Device and method

Abstract

A device according to the present invention generates recommendation text about a target facility that is aimed at a target user. The device comprises a reception unit that receives target facility information about a target facility and demographic information for a target user and a prompt generation unit that generates a prompt that instructs generation of recommendation text about the target facility that is aimed at the target user on the basis of the target facility information and the demographic information for the target user.

Description

Apparatus and method

[0001] The present disclosure relates to an apparatus and method for generating recommendation sentences for a target user regarding a target facility.

[0002] Patent Literature 1 describes a device that automatically generates advertisement text based on the basic text of the advertisement and keywords corresponding to the advertisement. For example, there are a huge number of rental properties. Therefore, it is conceivable that recommendation text for these rental properties could be automatically generated by the above-mentioned device or the like.

[0003] JP 2013-153669 A

[0004] For example, even if there is a recommendation sentence about a rental property, it is difficult to say that the content is suitable for all users who are considering moving in, etc. Therefore, the present disclosure describes an apparatus and method that can generate a recommendation sentence about a target facility with content suitable for a target user.

[0005] The device according to the present disclosure includes a reception unit that receives target facility information regarding the target facility and demographic information of the target user, and a prompt generation unit that generates a prompt that instructs the generation of a recommendation sentence regarding the target facility for the target user based on the target facility information and the demographic information of the target user.

[0006] According to the present disclosure, it is possible to generate recommendation sentences about a target facility that have content suitable for a target user.

[0007] FIG. 1 is a diagram showing the overall configuration of a system including a prompt generation device of the present disclosure. FIG. 2 is a block diagram showing the functional configuration of a sentence generation device. FIG. 3 is a diagram showing an example of basic data including property information and behavioral data. FIG. 4 is a block diagram showing the functional configuration of a prompt generation device. FIG. 5 is a diagram showing an example of a prompt generated by a prompt generation unit when a target user is a tenant. FIG. 6 is a diagram showing an example of a prompt generated by a prompt generation unit when a target user is a tenant. FIG. 7 is a diagram showing an example of a prompt generated by a prompt generation unit when a target user is a purchaser. FIG. 8 is a flowchart showing the flow of LLM fine-tuning processing performed in the sentence generation device. FIG. 9 is a flowchart showing the flow of processing performed in the prompt generation device for generating recommendation sentences for a target user regarding a target facility. FIG. 10 is a diagram showing an example of the hardware configuration of a prompt generation device.

[0008] 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.

[0009] FIG. 1 is a diagram illustrating the overall configuration of a system including a prompt generation device according to the present disclosure. This system generates recommendation sentences for recommending a target facility. In this embodiment, a rental property is used as an example of the target facility. Examples of rental properties include apartment rooms, condominium rooms, commercial rooms, and rental houses. For example, recommendation sentences for rental properties may be used by providers of websites that introduce rental properties.

[0010] As shown in Figure 1, the system includes a prompt generation device (device) 100 and a sentence generation device 200. The prompt generation device 100 and the sentence generation device 200 are communicatively connected to each other via a network (NM). A user terminal 300 is communicatively connected to the prompt generation device 100 via the network.

[0011] The user terminal 300 transmits a request to generate recommendation sentences for rental properties to the prompt generation device 100. For example, an operator can input various pieces of input information by operating the user terminal 300. This operator may be, for example, a person in charge of a real estate company that brokers or sells rental properties (a provider of a rental property website), a tenant considering moving into a rental property, or a buyer considering purchasing a rental property.

[0012] The prompt generation device 100 generates a prompt in response to a request from the user terminal 300 to generate a recommended sentence, transmits the prompt to the sentence generation device 200, and receives a response. The prompt generation device 100 transfers the response to the user terminal 300. For example, the user terminal 300 displays the response transferred from the prompt generation device 100 on a display screen or the like. This allows the operator of the user terminal 300 to obtain the response.

