Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device capable of supporting the understanding of appealing contents to a user in a transaction object, an information processing method, and an information processing program.SOLUTION: An information processing device comprises: an estimation unit that estimates an impression type of a user to a transaction object and an impression degree of the user in the type on the basis of action history information of the user to the transaction object; an acquisition unit that acquires evaluation information, which is information indicative of an evaluation to the transaction object; and an identification unit that identifies an impression type having a predetermined relationship between the evaluation indicated by the evaluation information acquired by the acquisition unit and the impression degree estimated by the estimation unit.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] Conventionally, there are known techniques for supporting product development, etc. For example, Patent Document 1 proposes a technique in which a customer is prompted to input a response regarding the level of customer satisfaction with the specification values ​​of each specification of a product, and based on the customer satisfaction, the specifications to be improved are quantitatively determined, and the specifications to be improved and the specification values ​​after the improvement are determined. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-92818 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology described in Patent Document 1 proposes improvements to specifications included in a questionnaire prepared in advance, and does not propose improvements to specifications not included in the questionnaire.

[0005] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can assist in understanding the appeal content to users of a trading subject. [Means for solving the problem]

[0006] The information processing device according to the present application includes an estimation unit that estimates the type of impression a user has of a transaction object and the degree of the user's impression for each type based on information about the user's behavioral history regarding the transaction object; an acquisition unit that acquires evaluation information, which is information indicating an evaluation of the transaction object; and an identification unit that identifies the type of impression for which there is a predetermined relationship between the evaluation indicated in the evaluation information acquired by the acquisition unit and the impression degree estimated by the estimation unit. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to provide an effect of assisting in understanding the appeal content of the transaction target to users. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a user information table stored in a user information storage unit according to the embodiment. [Figure 5] FIG. 5 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [1. An example of information processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment, which is executed by an information processing device 1.

[0011] The information processing device 1 shown in Fig. 1 is an information processing device that cooperates with a terminal device 2 of a business operator O and a terminal device 3 of a user U to provide various types of information online to the business operator O and the user U, and is realized, for example, by one or more servers or a cloud system. The business operator O is, for example, an executive or employee of a company that provides a transaction object to the user U. The transaction object is, for example, a product or a service.

[0012] In the example shown in Figure 1, one each of terminal devices 2 and 3 is shown, but the information processing device 1 can cooperate with each of multiple terminal devices 2 and multiple terminal devices 3 to provide various online services to operators O of each terminal device 2 and users U of each terminal device 3.

[0013] The service provided to the user U by the information processing device 1 is, for example, a service that supports understanding of the appeal content of the transaction target to the user (hereinafter, may be referred to as appeal content identification service).

[0014] The services provided by the information processing device 1 are not limited to appeal content identification services, but may also include services such as e-commerce services (e.g., online shopping malls, flea markets, auctions, etc.), web search services, and Q&A (Question and Answer) services.

[0015] The information processing device 1 acquires behavior history information including information on the behavior history of the user U with respect to each transaction object from, for example, an internal storage unit or an external server (step S1).

[0016] The behavioral history information includes, for each transaction object, information such as search keywords related to the transaction object used by user U in web searches, questions related to the transaction object asked by user U using a Q&A service, and review comments posted by user U about the transaction object.

[0017] The search keywords related to the transaction object used by the user U in the web search include, for example, a first keyword and a second keyword. The first keyword is a search keyword that is included in the same search query as a search keyword indicating the transaction object (for example, the name of the transaction object).

[0018] The second keyword is a search keyword other than the search keyword indicating the transaction object, which includes a search query including a search keyword indicating the transaction object and is included in multiple search queries transmitted from the terminal device 3 of the same user U within a predetermined time period. For example, the second keyword is a search keyword included in a search query transmitted from the terminal device 2 of the user U after a search query including a search keyword indicating the transaction object.

[0019] The search keywords related to the transaction target used by user U in a web search are, for example, search keywords related to the transaction target used by user U in a web search before the transaction for the transaction target. The question related to the transaction target asked by user U in a Q&A service is, for example, a question related to the transaction target asked by user U in a Q&A service before the transaction for the transaction target.

[0020] "Pre-transaction" refers to a period from the time of the transaction to a predetermined period before the transaction. The predetermined period differs, for example, depending on the transaction object or category of the transaction object. Furthermore, "transaction" refers to the reservation, ordering, or purchase of a product when the transaction object is a product, and the purchase or use of a service when the transaction object is a service.

[0021] Based on the behavioral history information acquired by the processing of step S1, the information processing device 1 estimates the type of impression (hereinafter sometimes referred to as impression type) of user U regarding the transaction object and the degree of impression (hereinafter sometimes referred to as impression degree) of user U for each impression type for each transaction object (step S2).

[0022] The impression types include various types such as heavy, light, large, small, stylish, uncool, old-fashioned, simple, cute, refreshing, elegant, etc. The impression level indicates, for example, how strongly the user U thinks about it, but it may also indicate how good or bad the user thinks about it.

[0023] The information processing device 1 can estimate the impression type and impression degree for each transaction object from the behavior history information using, for example, a distributed representation technology, an impression type dictionary, etc. Examples of the distributed representation technology include W2V (Word2Vec), FastText, GloVe (Global Vectors), and ELMo (Embeddings from Language Models).

[0024] For example, the information processing device 1 performs preprocessing to remove unnecessary numbers, symbols, words, etc. contained in the behavior history information, and then converts each word contained in the preprocessed behavior history information into a vector using distributed representation technology.

