Information processing device and information processing method

Abstract

This information processing device is provided with: an acquisition unit that acquires past information pertaining to a past campaign on the basis of meta information pertaining to a target campaign; an estimation unit that estimates the likelihood of success of the target campaign on the basis of the meta information and the past information; and a generation unit that generates generation information for generating advice regarding the implementation of the target campaign, on the basis of the likelihood of success.

Description

Information processing device and information processing method

[0001] The present disclosure relates to an information processing device and an information processing method.

[0002] Patent Literature 1 discloses a device for generating campaign documents to be provided to customers. When generating new campaign documents for customers, this device generates new campaign documents that prioritize information content about untried interests of the customer (interests other than those that have not been responded to by the customer, among the interests of information content published in campaign documents previously provided to the customer).

[0003] JP 2013-228934 A

[0004] Conventionally, when planning a campaign, for example, it has been required to provide effective advice for the target campaign that is the subject of the planning.

[0005] The present disclosure aims to provide effective advice for targeted campaigns.

[0006] An information processing device according to one aspect of the present disclosure includes an acquisition unit that acquires past information related to past campaigns based on meta information related to a target campaign, an estimation unit that estimates the likelihood of success of the target campaign based on the meta information and the past information, and a generation unit that generates generation information for generating advice for the target campaign based on the likelihood of success.

[0007] An information processing method according to another aspect of the present disclosure is executed by a processor and includes the steps of: obtaining past information relating to past campaigns based on meta information relating to a target campaign; estimating the likelihood of success of the target campaign based on the meta information and the past information; and generating generation information for generating advice for the target campaign based on the likelihood of success.

[0008] According to the present disclosure, effective advice on targeted campaigns can be provided.

[0009] FIG. 1 is a block diagram showing the configuration of a RAG system according to this embodiment. FIG. 2 is a diagram showing an example of the database shown in FIG. 1. FIG. 3 is a flowchart showing an operation method of the RAG system according to this embodiment. FIG. 4 is a diagram showing an example of how past information is acquired. FIG. 5 is a diagram showing an example of how a likelihood of success is estimated. FIG. 6 is a diagram showing an example of how generated information is generated. FIG. 7 is a diagram showing an example of how a risk is estimated. FIG. 8 is a diagram showing an example of how advice is output. FIG. 9 is a diagram showing the hardware configuration of a RAG system according to this embodiment.

[0010] The present disclosure will be described with reference to the accompanying drawings. Whenever possible, the same parts are designated by the same reference numerals and redundant description will be omitted.

[0011] 1 is a block diagram showing a system 10 including a RAG system 1 according to the present embodiment. The system 10 provides users with, for example, a service for implementing a campaign. The service includes, for example, outputting advice (hereinafter simply referred to as "advice") regarding the implementation of a campaign that is the subject of the advice (hereinafter referred to as a "target campaign") based on information (hereinafter referred to as "meta information") related to the campaign. More specifically, the service includes, for example, providing users with information about campaigns that are expected to generate revenue.

[0012] A campaign includes, for example, a promotion of a product. A product includes both tangible and intangible items. An intangible product includes, for example, the provision of a service to a customer. A promotion of a product includes, for example, advertising using media such as SNS (Social Networking Service), email, or video. Advertising includes, for example, providing a product advertisement to a customer using the above media. The system 10 includes a RAG system 1 (information processing device), a terminal 2, a database 3, and a server device 4.

[0013] The RAG system 1 is configured to be able to communicate with each of the terminal 2, database 3, and server device 4 via a network. The network includes, for example, a wireless communication network and a fixed communication network. The RAG system 1, for example, receives meta information from the terminal 2. The RAG system 1, for example, outputs advice based on the received meta information to the terminal 2. The RAG system 1 provides advice to the user by, for example, outputting the output advice to the terminal 2.

[0014] The terminal 2 is a device used by a user who wishes to receive a service for implementing a campaign. The terminal 2 is, for example, a personal computer, a smartphone, a tablet terminal, a game device, etc. The type of the terminal 2 is not particularly limited.

