JP2018041307A - Estimation apparatus, estimation method, and estimation program - Google Patents

Abstract

An object of the present invention is to appropriately estimate which part of character information affects a user. An estimation apparatus according to the present application includes an acquisition unit and an estimation unit. An acquisition part acquires the character information regarding the object provided to the user who purchased the object of commerce before the object purchase. An estimation part estimates the influence location which is a location which influences purchase of object in character information based on the character information acquired by the acquisition part. For example, the estimation unit estimates an affected part in the character information based on a comparison between the character information and other character information. [Selection] Figure 3

Description

  The present invention relates to an estimation device, an estimation method, and an estimation program.

  Conventionally, various techniques relating to character information analysis have been provided. For example, a technique for estimating the topic from predetermined character information is provided.

Japanese Patent Laying-Open No. 2015-219583

  However, in the above-described conventional technology, it is difficult to appropriately estimate which part of the character information has affected the user. For example, it is possible to estimate the main target of the character information only by estimating the topic from the character information, but it is difficult to appropriately estimate which part of the character information has affected the user. .

  The present application has been made in view of the above, and an object thereof is to provide an estimation device, an estimation method, and an estimation program that appropriately estimate which part of character information has affected a user.

  The estimation apparatus according to the present application is based on an acquisition unit that acquires character information related to the target provided to the user who purchased the target of the commercial transaction, and the character information acquired by the acquisition unit. And an estimation unit that estimates an influence location that is a location that affects the purchase of the object in the character information.

  According to the aspect of the embodiment, there is an effect that it is possible to appropriately estimate which part of the character information has affected the user.

FIG. 1 is a diagram illustrating an example of an estimation process according to the embodiment. FIG. 2 is a diagram illustrating an example of an estimation process according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the estimation apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a review information storage unit according to the embodiment. FIG. 6 is a flowchart illustrating an example of estimation of review evaluation according to the embodiment. FIG. 7 is a diagram illustrating a configuration example of an estimation apparatus according to a modification. FIG. 8 is a diagram illustrating an example of the target related information storage unit according to the modification. FIG. 9 is a diagram illustrating an example of the estimation of the affected part according to the modification. FIG. 10 is a flowchart illustrating an example of the estimation process according to the modification. FIG. 11 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the estimation device.

  Hereinafter, a mode for carrying out an estimation device, an estimation method, and an estimation program according to the present application (hereinafter referred to as “embodiment”) will be described in detail with reference to the drawings. In addition, the estimation apparatus, the estimation method, and the estimation program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. (Estimation process)
An example of the estimation process according to the embodiment will be described with reference to FIG. 1 and 2 are diagrams illustrating an example of an estimation process according to the embodiment. Below, the case where the character information regarding the object provided to the user is a review posted to the object is shown as an example. In the example of FIG. 1 and FIG. 2, the estimation device 100 estimates the influence location included in the review based on the user's reaction provided with information related to the review (hereinafter also referred to as “review information”). Show. In addition, the object referred to here is not limited to products and services, and may include various objects.

  As shown in FIG. 1, the estimation system 1 includes a terminal device 10, a commercial transaction device 50 (see FIG. 2), and an estimation device 100. The terminal device 10, the commercial transaction device 50, and the estimation device 100 are connected to be communicable by wire or wireless via a predetermined communication network (not shown). In addition, the estimation system 1 illustrated in FIG. 1 may include a plurality of terminal devices 10, a plurality of commercial transaction devices 50, and a plurality of estimation devices 100.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. In the example illustrated in FIG. 1, the terminal device 10 is a smartphone. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10.

  The commercial transaction apparatus 50 is an information processing apparatus used for providing an electronic commercial transaction service. For example, the commercial transaction device 50 provides an electronic commercial transaction service in response to a purchase request from a user. Further, the commercial transaction device 50 provides the estimation device 100 with information related to user purchase (hereinafter also referred to as “purchase information”). Note that the service provided by the provider using the commercial transaction device 50 is not limited to the electronic commercial transaction service and may be any type of service as long as the product or service purchased by the user can be provided to the user. Further, the commercial transaction device 50 may be integrated with the estimation device 100. For example, when the commercial transaction device 50 is integrated with the estimation device 100, the estimation device 100 may provide an electronic commercial transaction service.

  The estimation apparatus 100 estimates an affected part, which is a part that affects the purchase of the object, in the character information regarding the object provided to the user who purchased the object of the commercial transaction before the purchase of the object. 1 and 2, the estimation apparatus 100 shows a case in which an influence part of a review is estimated based on whether or not the review target has been purchased after the review is browsed. In the example of FIGS. 1 and 2, the estimation device 100 is assumed to provide the terminal device 10 used by the user with a review list regarding a predetermined target in response to a request from the user. Moreover, in the example of FIG.1 and FIG.2, the estimation apparatus 100 shall acquire the posting of the review from the user with respect to a predetermined | prescribed object.

  First, in the example of FIG. 1, the terminal device 10 used by the user identified by the user ID “U1” (hereinafter also referred to as “user U1”) reviews the estimation device 100 according to the operation by the user U1. A request is made (step S11). For example, the terminal device 10 requests the estimation device 100 to review the candy A. For example, the terminal device 10 may request the estimation device 100 to review the candy A when the user U1 selects the candy A among a plurality of objects displayed in a list on the screen. For example, the terminal device 10 transmits a review to the estimation device 100 by transmitting information indicating that the user requesting the review is the user U1 and information indicating that the target of the review is the candy A. Request.

