Information processing system, information processing method, and information processing program

Abstract

To improve accuracy of content filtering.SOLUTION: An information processing system 1 includes a first extraction unit that extracts first BCT component information related to a component of a first behavior change technique (BCT) contained in a first content determined to be a filtering target, a second extraction unit that extracts second BCT component information related to a component of a second behavior change technique (BCT) contained in a second content not determined to be a filtering target, and a generation unit that estimates reference information that serves as a criterion for determining whether a content is a filtering target on the basis of the first BCT component information and the second BCT component information, and generates a model based on the reference information.SELECTED DRAWING: Figure 2B

Description

[Technical field]

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

[0002] Conventionally, it is known to filter various information using a model based on machine learning. For example, Patent Document 1 describes a method in which learning data in a Bayesian filter is managed as a learning spam filter, and the learning spam filter is used to determine unwanted messages. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5676709 Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional spam filter described in Patent Document 1, for example, there is a risk that a non-spam email may be mistakenly determined to be spam (false positive), or that a spam message may mistakenly slip through the filter (false negative). Such problems may occur not only in spam message filters, but also in filters for various content.

[0005] Therefore, an object of the present invention is to provide an information processing system, an information processing method, and an information processing program that can improve the accuracy of content filtering. [Means for solving the problem]

[0006] An information processing system according to one embodiment of the present invention includes a first extraction unit that extracts first BCT component information regarding components of a first behavior change technique (first BCT) contained in first content determined to be subject to filtering, a second extraction unit that extracts second BCT component information regarding components of a second behavior change technique (second BCT) contained in second content that is not determined to be subject to filtering, and a generation unit that estimates reference information that serves as a criterion for determining whether or not a content is subject to filtering based on the first BCT component information and the second BCT component information, and generates a model based on the reference information.

[0007] An information processing method according to another aspect of the present invention includes a step of an information processing device extracting first BCT component information regarding components of a first behavior change technique (first BCT) contained in first content determined to be subject to filtering, extracting second BCT component information regarding components of a second behavior change technique (second BCT) contained in second content not determined to be subject to filtering, and estimating reference information that serves as a criterion for determining whether or not a content is subject to filtering based on the first BCT component information and the second BCT component information, and generating a model based on the reference information.

[0008] An information processing program according to another aspect of the present invention causes a computer to execute the steps of extracting first BCT component information relating to components of a first behavior change technique (first BCT) contained in first content determined to be subject to filtering, extracting second BCT component information relating to components of a second behavior change technique (second BCT) contained in second content not determined to be subject to filtering, and estimating reference information that serves as a criterion for determining whether or not a content is subject to filtering based on the first BCT component information and the second BCT component information, and generating a model based on the reference information. Effect of the Invention

[0009] According to the present invention, the accuracy of content filtering can be improved. [Brief description of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of a classification of BCT according to this embodiment. [Figure 2A] FIG. 2A is a conceptual diagram of generating a model for filtering according to the prior art. [Figure 2B] FIG. 2B is a conceptual diagram of generation of a model for filtering according to this embodiment. [Diagram 3] FIG. 3 is a diagram showing an example of a hardware configuration of each information processing device in the information processing system according to the present embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a functional configuration of the information processing system according to the present embodiment. [Figure 5A] FIG. 5A is a diagram showing an example of the first BCT component information according to this embodiment. [Figure 5B] FIG. 5B is a diagram showing an example of second BCT component information according to this embodiment. [Figure 6] FIG. 6 is a flowchart showing an example of the operation of the generating device according to this embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of the operation of the filter device according to this embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described with reference to the accompanying drawings, in which the same reference numerals denote the same or similar configurations.

[0012] (overview) In the information processing system according to this embodiment, the information processing device extracts information on components of a first behavior change technique (first BCT) contained in a first content determined to be a filtering target (hereinafter referred to as "first BCT component information"). The information processing device extracts information on components of a second behavior change technique (first BCT) contained in a second content not determined to be a filtering target (hereinafter referred to as "second BCT component information"). Based on the first BCT component information and the second BCT component information, the information processing device estimates information (hereinafter referred to as "reference information") that serves as a criterion for determining whether or not a content is a filtering target, and generates a model based on the reference information. Note that extraction can also be rephrased as encoding, etc.