[0025] Then, the information processing device 1 calculates, for example, the similarity between the vector of each predetermined impression type and the vector of each word (for example, a value obtained by multiplying the cosine similarity by a coefficient), and determines for each word vector whether the similarity with the vector of the impression type is within a threshold value.

[0026] When there is an impression type whose vector has a similarity to a word vector within a threshold, the information processing device 1 determines that the user U has that impression type with respect to the transaction object. For example, the information processing device 1 determines the similarity of the word vector that has the highest similarity to the impression type vector that the user U has with respect to the transaction object as the impression degree.

[0027] Furthermore, the information processing device 1 can input the vector of each word to a classifier that determines the impression type and impression degree, and estimate the impression type and impression degree for one or more impression types from the output result of the classifier. The classifier can be, for example, a decision tree, a random forest, a neural network, or the like, but is not limited to these examples.

[0028] For example, the information processing device 1 uses a classifier to determine the highest impression degree among the impression degrees of the impression types of each word, thereby estimating the user U's impression type and impression degree for each transaction object.

[0029] Furthermore, the information processing device 1 can also estimate the impression type and impression degree for each transaction object from the behavior history information using the impression type dictionary. The impression type dictionary includes information on words indicating predetermined impression types (hereinafter, may be referred to as impression type words) for each impression type.

[0030] For example, the information processing device 1 calculates the number of appearances of impression-type words included in the behavior history information for each impression-type word. Then, the information processing device 1 estimates the impression type and impression degree for each transaction object based on the number of appearances of each impression-type word. For example, the information processing device 1 estimates the impression degree for each impression type as the total number of appearances of impression-type words for each impression type.

[0031] The impression-type dictionary may be a dictionary that includes information relating impression-type words to impression values ​​for each impression-type word. In this case, the information processing device 1 can estimate the impression degree for each impression type by multiplying the impression value by the total number of appearances of each impression-type word and adding up the multiplication results for each impression type. Note that the impression value can be a positive or negative value, but it may also be a value that does not become negative.

[0032] Furthermore, the information processing device 1 can also estimate the impression type and impression degree for each transaction object using a language model that performs natural language processing, such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers).

[0033] The information processing device 1 can estimate the impression type and impression degree using information on all users U, or can perform a process of estimating the impression type and impression degree for each user U or for each attribute of user U for each transaction object.

[0034] Furthermore, for example, if the impression type is an impression related to the weight of the transaction object, it may be represented by an axis including "light" and "heavy." In this case, the information processing device 1 can treat, for example, two mutually contradictory impression types among the plurality of impression types estimated as described above as one impression type.

[0035] For example, the information processing device 1 treats two opposing impression types as one impression type based on words indicating impression types contained in review comments of each evaluation of the transaction object and words indicating impression types contained in each evaluation of a higher-level category of the transaction object.

[0036] For example, suppose the transaction object is a rice cooker, and the word "light" appears only in review comments with high ratings for the rice cooker, but the word "light" appears in review comments ranging from high to low ratings for household appliances, which is a higher category than rice cookers. In this case, the information processing device 1 can treat the two mutually opposing impression types, "light" and "heavy," as a single impression type.

[0037] Furthermore, the information processing device 1 can estimate an impression type for which the user U has determined an ideal in the processing of step S2, or can estimate two opposing impression types for which the user U has determined an ideal as one impression type in the processing of step S2.

[0038] For example, when estimating the impression type and impression degree based on review comments about a transaction object posted by a user U, the information processing device 1 estimates the impression type and impression degree for each evaluation value of the user U for the transaction object. The evaluation value of the user U for the transaction object is a five-point scale with a maximum of 5 points, but may be a four-point scale or less, or a six-point scale or more. The evaluation of the transaction object includes an overall evaluation and an evaluation by item. The evaluation by item is, for example, an evaluation by impression type.

[0039] Next, the information processing device 1 receives a designation of a competing object from the business operator O (step S3). The competing object is a trading object that competes with a specific trading object. The specific trading object is a new product or a new service, for example, a trading object that the business operator O plans to provide to the user U or a trading object that the business operator O is providing to the user U.

[0040] In the processing of step S3, the information processing device 1 accepts the designation of a conflicting target from the operator O, for example, by receiving conflicting target designation information transmitted from the terminal device 2 of the operator O, which includes information on the conflicting target designated by the operator O.

[0041] Next, the information processing device 1 acquires evaluation information indicating the evaluation of the competing object as evaluation information indicating the user U's evaluation of the transaction object (step S4). The user U's evaluation of the competing object is, for example, a five-point scale, but may be an evaluation value of four points or less, or six points or more. The evaluation of the transaction object includes an overall evaluation and an evaluation by item. The evaluation by item is, for example, an evaluation by impression type.

[0042] In addition, in the processing of step S4, the information processing device 1 can also acquire, as evaluation information, information indicating evaluations of multiple transaction objects included in a higher-level category that includes the competing object. For example, if the competing object is a rice cooker, the higher-level category may be a household appliance or a home appliance.

[0043] Next, the information processing device 1 identifies the type of impression that has a predetermined relationship between the evaluation indicated by the evaluation information acquired in the processing of step S4 and the degree of impression of the user U toward the competing object estimated in the processing of step S2 (step S5).

[0044] For example, the information processing device 1 identifies impression types in which the evaluation indicated by the evaluation information and the degree of impression of the user U for the competing object have a predetermined relationship. The predetermined relationship is, for example, a condition in which the evaluation indicated by the evaluation information and the degree of impression of the user U for the impression type have an opposing relationship.