[0015] Terminal 2 includes, for example, an input unit and an output unit. The input unit, for example, accepts input of meta information. If terminal 2 is a smartphone, the input unit is a touch panel mounted on terminal 2. The output unit, for example, outputs advice output from RAG system 1 to the user. If terminal 2 is a smartphone, the output unit is a display (including a touch panel) mounted on terminal 2.

[0016] The database 3 stores predetermined information. For example, the database 3 stores information indicating the content of past campaigns (hereinafter referred to as "content information"). "Past" means, for example, a time before the RAG system 1 provided advice to the user. The content information includes information related to past campaigns. The database 3 is stored, for example, in a device external to the RAG system 1.

[0017] 2 is a table showing an example of the database 3 shown in FIG. 1. The content information includes, for example, multiple implementation conditions. The multiple implementation conditions are conditions for implementing the campaign. The multiple implementation conditions include, for example, the name of the campaign, the target demographic, the implementation means, the target product that is the subject of the campaign, the effect, and the cost.

[0018] The name of a campaign is information that uniquely identifies the campaign. The database 3 may include information that uniquely identifies the campaign, and may include identification information (e.g., ID (Identification)) of the campaign instead of the name of the campaign.

[0019] The target demographic is a customer demographic that is expected to be the target of the campaign. For example, the target demographic may be a customer demographic that is expected to receive the product promoted by the campaign. The target demographic includes, for example, age and gender.

[0020] The implementation means is the means used to implement the campaign. Examples of the implementation means include social media, email, and video advertisements. The target product is the product that is the target of the campaign. Examples of the target product include lotions. Examples of lotions include moisturizing lotions, astringent lotions, and whitening lotions. The means and the content of the target product can be changed as appropriate.

[0021] The effect is, for example, the effect obtained by implementing a campaign. The effect is, for example, the number of new users acquired by implementing a campaign. The effect may be calculated, for example, by conducting a survey of customers. The cost is the amount required to implement the campaign. The cost may be, for example, the total of labor costs, advertising costs, equipment costs, etc. required to implement the campaign.

[0022] The server device 4 is a device that enables the provision of advice using a generative AI model 41. The server device 4 stores, for example, the generative AI model 41. In response to input of generation information (e.g., a prompt) including input information, the generative AI model 41 generates advice according to any one or a combination of instructions, context, questions, and output formats indicated by the generation information. The generative AI model 41 is an AI model that can return the generated advice as response information. Specific examples of the generation information will be described later.

[0023] The generative AI model 41 may be, for example, an interactive AI that includes a large language model (LLM) and a user interface (UI) for interacting with the user, enabling text or voice chat with the user. Examples of such generative AI models 41 include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc. The generative AI model 41 may also be, for example, an AI model specialized for images (e.g., Stable Diffusion XL 1.0, Midjourney, etc.).

[0024] The generative AI model 41 may be stored in the server device 4, or may be stored in another device connected to the server device 4 via a network so that information can be exchanged with the user via the server device 4. The generative AI model 41 may be stored in, for example, the RAG system 1. Note that although only one server device 4 is illustrated in FIG. 1, the system 10 may include multiple server devices 4.

[0025] Next, a description will be given of the functional configuration of the RAG system 1. The RAG system 1 includes a reception unit 11, an acquisition unit 12, an estimation unit 13, a generation unit 14, and an output unit 15 as its functional configuration.

[0026] The reception unit 11 receives, for example, meta information. The meta information includes target implementation conditions, which are implementation conditions for the target campaign. The meta information includes, for example, a plurality of target implementation conditions. The plurality of target implementation conditions includes, for example, a target effect, which is the goal of the effect of the target campaign. Specific examples of meta information will be described later.