[0013] Figure 2 is a block diagram showing the functional configuration of a sentence generation device. The sentence generation device 200 shown in Figure 2 generates a recommendation sentence as an answer based on a prompt sent from the prompt generation device 100. The sentence generation device 200 includes a data acquisition unit 210 and an LLM 220. The data acquisition unit 210 acquires and stores basic data that forms the basis of knowledge used by the LLM 220 when generating a recommendation sentence.

[0014] The basic data includes, for example, property information and behavioral data. FIG. 3 is a diagram showing an example of basic data including property information and behavioral data. The property information is various information related to rental properties. For example, as shown in FIG. 3, the property information includes "property ID," "address," "age of building," "floor plan," and "exclusive area." The behavioral data is information related to the content of a person's behavior and the demographic information of the person who performed the behavior. The demographic information of a person is information related to a person's attributes, such as gender, age, marital status, income, and occupation. For example, as shown in FIG. 3, the behavioral data includes the "user ID" of the person who performed the behavior, the "date and time" of the behavior, "gender," "age," "marital status," and "content of the behavior."

[0015] The data acquisition unit 210 may acquire property information from, for example, a device that manages information on rental properties, or may acquire property information entered by an administrator that manages information on rental properties. The data acquisition unit 210 may acquire behavioral data from, for example, a server that collects user behavior details.

[0016] Furthermore, based on the acquired property information and behavioral data, the data acquisition unit 210 performs tuning (fine tuning) of a part or the entire trained model pre-trained by the LLM 220. Note that the data acquisition unit 210 may be provided separately from the LLM 220 or may be provided within the prompt generation device 100.

[0017] The LLM 220 generates an answer (a recommended sentence in this embodiment) based on the input information and the prompt using a pre-trained model. The LLM 220 transmits the generated answer to the prompt generation device 100.

[0018] In this disclosure, the LLM 220 is used as the language model, but other models may be used as long as they are generative AI models. In this disclosure, a generative AI model is a model that can generate content in response to a prompt (Prompt) containing input information, according to the instructions, context, question, and output format indicated by the prompt, and return the content as response information. The prompt can also include input information. In this case, the generative AI model generates response information targeted at the input information. The generative AI model may be, for example, an interactive AI model 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 include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, PaLM2, etc. In this disclosure, the prompt generation device 100 is capable of providing content provision functions using interactive AI models, which are multiple types of models. These interactive AI models may be stored within the prompt generation device 100, or may be stored in another device connected to the prompt generation device 100 via a network so that information can be exchanged with the user via the prompt generation device 100. Although only one prompt generation device 100 is shown in the figure, multiple prompt generation devices 100 may be included.

[0019] In this disclosure, a prompt is information indicating an instruction or question entered by a user in an interactive system such as an interaction with a generative AI model or a command line interface (CLI).

[0020] 4 is a block diagram showing the functional configuration of the prompt generation device. As shown in FIG. 4, the prompt generation device 100 includes a reception unit 110 and a prompt generation unit 120. The reception unit 110 receives target facility information about a target facility and demographic information about a target user from a user terminal 300. In this embodiment, the target facility is a rental property. The target facility information includes information for identifying the rental property (e.g., a property ID).

[0021] The target user may be a tenant of a rental property or a purchaser of a rental property. In other words, the target user is a person to whom a rental property is recommended and to whom a recommendation sentence is provided. In this way, the prompt generation device 100 can generate recommendation sentences for tenants of rental properties and can generate recommendation sentences for purchasers of rental properties. The demographic information of the target user is information about the attributes of the target user, such as gender, age, marital status, income, and occupation.

[0022] The prompt generation unit 120 generates a prompt that instructs the user to generate a recommendation sentence for a rental property for the target user based on the target facility information and demographic information of the target user received by the reception unit 110. The prompt includes a task, which is the instruction content, and input information. The input information includes the target facility information and demographic information of the target user received by the reception unit 110.