[0045] An opposing relationship is, for example, a relationship in which the evaluation for each item indicated in the evaluation information is greater than the median and the impression degree corresponding to such item is less than the median, or a relationship in which the evaluation for each item indicated in the evaluation information is less than the median and the impression degree corresponding to such item is greater than the median.

[0046] For example, if the transaction object is a rice cooker, and user U's evaluation of the item "overflow" is smaller than the median and the impression degree of the impression type "overflow" is greater than the median, the information processing device 1 determines that there is a predetermined relationship, and also determines that there is a predetermined relationship if the opposite is true.

[0047] In addition, the information processing device 1 determines that there is a predetermined relationship if the transaction object is a rice cooker, the user U's evaluation of the item ``rice cooking speed'' is smaller than the median, and the impression level of the impression type ``rice cooking speed'' is greater than the median, and also determines that there is a predetermined relationship if the opposite is true.

[0048] Furthermore, the predetermined relationship may be a contradictory relationship between the evaluation for each item indicated in the evaluation information and the impression degree for the impression type corresponding to such item, and further, a condition such that the difference between the evaluation for each item indicated in the evaluation information and the impression degree for the impression type corresponding to such item is greater than or equal to a threshold value.

[0049] In addition, the information processing device 1 can also identify impression types for which the difference between the evaluation for each item indicated in the evaluation information and the impression degree of the impression type corresponding to such item is greater than or equal to a threshold value as impression types having a predetermined relationship.

[0050] For example, the information processing device 1 identifies, as an impression type having a predetermined relationship, an impression type for which the item-specific evaluation indicated in the evaluation information is higher than the degree of impression of the user U by a threshold or more. For example, suppose that the evaluation of the item "heavy" by the user U is "4," the degree of impression of the user U for the impression type "heavy" is "2," and the threshold is "2." In this case, the information processing device 1 identifies the impression type "heavy" as an impression type having a predetermined relationship.

[0051] Furthermore, the information processing device 1 can also identify impression types whose impression degrees are higher than the item-specific evaluations indicated in the evaluation information by a threshold or more as impression types having a predetermined relationship. For example, assume that the evaluation of the item "heavy" by user U is "3," the degree of user U's impression of the impression type "heavy" is "5," and the threshold is "2." In this case, the information processing device 1 identifies the impression type "heavy" as an impression type having a predetermined relationship.

[0052] The information processing device 1 can also change the above-mentioned threshold value according to the attributes of the poster, who is the user U who posted the review comment. For example, if the transaction object is a rice cooker, the impression type is "rice cooking speed," and the poster has family members living with them, the information processing device 1 decreases the threshold value according to the number of family members. The information processing device 1 can also change the above-mentioned threshold value for each category of the transaction object.

[0053] Furthermore, the predetermined relationship (e.g., an opposing relationship) may be a relationship in which a higher overall rating (e.g., the overall rating value) indicates a lower impression level of the impression type estimated from the review comments than a lower overall rating (e.g., the overall rating value).

[0054] For example, if the object of transaction is a rice cooker and the impression level of the impression type "light" estimated from the review comments of user U who gave the overall rating is lower for a product with a higher overall rating value than for a product with a lower overall rating value, the information processing device 1 identifies the impression type "light" as a type of impression that has a predetermined relationship.

[0055] For example, the review comment of user U who gave an overall rating of "5" contains the term "light," but the other overall ratings do not contain the term "light." In this case, the information processing device 1 determines that the impression level of the impression type "light" estimated from the review comment of user U who gave the overall rating is lower for the higher overall rating value than for the lower overall rating value.

[0056] In the processing of step S5, the information processing device 1 identifies the impression type determined to be in a predetermined relationship as an appealing point of the new product or new service. For example, if the competing object or the specific trading object is a "rice cooker" and the impression type determined to be in a predetermined relationship in the processing of step S5 is "speed of cooking rice," the information processing device 1 identifies "speed of cooking rice" as an appealing point.

[0057] Furthermore, when the competing object or the specific trading object is a "rice cooker" and the impression type identified as being in a predetermined relationship in the processing of step S5 is "overflow," the information processing device 1 identifies "few overflows" as an appealing point.

[0058] The predetermined relationship may be, for example, a relationship in which the higher the overall evaluation (for example, the value of the overall evaluation), the lower the impression degree of the impression type estimated from the review comments.

[0059] Next, the information processing device 1 provides the business operator O with information indicating the appealing points of the new product or new service identified in the processing of step S5 (step S6). For example, the information processing device 1 provides the business operator O with information indicating the appealing points identified in the processing of step S5 by transmitting the information indicating the appealing points identified in the processing of step S5 to the terminal device 3 of the business operator O.

[0060] The information indicating the appealing points of a new product or service is, for example, information indicating the advertising concept of the new product or service, or information indicating the development concept of the new product or service.

[0061] In this way, the information processing device 1 estimates the type of impression the user has of the transaction object and the level of the user's impression for each impression type based on information about the user's behavior history with respect to the transaction object, and identifies impression types for which the evaluation indicated in the evaluation information and the impression level have a predetermined relationship. This allows the information processing device 1 to easily grasp the appealing points of the transaction object and to support the understanding of the appealing content of the transaction object to the user U.

[0062] The configuration of an information processing system including the information processing device 1, terminal device 2, and terminal device 3 that perform such processing will be described in detail below.

