the wording is tokenized (divided into words or characters), and what the tokens are composed of. The wording of each cognitive bias is collected, and a score is assigned based on the frequency of token appearance. Specific processing will be described below using conformity bias wording as an example, as shown in the example table in FIG. 11.

[0062] The extraction unit 14 first focuses on conformity bias and converts each phrase into word tokens (the tokenization method does not matter). Fig. 12 is a diagram showing an example table of content cognitive bias information (part 4). In the example table shown in Fig. 12, the "content" in the example table shown in Fig. 11 is converted into word tokens. A delimiter " / " is inserted between each token.

[0063] The extraction unit 14 then calculates the number of occurrences and score (occurrence rate) of each token to create a token score dictionary, which is a dictionary. FIG. 13 is a diagram showing an example of a table of the token score dictionary. In the example table shown in FIG. 13, the extraction unit 14 calculates the score assuming that the total number of occurrences of tokens is "5,000." For example, in the first record of the example table shown in FIG. 13, it can be seen that the number of occurrences of the token "many" is calculated as "500," and therefore the score is calculated as "0.1," which is the result of the formula "500 / 5,000."

[0064] The determination unit 12 labels a word (another piece of information) with no history of intervention as a cognitive bias. As a specific method, the determination unit 12 makes the determination based on which cognitive bias's token score dictionary (generated by the extraction unit 14) a token of the word with no history of intervention is likely to appear in. When making this determination, the determination unit 12 may generate token cognitive bias-specific score information regarding the score for each cognitive bias of each token of the word with no history of intervention.

[0065] 14 is a diagram showing an example of a table of score information by token cognitive bias. In the example table shown in FIG. 14, tokens of phrases with no history of intervention are associated with the score for the cognitive bias "synchronization" of the token, the score for the cognitive bias "limitation" of the token, and the score for the cognitive bias "gain" of the token (scores for other cognitive biases may also be associated). In the example table shown in FIG. 14, the sum of the appearance rates of each token is further associated with each cognitive bias as a total score for the cognitive bias. The determination unit 12 determines the cognitive bias with the highest total score as the cognitive bias of phrases with no history of intervention.

[0066] The update unit 15 actually performs the intervention and causes the storage unit 10 to store the accumulated data. Fig. 15 is a diagram showing an example table (part 3) of user reaction information. The update unit 15 performs the intervention and causes the storage unit 10 to store the accumulated data, such as the example table shown in Fig. 15.

[0067] Next, an example of processing executed by the device 1 will be described with reference to Fig. 16. Fig. 16 is a flowchart showing an example of processing (part 1) executed by the device 1. First, the acquisition unit 11 acquires a statement and intervention history (step S1). Next, the determination unit 12 determines a cognitive bias and performs labeling (step S2). Next, the determination unit 12 stores the statement after labeling (step S3). Steps S1 to S3 are processing related to (1).

[0068] Next, the acquisition unit 11 acquires various words (step S4). Next, the extraction unit 14 extracts features (step S5). Next, the determination unit 12 acquires new words with no intervention history to be labeled (step S6). Next, the determination unit 12 determines cognitive bias and performs labeling (step S7). Next, the determination unit 12 stores the words after labeling (step S8). Steps S4 to S8 are processes related to (2).

[0069] Next, the update unit 15 stores the intervention record (step S9). Next, the device 1 repeats the process from step S1 to re-label the area based on the intervention record.

[0070] Next, another example of processing executed by the device 1 will be described with reference to Fig. 17. Fig. 17 is a flowchart showing an example of processing (part 2) executed by the device 1. First, the acquisition unit 11 acquires reaction information regarding reactions of one or more users to a piece of information and cognitive information regarding cognitive biases possessed by each of the users (step S10, acquisition step). Next, the determination unit 12 determines cognitive biases that users who react to a piece of information tend to have, based on the reaction information and cognitive information acquired in step S10 (step S11, determination step).

[0071] Next, the effects of the device 1 according to the embodiment will be described.

[0072] The device 1 includes an acquisition unit 11 that acquires reaction information regarding reactions of one or more users to a piece of information and cognitive information regarding cognitive biases possessed by each of the users, and a determination unit 12 that determines the cognitive biases that users who react to the piece of information tend to have based on the reaction information and the cognitive information. With this configuration, the cognitive biases that users who react to the piece of information tend to have are determined based on the reaction information and the cognitive information. In other words, it is possible to determine the cognitive biases that users who react to the piece of information tend to have.