  The estimation apparatus 100 that has acquired the review request for the candy A from the terminal device 10 provides the terminal device 10 with a review list of the candy A (step S12). For example, the estimation device 100 provides the terminal device 10 with a list of review information related to the candy A among the review information stored in the review information storage unit 122.

  In the example illustrated in FIG. 1, a review identified by review IDs “RV11” to “RV13” or the like is posted on the target “candy A” identified by the target ID “TG1”. Hereinafter, the review identified by the review ID “RV11” is “review RV11”, the review identified by the review ID “RV12” is “review RV12”, and the review identified by the review ID “RV13” is “review RV13”. ".

  In the example of FIG. 1, “date and time” in the review information storage unit 122 indicates the date and time when the corresponding review was posted. “* (* Is an arbitrary numerical value)” following “dt” in the date and time “dt *” indicates the date and time when the review identified by the corresponding review ID is posted, and the date and time “dt *” indicates “* The larger the value of “”, the newer the date. For example, the date “dt2” indicates that the date is newer because the numerical value following “dt” is larger than the date “dt1”. In other words, the example shown in FIG. 1 indicates that the reviews are posted in the order of RV11, RV12, and RV13.

  In the example of FIG. 1, in order to simplify the description, the estimating apparatus 100 displays a review list on the terminal device 10 that displays the review RV11 to review RV13 and the like of the candy A in order from the latest posting date. Shall be provided. Specifically, the estimation apparatus 100 provides the terminal device 10 with a review list in which the review RV13 having the latest date, the review RV12 having the latest date after the review RV13, and the review RV11 having the latest date after the review RV12 are arranged in this order. provide.

  As shown in FIG. 1, a page W10 is displayed on the terminal device 10 provided with the review list of sweets A arranged in the order of reviews RV13, RV12, and RV11. Specifically, the terminal device 10 includes a page W10 that includes the review RV13, RV12, and RV11 being “Sweet A”, the contributors of each review RV13, RV12, and RV11, and satisfaction and comments. Is displayed. For example, the terminal device 10 displays a page W10 that includes a review RV13 including a poster “user U13”, a satisfaction level “4”, and a comment “I really like ...” at the top of the review. Also, on the page W10, immediately below the review RV13, a review RV12 including a contributor “user U4”, a satisfaction level “5”, and a comment “It was very good” is displayed. In addition, on the page W10, immediately below the review RV12, a review RV11 including a contributor “user U11”, a satisfaction level “3”, and a comment “not particularly good” is displayed.

  In the example of FIG. 1, the user U1 provided with the review list of the candy A does not react within a predetermined period (for example, within one week from step S12) (step S13). That is, in the example of FIG. 1, the user U1 to whom the review list of the candy A is provided did not purchase the candy A.

  Thereafter, the estimating apparatus 100 acquires a review posting from the terminal device 10 used by the user identified by the user ID “U2” (hereinafter also referred to as “user U2”) (step S14). The estimation device 100 acquires a review RV14 post for the candy A from the terminal device 10 used by the user U2 (step S14). As described above, the review identified by the review ID “RV14” may be referred to as “review RV14”.

  In the example of FIG. 1, the user U2 posts a review RV14 for the candy A by inputting a satisfaction level and a comment for the candy A on a page W11 that is a page for posting a review of the candy A. In the example of FIG. 1, the user U2 enters the review RV14 for the candy A with the date “dt4” by inputting the satisfaction level “4” for the candy A and the comment “Fluffy texture ...” on the page W11. Post to.

  The estimation apparatus 100 that has acquired the posting of the review RV14 from the user U2 adds the review RV14 to the review information storage unit 122 (step S15). Thereby, in the example of FIG. 1, the estimation apparatus 100 updates the content stored in the review information storage unit 122. The review information storage unit 122-2 in FIG. 1 shows the state of the review information storage unit 122 after adding the review RV14. The review information storage unit 122 and the review information storage unit 122-2 are the same review information storage unit 122 except for the difference in the stored information. For example, the estimation apparatus 100 targets the review information identified by the review ID “RV14” including information such as the user ID “U4”, the degree of satisfaction “4”, and the comment “fluffy texture ...” In the review information storage unit 122.

  Next, a case where the review RV 14 is posted on the date and time dt4 and started to be provided as review information to the user will be described with reference to FIG. In the example of FIG. 2, the terminal device 10 used by the user U1 requests a review from the estimation device 100 in response to an operation by the user U1 (step S21). For example, the terminal device 10 requests the estimation device 100 to review the candy A. In the example of FIG. 2, the user U1 requests the estimation apparatus 100 to review the confectionery A at a date dt41 later than the date dt4 when the review RV14 is posted.

  The estimation apparatus 100 that has acquired the review request for the candy A from the terminal device 10 provides the terminal device 10 with a review list of the candy A (step S22). For example, the estimation device 100 provides the terminal device 10 with a list of review information related to the candy A among the review information stored in the review information storage unit 122-2.

  In the example of FIG. 2, in order to simplify the description, the estimation apparatus 100 displays a review list on the terminal device 10 in which the review RV11 to the review RV14 of the candy A are displayed in order from the latest posting date on the terminal device 10. Shall be provided. Specifically, the estimation apparatus 100 includes the review RV14 with the latest date, the review RV13 with the newest date after the review RV14, the review RV12 with the newest date after the review RV13, and the review RV11 with the newest date after the review RV12. The review list arranged in the order of is provided to the terminal device 10.