[0063] [2. Information Processing System Configuration] 2 is a diagram showing an example of the configuration of an information processing system according to the embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1 and a plurality of terminal devices 2.

[0064] The multiple terminal devices 2 are used by different users U. The terminal devices 2 are, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, but not limited to, smart glasses or a smart watch. The user U is a user who uses a service provided by the information processing device 1 or the like.

[0065] The multiple terminal devices 3 are used by different businesses O. The terminal devices 3 are, for example, notebook PCs, desktop PCs, smartphones, tablet PCs, etc., but are not limited to these examples.

[0066] The information processing device 1, the terminal device 2, and the terminal device 3 are connected to each other so as to be able to communicate with each other via a network N, either wired or wirelessly. Note that the information processing system 100 shown in FIG. 2 may include a plurality of information processing devices 1 and the like.

[0067] The network N includes, for example, a WAN (Wide Area Network) such as the Internet and a mobile communication network such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th generation mobile communication system).

[0068] The terminal devices 2 and 3 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.

[0069] 3. Configuration of Information Processing Device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0070] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a communication module or a network interface card (NIC). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from terminal devices 2 and 3 via the network N.

[0071] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 has a user information storage unit 20, a search history information storage unit 21, a question history information storage unit 22, and a posted information storage unit 23.

[0072] [3.2.1. User information storage unit 20] The user information storage unit 20 stores various types of information related to the user U. Fig. 4 is a diagram showing an example of a user information table stored in the user information storage unit 20 according to the embodiment.

[0073] 4, the user information table stored in the user information storage unit 20 includes information items such as "user ID (identifier)," "attribute information," and "setting information." The "user ID" is an identifier that identifies a user U, and is information assigned to each user U.

[0074] "Attribute information" is attribute information indicating the attributes of user U associated with "user ID." The attributes of user U include, for example, demographic attributes and psychographic attributes. Demographic attributes are demographic attributes and include multiple attribute items such as age, gender, occupation, place of residence, annual income, and family composition.

[0075] Psychographic attributes are psychological attributes and include, for example, multiple attribute items related to lifestyle, values, interests, etc. For example, each of the multiple attribute items in the psychographic attributes is an object of interest to user U, such as cars, clothes, travel, games, camping, motorcycles, trains, home appliances, or computers.

[0076] The "setting information" is information set in the information processing device 1 by the user U associated with the "user ID."

[0077] 3.2.2. Search History Information Storage Unit 21 The search history information storage unit 21 stores various information related to searches. For example, the search history information storage unit 21 stores information on search keywords related to transaction objects used in web searches for each transaction object.

[0078] The search keywords related to the transaction object used by the user U in the web search include, for example, a first keyword and a second keyword. The first keyword is a search keyword that is included in the same search query as a search keyword indicating the transaction object (for example, the name of the transaction object).

[0079] The second keyword is a search keyword other than the search keyword indicating the transaction object, which includes a search query including a search keyword indicating the transaction object and is included in multiple search queries transmitted from the terminal device 3 of the same user U within a predetermined time period. For example, the second keyword is a search keyword included in a search query transmitted from the terminal device 2 of the user U after a search query including a search keyword indicating the transaction object.

[0080] The search keywords related to the transaction object used by user U in a web search are, for example, search keywords related to the transaction object used by user U in a web search before the transaction of the transaction object. "Before the transaction" refers to the period from the time of the transaction to a predetermined period before.

[0081] The predetermined period differs for each transaction object or each category of transaction object, for example. Furthermore, a "transaction" refers to a reservation, order, or purchase of a product when the transaction object is a product, and to a purchase or use of a service when the transaction object is a service.

[0082] 3.2.3. Question History Information Storage Unit 22 The question history information storage unit 22 stores, for each transaction object, various types of question information about questions about the transaction object that the user U has asked in the Q&A service. The Q&A service is a service provided online.

[0083] A question about a transaction target that user U asks in the Q&A service is, for example, a question about a transaction target that user U asks in the Q&A service before the transaction of the transaction target. "Before the transaction" refers to a period from the time of the transaction to a predetermined period before.

[0084] The predetermined period differs for each transaction object or each category of transaction object, for example. Furthermore, a "transaction" refers to a reservation, order, or purchase of a product when the transaction object is a product, and to a purchase or use of a service when the transaction object is a service.

[0085] 3.2.4. Posted Information Storage Unit 23 The posted information storage unit 23 stores various types of posted information about transaction objects by the user U for each transaction object.

[0086] The posted information includes, for example, information such as review comments about the transaction object posted by the user U, and information indicating the evaluation of the transaction object (for example, overall evaluation, evaluation by item, etc.) posted by the user U. The items to be evaluated include, for example, at least one item corresponding to the impression type.

[0087] The user U's evaluation value for the transaction object is a five-point scale with a maximum of 5 points, but may be a four-point scale or less, or a six-point scale or more. The evaluation for the transaction object includes an overall evaluation value and an item-specific evaluation value. The item-specific evaluation value is, for example, an evaluation value for each impression type.

[0088] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the terminal device 2 using RAM as a working area.

[0089] The processing unit 12 may be partially or entirely realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0090] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, an estimation unit 32, an identification unit 33, and an output unit 34, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it performs the information processing described below.

[0091] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from external information processing devices and terminal devices 2 and 3 via the communication unit 10, and stores the acquired information in the storage unit 11.

[0092] For example, the acquisition unit 30 acquires user information, which is information about the user U, from an external information processing device or terminal device 2 via the communication unit 10, and adds the acquired user information to the user information table in the user information storage unit 20.