[0027] The acquisition unit 12 acquires past information related to past campaigns based on the meta information accepted by the acceptance unit 11. The acquisition unit 12 acquires, for example, past campaigns including past implementation conditions that satisfy the target implementation conditions as past information. The past information includes past implementation conditions that correspond to the target implementation conditions and are implementation conditions for the past campaigns. The past information includes, for example, multiple past implementation conditions. The multiple past implementation conditions include implementation means for the past campaigns. The acquisition unit 12 extracts, for example, past campaigns that satisfy at least one of the multiple target implementation conditions. The acquisition unit 12 acquires the implementation conditions of the extracted past campaigns as past implementation conditions. The target implementation conditions used to extract past campaigns are, for example, set in advance.

[0028] "The past implementation condition corresponds to the target implementation condition" means that the type of the past implementation condition is the same as the type of the target implementation condition. The multiple past implementation conditions include, for example, past effects, which are the effects of past campaigns. The past effects correspond to the target effect, which is the target implementation condition. Specific examples of past information will be described later.

[0029] The estimation unit 13 estimates the likelihood of success of the target campaign based on the meta information accepted by the acceptance unit 11 and the past information acquired by the acquisition unit 12. The likelihood of success is, for example, a degree of possibility that an effect exceeding a target effect will be achieved by implementing the target campaign.

[0030] The generation unit 14 generates generation information for generating advice based on the likelihood of success estimated by the estimation unit 13. The generation information is, for example, a prompt to be input to the generation AI model 41. Specific examples of the generation information will be described later.

[0031] The output unit 15 inputs the generation information generated by the generation unit 14 to the generation AI model 41. The output unit 15 acquires the advice output from the generation AI model 41. The output unit 15 outputs the acquired advice to the terminal 2, for example. The output unit 15 causes the advice to be output to the output unit of the terminal 2, for example.

[0032] Next, an operation method (including an example of an information processing method) of the RAG system 1 according to this embodiment will be described. Fig. 3 is a flowchart showing the operation method of the RAG system 1 according to this embodiment. First, the reception unit 11 receives meta information (step S1). In step S1, the user inputs the meta information via the input unit of the terminal 2.

[0033] 4, the user inputs, for example, a target demographic, a target product, a target effect, and a budget as multiple target implementation conditions. For example, the user inputs that the target demographic is teenage girls and the target product is a moisturizing lotion. For example, the user inputs that the target effect is to acquire 10,000 new users and that the budget is 20 million yen.

[0034] The terminal 2 transmits the input meta-information to the RAG system 1. The reception unit 11 accepts the received meta-information.

[0035] Next, the acquisition unit 12 acquires past information based on the meta information received in step S1 (step S2). In step S2, the acquisition unit 12 acquires past campaigns including past implementation conditions that satisfy the target implementation conditions received in step S1 as past information. More specifically, the acquisition unit 12 extracts campaigns that satisfy at least one of the target implementation conditions received in step S1.

[0036] In the example of Fig. 4, the acquisition unit 12 extracts past campaigns whose target products match the target implementation conditions. As shown in Fig. 2, the target products of each of campaigns A to F are lotions. Therefore, the acquisition unit 12 identifies campaigns A to F. The acquisition unit 12 acquires the implementation conditions indicated by the content information of the identified past campaigns as past implementation conditions. The acquisition unit 12 acquires the past implementation conditions of the acquired past campaigns as past information.

[0037] Next, the estimation unit 13 estimates the likelihood of success based on the meta information received in step S1 and the past information acquired in step S2 (step S3). In step S3, the estimation unit 13 estimates the likelihood of success based on the target effect received in step S1 and the past effects acquired in step S2. The estimation unit 13 estimates the likelihood of success for each implementation means, for example. The estimation unit 13 estimates the likelihood of success by dividing the number of past campaigns whose past effects exceed the target effect by the number of past campaigns included in the past information, for example.

[0038] In the example of Figure 5, of campaigns A to F, the implementation means for campaigns A and C is SNS, the implementation means for campaigns B, E, and F is email, and the implementation means for campaign D is video advertising. Furthermore, of campaigns A to F, the past effects of campaigns B and E exceed the target effect, while the past effects of the other campaigns do not exceed the target effect. From the above, the estimation unit 13 estimates the probability of success to be the value (67%) obtained by dividing the number of past campaigns that used email as the implementation means and had a past effect exceeding the target effect (2) by the number of past campaigns that used email as the implementation means (3).

