Information providing device, information providing method, and information providing program

Abstract

To provide an information providing apparatus capable of providing useful information on a user, an information providing method, and an information providing program.SOLUTION: An information providing apparatus 10 includes a collection unit and a calculation unit. The collection unit collects user information (S1). The calculation unit calculates, on the basis of the user information, reliability on a transaction target of a second user having a relationship with a first user who has purchased the transaction target (S5).SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] In recent years, with the rapid spread of the Internet, analytical techniques using various information on the Internet have been provided. For example, techniques are known that analyze customers (referred to as "users" as appropriate) by taking into account trends over time using purchase history data, etc. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-146145 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional techniques have room for improvement in terms of providing useful information about users.

[0005] The present application has been made in view of the above, and aims to provide an information providing device, an information providing method, and an information providing program that are capable of providing useful information about a user. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objectives, the information providing device of the present invention is characterized by comprising a collection unit that collects user information, and a calculation unit that calculates, based on the user information, the reliability of a second user who has a relationship with a first user who performed a purchasing behavior of the transaction target with respect to the transaction target.

[0007] In addition, the information provision method of the present invention is an information provision method executed by an information provision device, and is characterized by including a collection step of collecting user information, and a calculation step of calculating, based on the user information, the reliability of a second user who has a relationship with a first user who performed a purchasing behavior of the transaction target with respect to the transaction target.

[0008] In addition, the information provision program of the present invention is characterized in that it causes a computer to execute a collection procedure for collecting user information and a calculation procedure for calculating, based on the user information, the trustworthiness of a second user who has a relationship with a first user who performed a purchasing behavior of the transaction target with respect to the transaction target. [Effects of the Invention]

[0009] The present invention can provide useful information about the user. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an example of processing of an information providing system according to an embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of the configuration of the information providing device according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a user information storage unit according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a reliability information storage unit according to the embodiment. [Figure 5] FIG. 5 is a diagram showing a specific example 1 of the reliability calculation process according to the embodiment. [Figure 6] FIG. 6 is a diagram showing a specific example 2 of the reliability calculation process according to the embodiment. [Figure 7] FIG. 7 is a diagram illustrating a specific example 3 of the reliability calculation process according to the embodiment. [Figure 8] FIG. 8 is a diagram showing a specific example 4 of the reliability calculation process according to the embodiment. [Figure 9] FIG. 9 is a flowchart showing an example of the flow of the information providing process according to the embodiment. [Figure 10] FIG. 10 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an information providing device, an information providing method, and an information providing program according to the present application (hereinafter, referred to as an embodiment) will be described in detail with reference to the drawings. Note that the information providing device, the information providing method, and the information providing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0012] [Embodiment] The following describes the processing of the information providing system 100 according to the embodiment, the configuration of the information providing device 10, a specific example of the reliability calculation processing, and the flow of the information providing processing, and finally the effects of the embodiment.

[0013] [1. Processing of information provision system 100] The processing of an information providing system (referred to as the present system, as appropriate) 100 according to the embodiment will be described using Fig. 1. Fig. 1 is a diagram showing an example of the processing of the information providing system according to the embodiment. Below, an example of the configuration of the present system 100, the processing of the present system 100, and the effects of the present system 100 will be described in that order.

[0014] (1-1. Example of the configuration of the system 100) The information providing system 100 shown in FIG. 1 includes an information providing device 10 and user terminals 20 (first user terminal 20A, second user terminal 20B). Here, the information providing device 10 and the user terminals 20 are connected to each other via a predetermined communication network (not shown) so as to be able to communicate with each other via wired or wireless communication. Similarly, the first user terminal 20A and the second user terminal 20B are connected to each other via a predetermined communication network (not shown) so as to be able to communicate with each other via wired or wireless communication. Note that the system 100 may include multiple information providing devices 10.

[0015] (1-1-1. Information provision device 10) The information providing device 10 is a device that transmits and receives data to and from user terminals 20 (20A, 20B), and is realized, for example, by a server device, a cloud system, etc. The example in Fig. 1 shows a case where the information providing device 10 is realized by a server device.

[0016] (1-1-2. User terminal 20) The user terminals 20 (20A, 20B) are devices (computers) used by users U (first user UA, second user UB) to browse web pages, conduct internet shopping on the web, etc. The first user terminal 20A accepts operations by the first user UA. The second user terminal 20B accepts operations by the second user UB. The user terminals 20 may be realized, for example, by smartphones, tablet terminals, notebook PCs (Personal Computers), desktop PCs, mobile phones, PDAs (Personal Digital Assistants), etc. The example in FIG. 1 shows a case where the user terminal 20 is realized by a smartphone.

