Information processing device and information processing method

Abstract

This information processing device is provided with: a search unit that searches information resources on the basis of a promotion target word relating to a promotion target to obtain related information related to the promotion target word; an extraction unit that, on the basis of user attribute information associated with a user to whom a promotion is to be provided, extracts user-related information, which is information specific to the user and relating to the promotion target, from the related information; and a generation unit that generates an individual promotion sentence specific to the user by entering input information including at least a basic promotion sentence for promotion and the user-related information into a large language model.

Description

Information processing device and information processing method

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

[0002] Conventionally, there has been known a technique for distributing promotional messages to users to promote sales of products, etc. (See, for example, Patent Document 1.) By transmitting promotional messages to users via such a technique, member stores of electronic payment services can increase sales and the number of customers.

[0003] Japanese Patent Application Laid-Open No. 2017-227953

[0004] By providing promotional text specific to each user based on their attributes, etc., instead of using a uniform promotional text, it is expected that the conversion rate will increase as users purchase products, etc. However, creating different promotional texts for each user is costly in terms of money and time.

[0005] Therefore, an object of the present disclosure is to enable more effective appeal to promotion targets by providing users with promotional text tailored to individual users.

[0006] In order to solve the above problem, an information processing device according to one aspect of the present disclosure includes a search unit that acquires related information related to a promotion target word by searching information resources based on a promotion target word related to the target of the promotion, an extraction unit that extracts user-related information, which is information specific to a user related to the target of the promotion, from the related information based on user attribute information associated with the user to whom the promotion is provided, and a generation unit that generates an individual promotion sentence specific to the user by inputting input information including at least a basic promotion sentence for the promotion and the user-related information into a large-scale language model.

[0007] According to the above aspect, user-related information is extracted from related information related to a promotion target based on user attribute information, and input information including a basic promotion statement and the user-related information is input to a large-scale language model, whereby the large-scale language model outputs a promotion statement specific to the user that reflects the content of the user-related information. By providing the promotion statement thus output to the user, it is possible to effectively appeal to each individual user about the promotion target.

[0008] By providing promotional text tailored to each individual user, it becomes possible to more effectively appeal to the promotion target.

[0009] 1 is a block diagram showing the functional configuration of an information processing device of this embodiment. FIG. 1 is a diagram showing the configuration of a basic promotion statement storage unit and examples of stored basic promotion statements. FIG. 2 is a diagram showing an example of an acquisition process for acquiring promotion target words from basic promotion statements. FIG. 3 is a diagram showing an example of a search process for searching external information resources based on promotion target words to acquire related information. FIG. 4 is a diagram showing the configuration of a user attribute storage unit and examples of stored attribute information. FIG. 5 is a diagram showing an example of an extraction process for extracting user-related information from related information. FIG. 6 is a diagram showing an example of an extraction process for extracting user-related information from related information. FIG. 7 is a diagram showing an example of a generation process for generating individual promotion statements by inputting input information into a large-scale language model. FIG. 8 is a diagram showing an example of a prompt, which is one aspect of input information. FIG. 9 is a flowchart showing the processing contents of an information processing method in an information processing system. FIG. 10 is a diagram showing the configuration of an information processing program. FIG. 11 is a hardware block diagram of an information processing device.

[0010] An information processing device according to an embodiment of the present invention will be described with reference to the drawings. Whenever possible, the same components are designated by the same reference numerals, and redundant description will be omitted.

[0011] 1 is a block diagram showing the device configuration of an information processing system including an information processing device according to this embodiment and the functional configuration of the information processing device. The information processing system 1 is a system that provides users with promotional text related to promotional targets such as products and services.

[0012] As shown in Fig. 1, the information processing system 1 includes an information processing device 10 and a user terminal T. The terminal T is configured to be accessible to the information processing device 10 via a network N. The devices constituting the terminal T are not limited, and may be, for example, a mobile terminal such as a highly functional mobile phone (smartphone), a mobile phone, or a personal digital assistant (PDA), or may also be a computer terminal. Note that, although Fig. 1 shows two terminals T as an example, the number of terminals T is not limited to this example.

