Information processing device and information processing method

Abstract

An information processing device according to one embodiment comprises: a first acquisition unit that acquires first preference information indicating a preference of a user who uses a product group; a second acquisition unit that acquires identifying information for identifying a person related to the user; and a recommendation unit that recommends, to the user, a product that is selected with consideration to second preference information in addition to the first preference information, the second preference information indicating preferences of the related person regarding the product group.

Description

INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD

[0001] The present invention relates to an information processing apparatus and an information processing method for recommending products that take into account user preferences.

[0002] A technique is known for recommending products with high relevance to users when products are sold through EC (Electronic Commerce) sites. For example, Patent Document 1 discloses a technique of extracting and recommending products that are subsequently purchased by other users who have purchased a specific product when a user becomes interested in said specific product.

[0003] Japanese Patent No. 6251465 Problem to be Solved

[0004] When purchasing perfume through an EC site, the purchaser imagines the scent from texts such as the seller's description and purchaser reviews before making the purchase. However, since scent also affects the surrounding environment, it is necessary to consider not only the preference of the purchaser themselves but also the preferences of people related to the purchaser.

[0005] In view of this, the present invention provides a technique for recommending products with higher satisfaction for a user by considering not only the user's preferences but also the preferences of people related to the user.

[0006] One aspect of the present disclosure provides an information processing apparatus including: a first acquisition unit that acquires first preference information indicating preferences of a user who uses a product group; a second acquisition unit that acquires specifying information for specifying a person related to the user; and a recommendation unit that recommends, to the user, a product selected in consideration of second preference information indicating preferences of the related person regarding the product group, in addition to the first preference information.

[0007] Another aspect of the present disclosure provides an information processing method including the steps of: acquiring first preference information indicating preferences of a user who uses a product group; acquiring specifying information for specifying a person related to the user; and recommending, to the user, a product selected in consideration of second preference information indicating preferences of the related person regarding the product group, in addition to the first preference information.

[0008] According to this disclosure, by considering not only the user's preferences but also the preferences of those involved, it is possible to recommend products that are more satisfying to the user.

[0009] A diagram illustrating the overall configuration of the information processing system according to the embodiment. A diagram illustrating the functional configuration of the server according to the embodiment. A diagram illustrating the hardware configuration of the server according to the embodiment. A sequence diagram illustrating the operation overview of the information processing system according to the embodiment. A diagram illustrating the first input screen according to the embodiment. A diagram illustrating the first input screen according to the embodiment. A diagram illustrating the first input screen according to the embodiment. A conceptual diagram of stakeholders. A diagram illustrating the configuration of the stakeholders database according to the embodiment. A diagram illustrating the second input screen according to the embodiment. A diagram illustrating the second input screen according to the embodiment. A diagram illustrating the second input screen according to the embodiment. A diagram illustrating the configuration of the preference information database according to the embodiment. A diagram illustrating the configuration of the tag information database according to the embodiment. A flowchart illustrating the recommended product determination process. A diagram illustrating the output screen according to the embodiment.

[0010] 1. Diagram 1 illustrates the system configuration of the information processing system 1 according to the embodiment. The information processing system 1 is a system that provides product recommendations that take into account the user's preferences. The information processing system 1 comprises a server 100 and a terminal 200. The server 100 is a server device that performs product recommendations based on information received from the terminal 200 via a network N such as the Internet. The terminal 200 is a device that accepts information input from the user and displays the product recommendation results received from the server 100. The server 100 is an example of an "information processing device". The terminal 200 is, for example, a personal computer, a smartphone, and a tablet. The products referred to here are, for example, items that stimulate the user's five senses, especially senses other than sight. Senses other than sight include, for example, the sense of smell, and items include, for example, perfume.