[0093] In addition, the acquisition unit 30 acquires search information, question information, posted information, etc. from an external information processing device, etc. via the communication unit 10, and stores the acquired information in the search history information storage unit 21, the question history information storage unit 22, and the posted information storage unit 23.

[0094] The acquisition unit 30 also acquires various types of information from the storage unit 11. For example, the acquisition unit 30 acquires user information, which is information about the user U, from the user information storage unit 20 or the like, and acquires search information from the search history information storage unit 21 or the like. The acquisition unit 30 also acquires question information from the question history information storage unit 22 or the like, and acquires posted information from the posted information storage unit 23 or the like.

[0095] For example, the acquisition unit 30 acquires evaluation information, which is information indicating an evaluation of the transaction target, from the posted information storage unit 23. One or more of the search information, the evaluation information, and the posted information are examples of information on the user U's behavior history with respect to the transaction target, and may be referred to as behavior history information hereinafter.

[0096] The acquiring unit 30 also acquires information including information indicating evaluations of the competing target as evaluation information from the posted information storage unit 23, etc. The acquiring unit 30 can also acquire information indicating evaluations of multiple trading targets included in a higher category that includes the competing target as evaluation information from the posted information storage unit 23, etc. For example, if the competing target is a rice cooker, the higher category would be a household appliance or a home appliance.

[0097] [3.3.2. Reception Unit 31] The reception unit 31 receives the designation of a competing object, which is a trading object that is in a competitive relationship with a specific trading object. A competing object is a trading object that competes with the specific trading object. The specific trading object is a new product or a new service, for example, a trading object that a business operator O plans to provide to a user U, or a trading object that a business operator O is providing to a user U.

[0098] The reception unit 31 receives the designation of a conflicting target from the operator O, for example, by receiving conflicting target designation information that is information transmitted from the terminal device 3 of the operator O and includes information on the conflicting target designated by the operator O.

[0099] [3.3.3. Estimation section 32] The estimation unit 32 estimates the type of impression that the user U has of the transaction object and the user's impression level for each impression type, based on the behavior history information acquired by the acquisition unit 30. For example, the estimation unit 32 estimates the type of impression that the user U has of a competing object and the user's impression level for each impression type.

[0100] The impression types include various types such as heavy, light, large, small, stylish, uncool, old-fashioned, simple, cute, refreshing, elegant, etc. The impression level indicates, for example, how strongly the user U thinks about it, but it may also indicate how good or bad the user thinks about it.

[0101] The estimation unit 32 can estimate the impression type and impression degree for each transaction object from the behavior history information using, for example, a distributed representation technology, an impression type dictionary, etc. Examples of the distributed representation technology include W2V, FastText, GloVe, and ELMo.

[0102] For example, the estimation unit 32 performs preprocessing to remove unnecessary numbers, symbols, words, etc. contained in the behavioral history information, and then converts each word contained in the preprocessed behavioral history information into a vector using distributed representation technology.

[0103] Then, the estimation unit 32 calculates, for example, the similarity between the vector of each predetermined impression type and the vector of each word (for example, a value obtained by multiplying the cosine similarity by a coefficient), and determines for each word vector whether the similarity with the vector of the impression type is within a threshold value.

[0104] For example, if there is an impression type for which the similarity between the vector of each predetermined impression type and the vector of each word (e.g., similarity with the vector of the word) is within a threshold, the estimation unit 32 determines that the user U has that impression type with respect to the transaction object. For example, the estimation unit 32 determines the similarity between the vector of each predetermined impression type and the vector of each word (e.g., the similarity between the vector of the word that has the highest similarity with the vector of the impression type that the user U has with respect to the transaction object) as the impression degree.

[0105] The estimation unit 32 can also input the vector of each word to a classifier that determines the impression type and impression degree, and estimate the impression type and impression degree for one or more impression types from the output result of the classifier. The classifier can be, for example, a decision tree, a random forest, a neural network, or the like, but is not limited to these examples.

[0106] For example, the estimation unit 32 uses a classifier to determine the highest impression degree for each impression type among the impression degrees for each word impression type, thereby estimating the user U's impression type and impression degree for each transaction object.

[0107] The estimation unit 32 can also estimate the impression type and impression degree for each transaction object from the behavior history information using an impression type dictionary. The impression type dictionary includes information on impression type words, which are words that indicate predetermined impression types, for each impression type.

[0108] For example, the estimation unit 32 calculates the number of appearances of impression-type words included in the behavior history information for each impression-type word. Then, the estimation unit 32 estimates the impression type and impression degree for each transaction object based on the number of appearances of each impression-type word. For example, the estimation unit 32 estimates the total number of appearances of impression-type words for each impression type as the impression degree for each impression type.

[0109] The impression-type dictionary may be a dictionary that includes, for each impression-type word, information associating impression-type words with impression values. In this case, the estimation unit 32 may estimate the impression degree for each impression type by multiplying the impression value by the total number of appearances of each impression-type word and adding up the multiplication results for each impression type. Note that the impression value may be a positive or negative value, but may not be a negative value.

[0110] Furthermore, the estimation unit 32 can also estimate the impression type and impression degree for each transaction object using a language model that performs natural language processing, such as GPT or BERT.

[0111] The estimation unit 32 can estimate the impression type and impression degree using information on all users U, or can perform a process of estimating the impression type and impression degree for each user U or for each attribute of user U for each transaction object.