[0013] The information processing device 10 is a device that provides users with promotional text tailored to each individual user, and functionally includes a target word acquisition unit 11, a search unit 12, an extraction unit 13, a generation unit 14, and a provision unit 15. The generation unit 14 includes a large-scale language model md. In the example shown in FIG. 1, the functional units 11 to 15 are configured in a single information processing device 10, but they may also be configured in a distributed manner across multiple devices. Furthermore, one or more of the functional units 11 to 15 may be configured in a terminal T. Furthermore, the large-scale language model md may be configured in another device accessible from the information processing device 10.

[0014] Each functional unit of the information processing device 10 is configured to be able to access storage means (storage) such as a basic promotion statement storage unit 21 and a user attribute storage unit 22. The basic promotion statement storage unit 21 is a storage unit that stores basic promotion statements. The user attribute storage unit 22 is a storage unit that stores user attribute information. In the example shown in FIG. 1 , the basic promotion statement storage unit 21 and the user attribute storage unit 22 are configured in the information processing device 10, but they may also be configured in other devices accessible from the information processing device 10.

[0015] Next, a description will be given of each functional unit of the information processing device 10. The target word acquisition unit 11 acquires named entities included in the basic promotion sentence as promotion target words.

[0016] The basic promotional text is a text for promoting a product or the like, and is a text for promotion common to all users, not specialized for each user to whom the text is to be distributed. The promotion target word is a word related to the target of the promotion. The promotion target word may be a word that represents the target of the promotion. Note that the target word acquisition unit 11 is not an essential component of the information processing device 10 of this embodiment.

[0017] 2 is a diagram showing the configuration of the basic promotional statement storage unit 21 and examples of basic promotional statements stored therein. As illustrated in FIG. 2, the basic promotional statement storage unit 21 stores a basic promotional statement for each ID that identifies each basic promotional statement, and stores, for example, a basic promotional statement such as, "Download the AAA app from the AAA store and link your new point card to receive a free coupon for a selected AAA cafe drink."

[0018] FIG. 3 is a diagram showing an example of an acquisition process for acquiring promotion target words from a basic promotion sentence.

[0019] The target word acquisition unit 11 extracts named entities from the basic promotion sentence bm and acquires the extracted named entities as promotion target words pw. The target word acquisition unit 11 may extract named entities from the basic promotion sentence bm using a known named entity extraction technique. In the example shown in Figure 3, the target word acquisition unit 11 extracts named entities such as "AAA store," "AAA app," "point card," "AAA cafe drink," and "free exchange ticket" from the basic promotion sentence bm as promotion target words pw.

[0020] In this way, by acquiring the words contained in the basic promotion sentence bm as the promotion target words pw, it is possible to acquire words and the like that are highly likely to represent the target of the promotion as the promotion target words.

[0021] The search unit 12 searches predetermined information resources based on the promotion target words to acquire information related to the promotion target words. The search unit 12 may search for information resources based on the promotion target words pw acquired by the target word acquisition unit 11. Alternatively, the search unit 12 may manually search for information resources based on the promotion target words pw that have been set in advance.

[0022] The information resource may be, for example, an information resource accessible via the Internet, such as a website, a social media log, a search result from a predetermined search engine, etc. The related information may be, for example, sentences and phrases related to the target of the promotion.

[0023] 4 is a diagram schematically illustrating an example of a search process for searching external information resources based on promotion target words to acquire related information. In the example shown in FIG. 4, the search unit 12 searches external information resources based on promotion target words pw ("AAA Store," "AAA App," "Point Card," "AAA Cafe Drink," and "Free Coupon") to acquire related information ri, which is a sentence, phrase, or the like containing the promotion target word pw: "The AAA App is an app for the AAA Store convenience store chain, and offers features such as no waiting in line at the register, coupon and coupon acquisition, point card points accumulation, and point rewards through games and campaigns. The AAA Cafe Drink is a lineup of drinks offered at the AAA Store's in-store cafe, "AAA Cafe," and offers a menu including smoothies made with fresh bananas, coffee and cafe lattes made on the spot using specially ground beans."