[0011] It is difficult to convey information about senses other than sight, such as smell. For example, even when trying to buy perfume on an e-commerce site, the most important characteristic of perfume, its "scent," cannot be actually confirmed on the site. Therefore, users refer to the description provided by the seller or reviews from past buyers and imagine the scent before making a purchase. However, it is possible that after actually purchasing the product, the scent may be different from what was imagined, and the product may end up not being used. In particular, for products like perfume, which can stimulate (influence) the sense of smell of not only the user but also those around them, it is preferable to consider the evaluations of those around them, i.e., stakeholders. This embodiment addresses this problem.

[0012] Figure 2 is a diagram illustrating the functional configuration of a server 100 according to an embodiment. The server 100 includes, for example, a first acquisition unit 101, a second acquisition unit 102, a recommendation unit 103, a storage unit 104, a first access unit 105, a second access unit 106, a communication unit 107, and a control unit 108.

[0013] The first acquisition unit 101 acquires first preference information that indicates the preferences of users who use the product group. The first preference information can be any information that directly or indirectly indicates the user's preferences, such as the user's attributes and the user's evaluation of the product. User attributes refer to information about the user's characteristics or features. User attributes include information such as age, gender, and place of residence.

[0014] The second acquisition unit 102 acquires identification information to identify the user's related parties. Related parties will be described later. Related parties are identified, for example, according to the purpose of use of the product, in which case the identification information includes information such as purpose information indicating the purpose for which the user uses the product. Purpose information is information related to the situation or use, such as for work, daily use, and for dating. The second acquisition unit 102 identifies related parties, for example, according to information such as purpose information.

[0015] The recommendation unit 103 recommends selected products to the user, taking into account the second preference information in addition to the first preference information acquired by the first acquisition unit 101. The second preference information indicates the preferences of the person concerned regarding product groups, which are identified based on the specific information acquired by the second acquisition unit 102. The second preference information includes, for example, the attributes of the person concerned and information such as the evaluation the person concerned has given to the product. The attributes of the person concerned refer to information about the characteristics or features of the person concerned. For example, the attributes of the person concerned include information such as age, gender, and place of residence. The evaluation refers to information about preferences such as whether or not the person likes the product.

[0016] In this example, the recommendation unit 103 recommends products selected based on the degree of match between the first preference information and the tag information. Tag information is information that indicates the attributes of each of the multiple products that make up the product group. Product attributes are information about the characteristics or features of the product. In the case of a product called "perfume," the attributes would be items such as fragrance type, fragrance strength, and target audience (of the user). The degree of match is an indicator that shows how well the product is suited to the user or related parties.

[0017] In this example, the recommendation unit 103 recommends products selected based on the degree of match between the second preference information and the tag information. The recommendation unit 103 also recommends products selected based on the statistical value of the degree of match between the second preference information and the tag information obtained for each of multiple individuals (stakeholders). Furthermore, the recommendation unit 103 recommends products selected based on the satisfaction level obtained by inputting into the machine learning model 109.

[0018] The memory unit 104 stores various types of data and programs. The data and programs stored in the memory unit 104 include a database 1040 and a machine learning model 109. The database 1040 is a collection of multiple databases. The database 1040 includes, for example, a stakeholders database 1041, a preference information database 1042, and a tag information database 1043. Details of each database will be described later. When stakeholders and products are specified, the machine learning model 109 outputs an estimated satisfaction level. Details of the machine learning model 109 will be described later.

[0019] The first access unit 105 accesses a database in which tag information indicating attributes for each of the multiple products that make up the product group is recorded. The second access unit 106 accesses a machine learning model 109 that has been trained using training data including attribute information of stakeholders, tag information of products, and stakeholders' satisfaction with the products.

[0020] The communication unit 107 transmits and receives data to and from the terminal 200 via the network N. The control unit 108 controls the operation of the entire information processing system 1.

[0021] Figure 3 illustrates the hardware configuration of server 100 in an embodiment. Physically, server 100 is configured as a computer including a processor 151, memory 152, storage 153, communication device 154, input device (optional), display device (optional), and a bus connecting these. Each of these devices operates on power supplied from a battery (not shown). In the following description, the term "device" can be read as a circuit, device, unit, etc. The hardware configuration of server 100 may include one or more of the devices shown in Figure 3, or it may be configured without some of the devices. Alternatively, multiple devices with different enclosures may be connected via communication to constitute server 100.