[0017] (1-2. Processing of the System 100) (1-2-1. Processing of step S1) In the present system 100, first, the information providing device 10 collects user information of the first user UA from the first user terminal 20A (step S1). Here, the user information is information about the user U of the present system 100, including, for example, registration information, history information, location information, etc. The registration information includes user attributes such as the user U's gender, age, generation, occupation, annual income, place of residence, marital status, and whether or not they have children, as well as information about the user U's social relationships with acquaintances, friends, and communities to which they belong. History information includes purchase history, browsing history, search history, communication history, etc. Location information is information about the user U's location, movements, etc., acquired by the user terminal 20. Furthermore, the user information may be information including screen information, biometric information, etc., of the user terminal 20, and is not particularly limited. In the example of FIG. 1, the information providing device 10 acquires the user information of the first user UA from the first user terminal 20A. However, the information providing device 10 may acquire the user information of the first user UA from the user U's terminal 20A, or from other terminals, databases, etc. (not shown).

[0018] (1-2-2. Processing of step S2) Secondly, in the present system 100, the information providing device 10 determines whether or not the user UA has made a purchase of the transaction object from the collected user information of the first user UA (step S2). That is, the information providing device 10 uses history information such as browsing history and purchase history of multiple users U to acquire primary information such as advertisements recommending the transaction object from a predetermined medium, and then identifies the first user UA who purchased the transaction object. Here, the medium providing the primary information may be, but is not limited to, web advertisements, people, SNS (Social Networking Service), etc.

[0019] (1-2-3. Processing of step S3) Thirdly, in the present system 100, the information providing device 10 collects user information of the second user UB from the second user terminal 20B (step S3). In the example of Fig. 1, the information providing device 10 acquires the user information of the second user UB from the second user terminal 20B, but it may also acquire the user information from the terminal of user U (not shown), other terminals, databases, etc.

[0020] (1-2-4. Processing of step S4) Fourth, in the present system 100, the information providing device 10 determines whether or not the second user UB has recommended a transaction object to the first user UA from the collected user information of the second user UB (step S4). That is, the information providing device 10 uses the registration information, history information such as communication history, and location information of multiple users U to identify the second user UB who provided secondary information, such as a message recommending the transaction object to the first user UA, before the first user UA purchased the transaction object. Here, the secondary information may be, but is not limited to, communication or phone calls using the user terminal 20, as well as face-to-face conversations.

[0021] (1-2-5. Processing of step S5) Fifth, in the system 100, the information providing device 10 calculates the trustworthiness of the second user UB from the collected user information (step S5). Here, the trustworthiness is a numerical representation of the degree of support for the second user UB's purchasing behavior toward the first user UA who performed the purchasing behavior of the transaction target. For example, the information providing device 10 uses a machine learning model based on the registration information, history information, location information, etc. of the user U (UA, UB) to calculate the trustworthiness so that it takes a value between 0 and 1 depending on the degree of influence of the second user UB on the first user UA. For example, when the registration information, history information, and location information of the user U are input, the information providing device 10 calculates the trustworthiness using a machine learning model such as a DNN (Deep Neural Network) that is trained to output the trustworthiness of each second user UB who has a relationship with the first user UA. Alternatively, the information providing device 10 may calculate the trustworthiness based on rules.

[0022] The above-mentioned step S5 will be described using a specific example. In the following, an example will be described in which a first user UA acquires primary information about a product X, acquires secondary information about the product X from a second user UB, and finally purchases the product X.

[0023] For example, if the second user UB owns product X, the information providing device 10 determines that the second user UB is trustworthy and calculates a high level of trustworthiness. Furthermore, if the second user UB has a deep understanding of product X, the information providing device 10 determines that the second user UB is trustworthy and calculates a high level of trustworthiness. Furthermore, the information providing device 10 calculates the level of trustworthiness based on the frequency of messages between the first user UA and the second user UB using their user terminals, the number of times product X appears in messages and calls, and other factors. Furthermore, the information providing device 10 calculates the level of trustworthiness based on the number of contacts, contact duration, contact frequency, and other factors between the first user UA and the second user UB. Furthermore, if the first user UA's probability of purchasing product X before purchasing it is low or if the time between obtaining secondary information and purchasing product X is short, the information providing device 10 determines that the influence of the second user UB is large and calculates a high level of trustworthiness. Furthermore, the information providing device 10 calculates the level of trustworthiness based on the number of first users UA to whom the second user UB has provided secondary information about product X.

[0024] (1-2-6. Processing of step S6) In the present system 100, sixthly, the information providing device 10 transmits the provided information to the second user terminal 20B of the identified second user UB (step S6). Using the example of step S5 above, for example, the information providing device 10 transmits an advertisement recommending a related product Y of product X to the second user UB. The information providing device 10 may also transmit a benefit such as a discount coupon for product X or related product Y to the second user UB.

[0025] (1-2-7. Processing of step S7) Seventh, in the present system 100, the information providing device 10 learns the calculated reliability (step S7). For example, when information (registration information, history information, location information) indicating support for the second user UB from the first user UA is input to the machine learning model, the information providing device 10 learns using backpropagation or the like so as to output the reliability of the second user UB as a numerical value approaching "1."