[0024] The search unit 12 may acquire related information by inputting information to large language models (LLMs) to instruct them to generate sentences that explain the outline, characteristics, etc. of the promotion target word pw. The search unit 12 may cause the large language models to generate related information via a LanguageChain. The LanguageChain is a library for using large language models and may constitute an interface for using large language models.

[0025] Specifically, the search unit 12 may obtain related information ri by inputting a prompt, which is information instructing the generation of a sentence explaining the overview and characteristics of the promotion target word pw (for example, "Please summarize the overview and characteristics of the AAA store, the AAA app, and the AAA cafe drink in about 100 characters each."), into a large-scale language model via the Language Chain.

[0026] The extraction unit 13 extracts user-related information, which is information on the target of a promotion specific to a user, from the related information based on user attribute information associated with the user to whom the promotion is provided. The user-related information may be a sentence or phrase including at least a part of the related information.

[0027] 5 is a diagram showing the configuration of the user attribute storage unit 22 that stores user attribute information and an example of the stored attribute information. As shown in Fig. 5, the user attribute storage unit 22 stores attribute information such as gender, age, interests, hobbies, etc. in association with a user ID that identifies a user.

[0028] The extraction unit 13 can extract user-related information by various methods using the user attribute information. Figures 6 to 8 are diagrams showing examples of extraction processing for extracting user-related information from related information.

[0029] Specifically, the extraction unit 13 may extract user-related information by searching for related information based on keywords included in the user attribute information. As shown in FIG. 6 , the extraction unit 13 searches for related information ri based on the keyword kw11 "game" included in the user attribute information ua1 of user U01, and extracts a sentence / phrase containing the keyword kw12 "game," such as "It has features such as earning points with a point card and earning points through game campaigns," as user-related information ui1 specific to user U01. By searching based on keywords included in the user attribute information in this way, related information that is likely to interest the user can be easily obtained as user-related information.

[0030] The extraction unit 13 may also extract user-related information by searching for related information based on related keywords related to keywords included in the user attribute information. As shown in Fig. 7 , the extraction unit 13 acquires related words rw (cafe, coffee, coffee shop) based on the keyword kw21 "coffee shop hopping" included in the user attribute information ua2 of user U02. The acquisition of related words may be achieved by any method, such as referencing a dictionary that pre-stores related words or using a large-scale language model.

[0031] The extraction unit 13 searches for related information ri based on one keyword kw22 "coffee" among the related words rw, and extracts a sentence / phrase containing the keyword kw23 "coffee," such as "We offer a variety of menu items, including smoothies made with fresh bananas and coffee and cafe lattes made on the spot using specially ground beans," as user-related information ui2 specific to user U02. In this way, by searching based on words related to keywords included in the user attribute information, related information that may interest the user can be more comprehensively acquired as user-related information.

[0032] The extraction unit 13 may also extract user-related information based on the similarity of related information to a sentence constructed using at least a portion of the user attribute information. Specifically, as shown in FIG. 8 , the extraction unit 13 converts at least a portion of the content of the user attribute information ua3 into a sentence. For example, the extraction unit 13 constructs the sentence us "I am a woman over 60 years old" based on the gender "female" and age "over 60 years old" in the user attribute information ua3. The extraction unit 13 also constructs the sentences us "I am interested in food and ingredients" and "My hobbies are reading and magazines" based on the interests and hobbies in the user attribute information ua3. The method for constructing these sentences may be any known method, but may also be, for example, a method of applying the content of the attribute information to a preset sentence template.