[0023] The prompt generation unit 120 can include in the prompt an instruction to generate a recommendation sentence based on behavioral data of people around the rental property (e.g., residents or people visiting the area). The LLM 220 performs pre-learning based on basic data including behavioral data acquired by the data acquisition unit 210. Therefore, the LLM 220 can generate a recommendation sentence that takes into account the behavioral data of people around the rental property based on the prompt generated by the prompt generation unit 120.

[0024] The target user accepted by the accepting unit 110 may be a tenant of a rental property. In this case, the prompt generating unit 120 may include in the prompt an instruction to generate a recommendation sentence including information about the tenant's behavior if they were to live in the rental property. The information about the tenant's behavior may include information about recommended places or facilities around the target rental property, information about using public transportation, etc.

[0025] The target user accepted by the accepting unit 110 may be a purchaser of a rental property. In this case, the prompt generating unit 120 may include in the prompt an instruction to generate a recommendation sentence including information about the profits that the purchaser will make if they rent out the rental property. This information about the profits may include information about the likelihood that a tenant will live in the rental property for a long period of time, information about the management or maintainability of the rental property, information about the development potential of the area surrounding the rental property and the expected future asset value of the rental property, etc.

[0026] The prompt generation unit 120 transmits the generated prompt to the LLM 220 of the sentence generation device 200, and acquires a recommended sentence corresponding to the prompt from the LLM 220. The prompt generation unit 120 transmits the recommended sentence acquired from the LLM 220 to the user terminal 300. For example, the operator of the user terminal 300 can use the acquired recommended sentence in an advertisement for a rental property.

[0027] Below, a specific example of a prompt generated by the prompt generation unit 120 and an output of the sentence generation device 200 (LLM 220) will be described. First, two examples of generating recommendation sentences for tenants of rental properties will be described. In the first example of generating recommendation sentences for tenants, the target rental property (target property) is "property 1," and the tenant's (client's) demographic information (client information) is "male," "in his 20s," and "spouse: none." Furthermore, the rental property "property 1" is located a 10-minute walk from the nearest station and has a floor plan of 1LDK. Target facility information and tenant demographic information related to these rental properties are received by the reception unit 110. In other words, the recommendation sentences generated by this prompt are sentences that encourage tenants who are "male," "in their 20s," and "spouse: none" to move into the rental property "property 1." This recommendation text can be used as an advertisement to encourage tenants with this attribute to move into the rental property.

[0028] 5 , the prompt generation unit 120 generates a prompt including the following instructions as an example of a task: "Utilize knowledge obtained from the residents' gender, age, marital status, and behavioral history contained in the fine-tuning data to generate recommendation sentences for recommending target properties that match the following client information." "In addition, when generating recommendation sentences, analyze the general behavioral patterns of residents with a similar profile who live near the target property, and generate recommendation sentences that assume the lifestyle of this client if they were to live in property 1. Specifically, focus on the activity times, leisure activities, transportation usage tendencies, and behavior patterns within the area of ​​the neighboring residents." Note that the above "fine-tuning data" refers to the data used by the data acquisition unit 210 when fine-tuning the LLM 220, specifically, basic data.

[0029] The prompt generator 120 also includes, as input information, target facility information about the rental property received by the receiver 110 and demographic information about the resident in the prompt. "Target property: property1" "Client information: - Gender: Male - Age group: 30s - Spouse: None"

[0030] In this example prompt, the content of the task field corresponds to an instruction to generate a recommendation sentence for a target user (here, for a resident) regarding a target facility based on the target facility information and the target user's demographic information. The task field also includes the instruction "When generating a recommendation sentence, analyze the general behavioral patterns of residents with a similar profile who live in the vicinity of the target property, and generate a recommendation sentence that assumes the client's lifestyle if they were to live in property1. Specifically, focus on the activity times, leisure activities, transportation usage trends, and behavior patterns within the area of ​​nearby residents." This instruction corresponds to an instruction to generate a recommendation sentence that includes information about the behavior of a resident if they were to live in the rental property, based on the resident's demographic information, and an instruction to generate a recommendation sentence based on behavioral data of people around the rental property.