[0013] In this embodiment, a behavior change technique (BCT) is a technique or method that acts (works) on behavior change. For example, BCTTv1 (Michie S, Richardson M, Johnston M, et al.: The behavior change technique taxonomy (v1) of 93 hierarchically clustered techniques: building an international consensus for the reporting of behavior change interventions. Ann Behav Med 2013; 46: 81-95.) specifies 93 BCTs in 16 groups. Note that the definition of BCTs is not limited to BCTTv1, and may be specified in any way as long as it comprehensively covers the methods of behavior change. In addition, the BCT according to this embodiment includes a group including one or more BCTs (hereinafter referred to as a "BCT group"), and the BCT group and the BCT may be interchangeable.

[0014] FIG. 1 is a diagram showing an example of classification of BCT according to this embodiment. One or more BCTs are classified according to a predetermined classification method. As shown in FIG. 1, BCTTv1 defines 16 BCT groups, namely, "1. Goals and planning", "2. Feedback and monitoring", "3. Social support", "4. Shaping knowledge", "5. Natural consequences", "6. Comparison of behaviour", "7. Associations", "8. Repetition and substitution", "9. Comparison of outcomes", "10. Reward and threat", "11. Regulation", "12. Antecedents", "13. Identity", "14. Scheduled consequences", "15. Self-belief", and "16. Covert learning".

[0015] In BCTTv1, one or more BCTs belong to each of the 16 BCT groups shown in Figure 1. For example, the BCT group "5. Natural consequences" includes BCTs such as "5.5. Anticipated regret." Also, the BCT group "10. Reward and threat" includes BCTs such as "10.11. Future punishment." Although not shown, one or more BCTs belong to the other groups as well.

[0016] Each BCT has a component, and the degree of each BCT included in a certain content may be indicated as a component value. Also, the sum of the component values ​​of each BCT belonging to the same BCT group may be indicated as the component value of the BCT group.

[0017] 2A and 2B are conceptual diagrams of the generation of a filtering model according to the conventional technology and the present embodiment. In FIG. 2B, the content to be filtered is a spam and / or junk message, the first content determined to be the subject of filtering is a spam message, and the second content not determined to be the subject of filtering is a message that is not a spam message (hereinafter, referred to as a "normal message"). However, FIG. 2B is merely an example, and the content to be filtered and the first content are not limited to spam messages, and the second content is not limited to normal messages.

[0018] Here, a spam message is a message that is intentionally designed to hinder a user's sound decision-making by exaggerating the loss of not acting quickly or by placing a psychological burden on the user with words that incite feelings of inferiority, without providing the user (e.g., the reader of the message) with information for better decision-making. Spam messages may be information transmitted by various media, such as e-mail, short messages, and stealth marketing sites known as "how was it?" sites. Spam messages may also be at least one of text data, image data, and audio data.

[0019] In addition, a spam message can be information that contains an excessive amount of a specific BCT. The specific BCT may be, for example, a BCT that belongs to at least one of the following categories: sludge, threat, and incitement (for example, “5.5. Anticipated regret” and / or “10.11. Future punishment” in Fig. 1). Sludge refers to a situation where a company or fraud group, for their own selfish gain, induces a user to act in a direction that is disadvantageous to the user or prevents a user from acting in a way that is advantageous to the user. For example, in the context of a spam message, sludge may be encouraging a user to enter a credit card number into a fraudulent website or not giving the user enough time to consult with their family before transferring money to a fictitious bill.

[0020] For example, as shown in Fig. 2A, in one example of the conventional technology, a judgment criterion based on Bayesian estimation is generated by machine learning using training data annotated as a nuisance message, and a filtering model based on the judgment criterion is generated. The judgment criterion based on Bayesian estimation estimates the probability of a message being a nuisance message using a conditional probability, and if the probability exceeds a preset threshold, the message is determined to be a nuisance message. Note that "annotation" may be rephrased as tagging, labeling, or the like.

[0021] Other known conventional filtering techniques based on training data annotated as spam messages include neural networks and random forests. Blocking techniques based on pre-set lists (e.g., blacklists, real-time blacklists, reputation lists, etc.) are also known. However, as spam messages using generative AI become more personalized and sophisticated, models using the above filtering and blocking techniques may increase the probability of false positives and false negatives, reducing the accuracy of filtering.