[0033] Next, the extraction unit 13 encodes the constructed sentence us into a vector representation. The extraction unit 13 then calculates the similarity between each sentence and each phrase included in the related information ri, which has also been encoded into a vector representation, and the vector representation of the sentence us. The extraction unit 13 extracts a sentence or phrase rf whose similarity is equal to or greater than a predetermined threshold as user-related information ui3, such as "We offer a variety of menu items, including smoothies made with fresh bananas and coffee and cafe lattes made on-site using carefully ground beans." This allows related information that is likely to attract the user's interest in terms of meaning and content to be extracted as user-related information.

[0034] The extraction unit 13 may selectively extract the user-related information shown in each of Figures 6 to 8, or may extract the user-related information in stages. That is, the extraction unit 13 may, for example, attempt to extract user-related information using the method shown in Figure 6, and if suitable user-related information cannot be extracted, may attempt to extract user-related information using the method shown in Figure 7. Furthermore, the extraction unit may attempt to extract user-related information using the method shown in Figure 7, and if suitable user-related information cannot be extracted, may attempt to extract user-related information using the method shown in Figure 8.

[0035] 1, the generator 14 generates individual promotion sentences specific to a user by inputting input information including at least a basic promotion sentence and user-related information into the large-scale language model, where the input information constitutes a so-called prompt for instructing the large-scale language model.

[0036] 9 is a diagram illustrating an example of a generation process for generating individual promotional statements by inputting input information into a large-scale language model. As shown in FIG. 9, the generation unit 14 inputs input information PT into a large-scale language model md (LLM). In the example shown in FIG. 9, the input information PT includes a basic promotional statement pt1, user attribute information pt2, and user-related information. The user attribute information pt2 includes at least a portion of the user attribute information of the n users to whom the promotional statement is to be provided.

[0037] The generation unit 14 inputs the input information PT as a prompt into the large-scale language model md, and thereby obtains the individual promotional text um output from the large-scale language model md: "A must-see for young people! Download the AAA app and link it to your new point card to receive a free AAA Cafe drink coupon! Enjoy a special drink in between watching anime or a movie! There are also games that allow you to accumulate points, so it's perfect for game lovers. Check out the app now!"

[0038] The generation unit 14 may input the input information PT as a prompt to the large-scale language model md via LangChain. LangChain is a library for using a large-scale language model and can configure an interface for using a large-scale language model, so that by using LangChain, a suitable prompt can be configured based on the input information PT.

[0039] 10 is a diagram showing an example of a prompt constructed based on input information PT. As shown in FIG. 10, the constructed prompt includes an instruction statement pt0 for generating an individual promotion statement um, followed by user-related information pt3 obtained by extraction unit 13, a basic promotion statement pt1 that is common to all users and not specialized for each user, and user attribute information pt2 of the users to whom the promotion statement is to be provided.

[0040] 1 , the providing unit 15 provides the individual promotional text um generated by the generating unit 14 to the target user. Specifically, the providing unit 15 transmits the individual promotional text um to, for example, the user's terminal T.

[0041] In addition, when the large-scale language model md is configured in another device accessible from the information processing device 10, the information processing device 10 may have, as a minimum configuration, a reception unit (search unit 12) that receives promotion request information including promotion target words related to the target of the promotion, an acquisition unit (search unit 12, extraction unit 13) that acquires related information related to the promotion target words and user attribute information associated with the user to whom the promotion is provided based on the promotion request information, an extraction unit (extraction unit 13) that extracts user-related information, which is information specific to the user related to the target of the promotion, from the related information based on the user attribute information, and an output unit (generation unit 14) that outputs input information including at least a basic promotion sentence for the promotion and the user-related information to the large-scale language model.

[0042] In this case, the search unit 12 as a reception unit receives promotion request information including a promotion target word. The promotion request information is, for example, information input to the information processing device 10 to request the generation of a promotion statement.