[0022] Each function in the server 100 is realized by loading predetermined software (programs) onto hardware such as the processor 151 and memory 152, which causes the processor 151 to perform calculations, control communication by the communication device 154, and control at least one of the reading and writing of data in the memory 152 and storage 153.

[0023] The processor 151 controls the entire computer, for example, by running the operating system. The processor 151 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control devices, arithmetic units, registers, etc. Alternatively, a baseband signal processing unit or a call processing unit may be implemented by the processor 151.

[0024] The processor 151 reads programs (program code), software modules, data, etc., from at least one of the storage 153 and the communication device 154 into the memory 152 and executes various processes accordingly. The program used is one that causes the computer to execute at least a part of the operations described later. Functional blocks of the server 100 may be stored in the memory 152 and implemented by control programs running on the processor 151. Various processes may be executed by one processor 151, or they may be executed simultaneously or sequentially by two or more processors 151. The processor 151 may be implemented by one or more chips. The program may also be transmitted to the server 100 via a telecommunications line.

[0025] The memory 152 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 152 may also be called a register, cache, main memory, etc. The memory 152 can store executable programs (program code), software modules, etc., for carrying out the method according to this embodiment.

[0026] The storage 153 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. The storage 153 may also be called an auxiliary storage device.

[0027] The communication device 154 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc.

[0028] Each device, such as the processor 151 and memory 152, is connected by a bus for communicating information. The bus may be configured using a single bus, or different buses may be configured for each device.

[0029] The server 100 may be configured with hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array), and some or all of each functional block may be realized by this hardware. For example, the processor 151 may be implemented using at least one of these hardware components.

[0030] In this example, the program stored in the storage 153 includes a program (hereinafter referred to as the "server program") that causes the computer to function as the server 100 in the server 100. When the processor 151 is executing the server program, at least one of the memory 152 and the storage 153 is an example of the storage unit 11, the processor 151 is an example of the acquisition unit 12, the generation unit 13, and the control unit 19, and the communication device 154 is an example of the output unit 14.

[0031] 2. Operation Diagram 4 is a sequence diagram illustrating the general operation of the information processing system 1 according to the embodiment. The process shown in Figure 4 shows the flow of processing from when the user launches the recommendation application on terminal 200 and the server 100 starts up until the recommendation results are displayed on terminal 200. The process shown in Figure 4 starts, for example, when the recommendation application is launched on terminal 200. In the following, hardware such as the server 100 will be described as the main processing unit, which means that hardware elements such as the processor 151 that executes a program such as a server program will work in cooperation with other hardware elements to execute the processing. At the start of Figure 4, the user on terminal 200 is logged into the information processing system 1 and has sent their user ID to the server 100. The user logged into the information processing system 1 from terminal 200 is referred to as the "target user".

[0032] In step S1, terminal 200 transmits first preference information and specific information to server 100. The details are as follows: Terminal 200 displays, for example, a first input screen 500 that accepts input of the target user's first preference information and specific information. Terminal 200 transmits, for example, the received first preference information and specific information to server 100.

[0033] Figures 5A to 5D illustrate a first input screen 500 according to an embodiment. Information about the user is accepted, for example, the user's personal information, the user's first preference information, and specific information. Personal information includes, for example, gender, age, date of birth, and address. In this example, the first input screen 500 consists of four sub-input screens, first input screens 500a to 500d. These input screens include UI objects for inputting various types of information. First input screen 500a accepts, for example, the user's personal information. First input screen 500a includes, for example, a question 501a, "Q1: What is your gender?", options 502a, "Male", "Female", and "No answer", a selection button 503, and a "Next" button 504.