[0022] On the other hand, as shown in Fig. 2B, in the information processing system according to this embodiment, first BCT component information on the components of the first BCT included in the first teacher data annotated as a nuisance message is extracted, and second BCT component information on the components of the second BCT included in the second teacher data annotated as a normal message is extracted. By analyzing the difference between the first BCT component information and the second BCT component information, reference information that is a criterion for determining whether or not a message is a nuisance message is estimated, and a model for filtering nuisance messages based on the reference information is generated.

[0023] In this way, in the information processing system according to this embodiment, first BCT component information is extracted from first content determined to be a filtering target (for example, first teacher data annotated as a nuisance message), and second BCT component information is extracted from second content determined not to be a filtering target (for example, second teacher data annotated as a normal message). Furthermore, based on a comparison between the extracted first BCT component information and second BCT component information, reference information is estimated as a criterion for determining whether or not a content is a filtering target (for example, a nuisance message), and a model based on the reference information is generated. Therefore, compared to conventional criteria, a model based on a criterion with a lower probability of false positives and false negatives can be generated, and as a result, the accuracy of filtering can be improved.

[0024] (composition) Next, the configuration of the information processing system 1 according to this embodiment will be described. The information processing system 1 may be configured to include a single information processing device, or may be configured to include multiple information processing devices. For example, the information processing system 1 may be configured to include multiple information processing devices that implement part of the functional configuration described below, and the functional configuration described below may be realized by the multiple devices connected by a wired and / or wireless network.

[0025] 3 is a diagram showing an example of the hardware configuration of each information processing device constituting the information processing system according to this embodiment. Each information processing device (for example, a generating device 10 and a filter device 20 described later) in the information processing system 1 has a processor 11 such as a CPU (Central Processing Unit) equivalent to a calculation device, a storage device 12, a communication device 13, and an input / output device 14. Each of these components is connected via a bus so as to be able to transmit and receive data to and from each other.

[0026] The processor 11 is, for example, a CPU, and controls each information processing device in the information processing system 1. The processor 11 may execute various processes described in this embodiment by reading and executing a program from the storage device 12. Each information processing device in the information processing system 1 may include one or more processors 11. Furthermore, each of the devices may be called a computer.

[0027] The storage device 12 is configured with, for example, storage such as a memory, a hard disk drive (HDD) and / or a solid state drive (SSD), etc. The storage device 12 may store various information required for the processor 11 to execute processing (for example, an information processing program executed by the processor 11, etc.).

[0028] The communication device 13 is a device that communicates via a network, and may include, for example, a network card, a communication module, a chip, an antenna, etc. The communication device 13 may include a transmitting unit that transmits various information via the network, and / or a receiving unit that receives various information via the network.

[0029] The input / output device 14 includes an input unit such as a keyboard, a touch panel, a mouse, and / or a microphone, and an output unit such as a display and / or a speaker. The input unit accepts input of various information from a user. The output unit may include a display unit that displays various information for the user.

[0030] The hardware configuration described above is merely an example. Each information processing device in the information processing system 1 may omit some of the hardware shown in FIG. 4, or may include hardware not shown in FIG. 4. The hardware shown in FIG. 4 may be configured with one or more chips. When the information processing device is configured with multiple devices, each device may include at least some of the hardware.

[0031] Fig. 4 is a diagram showing an example of a functional configuration of an information processing system according to this embodiment. As shown in Fig. 4, the information processing system 1 includes an information processing device (hereinafter referred to as a "generation device") 10 that generates the above model (e.g., Fig. 2B), and an information processing device (hereinafter referred to as a filter device) 20 that acquires content and filters the acquired content based on the model. Note that the generation device 10 and the filter device 20 may be configured as the same information processing device, or may be configured as separate information processing devices.

[0032] 4 is merely an example, and it goes without saying that the generating device 10 and the filter device 20 may each have a functional configuration not shown. The function of each functional configuration is realized by loading an information processing program into hardware such as the processor 11 shown in FIG. 3 and operating at least one of the storage device 12, the communication device 13, and the input / output device 14 under the control of the processor 11.