[0043] Next, the search unit 12 acquires related information related to the promotion target word, for example, by searching a predetermined information resource based on the promotion request information. Furthermore, the extraction unit 13 acquires user attribute information associated with the user to whom the promotion is to be provided, based on the promotion request information. Information indicating the user to whom the promotion is to be provided may be included in the promotion request information. The extraction unit 13 acquires user attribute information associated with the user, for example, by referring to the user attribute storage unit 22, based on the information indicating the user.

[0044] Furthermore, the extraction unit 13 extracts user-related information, which is information specific to the user and related to the promotion target, from the related information based on the user attribute information. Then, the generation unit 14 outputs input information (prompt) including at least a basic promotion sentence for the promotion and the user-related information to the large-scale language model md.

[0045] By having a minimum configuration of a reception unit (search unit 12), an acquisition unit (search unit 12, extraction unit 13), an extraction unit (extraction unit 13), and an output unit (generation unit 14), the information processing device 10 can obtain, as input information, a prompt for generating an individual promotional text specific to the user in a large-scale language model md configured in another device accessible from the information processing device 10.

[0046] FIG. 11 is a flowchart showing the processing steps of an information processing method for providing individual promotional messages to users in the information processing device 10.

[0047] In step S1, the target word acquisition unit 11 extracts named entities from the basic promotion sentence bm, and acquires the extracted named entities as promotion target words pw.

[0048] In step S2, the search unit 12 searches predetermined information resources based on the promotion target word pw to obtain related information ri related to the promotion target word pw.

[0049] In step S3, the extraction unit 13 extracts user-related information specific to the user and related to the target of the promotion from the related information ri, based on user attribute information associated with the user to whom the promotion is provided.

[0050] In step S4, the generation unit 14 inputs input information PT including at least a basic promotion sentence and user-related information into the large-scale language model md. Then, in step S5, the generation unit 14 acquires an individual promotion sentence um specific to the user output by the large-scale language model md.

[0051] In step S6, the providing unit 15 provides the individual promotional text um generated by the generating unit 14 to the target users.

[0052] Next, an information processing program for causing a computer to function as the information processing device 10 of this embodiment will be described with reference to Fig. 12. Fig. 12 is a diagram showing the configuration of the information processing program. The information processing program P1 is configured to include a main module m10 that controls information processing in the information processing device 10 in an overall manner, a target word acquisition module m11, a search module m12, an extraction module m13, a generation module m14, and a provision module m15. Each of the modules m11 to m15 realizes a function for each of the functional units 11 to 15.

[0053] The information processing program P1 may be transmitted via a transmission medium such as a communication line, or may be stored in a recording medium M1 as shown in FIG.

[0054] According to the information processing system 1, information processing device 10, information processing method, and information processing program P1 of the present embodiment described above, user-related information is extracted from related information relating to a promotion target based on user attribute information, and input information including a basic promotion statement and the user-related information is input to a large-scale language model, which then outputs a promotion statement specific to the user that reflects the content of the user-related information. By providing the promotion statement output in this manner to users, it is possible to effectively appeal to each individual user about the promotion target.

[0055] The information processing device and information processing method according to the present disclosure may have the following configurations: The actions and effects of each configuration will be described as follows.

[0056] An information processing device according to one aspect of the present disclosure includes a search unit that acquires related information related to a promotion target word by searching information resources based on a promotion target word related to the target of the promotion; an extraction unit that extracts user-related information, which is information specific to a user related to the target of the promotion, from the related information based on user attribute information associated with the user to whom the promotion is provided; and a generation unit that generates an individual promotion sentence specific to the user by inputting input information including at least a basic promotion sentence for the promotion and the user-related information into a large-scale language model.

[0057] An information processing method according to one aspect of the present disclosure includes a search step executed by a processor, which searches information resources based on a promotion target word related to the target of the promotion to obtain related information related to the promotion target word; an extraction step extracting user-related information, which is information specific to a user related to the target of the promotion, from the related information based on user attribute information associated with the user to whom the promotion is provided; and a generation step generating an individual promotion sentence specific to the user by inputting input information including at least a basic promotion sentence for the promotion and the user-related information into a large-scale language model.