[0031] The prompt generator 120 transmits the generated prompt shown in Fig. 5 to the LLM 220. The LLM 220 generates a recommendation sentence that serves as an answer based on this prompt.

[0032] As an example, LLM220 generates the following recommendation sentence: "It's conveniently located 10 minutes from the station, and there's a convenience store within a one-minute walk. There are also a full range of amusement stores around ABC Station, so you're sure to have a fulfilling time."

[0033] Next, we will explain a second example of generating a recommendation sentence for a tenant. In this second example, the target rental property is "property1," the same as in the first example. Assume that the tenant's demographic information is "female," "in their 30s," and "has a spouse." In other words, the recommendation sentence generated by this prompt is a sentence that encourages tenants who are "female," "in their 30s," and "has a spouse" to move into the rental property "property1." This recommendation sentence can be used as advertising copy to encourage tenants with these attributes to move into the rental property.

[0034] In this case, as shown in Fig. 6, the prompt generation unit 120 generates a prompt including the same instruction content as in Fig. 5 as an example of a task. The prompt generation unit 120 also includes, in the prompt, the target facility information about the rental property received by the reception unit 110 and the demographic information of the resident as input information. "Target property: property1" "Client information: - Gender: female - Age group: 30s - Spouse: yes"

[0035] In this case, the LLM 220 generates the following recommendation sentence as an example: "It's conveniently located 10 minutes from the station. The living / dining room is spacious enough that you won't have any trouble spending relaxing time with your family. There are also supermarkets, convenience stores, and spacious parks nearby, allowing you to live a relaxed lifestyle."

[0036] Next, an example of generating a recommendation sentence for a purchaser of a rental property will be described. In this example, the target rental property (target property) is "property1," and the purchaser (owner)'s demographic information (owner information) is "male," "in his 20s," "spouse: none," "annual income: 10 million yen," and "number of properties currently in operation: 2." In other words, the recommendation sentence generated by this prompt is a sentence that encourages a purchaser with the following attributes to purchase the rental property "property1." This recommendation sentence can be used as advertising copy, etc., to encourage purchasers with these attributes to purchase the rental property.

[0037] In this case, as shown in FIG. 7 , the prompt generation unit 120 generates a prompt including the following instruction as an example of a task: "Based on the fine-tuning data, please generate a recommendation sentence for selecting a beneficial tenant for the owner of the following target property." "In addition, when generating the recommendation sentence, please take into consideration the general behavioral patterns of local residents derived from the resident data and the characteristics of the area around the property, and write down the factors that the owner should consider when selecting a tenant. Also, please refer to the points that the owner pays attention to, analyze whether this tenant will increase the value of the property and can be expected to generate stable profits over the long term, and reflect this in the recommendation sentence." Note that the "owner" above corresponds to the purchaser of the rental property.

[0038] Furthermore, the prompt generation unit 120 includes, as input information, target facility information about the rental property received by the reception unit 110, demographic information about the purchaser of the rental property, and points of interest to the owner in the prompt. For example, if the operator has content that the owner wants to reflect in the recommendation text as points of interest to the owner, the operator can input various points. Note that input of the points of interest to the owner is not required. Furthermore, if the points of interest to the owner are predetermined, these contents may be included in the task in advance.

[0039] "Target property: property1" "Owner information: - Gender: Male - Age group: 20s - Spouse: None - Annual income: 10 million yen - Number of properties currently under management: 2" "Points the owner is focusing on: - Stability of tenants and possibility of long-term residence - Property profitability and opportunity to increase value - Ease of management and maintenance - Potential for development within the area and prospects for future asset value"

[0040] In this example prompt, the content of the task column corresponds to an instruction to generate a recommendation sentence for a target user (here, a buyer) regarding a target facility based on the target facility information and the target user's demographic information. The task column states, "When generating a recommendation sentence, please consider the general behavioral patterns of local residents derived from resident data and the characteristics of the area around the property, and document the factors that the owner should consider when selecting a tenant." This corresponds to an instruction to generate a recommendation sentence based on behavioral data of people around the rental property. The task column states, "Please also consider the points the owner pays attention to, and analyze whether this tenant will increase the value of the property and can be expected to generate stable revenue over the long term, and reflect this in the recommendation sentence." This corresponds to an instruction to generate a recommendation sentence that includes information about the revenue generated by renting out the property.

