JP2019095919A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To appropriately select representatives.SOLUTION: An information processing device according to the present application comprises an acquisition unit, a calculation unit and a selection unit. The acquisition unit is configured to acquire review information on a review including a first evaluation point and evaluation comment with respect to a store or product submitted by a purchase user purchasing the product handled by the store. The calculation unit is configured to analyze words included in the review comment acquired by the acquisition unit to calculate a second evaluation point with respect to the store or product. The selection unit is configured to select a representative on the basis of the second evaluation point calculated by the calculation unit from a plurality of first evaluation points, which are acquired by the acquisition unit as to at least one of the store, product and review and fall within a prescribed range.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

  BACKGROUND In recent years, electronic commerce for trading products (including services) on the Internet has been actively performed. Moreover, in the field of electronic commerce, a user who has purchased a product posts a review in which an evaluation score or an evaluation text for the purchased product or store is described. Such a review is an indicator by which a user who intends to purchase a product in the store in the future determines the quality of the product or the store.

Unexamined-Japanese-Patent No. 2017-054554

  By the way, there are cases where a product with high (or low) evaluation, a store, or a review is selected from a plurality of products, stores, or reviews using the evaluation points of such a review. The selected product, store, or review is displayed to the user as a representative of the plurality, for example.

  However, when a representative is selected based on the review score, the selected representative is not necessarily appropriate. For example, in the case of a method of selecting any one of five evaluations of 1 to 5 as evaluation points, the user tends to easily select extreme scores of “1” and “5”, while “2 There is a tendency not to select an intermediate score of “4”.

  For this reason, in a plurality of stores (or products or reviews), the average of the evaluation points is concentrated on one or five points, and there is a possibility that it can not be appropriately selected when a representative is selected from them.

  The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of appropriately selecting a representative.

  An information processing apparatus according to the present application includes an acquisition unit, a calculation unit, and a selection unit. The acquisition unit acquires review information related to a review including a first evaluation score and an evaluation statement for the store or the item posted by a purchase user who has purchased the item handled by the store. The calculation unit analyzes a word included in the evaluation sentence of the review acquired by the acquisition unit to calculate a second evaluation point for the store or the product. The selection unit is calculated by the calculation unit from among a plurality of the first evaluation points acquired by the acquisition unit within a predetermined range for at least one of the store, the product, and the review. A representative is selected based on the second evaluation point.

  According to one aspect of the embodiment, it is possible to appropriately select a representative.

FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. FIG. 2 is a diagram illustrating an exemplary configuration of an information processing system according to the embodiment. FIG. 3 is a diagram illustrating an exemplary configuration of the information processing apparatus according to the embodiment. FIG. 4 is a diagram showing an example of the evaluation information. FIG. 5 is a diagram showing an example of the product information. FIG. 6 is a diagram showing an example of store information. FIG. 7 is a diagram showing an example of user information. FIG. 8 is a diagram showing an example of word information. FIG. 9 is an explanatory diagram of a calculation process of the second evaluation point according to the embodiment. FIG. 10 is an explanatory diagram of the provision processing of the provision unit according to the embodiment. FIG. 11 is an explanatory diagram of the provision processing of the provision unit according to the embodiment. FIG. 12 is a flowchart illustrating the procedure of processing performed by the information processing apparatus according to the embodiment. FIG. 13 is a hardware configuration diagram illustrating an example of a computer that implements the function of the information processing apparatus according to the embodiment.

  Hereinafter, an information processing apparatus, an information processing method, and a mode for implementing an information processing program according to the present application (hereinafter, referred to as “embodiment”) will be described in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by the embodiment. Moreover, the same code | symbol is attached | subjected to the same site | part in the following each embodiment, and the overlapping description is abbreviate | omitted.

  First, an example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. FIG. 1 shows an example where the information processing apparatus 1 is a shopping server that functions as an EC (Electric Commerce) site.

  The information processing apparatus 1 as a shopping server provides a user U (purchasing user U1 or user U2) with information on a product or service (hereinafter, simply referred to as a "product") registered by the store manager M1. The purchase of a product from user U is accepted.

  In the following, the information processing apparatus 1 as a shopping server shown in FIG. 1 has a review function of accepting a review posting indicating an evaluation of a store that handles purchased items or purchased items by the purchasing user U1 who purchased the item. . In the example illustrated in FIG. 1, it is assumed that a store review that is a review for a store is accepted.

  As shown in FIG. 1, in the store review posted by the purchasing user U1, there are evaluation points where the evaluation of the purchasing user U1's evaluation is scored, and evaluation sentences where the evaluation of the purchasing user U1's evaluation is textualized. included. After purchasing the product, the purchasing user U1 gives a rating point and writes a rating sentence to post a review.