  As shown in FIG. 2, a page W20 is displayed on the terminal device 10 provided with the review list of the sweets A arranged in the order of reviews RV14, RV13, RV12, and RV11. Specifically, the terminal device 10 indicates that the subject of the reviews RV14, RV13, RV12, and RV11 is “Sweet A”, and the contributors, satisfaction levels, and comments of each review RV14, RV13, RV12, and RV11. The included page W20 is displayed. For example, the terminal device 10 displays a page W20 including a review RV14 including a poster “user U2”, a satisfaction level “4”, and a comment “fluffy texture is ...” at the top of the review. Also, on the page W20, immediately below the review RV14, a review RV13 including a contributor “user U13”, a satisfaction level “4”, and a comment “I like it very much” is displayed. Also, on the page W20, immediately below the review RV13, a review RV12 including a contributor “user U4”, a satisfaction level “5”, and a comment “very good” is displayed. Further, when the user U1 touches the screen of the terminal device 10 and performs a scrolling operation or the like, the review RV11 positioned immediately below the review RV12 is displayed on the terminal device 10.

  In the example of FIG. 2, a case where the user U1 to whom the review list of the candy A is provided purchases the candy A within a predetermined period (for example, within one week from step S22) will be described as an example. For example, the terminal device 10 requests purchase from the commercial transaction device 50 in response to an operation by the user U1 (step S23). For example, the terminal device 10 requests the commerce device 50 to purchase the candy A. For example, the terminal device 10 may request the commerce device 50 to purchase the candy A when the user U1 selects the candy A on the electronic commerce site provided by the commerce device 50 displayed on the screen. .

  In step S23, the commercial transaction device 50 that has received the purchase request for the candy A from the user U1 performs the candy A purchase process. For example, the commercial transaction device 50 performs a settlement process for the purchase of the candy A, and delivers the candy A to the registered (input) address of the user U1.

  Moreover, the commercial transaction apparatus 50 provides purchase information to the estimation apparatus 100 (step S24). For example, the commercial transaction apparatus 50 provides the estimation apparatus 100 with information indicating that the user U1 has purchased the candy A as purchase information. In addition, the commercial transaction device 50 provides the estimation device 100 with purchase information indicating that another user who has been provided with the review list of the candy A has purchased the candy A. For example, the commercial transaction device 50 provides the estimation device 100 with purchase information indicating that another user who has been provided with the review list of the candy A after date dt4 has purchased the candy A.

  The estimation apparatus 100 that has acquired the purchase information from the commercial transaction apparatus 50 estimates the affected part based on the acquired purchase information, the review information provided to the user, or the like (step S25). In the example of FIG. 1, the estimation device 100 calculates a change related to the sales related to the candy A based on the purchase information acquired from the commercial transaction device 50. For example, the estimation device 100 calculates a change related to sales related to the candy A as shown in the sales transition information SG11. In the sales transition information SG11 shown in FIG. 1, since the sales of the confectionery A have increased after the date dt4, the estimation device 100 is influenced by the character string unique to the review that has been provided to the user from the date dt4. Presumed to have been given. Therefore, the estimation apparatus 100 estimates the character string “Fuwafuwa”, the character string “food texture”, and the like as locations that have affected the increase in sales of the candy A, as shown in the influence location list IL11. The character strings “Fuwa Fuwa” and “Texture” are character strings that are unique to the review RV14 that has begun to be provided to the user after the date and time dt4, and are not included in the reviews RV11 to RV13. Shall.

  As described above, the estimating apparatus 100 can appropriately estimate which part of the character information has affected the user. Specifically, the estimation apparatus 100 includes the reviews RV11 to RV13 provided at a second time point (for example, date and time dt3) before the first time point (for example, date and time dt4) when the review RV14 is provided to the user. Based on the comparison, the affected part in the review RV14 is estimated. In FIG. 2, since the sales of sweets A have increased since date dt4, the estimating apparatus 100 uses the character string “fluffy” and the character string “food” that are keywords (character strings) unique to the review RV14. It is estimated that “feel” is an affected part that has influenced the user. Thereby, the estimation apparatus 100 can appropriately estimate which part of the review RV 14 has affected the user.

  In the above-described example, the estimation device 100 has shown a case in which which part of the character information affects the user based on the character information included in the review related to the target. The affected part may be estimated for any character information. Details of the estimation process using information other than the review will be described later.

  In addition, the estimation apparatus 100 may provide information regarding the estimated influence location. For example, the estimation apparatus 100 provides information on the affected part in the estimated character information to the provider that provides the target. For example, the estimation apparatus 100 generates an influence location list IL11 indicating that the character string “fluffy”, the character string “texture”, and the like have affected the increase in sales of the candy A, and the predetermined electronic commerce site. It may be provided to the manager of a store that sells sweets A. For example, the estimation apparatus 100 may provide the affected part list IL11 to a predetermined provider such as a manufacturer that manufactures the candy A. Further, for example, the estimating apparatus 100 may provide the affected part list IL11 to an agency or the like that performs advertising activities or marketing of the candy A. Thereby, the manufacturer, the agency, etc. which received information provision from the estimation apparatus 100 can estimate the information which influences the sales of the candy A. That is, a manufacturer, an agent, or the like that has received information from the estimation device 100 can estimate points that are characteristic of the candy A.