[0041] Based on this prompt, LLM220 generates a recommendation sentence that serves as a response. As an example, LLM220 generates the following recommendation sentence: "This area tends to be home to many young, single people with high job stability. The average length of residence for this property is about five years, but there are few vacant periods, so stable rental management can be expected. In addition, as it is an area popular with young, single people, management and maintenance are also easy. The area is also partially undergoing redevelopment, so the property is expected to see an increase in asset value in the future. This property will be an ideal choice that matches the owner's management policy."

[0042] Next, the flow of the fine-tuning process of the LLM 220 performed in the sentence generation device 200 will be described. FIG. 8 is a flowchart showing the flow of the fine-tuning process. The process shown in FIG. 8 is repeatedly executed at a predetermined timing. As shown in FIG. 8, the data acquisition unit 210 acquires property information and updates the property information database (S101). The data acquisition unit 210 also acquires behavioral data and updates the behavioral data database (S102). The data acquisition unit 210 then fine-tunes the trained model of the LLM 220 (S103). This allows the LLM 220 to generate recommendation sentences using the updated basic data (property information and behavioral data) as the knowledge base.

[0043] Next, a description will be given of the processing flow of a method for generating recommendation sentences for a target user regarding a target facility, which is performed in the prompt generation device 100. Fig. 9 is a flowchart showing the processing flow of a method for generating recommendation sentences for a target user regarding a target facility, which is performed in the prompt generation device. As shown in Fig. 9, the reception unit 110 receives target facility information regarding the target facility (rental property) and demographic information of the target user (tenant or purchaser) from the user terminal 300 (S101: reception step).

[0044] The prompt generation unit 120 determines whether the target for generating a recommendation sentence for a rental property is a resident of the rental property (S202: target user determination step). For example, the target user information received by the reception unit 110 includes information for identifying whether the target user is a resident or a purchaser. Based on this information, the prompt generation unit 120 can determine whether the target for generating a recommendation sentence is a resident.

[0045] If the target for generating the recommendation text is a tenant (S202: YES), the prompt generation unit 120 generates a prompt that instructs the generation of a recommendation text for the tenant regarding the target rental property (S203: prompt generation step).Also, if the target for generating the recommendation text is not a tenant, that is, if the target for generating the recommendation text is a purchaser of the rental property (S202: NO), the prompt generation unit 120 generates a prompt that instructs the generation of a recommendation text for the purchaser of the target rental property (S207: prompt generation step).

[0046] After generating the prompt in S203 or S207, the prompt generation unit 120 transmits the generated prompt to the LLM 220 (S204: prompt transmission step). Based on this prompt, the LLM 220 generates a recommendation sentence. The LLM 220 transmits the generated recommendation sentence to the prompt generation device 100. The prompt generation unit 120 acquires a response to the transmitted prompt (recommendation sentence) from the LLM 220 (S205: recommendation sentence acquisition step). The prompt generation unit 120 transmits the acquired recommendation sentence to the user terminal 300 (S206: recommendation sentence transmission step). The user terminal 300 acquires the recommendation sentence from the prompt generation device 100 and displays the recommendation sentence on a display unit or the like. This allows the operator of the user terminal 300 to acquire a recommendation sentence for the target user regarding the target rental property.

[0047] As described above, the receiving unit 110 of the prompt generation device 100 receives target facility information related to a target rental property and demographic information of a target user (tenant or purchaser). Based on this information, the prompt generation unit 120 generates a prompt that instructs the generation of a recommendation sentence for the target user related to the target rental property. The LLM 220 generates a recommendation sentence based on this prompt. The prompt includes demographic information about the target user to whom the recommendation sentence is to be provided. This allows the LLM 220 to generate a recommendation sentence related to the target rental property and for the target user based on the target user's demographic information. Therefore, the prompt generation device 100 can provide a more specific image of the rental property that is tailored to the target user. In this way, the prompt generation device 100 can generate a recommendation sentence related to the target facility (rental property) with content tailored to the target user.