[0034] The first input screen 500b accepts input of target information from among specific information. The first input screen 500b includes, for example, the question "Q2: What is the scene (occasion or purpose) in which you use perfume?" 501b, the options 502b "For work", "For everyday use", "For dates", and "Other", a selection button 503, and a "Next" button 504.

[0035] The first input screen 500c accepts input of information regarding fragrance profiles from the first preference information. The first input screen 500c includes, for example, a question 501c titled "Q3: What is your favorite scent (fragrance profile)?", options 502c such as "Woody", "Citrus", "Floral", and "Other", a selection button 503, and a "Next" button 504.

[0036] The first input screen 500d accepts input of information regarding the intensity of the scent, for example, from the first preference information. The first input screen 500d includes, for example, the question "Q4: What is your preferred scent intensity?" 501d, the options 502d "Weak", "Normal", "Strong", and "Other", a selection button 503, and a "Next" button 504. The first input screen 500 may also include information other than this. In addition, a first input screen 500 other than the first input screens 500a to d in the example of Figure 5 may be displayed, and input of other information about the user may be accepted.

[0037] Let's return to the sequence diagram in Figure 4 and resume the explanation. Server 100 acquires first preference information and specific information from terminal 200. Server 100 stores the received first preference information and specific information in storage unit 104, for example. If the target user's first preference information is already stored in storage unit 104, server 100 may skip the process of accepting input of the target user's first preference information.

[0038] Server 100 identifies the people related to the target user based on the specific information (step S2).

[0039] Figure 6 is a conceptual diagram of stakeholders. Stakeholders are individuals who are involved in the user's life. Stakeholders can be categorized, for example, as colleagues, superiors, subordinates (hereinafter simply referred to as "colleagues, etc."), family, romantic partners, and friends. In the example in Figure 6, the user is assumed to be a so-called salaried worker, living with his family (parents) in his family home, and also a man with a romantic partner (woman). In terms of the relationship with the product, the stakeholders affected by the product change depending on the purpose or scenario of use of the product. In this example, colleagues, etc. are stakeholders corresponding to the purpose of use "work," family members are stakeholders corresponding to the purpose of use "daily life," and romantic partners are stakeholders corresponding to the purpose of use "dating." In this example, the relationship between the purpose of use and stakeholders is defined by the database.

[0040] Figure 7 illustrates the configuration of the stakeholders database 1041 according to the embodiment. The stakeholders database 1041 is a database that stores user purpose information and information about the user's stakeholders that corresponds to that information. The stakeholders database 1041 includes multiple records. Each record includes information about the user. The stakeholders database 1041 includes, for example, "purpose information" and "stakeholders".

[0041] In the example in Figure 7, the top record in the stakeholders database 1041 includes "Purpose Information: Work" and "Stakeholders: Colleagues, etc." This indicates that the user is using the product for work purposes, and the stakeholders in that case are colleagues. The second-to-last record in the stakeholders database 1041 includes "Daily Life" and "Family." This indicates that the user is using the product for daily life purposes, and the stakeholders are family members. The stakeholders database 1041 may contain other records, but for the sake of simplicity in the diagram, other descriptions are omitted here.

[0042] Let's return to the sequence diagram in Figure 4 and resume the explanation. Server 100 transmits data to terminal 200 to display a second input screen 800 that prompts the user to input second preference information. Terminal 200 displays the second input screen 800 according to the received data and accepts input of the second preference information from the relevant parties (step S3).

[0043] Figures 8A to 8D illustrate a second input screen 800 according to the embodiment. The second input screen is a screen for receiving information about the user's related parties. Information about related parties includes, for example, information such as second preference information. In this example, the second input screen 800 is composed of four sub-screens, second input screens 800a to 800d. Second input screen 800a is the screen displayed when the related party is, for example, a family member. Second input screen 800a includes, for example, the question "Q4: What scent (fragrance) does your family like?" 801a, the options "Woody", "Citrus", "Floral", "Other", and "No answer" 802a, a selection button 803, and a "Next" button 804. The second input screen 800 may also include information other than this. In addition, second input screens 800 other than the second input screens 800a to 800d in the example of Figure 8 may be displayed to receive input of other information about related parties.