  In the above example, since the sales of confectionery A have increased after date dt4, the estimation apparatus 100 determines that the character string “Fuwafuwa” and the character string “texture” included in the affected part list IL11 are Although it is estimated that the place has a positive influence on the confectionery A, the estimation device 100 may estimate various influences without being limited to the positive influence. For example, when the sales of the confectionery A has decreased after the date and time dt4, the estimation apparatus 100 causes the character string “Fuwafuwa” and the character string “texture” included in the affected part list IL11 to be negative to the confectionery A. You may presume that it is the place which influences. In addition, for example, when the sales of the confectionery A has not substantially changed after the date and time dt4 (for example, within ± 5%), the estimation apparatus 100, for example, the character string “fluffy” included in the affected part list IL11. And the character string “texture” or the like may be estimated as a portion that does not affect the candy A.

[2. Configuration of estimation device]
Next, the configuration of the estimation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the estimation apparatus 100 according to the embodiment. As illustrated in FIG. 3, the estimation apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The estimation device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the estimation device 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network by wire or wirelessly, and transmits and receives information to and from the terminal device 10 included in the estimation system 1, for example.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 3, the storage unit 120 according to the embodiment includes a user information storage unit 121 and a review information storage unit 122.

(User information storage unit 121)
The user information storage unit 121 according to the embodiment stores various types of information regarding the user. For example, the user information storage unit 121 stores various types of information regarding user attributes. FIG. 4 is a diagram illustrating an example of a user information storage unit according to the embodiment. The user information storage unit 121 illustrated in FIG. 4 includes items such as “user ID”, “terminal ID”, “age”, “gender”, “number of reviews”, and “reviewed list”.

  “User ID” indicates identification information for identifying a user. “Terminal ID” indicates information for identifying the terminal device 10 used by the corresponding user. When a corresponding user uses a plurality of terminal devices 10, a plurality of “terminal IDs” may be stored in the user information storage unit 121. “Age” indicates the age of the user identified by the corresponding user ID. The “age” may be a specific age of the user identified by the corresponding user ID, such as 35 years old. “Gender” indicates the gender of the user identified by the corresponding user ID.

  The “number of reviews” indicates the number of reviews posted by the user identified by the corresponding user ID. The “reviewed list” indicates a review list posted by the user identified by the corresponding user ID. The “reviewed list” includes items such as “target 1” and “target 2”.

  For example, in the example shown in FIG. 4, the user identified by the user ID “U1” (corresponding to the user U1 in FIG. 1) uses the terminal device 10 identified by the terminal ID “TM1”. Show. In addition, the age of the user identified by the user ID “U1” is “30s”, and the gender is “male”. Further, the number of reviews posted by the user identified by the user ID “U1” is “50”. Further, the target to which the user identified by the user ID “U1” has posted the review indicates that the target is identified by the target ID “TG4” or the target identified by the target ID “TG7”.

  For example, in the example illustrated in FIG. 4, the user identified by the user ID “U2” indicates that the terminal device 10 identified by the terminal ID “TM2” is being used. In addition, the age of the user identified by the user ID “U2” is “20s”, and the gender is “female”. The number of reviews posted by the user identified by the user ID “U2” is “0”. In addition, it indicates that there is no target to which the user identified by the user ID “U2” has posted a review.

  The user information storage unit 121 is not limited to the above, and may store various types of information according to the purpose. For example, the user information storage unit 121 may store information such as name, residence, interest, family structure, income, lifestyle, and the like. The user information storage unit 121 may store purchase information for each user. For example, the estimation device 100 may store purchase information of each user acquired from the commercial transaction device 50 in the user information storage unit 121.

(Review information storage unit 122)
The review information storage unit 122 according to the embodiment stores information related to reviews. FIG. 5 shows an example of information about the user stored in the review information storage unit 122. As shown in FIG. 5, the review information storage unit 122 includes “object ID”, “category”, “object”, “review ID”, “user ID”, “detailed information”, “date and time” as information relating to evaluation. Are included.

  “Target ID” indicates identification information for identifying a review target. “Category” indicates a category into which the object is classified. In the example illustrated in FIG. 5, the category is “product” or “service”. The “target” is a target identified by the target ID, and indicates a review posting target. “Review ID” indicates identification information for identifying a review. “User ID” indicates identification information for identifying a user who has posted a corresponding review.

  The “detailed information” includes items such as “satisfaction” and “comment”. “Satisfaction” indicates a user's satisfaction regarding the corresponding target. For example, the “satisfaction level” indicates how many of the user satisfaction levels regarding the corresponding target are out of 5 points. “Comment” indicates a comment posted by the user regarding the corresponding target.

  For example, in the example illustrated in FIG. 5, the target identified by the target ID “TG1” indicates the target “Sweet A” whose category is “product”. Moreover, it is shown that the review identified by review ID "RV11"-"RV13" etc. is contributed to object "candy A" identified by object ID "TG1". For example, it is indicated that a review identified by the review ID “RV11” is posted on the object “candy A” identified by the object ID “TG1”. The review identified by the review ID “RV11” indicates that the review is posted by the user identified by the user ID “U11”. The review identified by the review ID “RV11” indicates that the satisfaction level is “3” and includes a comment such as “Not particularly good”. Further, the date and time when the review identified by the review ID “RV11” is posted is “dt1”.