[0073] Furthermore, in the device 1, the reaction information may be information regarding whether or not the user has reacted to a piece of information. With this configuration, it is possible to more accurately determine cognitive bias based on information regarding whether or not the user has reacted to a piece of information.

[0074] Furthermore, in the device 1, the cognitive information may be information regarding the degree of each of one or more cognitive biases possessed by the user. With this configuration, it is possible to more accurately determine cognitive biases based on the information regarding the degree of each of one or more cognitive biases possessed by the user.

[0075] Furthermore, the determination unit 12 of the device 1 may determine the cognitive bias that each user who responded to a piece of information tends to have, based on the degree of each of one or more cognitive biases that each user has. This configuration makes it possible to more accurately determine cognitive biases based on the degree of each of one or more cognitive biases that each user who responded to a piece of information has.

[0076] The device 1 may further include an output unit 13 that outputs a piece of information in association with a cognitive bias that the determination unit 12 has determined to be a tendency of a user who reacts to the piece of information. With this configuration, for example, a piece of information associated with a cognitive bias can be easily generated as (a part of) training data.

[0077] Furthermore, the acquisition unit 11 of the device 1 may further acquire another piece of information different from the one piece of information and feature information relating to the features of the information to which users with the cognitive bias tend to respond for each cognitive bias, and the determination unit 12 may further determine the cognitive bias that users who respond to the other piece of information tend to have based on the other piece of information and the feature information. With this configuration, for example, it is possible to determine a cognitive bias even without reaction information.

[0078] Furthermore, in the device 1, the feature information may be information regarding the frequency of appearance of each element constituting information to which users with each cognitive bias tend to respond, for each cognitive bias. With this configuration, it is possible to more accurately determine a cognitive bias based on information regarding the frequency of appearance of each element constituting information to which users with each cognitive bias tend to respond, for each cognitive bias.

[0079] Furthermore, the determination unit 12 of the device 1 may determine a cognitive bias that a user who reacts to another piece of information tends to have based on each element and feature information that constitutes the other piece of information. With this configuration, it is possible to more accurately determine cognitive bias based on each element and feature information that constitutes the other piece of information.

[0080] Furthermore, the determination unit 12 of the device 1 may re-determine the cognitive bias that the user tends to have when reacting to another piece of information, based on the reaction information and cognitive information obtained with respect to the other piece of information for which a cognitive bias has been determined. This configuration enables more accurate determination of cognitive bias based on the reaction information.

[0081] The device 1 of the present disclosure may have the following configuration.

[0082] [1] A device comprising: an acquisition unit that acquires reaction information regarding reactions of one or more users to a piece of information and cognitive information regarding cognitive biases possessed by each of the users; and a determination unit that determines a cognitive bias that a user who reacts to the piece of information tends to have based on the reaction information and the cognitive information. [2] The device described in [1], wherein the reaction information is information regarding whether or not the user reacted to the piece of information. [3] The device described in [1] or [2], wherein the cognitive information is information regarding the degree of each of one or more cognitive biases possessed by the user. [4] The device described in any one of [1] to [3], wherein the determination unit determines a cognitive bias that a user who reacts to the piece of information tends to have based on the degree of each of one or more cognitive biases possessed by each of the users who reacted to the piece of information. [5] The device described in any one of [1] to [4], further comprising an output unit that outputs the piece of information in association with a cognitive bias that the determination unit has determined that the user who reacts to the piece of information tends to have. [6] The device described in any one of [1] to [5], wherein the acquisition unit further acquires another piece of information different from the one piece of information and feature information regarding features of information to which users with the cognitive bias tend to respond for each cognitive bias, and the determination unit further determines a cognitive bias that users who respond to the another piece of information tend to have based on the another piece of information and the feature information. [7] The device described in [6], wherein the feature information is information regarding the frequency of appearance of each element constituting information to which users with the cognitive bias tend to respond for each cognitive bias. [8] The device described in [6] or [7], wherein the determination unit determines a cognitive bias that users who respond to the another piece of information tend to have based on each element constituting the another piece of information and the feature information. [9] The device described in any one of [6] to [8], wherein the determination unit re-determines a cognitive bias that users who respond to the another piece of information tend to have based on the reaction information and the cognitive information obtained for the another piece of information for which a cognitive bias has been determined.