[0026] (1-3. Effects of System 100) In this system 100, the information providing device 10 collects user information about a user U (UA, UB) via a user terminal 20 (20A, 20B), and calculates the trustworthiness of a second user UB who has a relationship with a first user UA who has made a purchase of the transaction target based on the collected user information. Therefore, this system 100 can discover individuals within a community who can boost the trustworthiness of primary information disseminated by media, etc. Furthermore, this system 100 can estimate real word-of-mouth disseminated within a community.

[0027] Furthermore, the system 100 calculates the reliability of a transaction target of a second user UB who has a relationship with a first user UA who performed a purchasing behavior for the transaction target, based on the registration information, history information, or location information of each user indicated in the collected user information. At this time, the information providing device 10 identifies the first user UA who performed a purchasing behavior after obtaining primary information recommending the transaction target from a predetermined media, based on the registration information, history information, or location information of each user indicated in the user information, and identifies the second user UB who provided secondary information recommending the transaction target to the first user UA before the purchasing behavior. Therefore, the system 100 can accurately identify follow-up users who are likely to provide information that will lead to the conversion of the impression target by a user who has impressed the primary information.

[0028] 2. Configuration of Information Providing Device 10 The configuration of the information providing device 10 according to the embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the configuration of the information providing device 10 according to the embodiment. As shown in Fig. 2, the information providing device 10 includes a communication unit 11, a storage unit 12, and a control unit 13. The information providing device 10 may also include an input unit (e.g., a keyboard, a mouse, etc.) that accepts various operations from an administrator of the information providing device 10, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0029] (2-1. Communications Department 11) The communication unit 11 is realized by, for example, a network interface card (NIC), etc. The communication unit 11 is connected to a predetermined communication network by wire or wirelessly, and transmits and receives information to and from various devices.

[0030] (2-2. Storage section 12) The storage unit 12 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. As shown in Fig. 2, the storage unit 12 according to the embodiment has a user information storage unit 12a and a reliability storage unit 12b. The storage unit 12 stores various types of information referenced when the control unit 13 operates and various types of information acquired when the control unit 13 operates.

[0031] (2-2-1. User information storage unit 12a) The user information storage unit 12a stores various types of information (user information) related to the user U (UA, UB). Here, an example of information stored in the user information storage unit 12a will be described with reference to FIG. 3. FIG. 3 is a diagram showing an example of the user information storage unit 12a according to the embodiment. In the example of FIG. 3, the user information storage unit 12a has items such as "user ID," "registration information," "history information," and "location information."

[0032] "User ID" indicates identification information for identifying user U. "Registration information" includes user attributes such as user U's gender, age, generation, occupation, annual income, place of residence, marital status, and whether or not they have children, as well as information about user U's social relationships with acquaintances, friends, and communities to which they belong. "History information" includes information such as purchase history, browsing history, search history, and communication history. "Location information" is information about user U's location, movements, etc., acquired by user terminal 20.

[0033] That is, FIG. 3 shows an example in which, for user U identified by user ID "UID#1", the registration information is "registration information #1", the history information is "history information #1", and the location information is "location information #1".

[0034] (2-2-2. Reliability information storage unit 12b) The reliability information storage unit 12b stores the reliability (reliability information) for each second user UB that is related to the first user UA, calculated by the calculation unit 13c of the control unit 13. Here, an example of information stored in the reliability information storage unit 12b will be described with reference to FIG. 4. FIG. 4 is a diagram showing an example of the reliability information storage unit 12b according to the embodiment. In the example of FIG. 4, the reliability information storage unit 12b has items such as "first user ID," "second user ID," and "reliability."

[0035] "First user ID" indicates identification information for identifying the first user UA. "Second user ID" indicates identification information for identifying the second user UB. "Trustworthiness" indicates the degree of influence that the second user UB has on the purchasing behavior of the first user UA, and is a numerical value calculated for each transaction object, such as a product or service, or the classification or category in which the transaction object is included.

[0036] That is, Figure 4 shows an example in which, for a first user UA identified by a first user ID "UAID#1", the trustworthiness of a second user UB identified by a second user ID "UBID#1" is "trustworthiness #1", and the trustworthiness of a second user UB identified by a second user ID "UBID#2" is "trustworthiness #2".

[0037] (2-3. Control unit 13) The control unit 13 is realized by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information providing device 10 using RAM as a work area. The control unit 13 is also realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0038] As shown in Fig. 2, the control unit 13 has a collection unit 13a, an identification unit 13b, a calculation unit 13c, a transmission unit 13d, and a learning unit 13e, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the control unit 13 is not limited to the configuration shown in Fig. 2, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationship between the processing units included in the control unit 13 is not limited to the connection relationship shown in Fig. 2, and may be other connection relationships.