[0048] Because the prompt generation device 100 can generate recommendation sentences, recommendation sentences can be generated without manual intervention, even when there are a huge number of rental properties. Furthermore, when recommendation sentences are created by humans, the quality tends to vary depending on the creator. Therefore, by using the prompt generation device 100, recommendation sentences of roughly the same quality can be generated.

[0049] The prompt generation device 100 generates recommendation sentences for rental properties as target facilities. The prompt generation device 100 also generates recommendation sentences for tenants of rental properties as target users for whom recommendation sentences are generated. This allows the prompt generation device 100 to generate recommendation sentences that are suitable for tenants who are considering moving into the target rental properties.

[0050] The prompt generation unit 120 generates a prompt including an instruction to generate a recommendation sentence including information about the behavior of a resident if the resident were to live in the rental property, based on the resident's demographic information. This allows the prompt generation device 100 to generate information about the resident's behavior if the resident were to live in the target rental property. Therefore, the prompt generation device 100 can provide a more specific image of the rental property that is suited to the target resident.

[0051] The prompt generation device 100 generates recommendation sentences for purchasers of rental properties as target users for which recommendation sentences are to be generated. This allows the prompt generation device 100 to generate recommendation sentences that are suited to purchasers who are considering purchasing the target rental property.

[0052] The prompt generation unit 120 generates a prompt including an instruction to generate a recommendation sentence including information about the profits that may be made by renting out a rental property. This allows the prompt generation device 100 to generate a recommendation sentence including information about the profits that may be of interest to a purchaser of a rental property. Therefore, the prompt generation device 100 can provide a purchaser with a concrete idea of ​​the profits that may be made by purchasing the rental property.

[0053] The prompt generation unit 120 generates a prompt including an instruction to generate a recommendation sentence based on behavioral data of people around the rental property. This allows the prompt generation device 100 to generate a recommendation sentence that takes into account the actual movements of people in the area where the target rental property is located. Therefore, the prompt generation device 100 can provide a more specific image of the rental property that takes into account the movements of people in the area where the rental property is located.

[0054] The prompt generation unit 120 generates a prompt including an instruction to generate a recommendation sentence. The prompt generation unit 120 transmits the generated prompt to the LLM 220 and obtains an answer (recommended sentence) generated by the LLM 220. This allows the prompt generation unit 120 to generate a recommendation sentence using the LLM 220.

[0055] The method for generating recommendation sentences performed by the prompt generation device 100 includes a receiving step of receiving target facility information about a target facility and demographic information about a target user, and a prompt generation step of generating a prompt that instructs the generation of a recommendation sentence about the target facility for the target user based on the target facility information and the demographic information of the target user. In this way, this method can generate recommendation sentences about the target facility (rental property) that have content suitable for the target user.

[0056] The above description is an example of the present disclosure and is not limited to these descriptions. For example, the prompt generation device 100 generated a recommendation sentence regarding a rental property as the target facility. The target facility for which the recommendation sentence is generated is not limited to a rental property. For example, the prompt generation device 100 can also generate a recommendation sentence regarding a tourist facility, a train station, or other facility as the target facility. The prompts and their answers described above are provided for illustrative purposes and are not limited to these examples. The instructions included in the prompt may be changed as appropriate.

[0057] The device and method of the present disclosure have the following configuration.