[0058] According to the above aspect, user-related information is extracted from related information related to a promotion target based on user attribute information, and input information including a basic promotion statement and the user-related information is input to a large-scale language model, whereby the large-scale language model outputs a promotion statement specific to the user that reflects the content of the user-related information. By providing the promotion statement thus output to the user, it is possible to effectively appeal to each individual user about the promotion target.

[0059] In addition, in an information processing device according to another aspect, the promotion target word may be a word or phrase included in a basic promotion sentence.

[0060] According to the above aspect, it is possible to acquire sentences, phrases, etc. related to the promotion target as related information.

[0061] In addition, an information processing device relating to another aspect may further include a target word acquisition unit that acquires named entities included in the basic promotion sentence as promotion target words, and the search unit may search for information resources based on the promotion target words extracted by the target word acquisition unit.

[0062] According to the above aspect, it is possible to acquire, as promotion target words, words and the like that are highly likely to represent the target of promotion.

[0063] In addition, in an information processing device according to another aspect, the extraction unit may extract the user-related information by searching for related information based on a keyword included in the user attribute information.

[0064] According to the above aspect, related information that is likely to attract the user's interest can be easily acquired as user-related information.

[0065] In addition, in an information processing device according to another aspect, the extraction unit may extract user-related information by searching for related information based on related keywords related to keywords included in the user attribute information.

[0066] According to the above aspect, related information that may interest a user can be more comprehensively acquired as user-related information by searching based on related keywords.

[0067] In addition, in an information processing device according to another aspect, the extraction unit may extract user-related information based on a similarity of the related information to a sentence constructed using at least a portion of the user attribute information.

[0068] According to the above aspect, related information that is highly likely to attract the user's interest in terms of meaning and content can be extracted as user-related information.

[0069] In addition, in an information processing device according to another aspect, the generation unit may input input information including at least a portion of the user attribute information, a promotional statement, and user-related information to a large-scale language model.

[0070] According to the above aspect, input information including user attribute information is input to a large-scale language model, making it possible to generate an individual promotional message that is more appealing to the user.

[0071] In addition, an information processing device according to one aspect of the present disclosure includes a reception unit that receives promotion request information including a promotion target word related to a target of promotion; an acquisition unit that acquires related information related to the promotion target word and user attribute information associated with a user to whom the promotion is provided based on the promotion request information; an extraction unit that extracts user-related information, which is information specific to a user related to the target of promotion, from the related information based on the user attribute information; and an output unit that outputs input information including at least a basic promotion sentence for the promotion and the user-related information to a large-scale language model.

[0072] According to the above aspect, a prompt for generating an individual promotional text specific to a user in a large-scale language model configured in another device accessible from an information processing device can be obtained as input information.

[0073] The block diagram shown in FIG. 1 shows functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0074] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0075] For example, the information processing device 10 according to an embodiment of the present invention may function as a computer. Fig. 13 is a diagram showing an example of the hardware configuration of the information processing device 10 according to this embodiment. The information processing device 10 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.

[0076] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in Fig. 13, or may be configured to exclude some of the apparatuses.

[0077] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations and control communication via the communication device 1004 and the reading and / or writing of data in the memory 1002 and storage 1003.

[0078] The processor 1001 controls the entire computer by running, for example, an operating system. 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 functional units 11 to 15 shown in FIG. 1 may be realized by the processor 1001.

[0079] The processor 1001 also reads programs (program codes), software modules, and data from the storage 1003 and / or the communication device 1004 into the memory 1002 and executes various processes in accordance with these. 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 functional units 11 to 15 of the information processing device 10 may be implemented by a control program stored in the memory 1002 and running on the processor 1001. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented on one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0080] The memory 1002 is a computer-readable recording medium and may be composed of at least one of, for example, a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), and a random access memory (RAM). The memory 1002 may also be called a register, a cache, a main memory (primary storage device), or the like. The memory 1002 can store executable programs (program codes), software modules, and the like for implementing an information processing method according to one embodiment of the present invention.