[0039] (2-3-1. Collection unit 13a) The collection unit 13a collects user information related to a user U (UA, UB). For example, the collection unit 13a collects, as user information, registration information, history information, location information, etc. of the user U from the user terminal 20 of the user U. The collection unit 13a stores the collected user information in the user information storage unit 12a.

[0040] (2-3-2. Specific part 13b) The identification unit 13b identifies a first user UA who performed a purchasing behavior after obtaining first recommendation information (primary information) recommending a transaction target from a predetermined medium based on the registration information, history information, or location information of each user indicated in the user information, and identifies a second user UB who provided second recommendation information (secondary information) recommending a transaction target to the first user UA before the purchasing behavior. For example, the identification unit 13b uses the first user UA's purchase history, search history, browsing history, etc. to identify the first user UA's behavior of obtaining primary information about the transaction target and the first user UA's purchasing behavior of the transaction target. Furthermore, the identification unit 13b uses the first user UA's registration information, communication history, location information, etc. to identify the second user UB's behavior of providing secondary information about the transaction target.

[0041] (2-3-3. Calculation unit 13c) The calculation unit 13c calculates the reliability of the transaction object of a second user UB who has a relationship with a first user UA who has performed a purchasing behavior of the transaction object based on the user information. For example, the calculation unit 13c calculates the reliability of the transaction object for each second user UB who has a relationship with the first user UA using the user information such as registration information, history information, or location information of the user U. Furthermore, the calculation unit 13c may calculate the reliability for each category of the transaction object.

[0042] To explain the calculation method, the calculation unit 13c calculates the reliability using a machine learning model such as a DNN that is trained to output the reliability of each second user UB having a relationship with the first user UA when the registration information, history information, and location information of the user U are input. The calculation unit 13c may also calculate the reliability on a rule basis.

[0043] Regarding the calculated numerical values, the calculation unit 13c calculates the reliability so that it takes a numerical value between 0 and 1 depending on the credibility and influence of each second user UB. Furthermore, the calculation unit 13c may calculate the reliability so that it takes a numerical value between 0 and 100% depending on the credibility and influence of each second user UB, and the range and unit of the calculated numerical values ​​are not particularly limited.

[0044] Regarding the information used for the calculation, the calculation unit 13c calculates the reliability based on whether the second user UB owns the transaction object. For example, the calculation unit 13c uses the purchase history of the second user UB to determine whether the second user UB owns the transaction object recommended in the secondary information, and calculates the reliability based on the determination result. That is, the calculation unit 13c calculates a high reliability if it determines that the second user UB owns the transaction object, and calculates a low reliability if it determines that the second user UB does not own the transaction object.

[0045] Furthermore, the calculation unit 13c calculates the reliability based on the second user UB's level of understanding of the transaction target. For example, the calculation unit 13c calculates the second user UB's level of understanding of the transaction target recommended by the secondary information using the second user UB's registered information such as user attributes, purchase history, search history, browsing history, etc., and calculates the reliability based on the calculated level of understanding.

[0046] Furthermore, the calculation unit 13c calculates the reliability based on communication between the first user UA and the second user UB using the terminals. For example, the calculation unit 13c uses the communication history between the first user UA and the second user UB to calculate the frequency of communication and the number of times the transaction object appears in the communication data, such as sent and received text data, video data, and audio data, and calculates the reliability based on the calculation result.

[0047] Furthermore, the calculation unit 13c calculates the reliability based on contact behavior indicated by the position information of the first user UA and the second user UB. For example, the calculation unit 13c calculates the number of contacts, contact time, contact frequency, etc. between the first user UA and the second user UB using the position information of the first user UA and the second user UB, and calculates the reliability based on the calculation result.

[0048] Furthermore, the calculation unit 13c calculates the reliability based on history information before the first user UA makes a purchase. For example, the calculation unit 13c uses the purchase history, search history, browsing history, communication history, location information, etc. of the first user UA and the second user UB to calculate the probability of the first user UA purchasing the transaction target when the primary information was acquired and the time from the first user UA acquiring the secondary information to the purchasing behavior, and calculates the reliability based on the calculation results. That is, if the probability of the first user UA purchasing the transaction target when the primary information was acquired is low or if the time from the secondary information acquisition to the purchasing behavior is short, the calculation unit 13c determines that the secondary information was effective and calculates a high reliability.

[0049] Furthermore, the calculation unit 13c calculates the reliability based on the number of first users UA to whom the second user UA provided secondary information. For example, the calculation unit 13c uses registration information, purchase history, search history, browsing history, communication history, location information, etc. of the first user UA and the second user UB to calculate the number of first users UA to whom the second user UB provided secondary information about the transaction target and who took purchasing action for the transaction target, and calculates the reliability based on the calculation result.

[0050] The calculation unit 13c acquires the user information from the user information storage unit 12a. Meanwhile, the calculation unit 13c stores the calculated reliability in the reliability information storage unit 12b.