[0033] As shown in FIG. 4, the generating device 10 includes a storage unit 101, a first extraction unit 102, a second extraction unit 103, and a generating unit 104.

[0034] The storage unit 101 stores a first content determined to be a filtering target and a second content not determined to be a filtering target. Specifically, the storage unit 101 may store, as the first content, first training data annotated to be a filtering target (e.g., training data annotated as a nuisance message). The storage unit 101 may also store, as the second content, second training data annotated to be not a filtering target (e.g., training data annotated as a normal message).

[0035] Furthermore, the storage unit 101 may store a model generated by the generation unit 104. Note that the storage unit 101 may store a model distilled based on the model generated by the generation unit 104.

[0036] The first extraction unit 102 extracts first BCT component information related to the components of the first BCT contained in the first content determined to be a filtering target. Specifically, the first extraction unit 102 may extract the first BCT component information by machine learning using the first content (for example, first teacher data annotated as a filtering target).

[0037] The first BCT component information may be a component table showing a fixed value based on the average of the first BCT components included in the first content, or may show the distribution of the first BCT components included in the first content. The first BCT component information may include at least one of information on the ratio of the information amount of the first BCT components to the information amount of the first content (hereinafter referred to as "first content ratio information") and information on the ratio of the information amount of a specific BCT component to the information amount corresponding to the first BCT component (hereinafter referred to as "first composition ratio information").

[0038] 5A is a diagram showing an example of the first BCT component information according to this embodiment. For example, FIG. 5A shows an example of the first BCT component information extracted from the first teacher data annotated as a nuisance message. In addition, in FIG. 5A, the first BCT component information is a component table showing fixed values ​​based on the average of the components of the first teacher data, but as described above, the first BCT component information may show the distribution of the components of the first teacher data.

[0039] For example, in FIG. 5A, the first BCT component information indicates that, when the amount of information of the first teacher data annotated as a spam mail is 100%, the amount of information of the components of the threatening BCT is 50%, the amount of information of the components of the provocative BCT is 40%, the amount of information of the components of the other BCT is 5%, and the amount of information of the components not belonging to any BCT (no BCT) is 5%. In this case, since the amount of information of the components of the first BCT (here, the threatening BCT, the provocative BCT, and the other BCT) included in the first teacher data is 95%, the first content ratio information may indicate 95 / 100. Also, since the amount of information of the components of the first BCT is 95%, and the amount of information of the components of a specific BCT (here, the threatening BCT, the provocative BCT) is 90% (=40%+50%), the first composition ratio information may indicate 90 / 95.

[0040] The second extraction unit 103 extracts second BCT component information related to the components of the second BCT contained in the second content that is not determined to be a filtering target. Specifically, the second extraction unit 103 may extract the second BCT component information by machine learning using the second content (for example, second teacher data annotated as a filtering target).

[0041] The second BCT component information may be a component table showing a fixed value based on the average of the second BCT components included in the second content, or may show the distribution of the second BCT components included in the second content. The second BCT component information may include at least one of information on the ratio of the information amount of the second BCT components to the information amount of the second content (hereinafter referred to as "second content ratio information") and information on the ratio of the information amount of a specific BCT component to the information amount corresponding to the second BCT component (hereinafter referred to as "second composition ratio information").

[0042] 5B is a diagram showing an example of second BCT component information according to this embodiment. For example, FIG. 5B shows an example of second BCT component information extracted from second teacher data annotated as a normal message. In addition, in FIG. 5B, the second BCT component information is a component table showing fixed values ​​based on the average of the components of the second teacher data, but as described above, the second BCT component information may show the distribution of the components of the second teacher data.

[0043] For example, in FIG. 5B, the second BCT component information indicates that, when the amount of information of the second teacher data annotated as a normal email is 100%, the amount of information not belonging to any BCT (no BCT) is 70%, the amount of information of the comparison BCT is 10%, the amount of information of the planning BCT is 10%, and the amount of information of the other BCT is 10%. In this case, since the amount of information corresponding to the components of the second BCT (here, the comparison BCT, the planning BCT, and the other BCT) included in the second teacher data is 30%, the second content ratio information may indicate 30 / 100. Also, since the amount of information corresponding to the components of the second BCT is 30%, and the amount of information corresponding to the components of a specific BCT (here, the threatening BCT and the instigating BCT) is 0%, the second composition ratio information may indicate 0.