  Further, the review information storage unit 122 may store information such as an image related to the object and a file path to the image. Note that the review information storage unit 122 is not limited to the above, and may store various types of information according to the purpose.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller and is stored in a storage device inside the estimation device 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of an estimation program) are implemented by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

  As illustrated in FIG. 3, the control unit 130 includes an acquisition unit 131, an estimation unit 132, and a provision unit 133, and realizes or executes functions and operations of information processing described below.

(Acquisition part 131)
For example, the acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires character information related to an object provided to the user who purchased the object of the commercial transaction before purchasing the object. In the example of FIG. 2, the acquisition unit 131 acquires purchase information from the commercial transaction device 50. For example, the acquisition unit 131 acquires a review post from the terminal device 10. In the example of FIG. 1, the acquisition unit 131 acquires a review RV14 post for the candy A from the terminal device 10 used by the user U2.

  The acquisition unit 131 acquires a request for review. In FIG. 1, the acquisition unit 131 acquires a review request from the terminal device 10 used by the user U1. In FIG. 1, the acquisition unit 131 acquires a request for review of the candy A from the terminal device 10.

(Estimation unit 132)
The estimation unit 132 estimates various information. For example, based on the character information acquired by the acquisition unit 131, the estimation unit 132 estimates an affected part that is a part that affects the purchase of the target in the character information. For example, the estimation unit 132 estimates an affected part in the character information based on a comparison between the character information and other character information. For example, the estimation unit 132 determines whether character information is included in the character information based on a comparison between the character information and other character information related to the object provided at the second time point before the first time point when the character information is provided to the user. Estimate the affected location in.

  For example, when the purchase status of the target at the first time point is better than the purchase status of the target at the second time point, the estimation unit 132 determines the target in the character information based on the comparison between the character information and other character information. Estimate the locations that have a positive (hereinafter also referred to as “plus”) impact on purchases. In addition, for example, when the purchase status of the target at the second time point is better than the purchase status of the target at the first time point, the estimation unit 132 determines whether the character information is included in the character information based on the comparison between the character information and other character information Estimate impact points that have a negative (hereinafter also referred to as “minus”) impact on the target purchase.

  In the example of FIG. 2, the estimation unit 132 estimates the affected part based on the acquired purchase information, the review information provided to the user, and the like. Further, for example, the estimation unit 132 calculates a change related to the sales related to the candy A based on the purchase information acquired from the commercial transaction device 50. For example, the estimation part 132 calculates the change regarding the sales regarding the candy A, as shown in the sales transition information SG11. In the sales transition information SG11 shown in FIG. 2, since the sales of the confectionery A have increased after the date dt4, the estimation unit 132 is influenced by the character string unique to the review that has been provided to the user from the date dt4. Presumed to have been given. Therefore, the estimation unit 132 estimates the character string “Fuwafuwa”, the character string “texture”, and the like as locations that have affected the increase in sales of the candy A, as shown in the influence location list IL11.

  In the example of FIG. 2, the estimation unit 132 includes the reviews RV11 to RV13 provided at a second time point (for example, date and time dt3) before the first time point (for example, date and time dt4) when the review RV14 is provided to the user. Based on the comparison with etc., the influence location in review RV14 is estimated. In FIG. 2, since the sales of confectionery A have increased since the date and time dt4, the estimation unit 132 uses the character string “fluffy” and the character string “food” which are keywords (character strings) unique to the review RV14. It is estimated that “feel” is an affected part that has influenced the user.

(Providing unit 133)
The providing unit 133 provides various types of information to an external information processing apparatus. For example, the providing unit 133 provides information on the affected part in the character information estimated by the estimating unit 132 to the providing source that provides the target. In the example of FIG. 2, the estimation unit 132 sets the influence location list IL11 indicating that the character string “fluffy”, the character string “texture”, and the like have affected the increase in sales of the candy A. It may be provided to a manager of a store that sells the candy A on the electronic commerce site. For example, the estimation unit 132 manufactures the confectionery A by using the influence part list IL11 indicating that the character string “Fuwafuwa” and the character string “texture” are the parts that have influenced the increase in sales of the candy A. It may be provided to a predetermined provider such as a manufacturer. For example, the estimation unit 132 may provide the affected part list IL11 to an agency or the like that performs advertising activities or marketing of the candy A.

  For example, the providing unit 133 provides review information. For example, the providing unit 133 provides review information in response to a review request. For example, the providing unit 133 provides review information to the terminal device 10 that has transmitted a review request to the estimation device 100. For example, the providing unit 133 provides a review list. For example, the providing unit 133 provides a review list in response to the review request. For example, the providing unit 133 provides a review list to the terminal device 10 that has transmitted a review request to the estimation device 100.

[3. Flow of estimation process for review evaluation)
Here, the procedure of the estimation process performed by the estimation apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 6 is a flowchart illustrating an example of the estimation process according to the embodiment.

  As illustrated in FIG. 6, the estimation device 100 acquires user reaction information (step S <b> 101). In FIG. 2, the estimation device 100 acquires purchase information indicating that the user U1 has purchased the candy A from the commercial transaction device 50 as the user reaction information. For example, the estimating apparatus 100 acquires purchase information indicating that a user other than the user U1 has purchased the candy A after the date and time dt4. Moreover, the estimation apparatus 100 acquires the character information provided to the user who purchased the target (Step S102). In FIG. 2, the estimation apparatus 100 acquires reviews RV11 to RV14 related to the candy A from the review information storage unit 122-2.