[0051] (2-3-4. Transmitting unit 13d) The transmitting unit 13d transmits the provided information to the second user UB based on the reliability calculated by the calculating unit 13c. For example, the transmitting unit 13d generates, as the provided information, an advertisement recommending a transaction object related to the transaction object (e.g., a variation product, a product in the same category), and transmits the generated information to the second user UB. The transmitting unit 13d can also obtain, as the provided information, a discount coupon to be used for online shopping, and transmit the obtained information to the second user UB. The transmitting unit 13d may store the generated and obtained provided information in the storage unit 12.

[0052] (2-3-5. Learning section 13e) The learning unit 13e learns the machine learning model so that, when the user information of the user U (UA, UB) is input, the reliability of the transaction object for each second user UB having a relationship with the first user UA is output. At this time, the learning unit 13e may learn the machine learning model by backpropagation or the like.

[0053] For example, when information that the second user UB owns the transaction object is input into the machine learning model, the learning unit 13e trains the machine learning model so that the reliability of the second user UB is output as a number approaching "1".

[0054] In addition, the learning unit 13e learns the machine learning model so that when information indicating that the second user UB has a high level of understanding of the transaction object is input to the machine learning model, the reliability of the second user UB is output as a number approaching "1".

[0055] In addition, when information such as the frequency of messages between the first user UA and the second user UB using the user terminals, or the number of times the transaction target appears in messages or calls, is input into the machine learning model, the learning unit 13e trains the machine learning model so that the larger the input number, the closer the reliability of the second user UB to "1" is output.

[0056] In addition, when information such as the number of contacts, contact time, and contact frequency between the first user UA and the second user UB is input into the machine learning model, the learning unit 13e learns the machine learning model so that the larger the input number, the closer the reliability of the second user UB to "1" is output.

[0057] In addition, when information such as the probability of purchasing the transaction target at the time the first user UA obtains the primary information or the time from when the first user UA obtains the secondary information to when the purchasing behavior occurs is input into the machine learning model, the learning unit 13e trains the machine learning model so that the larger the input number, the closer the reliability of the second user UB to "0" is output.

[0058] In addition, when the second user UB provides secondary information about the transaction object and information such as the number of first users UA who have taken purchasing action for the transaction object is input into the machine learning model, the learning unit 13e trains the machine learning model so that the larger the input number, the closer the reliability of the second user UB to "1" is output.

[0059] [3. Specific example of reliability calculation process] A specific example of the reliability calculation process according to the embodiment will be described in detail with reference to Fig. 5 to Fig. 8. Fig. 5 to Fig. 8 are diagrams showing a specific example of the reliability calculation process according to the embodiment.

[0060] (3-1. Example 1) A specific example 1 of the reliability calculation process will be described with reference to Fig. 5. In the following, an example will be described in which a first user UA1 does not own a product G1, which is a smartphone, and a second user UB1 owns the product G1.

[0061] As shown in FIG. 5, first, the information providing device 10 determines that the first user UA1 has come into contact with primary information about the product G1 transmitted through web advertisements, personal information, or SNS (see FIG. 5(1)). Next, the information providing device 10 determines that the first user UA1 does not own the product G1 (see FIG. 5(2)). Then, if the first user UA1 has come into contact with the second user UB1 and the first user UA1 has purchased the product G1, the information providing device 10 presumes that the second user UB1 has recommended the product G1 to the first user UA1 (provided secondary information) (see FIG. 5(3)). Therefore, the information providing device 10 determines that the second user UB1 is trustworthy from the first user UA1's perspective and calculates a high trustworthiness (e.g., second user UB1 [0.90]).

[0062] As shown in the above specific example 1, it is common for a review of a product owned by a friend or the like to encourage purchasing behavior. Therefore, the information providing device 10 can score the reliability of the second user UB1 by determining that the second user UB1 has encouraged (recommended) the first user UA1, who has left an impression on the primary information, to purchase a product based on the relationship between users (determined from friend registration on SNS or the like and the number of interactions), contact behavior (message history, stay at the same location, voice data, etc.), and propagation of owned products (the first user UA1 purchased the product G1 owned by the second user UB1).

[0063] (3-2. Example 2) Specific example 2 of the reliability calculation process will be described with reference to Fig. 6. Below, an example will be described of a first user UA1 who does not own product G2, which is a shirt, a second user UB1 who does not own product G2, and a second user UB2 who does not own product G2. That is, in specific example 2, an example will be described in which there are multiple second users UB, and the second users UB do not own the recommended product.