[0044] The generating unit 104 estimates reference information that is a criterion for determining whether or not a content is a filtering target based on the first BCT component information and the second BCT component information, and generates a model based on the reference information. The reference information may include at least one of information on the ratio of the amount of information of a component of a third behavior modification technique (third BCT) contained in the content to the amount of information of the filtering target content (hereinafter referred to as "content ratio information"), information on the ratio of the amount of information of a component of a specific BCT to the amount of information of the component of the third BCT (hereinafter referred to as "composition ratio information"), and information on the specific BCT (hereinafter referred to as "BCT information").

[0045] Specifically, the generating unit 104 may estimate the content rate information on the ratio of the information amount of the third BCT component contained in the content to the information amount of the content to be filtered based on the first content rate information and the second content rate information. For example, as described in Fig. 5A and 5B, when the first content rate information is 95 / 100 and the second content rate information is 30 / 100, the generating unit 104 may estimate the content rate information, which is the criterion for determining whether the content is a content to be filtered (i.e., a spam message), to be 50 / 100.

[0046] Furthermore, the generating unit 104 may estimate composition ratio information regarding the ratio of the information amount of a specific BCT component to the information amount of a third BCT component based on the first composition ratio information and the second composition ratio information. For example, as described in Figs. 5A and 5B, when the first composition ratio information is 90 / 95 and the second composition ratio information is 0, the generating unit 104 may estimate the composition ratio information, which is a criterion for determining whether the content is a filtering target (i.e., a spam message), to be 40 / 50.

[0047] Furthermore, the generating unit 104 may estimate BCT information indicating a specific BCT based on the first BCT component information and the second BCT component information. For example, as shown in Figs. 5A and 5B, the first BCT component information has a higher ratio of components of the threatening BCT and the instigating BCT than the ratio of components of the comparison BCT and the planning BCT, which are often included in normal messages. The generating unit 104 may estimate BCT information indicating a specific BCT that tends to be included in the content to be filtered (i.e., nuisance messages) based on a comparison between the first BCT component information and the second BCT component information.

[0048] As shown in FIG. 4, the filter device 20 includes an acquisition unit 201, a filter unit 202, and an output unit 203.

[0049] The acquiring unit 201 acquires content. Specifically, the acquiring unit 201 acquires content to be determined whether or not it is a filtering target (for example, a target message to be determined whether or not it is a nuisance message).

[0050] The filter unit 202 judges whether the content acquired by the acquisition unit 201 is a content to be filtered based on the model generated by the generation device 10, and performs filtering based on the judgment result. Note that the filter unit 202 may use the model generated by the generation unit 104 itself, or may use a model obtained by distilling the model. As described above, the model may use at least one of the content rate information and the composition ratio information as a judgment criterion.

[0051] Specifically, the filter unit 202 may determine whether or not the content is a filtering target by using a model based on the ratio of the amount of information of the BCT contained in the content to the amount of information of the content acquired by the acquisition unit 201 and the content content content information. For example, in the model, whether or not the content is a filtering target may be determined based on whether or not the ratio of the amount of information of the BCT contained in the content to the amount of information of the content acquired by the acquisition unit 201 exceeds a value (e.g., 50 / 100) indicated by the content content information, or how much it deviates from the value indicated by the content content information.

[0052] Furthermore, the filter unit 202 may determine whether or not the content is a filtering target by using a model based on the ratio of the information amount of a specific BCT component to the information amount of BCT included in the content acquired by the acquisition unit 201 and the above-mentioned composition ratio information. For example, in the model, whether or not the content is a filtering target may be determined based on whether or not the ratio of the specific BCT component to the information amount of BCT included in the content acquired by the acquisition unit 201 exceeds a value (e.g., 40 / 50) indicated by the above-mentioned composition ratio information, or how much it deviates from the value indicated by the composition ratio information.

[0053] In addition, the filter unit 202 may determine whether or not the content is to be filtered by using a model based on the ratio of the amount of information of a specific BCT component to the amount of information of the BCT contained in the content acquired by the acquisition unit 201 and the above-mentioned content rate information and composition ratio information.