[0039] Next, the generation unit 14 generates generation information based on the success probability estimated in step S3 (step S4). The process of generating the generation information will be described in detail below. As shown in FIG. 6, the generation information includes, for example, roles, tasks, and conditions.

[0040] The role specifies the position from which advice is generated. The task specifies the task that is required. The condition specifies the constraints required to execute the task.

[0041] The generating unit 14 generates, for example, generation information including a preset role. The generating unit 14 generates, for example, generation information including a role "marketing manager." The generating unit 14 may also generate, for example, generation information including a role based on an input by a user.

[0042] The generation unit 14 generates generation information including, for example, a preset task. For example, the generation unit 14 generates generation information including, as a task, an instruction to "explain the means of implementing the campaign and the basis for it." For example, the generation unit 14 may generate generation information including a task based on an input by a user.

[0043] The generating unit 14 generates generation information including the target implementation condition received in step S1. The generating unit 14 generates generation information including the target implementation condition as a condition of the generation information.

[0044] The generation unit 14 generates generation information including the past campaigns acquired in step S2. The generation unit 14 generates generation information including past implementation conditions of the past campaigns as conditions for the generation information.

[0045] The generation unit 14 generates generation information including the success probability estimated in step S3. The generation unit 14 generates generation information including the success probability for each implementation means. The generation unit 14 generates generation information including, as conditions for the generation information, the success probability for each implementation means and an instruction to output the success probability.

[0046] The generation unit 14 estimates the risk of implementing the target campaign by the implementation means based on the number of past campaigns for each implementation means acquired in step S2. The generation unit 14 generates generation information including an instruction to output the estimated risk. The generation unit 14 generates generation information including the estimated risk and an instruction to output the estimated risk as conditions for the generation information. The generation unit 14 generates generation information including, for example, the level of risk. The method for estimating risk will be described in detail below.

[0047] As shown in FIG. 7 , the generation unit 14 determines, for each implementation unit, whether the number of past campaigns implemented by the implementation unit is greater than a first value (e.g., 1). The first value is, for example, preset. When a large number of past campaigns have been implemented by a certain implementation unit, the likelihood of success of the implementation unit can be estimated based on many past campaigns, and therefore the likelihood of success can be estimated with high accuracy. Therefore, when the generation unit 14 determines that the number of past campaigns is greater than the first value, it estimates that the risk of the implementation unit is low. Conversely, when a small number of past campaigns have been implemented by a certain implementation unit, the likelihood of success of the implementation unit can be estimated based on fewer past campaigns, and therefore the accuracy of the estimation of the likelihood of success can be reduced. Therefore, when the generation unit 14 determines that the number of past campaigns is equal to or less than the first value, it estimates that the risk of the implementation unit is high.

[0048] The generation unit 14 generates generation information including an instruction to explain the content of the advice based on, for example, a comparison between the target implementation conditions accepted in step S1 and the past implementation conditions acquired in step S2. The generation unit 14 generates generation information including, for example, an instruction to output unsuccessful campaigns from among the past campaigns acquired in step S2.

[0049] Next, the output unit 15 outputs advice (step S5). In step S5, the output unit 15 transmits the generation information generated in step S4 to the server device 4 and inputs the generation information to the generation AI model 41. The generation AI model 41 generates advice using the generation information as input. The generation AI model 41 generates advice based on, for example, the role, task, and conditions included in the generation information. As shown in FIG. 8 , the generation AI model 41 generates advice including, for example, a recommended product and a recommended implementation means. The generation AI model 41 generates advice including, for example, reasons why the product and implementation means are recommended. The generation AI model 41 generates advice including, for example, the past effectiveness of a campaign targeting a product similar to the target product, which is the target implementation condition. The generation AI model 41 generates advice including, for example, the past effectiveness of a campaign targeting a product dissimilar to the target product, which is the target implementation condition.