[0064] As shown in FIG. 6, first, the information providing device 10 determines that the first user UA1 has come into contact with primary information about the product G1 transmitted through web advertisements, personal information, or SNS (see FIG. 6(1)). At this time, the information providing device 10 executes the same process as in Example 1 and determines that the first user UA1 does not own the product G2. Next, the information providing device 10 determines that the second user UB1 does not own the product G2 but has a deep knowledge (high level of understanding) of the "fashion" category to which the product G2 belongs (see FIG. 6(2)). Then, if there is contact behavior between the first user UA1 and the second user UB1 and contact behavior between the first user UA1 and the second user UB2, and if there is purchase behavior of the product G2 by the first user UA1, the information providing device 10 infers that the second user UB1 or the second user UB2 recommended the product G2 to the first user UA1 (provided secondary information) (see FIG. 6(3)). In this case, although neither second user UB1 nor second user UB2 owns product G2, the information providing device 10 determines that second user UB1 is more trustworthy than second user UB2 because second user UB1 has a deep knowledge of fashion, and calculates a higher trustworthiness for second user UB1 (e.g., second user UB1 [0.53], second user UB2 [0.17]).

[0065] As shown in the above specific example 2, when a product is propagated from multiple second users UB to first user UA, the information providing device 10 presumes that a recommendation has been made within the community. In this case, the information providing device 10 can score which of the multiple second users UB recommended the product more (whether the user is a trustworthy user who provided secondary information) based not only on whether or not the second users UB own the product as shown in specific example 1, but also on the relationship between the users, the frequency of appearance of relevant words (e.g., "product G2," "shirt") at the time of contact, and user attributes (e.g., high level of understanding of fashion, the food and beverage industry, music, and trends).

[0066] (3-3. Example 3) Specific example 3 of the reliability calculation process will be described using Fig. 7. Below, an example will be described of a first user UA1 who does not own product G3, which is a shirt different from that in specific example 2, a second user UB1 who owns product G3, and a second user UB2 who also owns product G3. That is, in specific example 3, an example will be described in which there are multiple second users UB, and the second users UB own the product recommended by them.

[0067] As shown in FIG. 7, first, the information providing device 10 determines that the first user UA1 has come into contact with primary information about product G3 that has been disseminated through web advertisements, people, or SNS (see FIG. 7(1)). At this time, the information providing device 10 executes the same process as in specific example 1 and determines that the first user UA1 does not own product G3. Next, the information providing device 10 determines that the second user UB1 owns product G3 and has a deep knowledge (high level of understanding) of "fashion," the category to which product G3 belongs (see FIG. 7(2)). Furthermore, the information providing device 10 determines that the second user UB2 owns product G3 and has had a long contact time with the first user UA1 (see FIG. 7(3)). Then, when there is contact behavior between the first user UA1 and the second user UB1, and contact behavior between the first user UA1 and the second user UB2, and when there is purchase behavior of the product G3 by the first user UA1, the information providing device 10 infers that the second user UB1 or the second user UB2 recommended the product G3 to the first user UA1 (provided secondary information) (see FIG. 7(4)). In this case, the information providing device 10 determines that both the second user UB1 and the second user UB2 are trustworthy because they both own the product G3, and the second user UB1 has a deep knowledge of fashion, while the second user UB2 has frequent contact with the first user UA1 and spends a long time at the same location, and calculates the reliability of the second user UB1 and the second user UB2 to be approximately the same (e.g., second user UB1 [0.53], second user UB2 [0.52]).

[0068] As shown in the above specific example 3, when a product is propagated from multiple second users UB to first user UA, the information providing device 10 presumes that a recommendation has been made within the community. In this case, the information providing device 10 can score which of the multiple second users UB recommended the product more (whether the user is a trustworthy user who provided secondary information) based not only on whether or not the second user UB owns the product shown in specific example 1, the relationship between users and the frequency of appearance of relevant words (e.g., "product G3" and "shirt") at the time of contact, and the user attributes shown in specific example 2 (e.g., high level of understanding of fashion, the food and beverage industry, music, and trends), but also on the frequency of contact and duration of stay based on location information.

[0069] (3-4. Example 4) Specific example 4 of the reliability calculation process will be described using Fig. 8. Below, an example will be described of a first user UA2 who does not own product G3 and is different from specific examples 1 to 3, a second user UB1 who owns product G3, and a second user UB3 who owns product G3 and is different from specific examples 2 and 3. That is, in specific example 4, an example will be described in which there are multiple second users UB and the second user UB recommends products to multiple first users UA.

[0070] As shown in FIG. 8, first, the information providing device 10 determines that the first user UA2 has come into contact with primary information about the product G3 transmitted through web advertisements, personal information, or SNS (see FIG. 8(1)). At this time, the information providing device 10 executes the same process as in Specific Example 1 and determines that the first user UA2 does not own the product G3. Next, the information providing device 10 determines that the second user UB1 owns the product G3 and, as shown in Specific Example 3, has recommended the product G3 to the first user UA1 in the same community (see FIG. 8(2)). Then, if there is contact behavior between the first user UA2 and the second user UB1, and contact behavior between the first user UA2 and the second user UB3, and if the first user UA2 has purchased the product G3, the information providing device 10 infers that the second user UB1 or the second user UB3 has recommended the product G3 to the first user UA2 (provided secondary information) (see FIG. 8(3)). At this time, the information providing device 10 determines that second user UB1 is more trustworthy than second user UB3 because both second user UB1 and second user UB2 own product G3, but second user UB1 has endorsed product G3 to multiple first users UA (UA1, UA2) and has high credibility within the same community, and calculates a higher trustworthiness for second user UB1 (e.g., second user UB1 [0.93], second user UB3 [0.22]).