[0081] Storage 1003 is a computer-readable recording medium, and may be, for example, at least one of 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 memory 1002 and / or storage 1003.

[0082] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via a wired and / or wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0083] 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. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0084] Furthermore, each device such as the processor 1001 and the memory 1002 is connected to a bus 1007 for communicating information. The bus 1007 may be configured as a single bus, or may be configured as different buses between the devices.

[0085] The information processing device 10 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 by at least one of these pieces of hardware.

[0086] 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.

[0087] Each aspect / embodiment described in the present disclosure may be applied to at least one of systems using LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (New Radio), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, UWB (Ultra-Wide Band), Bluetooth (registered trademark), or other suitable systems, and next-generation systems enhanced based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A with 5G, etc.) may also be applied.

[0088] 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.

[0089] In the present disclosure, a specific operation described as being performed by a base station may be performed by its upper node in some cases. In a network consisting of one or more network nodes having a base station, it is clear that various operations performed for communication with a terminal may be performed by at least one of the base station and another network node other than the base station (for example, an MME or an S-GW, etc., but are not limited to these). Although the above example illustrates a case where there is one other network node other than the base station, a combination of multiple other network nodes (for example, an MME and an S-GW) may also be used.

[0090] Information etc. may be output from a higher layer (or a lower layer) to a lower layer (or a higher layer), or may be input / output via multiple network nodes.

[0091] Input and output information may be stored in a specific location (for example, memory) or managed in 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.

[0092] 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).

[0093] 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).

[0094] 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.

[0095] 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.

[0096] Software, instructions, etc. may also be transmitted or received over a transmission medium. For example, if the software is transmitted from a website, server, or other remote source using wired technologies such as coaxial cable, fiber optic cable, twisted pair, and Digital Subscriber Line (DSL), and / or wireless technologies such as infrared, radio, and microwave, these wired and / or wireless technologies are included within the definition of transmission media.

[0097] 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.

[0098] It should be noted that terms explained in this disclosure and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

[0099] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0100] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed as absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0101] 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.

[0102] 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.

[0103] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0104] When designations such as "first," "second," etc. are used in this disclosure, any reference to an element does not generally limit the quantity or order of those elements. These designations may be used herein 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 therein or that the first element must precede the second element in some way.

[0105] The "means" in the configuration of each of the above devices may be replaced with "part," "circuit," "device," etc.

[0106] To the extent that the terms "include," "including," and variations thereof are used herein or in the claims, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used herein or in the claims, is not intended to be an exclusive or.

[0107] 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.

[0108] 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."

[0109] The information processing device 10 and the information processing method of the present disclosure may have the following configuration.