[0112] Furthermore, for example, if the impression type is an impression related to the weight of the transaction object, it may be represented by an axis including "light" and "heavy." In this case, the estimation unit 32 can treat, for example, two mutually contradictory impression types among the plurality of impression types estimated as described above as one impression type.

[0113] For example, the estimation unit 32 treats two opposing impression types as one impression type based on words indicating impression types contained in review comments of each evaluation of the transaction object and words indicating impression types contained in each evaluation of a higher-level category of the transaction object.

[0114] For example, suppose the transaction object is a rice cooker, and the word "light" appears only in review comments with high ratings for the rice cooker, but the word "light" appears in review comments ranging from high to low ratings for household appliances, which is a higher category than rice cookers. In this case, the estimation unit 32 can treat the two mutually opposing impression types, "light" and "heavy," as a single impression type.

[0115] Furthermore, the estimation unit 32 can estimate an impression type for which the user U has a set ideal, or can estimate two opposing impression types for which the user U has a set ideal as one impression type for which the estimation unit 32 has a set ideal.

[0116] For example, when the estimation unit 32 estimates the impression type and impression degree based on review comments regarding a transaction object posted by a user U, the estimation unit 32 estimates the impression type and impression degree for each evaluation value (e.g., overall evaluation value) of the user U regarding the transaction object.

[0117] [3.3.4. Specification part 33] The specifying unit 33 specifies the type of impression for which the evaluation indicated by the evaluation information acquired by the acquiring unit 30 and the impression degree estimated by the estimating unit 32 have a predetermined relationship.

[0118] For example, the identification unit 33 identifies the impression type in which the evaluation indicated by the evaluation information and the impression level of the user U for the competing object have a predetermined relationship. The predetermined relationship is, for example, a condition in which the evaluation indicated by the evaluation information and the impression level of the user U for the impression type have an opposing relationship.

[0119] An opposing relationship is, for example, a relationship in which the evaluation for each item indicated in the evaluation information is greater than the median and the impression degree corresponding to such item is less than the median, or a relationship in which the evaluation for each item indicated in the evaluation information is less than the median and the impression degree corresponding to such item is greater than the median.

[0120] For example, if the transaction object is a rice cooker, and user U's evaluation of the item "overflow" is smaller than the median, and the impression degree of the impression type "overflow" is greater than the median, the identification unit 33 determines that there is a predetermined relationship, and also determines that there is a predetermined relationship if the opposite is true.

[0121] In addition, the identification unit 33 determines that there is a predetermined relationship if the transaction object is a rice cooker, the user U's evaluation of the item ``rice cooking speed'' is smaller than the median, and the impression level of the impression type ``rice cooking speed'' is greater than the median, and also determines that there is a predetermined relationship if the opposite is true.

[0122] Furthermore, the predetermined relationship may be a contradictory relationship between the evaluation for each item indicated in the evaluation information and the impression degree for the impression type corresponding to such item, and further, a condition such that the difference between the evaluation for each item indicated in the evaluation information and the impression degree for the impression type corresponding to such item is greater than or equal to a threshold value.

[0123] In addition, the identification unit 33 can also identify an impression type in which the difference between the evaluation for each item indicated in the evaluation information and the impression degree of the impression type corresponding to that item is greater than or equal to a threshold value as an impression type having a predetermined relationship.

[0124] For example, the identification unit 33 identifies, as an impression type having a predetermined relationship, an impression type for which the evaluation for each item indicated in the evaluation information is higher than the degree of impression of the user U by a threshold or more. For example, suppose that the evaluation of the item "heavy" by the user U is "4," the degree of impression of the user U for the impression type "heavy" is "2," and the threshold is "2." In this case, the identification unit 33 identifies the impression type "heavy" as an impression type having a predetermined relationship.

[0125] Furthermore, the specifying unit 33 can specify an impression type whose impression degree is higher than the evaluation for each item indicated in the evaluation information by a threshold or more as an impression type having a predetermined relationship. For example, assume that the evaluation of the item "heavy" by the user U is "3," the degree of the user U's impression of the impression type "heavy" is "5," and the threshold is "2." In this case, the specifying unit 33 specifies the impression type "heavy" as an impression type having a predetermined relationship.

[0126] The specification unit 33 can also change the above-mentioned threshold value according to the attributes of the poster, who is the user U who posted the review comment. For example, if the transaction object is a rice cooker, the impression type is "rice cooking speed," and the poster has family members living with them, the specification unit 33 decreases the threshold value according to the number of family members. The specification unit 33 can also change the above-mentioned threshold value for each category of the transaction object.

[0127] Furthermore, the predetermined relationship (e.g., an opposing relationship) may be a relationship in which a higher overall rating (e.g., the overall rating value) indicates a lower impression level of the impression type estimated from the review comments than a lower overall rating (e.g., the overall rating value).

[0128] For example, if the transaction object is a rice cooker and the impression level of the impression type "light" estimated from the review comments of user U who gave the overall evaluation is lower for a product with a higher overall evaluation value than for a product with a lower overall evaluation value, the identification unit 33 identifies the impression type "light" as a type of impression having a predetermined relationship.

[0129] For example, the review comment of user U who gave an overall rating of "5" (five points) contains the term "light," but the other overall ratings do not contain the term "light." In this case, the specifying unit 33 determines that the impression level of the impression type "light" estimated from the review comment of user U who gave the overall rating is lower for a higher overall rating value than for a lower overall rating value.