[0050] The generation AI model 41 generates advice that includes, for example, the likelihood of success included in the generation information. The generation AI model 41 generates advice that includes, for example, past implementation conditions of past campaigns that did not go well. The generation AI model 41 generates advice that includes, for example, the risks of implementing the target campaign using the recommended implementation method.

[0051] In step S5, the server device 4 outputs the advice generated by the generative AI model 41 to the output unit 15. The output unit 15 transmits the advice output from the server device 4 to the terminal 2. The output unit 15 outputs the advice to the output unit of the terminal 2. After the above processing, the RAG system 1 completes the series of operations.

[0052] Next, the effects of the RAG system 1 will be described. The RAG system 1 estimates the likelihood of success based on meta information related to the target campaign and past information related to past campaigns, and generates generated information based on the estimated likelihood of success. This allows the generated information to be generated so as to provide advice for improving the likelihood of success, for example. Therefore, effective advice for the target campaign can be provided.

[0053] Furthermore, the method of operating the RAG system 1 described above has the same effects as the RAG system 1 described above.

[0054] The meta information includes target implementation conditions, which are implementation conditions for the target campaign, and the past information includes past implementation conditions, which are implementation conditions for past campaigns that correspond to the target implementation conditions, and the acquisition unit 12 acquires past campaigns that include past implementation conditions that satisfy the target implementation conditions as the past information. In this case, advice can be generated based on past campaigns that satisfy the target implementation conditions and are used as reference for implementing the target campaign.

[0055] The meta information includes a target effect, which is the target effect of the target campaign, and the past information includes past effects, which are the effects of past campaigns. The estimation unit 13 estimates the likelihood of success based on the target effect and the past effects. In this case, for example, the likelihood of success can be estimated based on past campaigns that have a high past effect relative to the target effect, which is the target of the target campaign. Therefore, the likelihood of success of the target campaign can be estimated with high accuracy.

[0056] The estimation unit 13 estimates the likelihood of success by dividing the number of past campaigns whose past effects exceed the target effect by the number of past campaigns included in the past information. In this case, the likelihood of success of the target campaign can be estimated based on the number of past campaigns whose past effects exceed the target effect. Therefore, the likelihood of success of the target campaign can be estimated with greater accuracy.

[0057] The generation unit 14 generates generation information including the success probability. In this case, for example, advice can be generated based on the success probability included in the generation information, so that advice can be generated to increase the success probability. Therefore, more effective advice can be provided for the target campaign.

[0058] The past information includes implementation means of past campaigns, the estimation unit 13 estimates the likelihood of success for each implementation means, and the generation unit 14 generates generated information including the likelihood of success for each implementation means. For example, in campaigns with similar content, the likelihood of success may differ for each implementation means. Since generated information including the likelihood of success for each implementation means is generated, it is possible to generate advice that recommends implementation means with a higher likelihood of success, for example. Therefore, more effective advice can be provided for the target campaign.

[0059] The past information includes implementation means of past campaigns, and the generation unit 14 estimates the risk of implementing the target campaign by the implementation means based on the number of past campaigns for each implementation means, and generates generation information including instructions to output the estimated risk. For example, if the number of past campaigns implemented by a certain implementation means is small, the generation information is generated based on the small number of past campaigns, which may mean that implementing the target campaign by that implementation means involves risk. In contrast, for example, if the number of past campaigns implemented by a certain implementation means is small, the generation information including instructions to output the risk can be generated to notify the user of the risk of implementing the target campaign by that implementation means.

[0060] Next, a modified example of the RAG system 1 will be described.

[0061] (1) In the above example, the generation unit 14 generated the generation information including the past campaigns acquired by the acquisition unit 12. However, the generation unit 14 may identify past campaigns that can be used as reference when implementing the target campaign, based on the likelihood of success estimated by the estimation unit 13 and the past effects acquired by the acquisition unit 12. The generation unit 14 may generate generation information including the identified past campaigns and instructions to output the identified past campaigns.

[0062] For example, the generation unit 14 may identify past campaigns that were implemented by an implementation means having a probability of success equal to or greater than a second value and that have a past effect exceeding a target effect. The second value may be, for example, set in advance. Then, the generation unit 14 may generate generation information including the identified past campaigns and instructions for outputting the identified past campaigns.