[0110] [1] An information processing device comprising: a search unit that acquires related information related to a promotion target word by searching information resources based on a promotion target word related to a target of the promotion; an extraction unit that extracts user-related information, which is information specific to a user related to the target of the promotion, from related information based on user attribute information associated with the user to whom the promotion is provided; and a generation unit that generates an individual promotion statement specific to the user by inputting input information including at least a basic promotion statement for the promotion and the user-related information into a large-scale language model. [2] The information processing device according to [1], wherein the promotion target word is a phrase included in the basic promotion statement. [3] The information processing device according to [2], further comprising a target word acquisition unit that acquires named entities included in the basic promotion statement as promotion target words, wherein the search unit searches for information resources based on the promotion target words extracted by the target word acquisition unit. [4] The information processing device according to any one of [1] to [3], wherein the extraction unit extracts user-related information by searching related information based on keywords included in the user attribute information. [5] The information processing device according to any one of [1] to [4], wherein the extraction unit extracts user-related information by searching for related information based on related keywords related to keywords included in the user attribute information. [6] The information processing device according to any one of [1] to [5], wherein the extraction unit extracts user-related information based on a similarity of the related information to a sentence constructed using at least a portion of the user attribute information. [7] The information processing device according to any one of [1] to [6], wherein the generation unit inputs input information including at least a portion of the user attribute information, a promotional statement, and the user-related information to a large-scale language model.[8] An information processing device comprising: a receiving unit that receives promotion request information including a promotion target word related to a target of a promotion, an acquiring unit that acquires related information related to the promotion target word and user attribute information associated with a user to whom the promotion is to be provided based on the promotion request information, an extracting unit that extracts user-related information that is information specific to the user related to the target of the promotion from the related information based on the user attribute information, and an output unit that outputs input information including at least a basic promotion statement for the promotion and the user-related information to a large-scale language model. [9] An information processing method executed by a processor, comprising: a searching step that acquires related information related to the promotion target word by searching information resources based on a promotion target word related to the target of the promotion, an extracting step that extracts user-related information that is information specific to the user related to the target of the promotion from the related information based on user attribute information associated with the user to whom the promotion is to be provided, and a generating step that generates an individual promotion statement specific to the user by inputting input information including at least the basic promotion statement for the promotion and the user-related information to a large-scale language model.

[0111] 1...information processing system, 10...information processing device, 11...target word acquisition unit, 12...search unit, 13...extraction unit, 14...generation unit, 15...provision unit, 21...basic promotion sentence memory unit, 22...user attribute memory unit, M1...recording medium, m11...target word acquisition module, m12...search module, m13...extraction module, m14...generation module, m15...provision module, md...large-scale language model, P1...information processing program, T...terminal.

[0112]

Claims

1. An information processing device comprising: a search unit that searches information resources based on promotion target words related to the target of the promotion to obtain related information related to the promotion target words; an extraction unit that extracts user-related information, which is information specific to the user related to the target of the promotion, from the related information based on user attribute information associated with the user to whom the promotion is provided; and a generation unit that generates individual promotion sentences specific to the user by inputting input information including at least a basic promotion sentence for the promotion and the user-related information into a large-scale language model.

2. The information processing device according to claim 1, wherein the promotion target word is a phrase included in the basic promotion sentence.

3. An information processing device as described in claim 2, further comprising a target word acquisition unit that acquires named entities included in the basic promotion sentence as the promotion target words, and wherein the search unit searches for the information resources based on the promotion target words extracted by the target word acquisition unit.

4. The information processing device according to claim 1, wherein the extraction unit extracts the user-related information by searching the related information based on keywords included in the user attribute information.

5. The information processing device according to claim 1, wherein the extraction unit extracts the user-related information by searching for the related information based on related keywords related to keywords included in the user attribute information.

6. The information processing device according to claim 1, wherein the extraction unit extracts the user related information based on a similarity of the related information to a sentence constructed using at least a part of the user attribute information.

7. The information processing device according to claim 1, wherein the generation unit inputs the input information, including at least a portion of the user attribute information, the promotional text, and the user-related information, into the large-scale language model.

8. An information processing device comprising: a reception unit that receives promotion request information including promotion target words related to a promotion target; an acquisition unit that acquires related information related to the promotion target words and user attribute information associated with a user to whom the promotion is to be provided based on the promotion request information; an extraction unit that extracts user-related information, which is information specific to the user related to the promotion target, from the related information based on the user attribute information; and an output unit that outputs input information including at least a basic promotion sentence for the promotion and the user-related information to a large-scale language model.

9. An information processing method executed by a processor, comprising: a search step of searching information resources based on a promotion target word related to a promotion target to obtain related information related to the promotion target word; an extraction step of extracting user-related information, which is information specific to the user related to the promotion target, from the related information based on user attribute information associated with the user to whom the promotion is provided; and a generation step of generating an individual promotion sentence specific to the user by inputting input information including at least a basic promotion sentence for the promotion and the user-related information into a large-scale language model.

Images