[0083] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0084] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0085] For example, the device 1 according to an embodiment of the present disclosure may function as a computer that performs processing of the method of the present disclosure. Fig. 18 is a diagram showing an example of the hardware configuration of the device 1 according to an embodiment of the present disclosure. The device 1 described above may be physically configured as a computer including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0086] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the apparatus 1 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0087] Each function in device 1 is realized by loading specified software (programs) onto hardware such as processor 1001 and memory 1002, causing processor 1001 to perform calculations, control communication via communication device 1004, and control at least one of reading and writing data in memory 1002 and storage 1003.

[0088] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, the above-mentioned acquisition unit 11, determination unit 12, output unit 13, extraction unit 14, update unit 15, etc. may be realized by the processor 1001.

[0089] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with the programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the acquisition unit 11, the determination unit 12, the output unit 13, the extraction unit 14, and the update unit 15 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be used for other functional blocks. While the above-described various processes have been described as being executed by a single processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0090] The memory 1002 is a computer-readable recording medium and may be configured by, for example, at least one of a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0091] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0092] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the above-mentioned acquisition unit 11, determination unit 12, output unit 13, extraction unit 14, update unit 15, etc. may be realized by the communication device 1004.

[0093] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0094] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0095] The device 1 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0096] Notification of information is not limited to the aspects / embodiments described in this disclosure, and may be performed using other methods.

[0097] Each aspect / embodiment described in the present disclosure may be applied to at least one of systems using LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (New Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth (registered trademark), or other suitable systems, and next-generation systems enhanced based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A with 5G, etc.) may also be applied.

[0098] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0099] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0100] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0101] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0102] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0103] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0104] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0105] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0106] In addition, terms explained in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings.

[0107] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0108] Furthermore, the information, parameters, etc. described in this disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information.

[0109] The names used for the above parameters are not limiting in any way, and furthermore, the mathematical formulas etc. using these parameters may differ from those explicitly disclosed in this disclosure.

[0110] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like, all of which are considered to be "determining." "Determining" and "determining" may also include resolving, selecting, choosing, establishing, comparing, and the like, all of which are considered to be "determining." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Also, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0111] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using one or more wires, cables, and / or printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0112] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0113] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0114] The "means" in the configuration of each of the above devices may be replaced with "part," "circuit," "device," etc.

[0115] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0116] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0117] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0118] 1...device, 10...storage unit, 11...acquisition unit, 12...determination unit, 13...output unit, 14...extraction unit, 15...update unit, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. An apparatus comprising: an acquisition unit that acquires reaction information regarding the reactions of one or more users to a piece of information and cognitive information regarding the cognitive biases possessed by each of the users; and a determination unit that determines the cognitive biases that users who react to the piece of information tend to have based on the reaction information and the cognitive information.

2. The device according to claim 1, wherein the reaction information is information regarding whether or not the user has reacted to the piece of information.

3. The device according to claim 1, wherein the cognitive information is information regarding the degree of each of one or more cognitive biases possessed by the user.

4. The device described in claim 1, wherein the determination unit determines the cognitive biases that users who react to a piece of information tend to have based on the degree of each of one or more cognitive biases that each user who reacts to the piece of information has.

5. The device according to claim 1, further comprising an output unit that outputs the information in association with a cognitive bias that the determination unit has determined the user who reacts to the information is likely to have.

6. The device described in claim 1, wherein the acquisition unit further acquires another piece of information different from the one piece of information and characteristic information regarding the characteristics of information to which users with that cognitive bias tend to respond for each cognitive bias, and the determination unit further determines the cognitive bias that users who respond to the other piece of information tend to have based on the other piece of information and the characteristic information.

7. The device according to claim 6, wherein the feature information is information regarding the frequency of occurrence of each element constituting information to which a user with each cognitive bias tends to respond.

8. The device according to claim 7, wherein the determination unit determines a cognitive bias that a user tends to have in response to the other piece of information based on each element constituting the other piece of information and the feature information.

9. The device described in claim 6, wherein the determination unit re-determines the cognitive bias that the user tends to have in reacting to the other piece of information based on the reaction information and the cognitive information obtained in response to the other piece of information for which a cognitive bias has been determined.

10. A computer-implemented method comprising: an acquisition step of acquiring reaction information regarding reactions of one or more users to a piece of information and cognitive information regarding cognitive biases possessed by each of the users; and a determination step of determining cognitive biases that users who react to the piece of information tend to have based on the reaction information and the cognitive information.

Images