[0044] Furthermore, if the user does not know the preferences of the relevant person, the user can skip this question by selecting "No Answer". The same applies to other second input screens 800 hereinafter. In addition, for example, when the relevant person is a colleague or the like, the second input screen 800 does not need to be displayed. Furthermore, when the second preference information of the relevant person is stored in the storage unit 104, the server 100 may skip the process of accepting the input of the second preference information of the relevant person.

[0045] The second input screen 800b is a screen displayed when the relevant person is, for example, a family member. The second input screen 800b includes, for example, a question sentence 801b "Q5: What intensity of scent does your family like?", options 802b including "Woody", "Citrus", "Floral", "Other" and "No Answer", a selection button 803, and a "Next" button 804.

[0046] Furthermore, the second input screen 800c is a screen displayed when the relevant person is, for example, a lover. The second input screen 800c includes, for example, a question sentence 801c "Q5: What scent (fragrance tone) does your lover like?", options 802c including "Woody", "Citrus", "Floral", "Other" and "No Answer", a selection button 803, and a "Next" button 804.

[0047] The second input screen 800d is a screen displayed when the relevant person is, for example, a lover. The second input screen 800d includes, for example, a question sentence 801d "Q6: What intensity of scent does your lover like?", options 802d including "Woody", "Citrus", "Floral", "Other" and "No Answer", a selection button 803, and a "Next" button 804.

[0048] Returning to the sequence diagram of FIG. 4 to resume the description. The terminal 200 transmits the accepted second preference information to the server 100. The server 100 stores the received second preference information in the preference information database 900, for example. Note that when the second preference information of the identified relevant person is stored in the storage unit 104, the server 100 may skip the process of step S3.

[0049] Figure 9 illustrates the configuration of a preference information database 1042 according to an embodiment. The preference information database 1042 is a database that stores first preference information and second preference information. The preference information database 1042 includes a plurality of records and columns. Each record and column includes information about the user or related party. For example, the preference information database 1042 includes "tag information" such as "fragrance type," "fragrance strength," and "gender" in a record. The preference information database 1042 also includes columns such as "target user," "- (unspecified)," "family," and "lover."

[0050] In the example in Figure 9, the top record in the preference information database 1042 includes "Target User," "Fragrance: Woody," and "Fragrance Strength: Normal." This indicates that the characteristics of the product preferred by the target user are that the fragrance is woody, the fragrance strength is normal, and the user is male.

[0051] Furthermore, the second-to-last record in the preference information database 1042 includes "- (unspecified)", "Fragrance: - (unspecified)", "Fragrance strength: weak", and "-". This indicates that the stakeholders are all people (unspecified persons), and the characteristic of a product that all people like is that the fragrance strength is weak, and the fragrance and gender are not specified. Furthermore, the third-to-last record in the preference information database 1042 includes "family", "Fragrance: citrus", "Fragrance strength: weak", and "Gender: -". This indicates that the stakeholders are the user's family, and the characteristic of a product that the family likes is that the fragrance is citrus and the fragrance strength is weak, and the gender is not specified. Note that the preference information database 1042 may contain other records, but for the sake of simplicity in the diagram, other descriptions are omitted here.

[0052] Let's return to the sequence diagram in Figure 4 and resume the explanation. Server 100 selects products to recommend to the user based on the user's first preference information, the stakeholders' second preference information, and the degree of matching of the tag information (step S4).

[0053] Figure 10 is a diagram illustrating the configuration of a tag information database 1043 according to an embodiment. The tag information database 1043 is a database that stores tag information corresponding to each product. The tag information database 1043 includes a plurality of records. Each record includes information about a product. The tag information database 1043 includes, for example, "product name" and "tag information". The "tag information" also includes, for example, "fragrance type", "fragrance strength", "target", and "scene".