[0063] In this case, among the past campaigns included in the past information, it is possible to identify past campaigns that are particularly useful as references because they have a high probability of success and have had past effects that exceed the target effect. Then, it is possible to generate generation information that includes instructions for outputting the identified past campaigns, so that advice can be generated based on past campaigns that are particularly useful as references for implementing the target campaign. Therefore, it is possible to provide more effective advice for the target campaign.

[0064] For example, the generation unit 14 may identify past campaigns that were implemented by an implementation means that is less than a third value (first threshold) indicating a likelihood of success and that are equal to or greater than a fourth value (second threshold) indicating a past effect. The third and fourth values ​​may be, for example, preset. The generation unit 14 may then generate generation information that includes the identified past campaigns and instructions to output the identified past campaigns.

[0065] In this case, it is possible to identify past campaigns that are particularly useful as references because they have a high past effect even if the probability of success is low, among the past campaigns included in the past information. Therefore, as in the above example, it is possible to provide more effective advice for the target campaign.

[0066] (2) In the example of (1) above, the generation unit 14 identifies past campaigns that were implemented by an implementation means whose likelihood of success is less than a third value and whose past effects are equal to or greater than a fourth value, and generates the identified past campaigns and generation information including instructions to output the identified past campaigns. However, the generation unit 14 may generate generation information including instructions to output notes about the identified past campaigns.

[0067] For example, when the generation unit 14 identifies a past campaign that was implemented by an implementation means whose likelihood of success is less than a third value and whose past effect is equal to or greater than a fourth value, the generation unit 14 generates generation information including an instruction to output a notice indicating that the likelihood of success is low. The generation unit 14 generates generation information including an instruction to output the identified campaign and a notice for the identified campaign.

[0068] In this case, for example, the generated information can include an instruction to output information indicating that the likelihood of success is low, so that the advice provided can include content that alerts the user to the low likelihood of success, thereby providing more effective advice for the target campaign.

[0069] (3) In the above example, the generation unit 14 generated the generated information including the level of risk. However, the generation unit 14 may generate the generated information including the degree of risk. For example, the generation unit 14 may calculate the degree of risk for each implementation means by dividing the number of past campaigns implemented by the implementation means by a certain fifth value. The fifth value is, for example, set in advance. The generation unit 14 may generate the generated information including the calculated degree of risk for each implementation means.

[0070] (4) In the above example, the meta information included the target demographic, target product, target effect, and budget as multiple target production conditions. However, the content of the meta information is not limited to the content described above. The meta information may include, for example, at least one of the following: an overview of the target campaign, an implementation date, an implementation period, and meta information indicating an overview of the target campaign. The meta information may include multiple elements for each of the multiple target production conditions. For example, the multiple target production conditions may include both "the implementation means is email, and acquiring 10,000 or more new users" and "the implementation means is email, and acquiring 20,000 or more new users" as the implementation means and the target effect.

[0071] (5) In the above example, the past information included the campaign name, target demographic, means, target product, past effects, and costs. However, the content of the past information is not limited to the content described above. The past information may include, for example, at least one of the following: the scale of the past campaign, the contents of the novelized product, whether or not the novelized product was offered, the date and period of the past campaign, information identifying those who entered the past campaign, and the specific content of the past campaign. The scale of the past campaign includes, for example, the scale of the past campaign. For example, if the implementation means is email, the scale of the past campaign includes the number of emails sent. For example, if the implementation means is social media, the scale of the past campaign includes the number of posts via social media. For example, if the implementation means is video advertising, the scale of the past campaign includes the airtime of the commercials.

[0072] (6) The generation unit 14 may generate generation information including the likelihood of success for each past campaign. For example, the estimation unit 13 may identify past campaigns that have a past effect exceeding the target effect from among the past campaigns acquired by the acquisition unit 12. The estimation unit 13 may estimate, as the likelihood of success, a value obtained by subtracting the target effect from the past effect of the identified past campaign and normalizing the result by a known means. The generation unit 14 may generate generation information including the likelihood of success for each past campaign estimated by the estimation unit 13. The method by which the estimation unit 13 estimates the likelihood of success for each past campaign is not limited to the method described above.