[0130] The identification unit 33 identifies the impression type determined to be in a predetermined relationship as an appealing point of the new product or new service. For example, if the competing object or the specific trading object is a "rice cooker" and the impression type identified in step S5 to be in a predetermined relationship is the impression type "speed of cooking rice," the identification unit 33 identifies "speed of cooking rice" as an appealing point.

[0131] Furthermore, when the competing object or the specific trading object is a "rice cooker" and the impression type identified as being in a predetermined relationship is the impression type "overflow," the identification unit 33 identifies "few overflows" as an appealing point.

[0132] The predetermined relationship may be, for example, a relationship in which the higher the overall evaluation (for example, the value of the overall evaluation), the lower the impression degree of the impression type estimated from the review comments.

[0133] [3.3.5. Output section 34] The output unit 34 outputs information on the type of impression identified by the identification unit 33. For example, the information processing device 1 provides the information on the appeal points identified by the identification unit 33 to the business operator O by transmitting the information on the appeal points identified by the identification unit 33 to the terminal device 3 of the business operator O.

[0134] The information indicating the appealing points of the new product or service is, for example, information indicating the advertising concept of the new product or service, information indicating the development concept of the new product or service, etc. In this way, the output unit 34 can output the information on the impression type identified by the identification unit 33 as information indicating the concept of the new product.

[0135] For example, when the specification unit 33 specifies that "rice is cooked quickly" is an appealing point, the output unit 34 outputs information indicating the character string "rice is cooked quickly" as information indicating the appealing point.

[0136] [4. Processing Procedure] Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 5 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0137] 5, the processing unit 12 of the information processing device 1 determines whether or not the estimation timing has arrived (step S10). The estimation timing is, for example, a timing that arrives at a predetermined cycle, but is not limited to this example.

[0138] When the processing unit 12 determines that the estimation timing has arrived (step S10: Yes), it acquires behavior history information (step S11) and estimates the impression type and the impression degree based on the acquired behavior history information (step S12).

[0139] When the processing of step S12 is completed or when it is determined that the estimation timing has not arrived (step S10: No), the processing unit 12 determines whether or not the designation of a conflict target has been accepted (step S13).

[0140] When the processing unit 12 determines that the designation of a competing target has been accepted (step S13: Yes), the processing unit 12 acquires evaluation information for the competing target (step S14) and identifies impression types having a predetermined relationship (step S15). Then, the processing unit 12 provides the information on the impression types identified in step S15 to the business operator O (step S16).

[0141] When the processing of step S16 is completed or when it is determined that the designation of the conflict target has not been accepted (step S13: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S17). The processing unit 12 determines that the operation end timing has arrived when, for example, the power of the information processing device 1 is turned off.

[0142] If the processing unit 12 determines that the operation end time has not yet arrived (step S17: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S17: Yes), it terminates the processing shown in Figure 5.

[0143] [5. Modifications] In the above example, the identification unit 33 identifies the appealing points of a specific transaction object based on the degree of impression of the user U on a competing object designated by the business operator O, but the present invention is not limited to such an example. For example, the identification unit 33 can also identify the appealing points of a specific transaction object based on the degree of impression of the user U on a transaction object designated by the business operator O.

[0144] In addition, when multiple transaction objects are specified by business operator O, the identification unit 33 can also identify the appealing points of the category to which these multiple transaction objects belong based on the degree of impression that user U has of the multiple transaction objects specified by business operator O.

[0145] For example, the identification unit 33 identifies the type of impression in which the impression degrees of the multiple transaction objects estimated by the estimation unit have the above-mentioned predetermined relationship with the evaluations indicated in the evaluation information of the multiple transaction objects acquired by the acquisition unit 30.

[0146] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 80 configured as shown in Fig. 6. Fig. 6 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0147] The CPU 81 operates and controls each part based on programs stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 starts up, programs that depend on the hardware of the computer 80, and the like.

[0148] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0149] The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard or a mouse, via the input / output interface 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs generated data to the output devices via the input / output interface 86.

[0150] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program or data from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0151] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes programs loaded onto the RAM 82 to realize the functions of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, the CPU 81 may obtain these programs from another device via the network N.

[0152] [7. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0153] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0154] For example, the information processing device 1 described above may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Furthermore, depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0155] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0156] [8. Effects] As described above, the information processing device 1 according to the embodiment includes an estimation unit 32 that estimates the type of impression of the user U with respect to the transaction object and the user U's impression level for each type based on information on the user U's behavioral history with respect to the transaction object, an acquisition unit 30 that acquires evaluation information that is information indicating an evaluation of the transaction object, and an identification unit 33 that identifies an impression type having a predetermined relationship between the evaluation indicated in the evaluation information acquired by the acquisition unit 30 and the impression level estimated by the estimation unit 32. This allows the information processing device 1 to support understanding of the appeal content of the transaction object to the user.

[0157] The information processing device 1 also includes a receiving unit 31 that receives the designation of a competing target, which is a trading target that is in a competitive relationship with a specific trading target, an estimation unit 32 that estimates the type of impression of the user U with respect to the competing target and the user U's impression level for each type, an acquisition unit 30 that acquires information including information indicating an evaluation of the competing target as evaluation information, and an identification unit 33 that identifies the impression type in which the evaluation of the competing target and the impression level for the competing target have a predetermined relationship. This allows the information processing device 1 to support the understanding of the appeal to users of new products, new services, etc.

[0158] Furthermore, the identification unit 33 identifies impression types in which the evaluation and the impression degree have a contradictory relationship as impression types having a predetermined relationship, thereby enabling the information processing device 1 to more accurately support understanding of the appeal content of the transaction object to the user.