[0071] As shown in the above specific example 4, when a product is propagated from multiple second users UB to a first user UA, the information providing device 10 presumes that a recommendation has been made within the community. In this case, the information providing device 10 can score which of the multiple second users UB recommended the product more (whether the user is a trustworthy user who provided secondary information) based on not only whether the second user UB owns the product as shown in specific example 1, the relationship between users and the frequency of appearance of relevant words (e.g., "product G3" or "shirt") at the time of contact, the user attributes (e.g., high level of knowledge about fashion, the food and beverage industry, music, and trends) as shown in specific example 2, and the frequency of contact and duration of stay based on location information as shown in specific example 3, but also the user's credibility within the same community (e.g., the number of people who provided secondary information).

[0072] [4. Information provision process flow] The procedure of information processing of the information providing device 10 according to the embodiment will be described with reference to Fig. 9. Fig. 9 is a flowchart showing an example of the flow of the information providing process according to the embodiment. Note that the following steps S101 to S106 may be executed in a different order. Also, some of the following steps S101 to S106 may be omitted.

[0073] (4-1. Collection and processing of user information) First, the collection unit 13a of the information providing device 10 executes a user information collection process (step S101). For example, the collection unit 13a collects user information (registration information, history information, location information) of the user U (UA, UB) from the user terminal 20 (20A, 20B).

[0074] (4-2. First User Identification Processing) Second, the identification unit 13b of the information providing device 10 executes a first user identification process (step S102). For example, the identification unit 13b uses a purchase history or the like indicated by the user information to acquire a first user UA who has performed a purchasing behavior after acquiring the primary information.

[0075] (4-3. Second User Identification Processing) Third, the identification unit 13b of the information providing device 10 executes a second user identification process (step S103). For example, the identification unit 13b uses communication information, location information, and the like indicated by the user information to identify the second user UB who provided the secondary information before the purchasing behavior of the first user UA.

[0076] (4-4. Reliability calculation process) Fourth, the calculation unit 13c of the information providing device 10 executes a reliability calculation process (step S104). For example, the calculation unit 13c calculates the reliability of each second user UB having a relationship with the first user UA by using the registration information, history information (purchase history, search history, browsing history, communication history), location information, etc. indicated by the user information.

[0077] (4-5. Provision information transmission process) Fifth, the transmitting unit 13d of the information providing device 10 executes a provided information transmitting process (step S105). For example, the transmitting unit 13d transmits the generated provided information or the acquired provided information to the user terminal 20B of the user UB.

[0078] (4-6. Reliability learning process) Sixth, the learning unit 13e of the information providing device 10 executes a reliability learning process (step S106). For example, the learning unit 13e learns the calculated reliability.

[0079] [5. Effects of the embodiment] (5-1. Effect 1) In the process according to the embodiment described above, user information is collected, and based on the user information, the trustworthiness of the second user UB who has a relationship with the first user UA who performed the purchase behavior of the transaction target is calculated. Therefore, this process can provide useful information about the user U.

[0080] (5-2. Effect 2) In the process according to the embodiment described above, based on the registration information, history information, or location information of each user indicated in the user information, a first user UA who performed a purchase after obtaining primary information recommending a transaction target from a predetermined medium is identified, and a second user UB who provided secondary information recommending the transaction target to the first user UA before the purchase is identified. Therefore, this process can provide useful information about the user U more effectively.

[0081] (5-3. Effect 3) In the process according to the embodiment described above, the reliability of the second user UB regarding the transaction object is calculated based on whether the second user UB owns the transaction object. Therefore, this process can more effectively provide useful information about the user U based on whether the second user UB owns the transaction object.

[0082] (5-4. Effect 4) In the process according to the embodiment described above, the reliability of the second user UB regarding the transaction target is calculated based on the second user UB's level of understanding of the transaction target. Therefore, in this process, useful information regarding the user U based on the level of understanding of the transaction target can be provided more effectively.

[0083] (5-5. Effect 5) In the process according to the embodiment described above, the trustworthiness of the second user UB regarding the transaction object is calculated based on communication between the first user UA and the second user UB using their terminals. Therefore, this process can more effectively provide useful information about the user U based on communication between the users using their terminals.

[0084] (5-6. Effect 6) In the process according to the embodiment described above, the reliability of the second user UB regarding the transaction object is calculated based on the contact behavior indicated by the location information of the first user UA and the second user UB. Therefore, this process can more effectively provide useful information about the user U based on the contact behavior between the users.