[0073] (7) In the above example, the database 3 is stored in a device external to the RAG system 1. However, the database 3 may also be stored in the RAG system 1.

[0074] (8) In the above example, the system 10 included the RAG system 1, the terminal 2, the database 3, and the server device 4. An example was described in which each functional unit (receiving unit 11, acquiring unit 12, estimating unit 13, generating unit 14, and output unit 15) was realized by processing in the RAG system 1. However, each functional unit may be realized by processing in the terminal 2. In this case, the system 10 does not need to include the RAG system 1. Also, if the database 3 is stored in the terminal 2, the system 10 does not need to include the database 3. The generative AI model 41 may be stored in the terminal 2, for example. In this case, the system 10 does not need to include the server device 4.

[0075] (9) In the above example, the RAG system 1 includes the reception unit 11. However, the RAG system 1 does not necessarily have to include the reception unit 11.

[0076] The information processing device and information processing method of the present disclosure have the following configuration.

[0077] [1] An information processing device comprising: an acquisition unit that acquires past information related to past campaigns based on meta information related to a target campaign; an estimation unit that estimates the likelihood of success of the target campaign based on the meta information and the past information; and a generation unit that generates generation information for generating advice related to the implementation of the target campaign based on the likelihood of success.

[0078] [2] The information processing device described in [1], wherein the meta information includes target implementation conditions that are implementation conditions for the target campaign, the past information includes past implementation conditions that correspond to the target implementation conditions and are implementation conditions for the past campaigns, and the acquisition unit acquires the past campaigns that include the past implementation conditions that satisfy the target implementation conditions as the past information.

[0079] [3] The information processing device according to [1] or [2], wherein the meta information includes a target effect that is a target for the effect of the target campaign, the past information includes a past effect that is the effect of the past campaign, and the estimation unit estimates the likelihood of success based on the target effect and the past effect.

[0080] [4] The information processing device according to [3], wherein the estimation unit estimates, as the likelihood of success, a value obtained by dividing the number of past campaigns having the past effect exceeding the target effect by the number of past campaigns included in the past information.

[0081] [5] The information processing device according to any one of [1] to [5], wherein the generation unit generates the generated information including the likelihood of success.

[0082] [6] The information processing device according to any one of [1] to [5], wherein the past information includes the implementation means of the past campaigns, the estimation unit estimates the likelihood of success for each of the implementation means, and the generation unit generates the generated information including the likelihood of success for each of the implementation means.

[0083] [7] The information processing device according to any one of [1] to [6], wherein the past information includes past effects, which are the effects of the past campaigns, and the generation unit identifies the past campaigns that can be used as reference when implementing the target campaign based on the likelihood of success and the past effects, and generates the generation information including instructions to output the identified past campaigns.

[0084] [8] The information processing device according to [7], wherein the generation unit identifies past campaigns that are less than a first threshold indicating the likelihood of success and are equal to or greater than a second threshold indicating the past effectiveness, and generates the generated information including an instruction to output notes about the identified past campaigns.

[0085] [9] An information processing device according to any one of [1] to [8], wherein the past information includes the implementation means of the past campaigns, and the generation unit estimates the risk of implementing the target campaign by the implementation means based on the number of past campaigns for each implementation means, and generates the generated information including an instruction to output the estimated risk.

[0086]

[10] An information processing method executed by a processor, comprising: a step of acquiring past information related to past campaigns based on meta information related to a target campaign; a step of estimating a likelihood of success of the target campaign based on the meta information and the past information; and a step of generating generation information for generating advice for the target campaign based on the likelihood of success.

[0087] 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 connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining the single device or multiple devices with software.

[0088] Functions include, but are not limited to, judgment, determination, discrimination, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, regard, 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.