[0054] In the example shown in Figure 10, the top record in the tag information database 1043 contains "Product Name: A", "Fragrance Profile: Woody", "Fragrance Strength: Weak", "Target: Men", and "Scene: Work". This indicates that the product is named A, has a woody fragrance profile, a weak fragrance strength, is targeted primarily to men, and is for work use. The tag information database 1043 may contain other records, but for the sake of simplicity in the diagram, other descriptions are omitted here.

[0055] Figure 11 is a flowchart illustrating the recommended product determination process. The recommended product determination process is the process in step S4 of the recommendation process. First, the server 100 calculates a first score based on the user's first preference information (step S401). The first score is an index that shows the degree of similarity, that is, how well each product suits the user, that is, how similar or consistent the attributes of each product are with the user's preferences. Any known method may be used to calculate the similarity, such as a method using vectorization, a method using a graph structure, or a rule-based method. For example, the server 100 stores the first score calculated for each product in the storage unit 104.

[0056] The calculation of the first score uses, for example, first preference information and tag information. Specifically, the smaller the difference between the first preference information and the tag information, the higher the score. In other words, products with a high score have a higher recommendation priority.

[0057] Next, the server 100 calculates a second score based on the second preference information of the stakeholders (step S402). The second score is an index that indicates the degree of similarity of each product to the stakeholders of the user, that is, the degree to which the attributes of each product are similar to or match the user's preferences. A well-known method is used to calculate the similarity, similar to the first score. The similarity of the first score and the second score may be calculated using different methods. For example, the server 100 stores the second score calculated for each product in the storage unit 104.

[0058] The calculation of the second score uses, for example, secondary preference information and tag information. Specifically, the smaller the difference between the secondary preference information and the tag information, the higher the score. In other words, products with a high score have a higher recommendation priority.

[0059] Next, the server 100 determines which products to recommend based on the first and second scores (step S403). A formula for calculating the degree of match from the first and second scores is defined, and in one example, it is a weighted average of the two. The weights for the two are defined. These weights may be defined for each use, or they may be increased or decreased according to the attributes of the target user or the number of stakeholders. The server 100 calculates, for example, the overall score for each product. The server 100 also selects which products to recommend to the user in order of highest overall score for each product.

[0060] The overall score is an estimated value indicating how well each product suits the user and stakeholders. The server 100 also stores the overall score calculated for each product in the storage unit 104. The server 100 then determines which products to recommend to the user, for example, in order of highest overall score.

[0061] The above example describes the case where "Scene: Work" is selected, but for example, if "Scene: Daily Use" is selected, the second preference information for "Family" in Figure 9 will be used. Also, for example, if "Scene: Dating" is selected, the second preference information for "Lover" in Figure 9 will be used. Note that if "Scene: Daily Use" or "Scene: Dating" is selected and the second preference information of the person concerned is not stored in the memory unit 104 (i.e., if the user selects "No Answer" because they do not know the preferences of the person concerned), the second preference information of "- (Unspecified)" may be used.

[0062] Let's return to the sequence diagram in Figure 4 and resume the explanation. Terminal 200 displays information about the selected product on the display unit (not shown) (step S5). Server 100, for example, transmits information about the selected product to terminal 200 and recommends it to the user.

[0063] Figure 12 illustrates an example of an output screen 1200 in the recommendation process. The output screen is a screen for recommending a predetermined product to the user. The predetermined product is the product selected in the recommendation process. The output screen 1200 includes, for example, the product name 1201 for "(1) Product [A]", the score 1202 for "Satisfaction: 88 points", the product image 1203, and the "Complete" button 1204. Note that the product name 1201, score 1202, and product image 1203 are shown for each recommended product, but are omitted for other products.

[0064] As described above, information processing system 1 can increase user purchasing intent and customer satisfaction by recommending products that match the user's needs. Furthermore, by considering the secondary preference information of stakeholders, it is possible to discover products that match potential needs or preferences that the user themselves may not have been aware of.