[0085] (5-7. Effect 7) In the process according to the present embodiment described above, the trustworthiness of the second user UB regarding the transaction object is calculated based on the history information of the first user UA before the purchase behavior of the first user UA. Therefore, in this process, useful information about the user U based on the history information before the purchase behavior can be provided more effectively.

[0086] (5-8. Effect 8) In the process according to the present embodiment described above, the trustworthiness of the second user UB regarding the transaction target is calculated based on the number of first users UA to whom the second user UB has provided secondary information. Therefore, in this process, useful information regarding the user U based on the number of first users UA can be provided more effectively.

[0087] (5-9. Effect 9) In the process according to the present embodiment described above, information to be provided to the second user UB is transmitted based on the reliability of the second user UB regarding the transaction object. Therefore, in this process, useful information regarding users can be provided more effectively, and useful information can be provided to the user UB.

[0088] [Hardware configuration] The information providing device 10 according to the embodiment described above is realized, for example, by a computer 1000 configured as shown in Fig. 10. The information providing device 10 will be described below as an example. Fig. 10 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information providing device 10. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0089] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0090] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network N.

[0091] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0092] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 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.

[0093] For example, when the computer 1000 functions as the information providing device 10 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 13. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0094] 〔others〕 Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. Furthermore, the above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0095] 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 a known method. 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.

[0096] 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.

[0097] For example, the information providing device 10 described above may be realized by multiple server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0098] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0099] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, a control section can be read as control means or a control circuit. [Explanation of symbols]

[0100] 10 Information provision device 11 Communications Department 12 Storage section 12a User information storage unit 12b Reliability information storage unit 13 Control Unit 13a Collection Department 13b Specific part 13c Calculation section 13d Transmitter 13e Learning Department 20, 20A, 20B User terminal 100 Information Provision System

Claims

1. a collection unit that collects user information; a calculation unit that calculates, based on the user information, a reliability of a second user who has a relationship with a first user who has performed a purchasing behavior of the transaction target, regarding the transaction target; an identification unit that identifies the first user who performed the purchasing behavior after obtaining first recommendation information recommending the transaction object from a predetermined medium based on the registration information, history information, or location information of each user indicated in the user information, and identifies the second user who provided second recommendation information recommending the transaction object to the first user through direct communication, telephone call, or conversation with the first user before the purchasing behavior; Equipped with the calculation unit calculates the reliability using a machine learning model trained to output a reliability for each second user having a relationship with the first user when the user information is input; An information providing device characterized by:

2. the calculation unit calculates the reliability based on whether or not the second user owns the object of transaction.

2. The information providing device according to claim 1.

3. the calculation unit calculates the reliability based on the second user's understanding of the object of transaction.

3. The information providing device according to claim 1 or 2.

4. the calculation unit calculates the reliability based on communication between the first user and the second user using a terminal.

4. The information providing device according to claim 1, wherein the information providing device is a device for providing information to a user.

5. the calculation unit calculates the reliability based on contact behavior indicated by position information of the first user and the second user.

5. The information providing device according to claim 1, wherein the information providing device is a device for providing information to a user.

6. the calculation unit calculates the reliability based on history information of the first user before the purchase behavior.

6. The information providing device according to claim 1, wherein the information providing device is a device for providing information to a user.

7. the calculation unit calculates the reliability based on the number of first users to whom the second user has provided the second recommendation information.

2. The information providing device according to claim 1.

8. a transmitting unit that transmits information to be provided to the second user based on the reliability; 8. The information providing device according to claim 1, further comprising:

9. An information providing method executed by an information providing device, comprising: a collection step of collecting user information; a calculation step of calculating a reliability of a second user having a relationship with a first user who has performed a purchasing behavior of the transaction target based on the user information; an identification step of identifying the first user who performed the purchasing behavior after obtaining first recommendation information recommending the transaction object from a predetermined medium based on the registration information, history information, or location information of each user indicated in the user information, and identifying the second user who provided second recommendation information recommending the transaction object to the first user through direct communication, telephone call, or conversation with the first user before the purchasing behavior; Including, the calculation step calculates the reliability using a machine learning model that has been trained to output a reliability for each second user who has a relationship with the first user when the user information is input; 1. An information providing method comprising:

10. the collection procedures for collecting user information; a calculation step of calculating a reliability of a second user having a relationship with a first user who has performed a purchasing behavior of the transaction target based on the user information; an identification step of identifying the first user who performed the purchasing behavior after obtaining first recommendation information recommending the transaction object from a predetermined medium based on the registration information, history information, or location information of each user indicated in the user information, and identifying the second user who provided second recommendation information recommending the transaction object to the first user through direct communication, telephone call, or conversation with the first user before the purchasing behavior; on the computer, the calculation step calculates the reliability using a machine learning model that has been trained to output a reliability for each second user who has a relationship with the first user when the user information is input. An information providing program characterized by:

Images