[0058] [1] A device comprising: a receiving unit that receives target facility information about a target facility and demographic information of a target user; and a prompt generating unit that generates a prompt that instructs the generation of a recommendation sentence about the target facility for the target user based on the target facility information and the demographic information of the target user. [2] The device described in [1] above, wherein the target facility is a rental property. [3] The device described in [2] above, wherein the target user is a tenant of the rental property. [4] The device described in [3] above, wherein the prompt includes an instruction to generate the recommendation sentence including information about the tenant's behavior if the tenant lived in the rental property, based on the tenant's demographic information. [5] The device described in [2] above, wherein the target user is a purchaser of the rental property. [6] The device described in [5] above, wherein the prompt includes an instruction to generate the recommendation sentence including information about the profits if the rental property is rented out. [7] The device according to any one of [1] to [6] above, wherein the prompt includes an instruction to generate the recommendation sentence based on behavioral data of people around the target facility. [8] The device according to any one of [1] to [7] above, wherein the prompt generation unit transmits the prompt to a generative AI model and obtains an answer corresponding to the prompt from the generative AI model. [9] A method including: a receiving step of receiving target facility information about a target facility and demographic information of a target user; and a prompt generation step of generating a prompt that instructs generation of a recommendation sentence about the target facility for the target user based on the target facility information and the demographic information of the target user.

[0059] 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.

[0060] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0061] For example, the prompt generation device 100 according to an embodiment of the present disclosure may function as a computer that performs processing for a method of generating recommendation sentences for a target user regarding a target facility according to the present disclosure. Fig. 10 is a diagram illustrating an example of the hardware configuration of the prompt generation device 100 according to an embodiment of the present disclosure. The prompt generation device 100 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage device 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0062] In the following description, the term "device" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the prompt generation device 100 may be configured to include one or more of the devices shown in the figures, or may be configured to exclude some of the devices.

[0063] Each function in the prompt generating device 100 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0064] 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 unit, an arithmetic unit, a register, etc. For example, the above-mentioned reception unit 110 and prompt generation unit 120 may be realized by the processor 1001.

[0065] The processor 1001 also loads 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 programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, the reception unit 110 and the prompt generation unit 120 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.

[0066] 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 ROM (EPROM), an electrically erasable programmable ROM (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 may store executable programs (program codes), software modules, etc. for implementing a prompt generation method according to one embodiment of the present disclosure.

[0067] 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.

[0068] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module. 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). The communication device 1004 may be implemented with a transmitter and a receiver that are physically or logically separated.

[0069] 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).

[0070] 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.

[0071] Furthermore, the prompt generation device 100 may 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. 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 using 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, such as an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0072] 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.

[0073] 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.

[0074] 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).

[0075] 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).

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0082] 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.

[0083] In this disclosure, the terms "Mobile Station (MS)," "user terminal," "User Equipment (UE)," "terminal," and the like may be used interchangeably.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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."

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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."

[0092] 100...prompt generation device (device), 110...reception unit, 120...prompt generation unit, 220...LLM (generation AI model).

Claims

1. A device comprising: a reception unit that receives target facility information regarding a target facility and demographic information of a target user; and a prompt generation unit that generates a prompt that instructs the generation of a recommendation sentence regarding the target facility for the target user based on the target facility information and the demographic information of the target user.

2. The apparatus of claim 1, wherein the target facility is a rental property.

3. The apparatus of claim 2, wherein the target users are tenants of the rental property.

4. The device of claim 3, wherein the prompt includes instructions to generate the recommendation sentence based on the demographic information of the tenant, the recommendation sentence including information about the tenant's behavior if the tenant lived in the rental property.

5. The apparatus of claim 2, wherein the target user is a purchaser of the rental property.

6. The device of claim 5, wherein the prompt includes instructions to generate the recommendation text including information about the revenue potential of renting out the rental property.

7. The device of claim 1, wherein the prompt includes instructions to generate the recommendation sentence based on behavioral data of people around the target facility.

8. The device of claim 1, wherein the prompt generator transmits the prompt to a generative AI model and obtains an answer corresponding to the prompt from the generative AI model.

9. A method including: a reception step of receiving target facility information regarding a target facility and demographic information of a target user; and a prompt generation step of generating a prompt that instructs the generation of a recommendation sentence regarding the target facility for the target user based on the target facility information and the demographic information of the target user.

Images