  Thereafter, the estimating apparatus 100 converts the character information provided at the first time point based on the character information provided at the first time point specified by the reaction information and the character information provided before the first time point. Specific information is estimated (step S103). In FIG. 2, since the sales of the confectionery A has increased after the date and time dt4 as shown in the sales transition information SG11, the estimation apparatus 100 has a character string unique to the review RV14 that has begun to be provided to the user from the date and time dt4. Estimated to have influenced.

  After that, the estimating apparatus 100 estimates a location estimated to be information unique to the character information provided at the first time point as an affected location that has affected the user (step S104). In FIG. 2, the estimation apparatus 100 estimates the character string “Fuwafuwa”, the character string “texture”, and the like as locations that have affected the increase in sales of candy A, as shown in the affected location list IL11.

(Modification)
In the above-mentioned example, the case where the influence location under review for the target is estimated based on the context of the time is shown. However, the influence location in the character information related to a certain target is estimated by comparison with the character information related to a different target. May be. The character information to be compared is not limited to the review, and any character information may be used as long as the character information is related to each target. For example, the extraction apparatus 100A may estimate an affected part in character information such as a description included in content related to a product or service. This point will be described with reference to FIGS.

[4. (Extractor configuration)
Next, the configuration of an extraction apparatus 100A according to a modification will be described with reference to FIG. FIG. 7 is a diagram illustrating a configuration example of an extraction apparatus 100A according to a modification. As illustrated in FIG. 7, the extraction device 100A includes a communication unit 110, a storage unit 120A, and a control unit 130A. Note that in the extraction device 100A, the same points as those of the extraction device 100 according to the embodiment are denoted by the same reference numerals, and description thereof will be omitted as appropriate.

(Storage unit 120A)
The storage unit 120A is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 7, the storage unit 120 </ b> A according to the modification includes a user information storage unit 121, a review information storage unit 122, and a target related information storage unit 123. In the example of FIG. 7, the storage unit 120 </ b> A is different from the storage unit 120 according to the embodiment in that it includes a target related information storage unit 123.

(Target related information storage unit 123)
The target related information storage unit 123 according to the embodiment stores various types of information related to the target. For example, the target related information storage unit 123 stores information related to content related to a target other than the review as target related information. FIG. 8 shows an example of target related information stored in the target related information storage unit 123. As illustrated in FIG. 8, the target related information storage unit 123 includes items such as “target ID”, “category”, “target”, “content ID”, “content”, and “content” as target related information. .

  “Target ID” indicates identification information for identifying a target corresponding to the content. “Category” indicates a category into which the object is classified. The category in the example illustrated in FIG. 8 indicates a case of “product” or “service”. “Target” is a target identified by the target ID, and indicates a target corresponding to the content. The “content ID” indicates identification information for identifying the content. “Content” indicates the content identified by the corresponding content ID. In the example of FIG. 8, the content is conceptually indicated by a symbol “C11” or the like, but as “content”, a file path name indicating the storage location thereof may be stored. “Content” indicates an outline of character information related to a target included in the corresponding content.

  For example, in the example illustrated in FIG. 8, the target identified by the target ID “TG1” is the target “Sweet A” whose category is “product”. In addition, the object “candy A” identified by the object ID “TG1” indicates that the content identified by the content ID “CT11” to “CT13” is disclosed. For example, the object “candy A” identified by the object ID “TG1” indicates that the content C11 that is the product description page of the candy A is published.

  The target related information storage unit 123 may store information such as an image included in the content and a file path to the image. Note that the target related information storage unit 123 is not limited to the above, and may store various types of information according to the purpose. For example, the target related information storage unit 123 may store information related to the date and time when the content related to the target is created (published). Further, for example, the target related information storage unit 123 may store information related to a content provider such as a creator of content related to the target.

(Control unit 130A)
Returning to the description of FIG. 7, the control unit 130A is a controller. For example, various programs (corresponding to an example of the extraction program) stored in the storage device inside the extraction device 100A are stored in the RAM by the CPU, the MPU, or the like. This is realized by being executed as a work area. The control unit 130A is a controller, and is realized by an integrated circuit such as an ASIC or FPGA, for example.

  As illustrated in FIG. 7, the control unit 130A includes an acquisition unit 131, an estimation unit 132A, and a provision unit 133, and realizes or executes information processing functions and operations described below.

(Estimation unit 132A)
The estimation unit 132A estimates various information. For example, the estimation unit 132A performs the same processing as the estimation unit 132 according to the embodiment.

  For example, the estimation unit 132A estimates an affected part in the character information based on a comparison between the character information and other character information related to a similar target similar to the target. For example, when the purchase status is better than that of a similar target, the estimation unit 132A determines an influence location that has a positive effect on the purchase of the target in the character information based on a comparison between the character information and other character information. presume. For example, when the similar target has a better purchase situation than the target, the estimation unit 132A determines an influence location that negatively affects the purchase of the target in the character information based on a comparison between the character information and other character information. presume.