[0065] 3. Modifications The present invention is not limited to the embodiments described above, and various modifications are possible. Several modifications are described below. Two or more of the matters described below may be combined and applied.

[0066] (1) First preference information In the above embodiment, the first preference information was entered by the user into the first input screen 500, but is not limited to this. The first preference information may be generated based on, for example, the user's purchase history of products purchased in the past, the user's evaluation of products, and the user's wish list of products (a list of products the user wants to purchase). In this case, the server 100 or terminal 200 stores a database of the target user's past purchase behavior (e.g., purchase history, evaluation, and wish list). The server 100 or terminal 200 identifies the first preference information by referring to this database.

[0067] (2) Second preference information In the above embodiment, the second preference information was entered by the user into the second input screen 800, but is not limited to this. The second preference information may be entered by the person concerned, for example, or it may be generated based on the purchase history of products that the person concerned has purchased in the past, the evaluations that the person concerned has made of products, and the wish list of products that the person concerned has created (a list of products that they would like to purchase).

[0068] In this case, the server 100 may have a user database (not shown) that records the attributes of each user, and may identify the second preference information by referring to this user database. The user referred to here is a person who is a specific candidate for a related party, and does not necessarily have to be a person who uses the information processing system 1 (i.e., a person who has registered as a user themselves). The user's attribute information may include personal information (e.g., name). Relationships between users may be defined in the user database. For example, in the record of a certain user Ua, users Ub, Uc, and Ud are recorded as colleagues, users Ue and Uf are recorded as family, and user Ud is recorded as a lover. For example, if the purpose information indicates the purpose of use as "work", the server 100 identifies the category of the corresponding related party from the related party database 1041 as "colleagues, etc." Furthermore, the server 100 identifies specific related parties from the user database who are related to the target user and belong to the identified category. If the target user is user Ua and the category of related parties is "colleagues, etc.", then users Ub, Uc, and Ud are identified as related parties. The specific preferences of these users are recorded in their user records.

[0069] (3) Schedule Information In the above embodiment, the specific information was the objective information, but is not limited to this. The specific information may be, for example, schedule information that shows the user's planned activities. Schedule information may be, for example, information about activities such as meetings, presentations, meals, and drives. The second acquisition unit 102 identifies the relevant parties according to the information, such as the schedule information.

[0070] (4) A comment about the product may be displayed on the product comment output screen 1200. A comment about the product is a sentence that recommends the product to the user. For example, a comment about the product may be sentences such as, "This product is recommended for customers who like woody fragrances," and "This product is popular with all types of customers." Information about the comments is stored in, for example, the tag information database 1043.

[0071] (5) Calculation of Match Score The method for calculating the match score, or the first score and the second score, is not limited to the examples of the embodiment. For example, the server 100 may calculate the match score using a machine learning model 109 or an LLM (Large Language Model). This machine learning model 109 is a machine learning model that has been trained using data such as the attribute information of the target user, the attribute information of the stakeholders, the tag information of the product, and the feedback (match score) of the stakeholders as training data. Alternatively, if an LLM is used, the server 100 inputs a prompt to the LLM to output the match score from the attributes of the target user, the attributes of the stakeholders, and the tag information of the product.

[0072] (6) Other programs executed by the processor 151 may be provided by downloading them via a network such as the Internet, or they may be provided recorded on a computer-readable non-temporary recording medium such as a DVD-ROM. Each processor may be, for example, a CPU, an MPU (Micro Processing Unit), or a GPU (Graphics Processing Unit).

[0073] The block diagrams used in the description of the above embodiments show functional units. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may also be realized by combining software with the one or more of the above devices.

[0074] Functions include, but are not limited to, judgment, decision, determination, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmission unit or transmitter. In all cases, as mentioned above, the method of implementation is not particularly limited.

[0075] For example, the information processing system 1 in one embodiment of the present disclosure may function as a computer that performs the processing described in the present disclosure.