[0159] Furthermore, the identification unit 33 identifies the impression type whose evaluation is higher than the impression degree by a threshold or more as the impression type having a predetermined relationship. This allows the information processing device 1 to more accurately support understanding of the appeal content to the user of the transaction object.

[0160] Furthermore, the identification unit 33 identifies the impression type whose impression degree is higher than the evaluation by a threshold or more as the impression type having a predetermined relationship. This allows the information processing device 1 to more accurately support understanding of the appeal content to the user of the transaction object.

[0161] The estimation unit 32 estimates the impression degree for each evaluation value of the transaction object, and the identification unit 33 identifies the impression type in which the impression degree is lower for a higher evaluation value than for a lower evaluation value as the impression type having a predetermined relationship. This enables the information processing device 1 to more accurately support the understanding of the appeal content of the transaction object to the user.

[0162] Furthermore, the specifying unit 33 specifies the impression type for which the difference between the evaluation and the impression degree is equal to or greater than a threshold value as the impression type having a predetermined relationship.

[0163] The information processing device 1 also includes an output unit 34 that outputs information on the impression type identified by the identification unit 33. This allows the information processing device 1 to better support understanding of the appeal content to users of the transaction object.

[0164] Furthermore, the output unit 34 outputs information on the impression type identified by the identification unit 33 as information indicating the concept of the new product. This allows the information processing device 1 to better support understanding of the appeal content to users of the transaction target.

[0165] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0166] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0167] 1. Information processing equipment 2,3 Terminal equipment 10. Communications Department 11 Storage section 12 Processing section 20 User information storage unit 21 Search history information storage unit 22 Question history information storage unit 23 Posted information storage unit 30 Acquisition Department 31 Reception 32 Estimation part 33 Specific part 34 Output section 100 Information Processing Systems N Network

Claims

1. an estimation unit that estimates the type of impression of the user with respect to the transaction object and the degree of impression of the user for each type based on information on the user's behavior history with respect to the transaction object; an acquisition unit that acquires evaluation information that indicates an evaluation by a user of the transaction object; an identification unit that identifies a type of impression having a predetermined relationship between the evaluation indicated in the evaluation information acquired by the acquisition unit and the impression degree estimated by the estimation unit, The estimation unit a similarity between a vector of each word included in the behavior history information and a vector of each impression type is calculated, an impression type for which the similarity with the vector of the word is within a threshold is estimated as a type of impression of the user, and the similarity for that type is estimated as a degree of impression of the user for that type; The identification unit The type of impression in which the value indicated by the evaluation and the impression degree are in a relationship in which one is higher and the other is lower based on their respective medians is identified as the type of impression having the predetermined relationship.

1. An information processing device comprising:

2. A reception unit for receiving the designation of the transaction object is provided.

2. The information processing apparatus according to claim 1, wherein:

3. The identification unit Identifying the impression type whose evaluation is higher than the impression degree by a threshold or more as the impression type having the predetermined relationship.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. The identification unit Identifying the impression type whose impression degree is higher than the evaluation by a threshold or more as the impression type having the predetermined relationship.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

5. The estimation unit estimating the impression level for each evaluation value of the transaction object; The identification unit The impression type in which the impression degree is lower for the higher evaluation value than for the lower evaluation value is identified as the impression type having the predetermined relationship.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

6. The identification unit Identifying the impression type for which the difference between the evaluation and the impression degree is equal to or greater than a threshold as the impression type having the predetermined relationship.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

7. an output unit that outputs information about the type of impression identified by the identification unit; 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

8. The output unit The information on the type of impression identified by the identification unit is output as information indicating a concept of a new product.

8. The information processing apparatus according to claim 7,

9. A computer-implemented information processing method, comprising: an estimation step of estimating the type of impression of the user with respect to the transaction object and the degree of impression of the user for each type based on information on the user's behavior history with respect to the transaction object; an acquisition step of acquiring evaluation information which is information indicating an evaluation by a user of the object of transaction; a specifying step of specifying a type of impression having a predetermined relationship between the evaluation indicated by the evaluation information acquired in the acquiring step and the impression degree estimated in the estimating step, The estimation step includes: a similarity between a vector of each word included in the behavior history information and a vector of each impression type is calculated, an impression type for which the similarity with the vector of the word is within a threshold is estimated as a type of impression of the user, and the similarity for that type is estimated as a degree of impression of the user for that type; The identifying step includes: The type of impression in which the value indicated by the evaluation and the impression degree are in a relationship in which one is higher and the other is lower based on their respective medians is identified as the type of impression having the predetermined relationship. An information processing method comprising:

10. an estimation step of estimating the type of impression of the user with respect to the transaction object and the degree of impression of the user for each type based on information on the user's behavior history with respect to the transaction object; an acquisition step of acquiring evaluation information which is information indicating an evaluation by a user of the trading object; a specifying step of specifying an impression type having a predetermined relationship between the evaluation indicated by the evaluation information acquired by the acquisition step and the impression degree estimated by the estimation step; The estimation procedure comprises: a similarity between a vector of each word included in the behavior history information and a vector of each impression type is calculated, an impression type for which the similarity with the vector of the word is within a threshold is estimated as a type of impression of the user, and the similarity for that type is estimated as a degree of impression of the user for that type; The identification procedure includes: The type of impression in which the value indicated by the evaluation and the impression degree are in a relationship in which one is higher and the other is lower based on their respective medians is identified as the type of impression having the predetermined relationship. An information processing program characterized by:

Images