  In the example of FIG. 9, the estimation unit 132 </ b> A estimates the character string “Fuwafuwa”, the character string “texture”, and the like as locations that have affected the sales of the candy A, as shown in the influence location list IL <b> 31. For example, the estimation unit 132A compares the contents related to the respective objects (the candy A and the candy B) to estimate the location that has affected the sales of the candy A as shown in the affected location list IL31. .

  In addition, when the sales of the candy A is greater than the sales of the candy B, the estimation unit 132A adds the character string “Fuwafuwa” and the character string “texture” included in the affected part list IL31 to the candy A. It is presumed that this will affect For example, when the sales of the candy A is less than the sales of the candy B, the estimation unit 132A determines that the character string “fluffy” and the character string “texture” included in the affected part list IL31 are the candy A It is estimated that it has a negative impact on

[5. (Estimation of affected parts)
Here, an example of the estimation of the affected part by the estimation apparatus 100A will be described with reference to FIG. FIG. 9 is a diagram illustrating an example of the estimation of the affected part according to the modification. In the example of FIG. 9, the content related to the candy A (hereinafter referred to as “first content”) and the content related to the candy B similar to the candy A (hereinafter referred to as “second content”) are compared. The estimation of the influence part based on is shown as an example. The second content is not limited to the content related to candy B, and may be content related to any target. For example, the second content may be content related to candy C or candy D, or content related to each target such as candy B to candy D.

  In the example of FIG. 9, the estimating apparatus 100A extracts the affected part based on the difference between the first content group GC1 related to the candy A and the second content group GC2 related to the candy B (step S31). For example, the estimating apparatus 100A extracts elements (character information) that are included in the first content group GC1 related to the candy A and are not included in the second content group GC2 related to the candy B. The influence part regarding the candy A is extracted.

  For example, the estimation apparatus 100A estimates the character string “Fuwafuwa”, the character string “texture”, and the like as locations that have influenced the sales of the candy A, as shown in the influence location list IL31. It is assumed that the character string “Fuwa Fuwa” and the character string “Food texture” are character strings specific to the first content group GC1 and are not included in the second content group GC2. As described above, the estimation device 100A compares the contents related to the respective objects (the candy A and the candy B), so that the location that has influenced the sales of the candy A as shown in the affected location list IL31. presume.

  For example, when the sales of the candy A is greater than the sales of the candy B, the estimation apparatus 100A adds the character string “Fuwafuwa” and the character string “texture” included in the affected part list IL31 to the candy A. It is presumed that this will affect Further, for example, when the sales of the candy A is less than the sales of the candy B, the estimation device 100A determines that the character string “Fuwafuwa” and the character string “texture” included in the affected part list IL31 are the candy A It is estimated that it has a negative impact on

  In addition, although the case where the influence location regarding the candy A was estimated was shown above, the estimation apparatus 100A may estimate the influence location regarding the candy B. For example, the estimating apparatus 100A extracts elements (character information) that are included in the second content group GC2 related to the candy B and are not included in the first content group GC1 related to the candy A. You may extract the influence location regarding the candy B. FIG.

[6. Flow of estimation process for review evaluation)
Here, the procedure of the estimation process performed by the estimation apparatus 100A according to the modification will be described with reference to FIG. FIG. 10 is a flowchart illustrating an example of the estimation process according to the modification.

  As illustrated in FIG. 10, the estimating apparatus 100A acquires first content related to a target (Step S201). In FIG. 9, the estimation device 100A acquires the first content group GC1. In addition, the estimation device 100A acquires second content related to another target similar to the target (step S202). In FIG. 9, the estimation apparatus 100A acquires the second content group GC2.

  Thereafter, the estimation device 100A estimates information unique to the character information included in the first content based on the first content and the second content (step S203). In FIG. 9, the estimation apparatus 100A extracts elements (character information) that are included in the first content group GC1 related to the candy A and are not included in the second content group GC2 related to the candy B.

  Thereafter, the estimating apparatus 100A estimates a location estimated to be information unique to the character information included in the first content as an affected location that has affected the user (step S204). In FIG. 9, the estimation device 100A estimates the character string “Fuwafuwa”, the character string “texture”, and the like as locations that have influenced the sales of the candy A, as shown in the influence location list IL31.

[7. effect〕
As described above, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification include the acquisition unit 131 and the estimation units 132 and 132A. The acquisition unit 131 acquires character information related to an object provided to the user who purchased the object of the commercial transaction before purchasing the object. Based on the character information acquired by the acquisition unit 131, the estimation units 132 and 132 </ b> A estimate an influence location that is a location that affects the target purchase in the character information.

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately estimate which part of the character information has affected the user.

  In addition, in the estimation device 100 according to the embodiment and the estimation device 100A according to the modification, the estimation units 132 and 132A estimate the affected part in the character information based on the comparison between the character information and other character information. .

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately estimate which part of the character information has affected the user.

  In addition, in the estimation device 100 according to the embodiment and the estimation device 100A according to the modification, the estimation units 132 and 132A have character information and a second time point before the first time point when the character information is provided to the user. Based on the comparison with other character information related to the provided object, the affected part in the character information is estimated.

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately estimate which part of the character information has affected the user.

  In addition, in the estimation device 100 according to the embodiment and the estimation device 100A according to the modification, the estimation units 132 and 132A perform character information when the target purchase status at the first time point is better than the target purchase status at the second time point. Based on the comparison with other character information, an influence location that positively affects the purchase of the object in the character information is estimated.