[0054] The output unit 203 outputs information on the result of filtering by the filter unit 202 (hereinafter, referred to as "filtering information"). The filtering information may be fed back to the generating device 10. For example, if the content filtered by the filter unit 202 as the content to be filtered is the content that should not be filtered (i.e., in the case of a false positive), the filtered content may be annotated as the content not to be filtered and fed back to the generating device 10 as the second teacher data. On the other hand, if the content not filtered by the filter unit 202 as the content to be filtered is the content that should be filtered (i.e., in the case of a false negative), the not filtered content may be annotated as the content to be filtered and fed back to the generating device 10 as the second teacher data. This can further improve the accuracy of filtering based on the model generated by the generating device 10. (operation) Next, the operation of the information processing system 1 according to this embodiment will be described. Note that the operations of the generating device 10 and the filter device 20 shown in Fig. 6 and Fig. 7 are merely examples and are not limited to those shown in the drawings. For example, some steps may be deleted and / or added, and some steps (e.g., steps S101 and S102 in Fig. 6) may be executed in a different order or in parallel.

[0055] Fig. 6 is a flowchart showing an example of the operation of the generating device 10 according to the present embodiment. As shown in Fig. 6, the generating device 10 extracts first BCT component information related to the components of the first BCT included in the first content determined to be a filtering target (step S101). For example, as described in Figs. 2B and 5A, the generating device 10 may extract the first BCT component information by machine learning using the first teacher data annotated as a spam email.

[0056] The generating device 10 extracts second BCT component information related to components of the second BCT included in the second content that is not determined to be a filtering target (step S102). For example, as described in FIGS. 2B and 5B, the generating device 10 may extract the second BCT component information by machine learning using the second teacher data annotated as a normal email.

[0057] The generating device 10 estimates reference information that serves as a criterion for determining whether or not a content is subject to filtering, based on the first BCT component information extracted in step S101 and the second BCT component information extracted in step S102 (step S103). Specifically, as described in Figs. 2B, 5A, and 5B, the generating device 10 may analyze the difference between the first BCT component information and the second BCT component information to estimate the reference information that serves as the criterion. The generating device 10 generates a model based on the reference information estimated in step S103 (step S104).

[0058] Fig. 7 is a flowchart showing an example of the operation of the filter device 20 according to this embodiment. As shown in Fig. 7, the filter device 20 acquires a content to be determined whether it is a filtering target (step S201). For example, the filter device 20 acquires a target message to be determined whether it is a nuisance message.

[0059] The filter device 20 judges whether the content acquired in step S201 is a content to be filtered based on the model generated by the generation device 10, and performs filtering based on the judgment result (step S202). For example, the filter device 20 judges whether the target message is a nuisance message based on the model, and performs filtering based on the judgment result.

[0060] The filter device 20 outputs filtering information related to the result of the filtering in step S202 (step S203).

[0061] As described above, in the information processing system 1 according to this embodiment, the generating device 10 estimates reference information as a criterion for determining whether or not a content is a filtering target (e.g., a spam message) based on the first BCT component information extracted from the first content determined to be a filtering target and the second BCT component information extracted from the second content determined not to be a filtering target, and generates a model based on the reference information. Therefore, it is possible to generate a filtering model based on a criterion with a lower probability of false positives and false negatives compared to conventional criteria.

[0062] Moreover, in the information processing system 1 according to the present embodiment, it is determined whether the acquired content is a content to be filtered based on the model generated by the generating device 10, and filtering is performed based on the determination result. Therefore, it is possible to improve the accuracy of filtering.

[0063] (Other embodiments) In the above embodiment, a spam message is exemplified as a content to be filtered, but the content to be filtered is not limited to the above. The content to be filtered can be any content, for example, a catch phrase, an advertisement, a content designed by prompt engineering, etc., as long as there is a combination of a first content that is highly likely to include a BCT showing a remarkable tendency and a second content that is less likely to include the BCT showing the remarkable tendency. For example, the combination of the first content and the second content may be determined based on whether the catch phrase is well-written or not, whether the advertisement is well-balanced or not, or whether the content designed by prompt engineering is appropriate or not.