[0089] 9 is a diagram showing an example of the hardware configuration of the RAG system 1 according to this embodiment. The RAG system 1 may be physically configured as a computer device 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.

[0090] In the following description, the term "device" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the RAG system 1 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

[0091] Each function in the RAG system 1 is realized by loading specified software (programs) onto hardware such as a processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via a communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0092] The processor 1001, for example, runs an operating system to control the entire computer. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, at least one of the functional units of the RAG system 1 described above may be realized by the processor 1001.

[0093] The processor 1001 also reads programs (program code), 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 these. The program may be a program that causes a computer to execute at least some of the operations described in the above-described embodiments. For example, at least one of the functional units of the RAG system 1 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.

[0094] The memory 1002 is a computer-readable recording medium and may be configured, for example, by 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 referred to as 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 the accompanying determination method according to one embodiment of the present disclosure.

[0095] 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.

[0096] 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 a network device, network controller, network card, 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, at least one of the functional units of the RAG system 1 described above may be realized by the communication device 1004. The communication device 1004 may be implemented with a transmitter and a receiver that are physically or logically separated.

[0097] 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).

[0098] 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.

[0099] The RAG system 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.

[0100] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0101] 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.

[0102] 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 sent to another device.

[0103] 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).

[0104] 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).

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0110] Furthermore, the information, parameters, etc. described in the present 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. For example, a radio resource may be indicated by an index.

[0111] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0112] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0113] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0114] 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 in 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. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0115] 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.

[0116] 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."

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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."

[0121] 1...RAG system (information processing device), 12...acquisition unit, 13...estimation unit, 14...generation unit, 41...generated AI model

Claims

1. An information processing device comprising: an acquisition unit that acquires past information related to past campaigns based on meta information related to a target campaign; an estimation unit that estimates the likelihood of success of the target campaign based on the meta information and the past information; and a generation unit that generates generation information for generating advice related to the implementation of the target campaign based on the likelihood of success.

2. The information processing device described in claim 1, wherein the meta information includes target implementation conditions that are implementation conditions for the target campaign, the past information includes past implementation conditions that correspond to the target implementation conditions and are implementation conditions for the past campaigns, and the acquisition unit acquires the past campaigns that include the past implementation conditions that satisfy the target implementation conditions as the past information.

3. The information processing device described in claim 1, wherein the meta information includes a target effect, which is the target effect of the target campaign, the past information includes a past effect, which is the effect of the past campaign, and the estimation unit estimates the likelihood of success based on the target effect and the past effect.

4. The information processing device according to claim 3, wherein the estimation unit estimates the likelihood of success as the value obtained by dividing the number of past campaigns having a past effect exceeding the target effect by the number of past campaigns included in the past information.

5. The information processing device according to claim 1, wherein the generation unit generates the generated information including the likelihood of success.

6. An information processing device as described in claim 1, wherein the past information includes the implementation means of the past campaigns, the estimation unit estimates the likelihood of success for each of the implementation means, and the generation unit generates the generated information including the likelihood of success for each of the implementation means.

7. The information processing device described in claim 1, wherein the past information includes past effects, which are the effects of the past campaigns, and the generation unit identifies past campaigns that can be used as reference when implementing the target campaign based on the likelihood of success and the past effects, and generates the generation information including instructions to output the identified past campaigns.

8. The information processing device according to claim 7, wherein the generation unit identifies past campaigns that are less than a first threshold indicating the likelihood of success and greater than or equal to a second threshold indicating the past effectiveness, and generates the generated information including instructions to output notes about the identified past campaigns.

9. An information processing device as described in claim 1, wherein the past information includes the implementation means of the past campaigns, and the generation unit estimates the risk of implementing the target campaign by the implementation means based on the number of past campaigns for each implementation means, and generates the generated information including instructions to output the estimated risk.

10. An information processing method executed by a processor, comprising: steps of obtaining past information related to past campaigns based on meta information related to a target campaign; estimating the likelihood of success of the target campaign based on the meta information and the past information; and generating generation information for generating advice for the target campaign based on the likelihood of success.

Images