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately estimate which part of the character information has affected the user.

  In addition, in the estimation device 100 according to the embodiment and the estimation device 100A according to the modification, the estimation units 132 and 132A perform character information when the target purchase status at the second time point is better than the target purchase status at the first time point. Based on the comparison with other character information, an influence location that negatively affects the purchase of the object in the character information is estimated.

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately estimate which part of the character information has affected the user.

  In addition, in the estimation device 100 according to the embodiment and the estimation device 100A according to the modification, the estimation units 132 and 132A perform character information based on a comparison between character information and other character information related to a similar target similar to the target. Estimate the affected area inside.

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately estimate which part of the character information has affected the user.

  In addition, in the estimation device 100 according to the embodiment and the estimation device 100A according to the modification, the estimation units 132 and 132A may compare the character information with other character information when the target is better in purchase than the similar target. Based on this, the influence location which has a positive influence on the purchase of the object in the character information is estimated.

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately estimate which part of the character information has affected the user.

  Further, in the estimation device 100 according to the embodiment and the estimation device 100A according to the modification, the estimation units 132 and 132A compare the character information with other character information when the similar target is better in purchase than the target. Based on this, the influence location which has a negative influence on the purchase of the object in the character information is estimated.

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately estimate which part of the character information has affected the user.

  In addition, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification include a providing unit 133. The providing unit 133 provides information on the affected part in the character information estimated by the estimating units 132 and 132A to the providing source that provides the target.

  As a result, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification provide the information on the affected part in the character information, so that the provided source that received the affected part is analyzed based on the affected part. It can be performed.

  In addition, in the estimation device 100 according to the embodiment and the estimation device 100A according to the modification, the providing unit 133 provides review list information displayed in the order based on the evaluation related to the review estimated by the estimation unit 132.

  Thereby, the estimation apparatus 100 according to the embodiment and the estimation apparatus 100A according to the modification can appropriately provide the service related to the review by providing the review list information displayed in the rank based on the evaluation regarding the review. .

[8. Hardware configuration)
The estimation apparatus 100 according to the embodiment described above is realized by a computer 1000 configured as shown in FIG. 11, for example. FIG. 11 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the estimation device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and provides the data generated by the CPU 1100 to other devices via the network N.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the estimation device 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them. However, as another example, these programs may be acquired from other devices via the network N.

  Although the embodiments of the present application have been described in detail with reference to the drawings, these are merely examples, and various modifications and improvements have been made based on the knowledge of those skilled in the art including the aspects described in the disclosure line of the invention. The present invention can be implemented in other forms.

[9. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  Further, the above-described embodiments can be appropriately combined within a range in which processing contents are not contradictory.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Estimation system 100 Estimation apparatus 121 User information storage part 122 Review information storage part 130 Control part 131 Acquisition part 132 Estimation part 133 Provision part 10 Terminal device N network

Claims (11)

An acquisition unit for acquiring character information related to the target provided to the user who purchased the target of the commercial transaction before the purchase of the target;
Based on the character information acquired by the acquisition unit, an estimation unit that estimates an influence location that is a location that affects the purchase of the target in the character information;
An estimation device comprising: The estimation unit includes
The estimation device according to claim 1, wherein the influence location in the character information is estimated based on a comparison between the character information and other character information. The estimation unit includes
Based on a comparison between the character information and other character information related to the object provided at a second time point before the first time point when the character information is provided to the user, the influence in the character information. The estimation device according to claim 2, wherein the location is estimated. The estimation unit includes
If the purchase status of the target at the first time point is better than the purchase status of the target at the second time point, the target in the character information is based on a comparison between the character information and the other character information. The estimation device according to claim 3, wherein the influence location having a positive influence on the purchase of is estimated. The estimation unit includes
If the purchase status of the target at the second time point is better than the purchase status of the target at the first time point, the target in the character information is based on a comparison between the character information and the other character information. The estimation device according to claim 3, wherein the influence location having a negative influence on the purchase of is estimated. The estimation unit includes
The estimation device according to claim 2, wherein the affected portion in the character information is estimated based on a comparison between the character information and other character information related to a similar target similar to the target. The estimation unit includes
When the purchase status of the target is better than that of the similar target, based on the comparison between the character information and the other character information, the influence location that positively affects the purchase of the target in the character information. The estimation apparatus according to claim 6, wherein estimation is performed. The estimation unit includes
When the purchase status of the similar target is better than that of the target, based on the comparison between the character information and the other character information, the influence location that negatively affects the purchase of the target in the character information. The estimation apparatus according to claim 6, wherein the estimation apparatus performs estimation. A providing unit that provides information on the affected part in the character information estimated by the estimating unit to a provider that provides the target;
The estimation apparatus according to claim 1, further comprising: An estimation method performed by a computer,
An acquisition step of acquiring character information relating to the target provided to the user who purchased the target of the commercial transaction before the purchase of the target;
Based on the character information acquired by the acquisition step, an estimation step of estimating an influence location that is a location that affects the purchase of the target in the character information;
The estimation method characterized by including. An acquisition procedure for acquiring character information about the target provided to the user who purchased the target of the commercial transaction before the purchase of the target;
Based on the character information acquired by the acquisition procedure, an estimation procedure for estimating an influence location that is a location that affects the purchase of the target in the character information;
An estimation program for causing a computer to execute.

Images