[0064] Furthermore, the content to be filtered may be "content that encourages a specific action." For example, the generating device 10 may generate a model for determining whether a content is trying to encourage a person in a weaker position to take an action by sending a coercive email, and the filter device may determine based on the model whether the target content is trying to encourage a person in a weaker position to take an action by sending a coercive email. Such a model may be used to determine whether or not there is sexual harassment, power harassment, or bullying of subcontractors.

[0065] In addition, the specific BCT may be any BCT that is expected to be included more prominently in the content determined to be the filtering target than in the content determined not to be the filtering target. For example, when the content determined to be well written is the filtering target, the specific BCT may be, for example, a BCT that presents an objective viewpoint of the target behavior, but is not limited to this. In addition, when the content determined to be well-balanced is the filtering target, the specific BCT may be, for example, a BCT that presents a new perspective, but is not limited to this. In addition, when the content designed by prompt engineering and determined to be appropriate is the filtering target, the specific BCT may be, for example, a BCT that provides feedback, but is not limited to this.

[0066] In addition, the numbers assigned to the first BCT, the second BCT, and the third BCT in this embodiment are assigned to distinguish the three types of BCT, and do not indicate the order. Therefore, as long as each BCT is distinguished, the first, second, and third numbers may be appropriately interchanged.

[0067] The above-described embodiment is intended to facilitate understanding of the present invention, and is not intended to limit the present invention. The flow charts, sequences, elements included in the embodiment, and their arrangements, materials, conditions, shapes, sizes, etc. described in the embodiment are not limited to those exemplified, and may be modified as appropriate. [Explanation of symbols]

[0068] 1...information processing system, 10...generation device, 20...filter device, 11...processor, 12...storage device, 13...communication device, 14...input / output device, 101...storage unit, 102...first extraction unit, 103...second extraction unit, 104...generation unit, 201...acquisition unit, 202...filter unit, 203...output unit

Claims

1. a first extraction unit that extracts first BCT component information related to a component of a first behavior change technique (first BCT) included in a first content determined to be a filtering target; a second extraction unit that extracts second BCT component information related to a component of a second behavior modification technique (second BCT) included in second content that is not determined to be a filtering target; a generation unit that estimates reference information that is a criterion for determining whether or not a content is a filtering target based on the first BCT component information and the second BCT component information, and generates a model based on the reference information; An information processing system comprising:

2. The reference information includes at least one of content ratio information on a ratio of an amount of information of a component of a third behavior modification technique (third BCT) included in the content to an amount of information of the content to be filtered, composition ratio information on a ratio of an amount of information of a component of a specific BCT to an amount of information of the component of the third BCT, and BCT information on the specific BCT.

2. The information processing system according to claim 1.

3. The first BCT component information includes at least one of first content ratio information on a ratio of an information amount of the first BCT component to an information amount of the first content, and first composition ratio information on a ratio of an information amount of the specific BCT component to an information amount corresponding to the first BCT component, The second BCT component information includes at least one of second content ratio information on a ratio of an information amount of the second BCT component to an information amount of the first content, and second composition ratio information on a ratio of an information amount of the specific BCT component to an information amount corresponding to the second BCT component.

3. The information processing system according to claim 2.

4. An acquisition unit that acquires content; a filter unit that determines whether the acquired content is a content to be filtered based on the model, and performs filtering based on the determination result; The information processing system according to claim 1 , further comprising:

5. the first content is an unsolicited message; the second content is a normal message other than a spam message, The content is a message sent to a user.

5. The information processing system according to claim 4.

6. An information processing device, extracting first BCT component information related to a component of a first behavior change technique (first BCT) included in the first content determined to be a filtering target; extracting second BCT component information related to a component of a second behavior change technique (second BCT) included in second content that is not determined to be filtered; A step of estimating reference information serving as a criterion for determining whether or not a content is a filtering target based on the first BCT component information and the second BCT component information, and generating a model based on the reference information; An information processing method comprising the steps of:

7. On the computer, extracting first BCT component information related to a component of a first behavior change technique (first BCT) included in the first content determined to be a filtering target; extracting second BCT component information related to a component of a second behavior change technique (second BCT) included in second content that is not determined to be filtered; A step of estimating reference information serving as a criterion for determining whether or not a content is a filtering target based on the first BCT component information and the second BCT component information, and generating a model based on the reference information; An information processing program for executing the above.

Images