[0076] Each aspect or embodiment described in this disclosure may be applied to at least one of the following: LTE (Long Term Evolution), LTE-A (LTE-Advanced), 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®, GSM®, CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi®), IEEE 802.16 (WiMAX®), IEEE 802.20, UWB (Ultra-WideBand), Bluetooth®, and other appropriate systems, as well as next-generation systems extended based thereon. Furthermore, multiple systems may be applied in combination (for example, a combination of at least one of LTE and LTE-A with 5G).

[0077] The processing procedures, sequences, flowcharts, etc., of each aspect or embodiment described in this disclosure may be reordered, provided they do not contradict each other. For example, the methods described in this disclosure present various step elements in an exemplary order and are not limited to the specific order presented.

[0078] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be sent to other devices.

[0079] The determination may be made by a value represented by one bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, by comparing with a predetermined value).

[0080] Although the present disclosure has been described in detail above, it will be 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 intent and scope of the present disclosure as defined by the claims. Therefore, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0081] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name. Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0082] The information, signals, etc., described herein may be represented using any of the following different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. Terms used herein and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meaning.

[0083] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0084] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0085] Any reference to elements using the designations “First,” “Second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to the First and Second elements do not imply that only two elements may be employed, or that the First element must precede the Second element in any way.

[0086] In the above-described configuration of each device, the term "part" may be replaced with "means," "circuit," "device," etc.

[0087] Where the terms “include,” “including,” and variations thereof are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0088] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0089] In this 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 "combine" may be interpreted similarly to "different."

[0090] 100...Server, 101...First acquisition unit, 102...Second acquisition unit, 103...Recommendation unit, 104...Storage unit, 105...First access unit, 106...Second access unit, 107...Communication unit, 108...Control unit, 109...Machine learning model, 200...Terminal, 1040...Database, 1041...Related party database, 1042...Preference information database, 1043...Tag information database

Claims

1. An information processing device comprising: a first acquisition unit for acquiring first preference information indicating the preferences of a user who uses a product group; a second acquisition unit for acquiring identification information for identifying the user's associates; and a recommendation unit for recommending selected products to the user, taking into account the first preference information and the second preference information indicating the associates' preferences regarding the product group.

2. The information processing apparatus according to claim 1, wherein the specified information includes purpose information indicating the purpose for which the user uses the product, and the relevant parties are identified according to the purpose.

3. The information processing device according to claim 1, wherein the identified information includes scheduled information indicating the user's planned actions, and the relevant parties are identified according to the planned actions.

4. The information processing device according to claim 1, comprising a first access unit that accesses a database in which tag information indicating attributes for each of the multiple products constituting the product group is recorded, and the recommendation unit recommends products selected based on the degree of match between the first preference information and the tag information.

5. The information processing device according to claim 1, comprising a first access unit that accesses a database in which tag information indicating attributes for each of the multiple products constituting the product group is recorded, and the recommendation unit recommends products selected based on the degree of match between the second preference information and the tag information.

6. The information processing apparatus according to claim 5, wherein the parties concerned include multiple individuals, and the recommendation unit recommends selected products based on a statistical value of the degree of match between the second preference information obtained for each of the multiple individuals and the tag information.

7. The information processing device according to claim 5, further comprising a second access unit that accesses a machine learning model trained using training data including attribute information of the persons concerned, tag information of the products, and satisfaction levels of the persons concerned with the products, wherein the recommendation unit recommends products selected based on satisfaction levels obtained by inputting data including attribute information of the persons concerned and tag information of the products into the machine learning model.

8. The information processing apparatus according to claim 1, wherein the product is an item that stimulates the user's five senses.

9. The information processing apparatus according to claim 8, wherein the product is perfume.

10. An information processing method comprising the steps of: acquiring first preference information indicating the preferences of a user who uses a product group; acquiring identification information for identifying the user's related parties; and recommending selected products to the user, taking into account the first preference information and second preference information indicating the related parties' preferences regarding the product group.

Images