  For example, for the review shown in FIG. 1, a rating of "5.0" together with a star-shaped figure, and "packing is necessary and sufficient, and it is satisfactory. In addition to the text on the response, "Discussion of the delivery stop procedure is very troublesome and closed when the advertisement e-mail comes to arrive. If this is improved, it is the best ...", such as dissatisfaction with Store A and improvement proposal etc. It may contain sentences about the opinion.

  Then, such a review is provided to the user U2 who is thinking of purchasing a product handled by the store from now, and helps to determine the quality of the store by the user U2.

  In addition, for example, using the evaluation points of the review, the representative of the high-rated (or low-rated) store or product or review is selected from the plurality of stores, products or reviews, and the selected representative is selected as the user U2. May be displayed.

  Here, for example, in the case of a method of selecting any one of five evaluations of 1 to 5 as shown in FIG. 1 as an evaluation point, generally, the purchasing user U1 selects one of “1” and “5”. It tends to be easy to select such an extreme score, but on the other hand, it tends not to select an intermediate score such as "2" to "4". That is, in the score given by the subjectivity of the purchasing user U1, the evaluation of the store may be extremely biased.

  Also, as in the review shown in FIG. 1, the purchasing user U1 may also post dissatisfaction with the store A in the evaluation statement even though the highest rating of “5.0” is given, and such evaluation If it was going to select the representative of the review to Store A only by the point, there was a possibility that an inappropriate review might be selected.

  Therefore, in the information processing according to the embodiment, an objective evaluation point is calculated based on the evaluation sentence described in the review, and a representative is selected using the calculated objective evaluation point. That is, by selecting the representative objectively, the representative can be appropriately selected as compared with the case where the representative is subjectively selected as in the conventional case. Hereinafter, the information processing according to the embodiment will be described along the flow of a series of processing with reference to FIG. 1.

  In the example illustrated in FIG. 1, the information processing device 1 according to the embodiment first receives registration of a product from the store manager M1 via the store terminal 10 (step S1). Subsequently, the information processing apparatus 1 according to the embodiment provides the information on the product to the purchasing user U1 (not yet purchased at this time) via the user terminal 100-1 (step S2).

  Subsequently, the information processing apparatus 1 according to the embodiment receives the purchase of a product from the purchasing user U1 via the user terminal 100-1, and an evaluation score for the store posted after the purchase (hereinafter referred to as a first evaluation score) And the review information regarding the review including the evaluation sentence (step S3), and stores the review information 41 in the evaluation information 41 (review ID "R2" of the evaluation information 41). That is, the first evaluation point corresponds to the subjective evaluation point of the purchasing user U1. In addition, since the first evaluation point is a method of selecting from the five-step evaluation of 1 to 5, it can be said that the first evaluation point is a discrete value.

  Subsequently, the information processing apparatus 1 according to the embodiment analyzes the word included in the evaluation sentence of the review to calculate an evaluation score (hereinafter, referred to as a second evaluation score) for the store or the product (step S4). In the example shown in FIG. 1, the second evaluation point “3.9” is calculated. That is, the second evaluation point corresponds to the objective evaluation point of the purchasing user U1. The second evaluation point is a sum of the sum of the weight of the word of the positive expression and the sum of the weight of the word of the negative expression (details will be described later with reference to FIG. 9).

  Subsequently, the information processing apparatus 1 according to the embodiment selects a representative review in the store (store A) based on the second evaluation point out of a plurality of reviews in which the first evaluation point is within the predetermined range. (Step S5).

  In the example illustrated in FIG. 1, the information processing apparatus 1 according to the embodiment selects the review ID “R1” having the highest second evaluation point from the same first evaluation points (that is, “5”).

  Then, the information processing apparatus 1 according to the embodiment receives the review request for the review in the store A from the user U2 via the user terminal 100-2 (step S6), the review of the selected representative (review ID “R1 ) Is provided to the user U2 (step S7).

  That is, in the information processing method according to the embodiment, when the user U2 wants to confirm a good evaluation of the store, the review in which the second evaluation point is the highest among the plurality of reviews in which the first evaluation point is “5.0” To be provided to user U2. Conversely, when the user U2 wants to confirm the bad evaluation of the store, the user with the lowest second evaluation score is selected from the plurality of reviews whose first evaluation score is “1.0” to the user U2 provide.

  Thus, according to the information processing method according to the embodiment, it is possible to appropriately select a review that is representative of one store by using the second evaluation point that is an objective evaluation point.

  Although FIG. 1 exemplifies the case of selecting a representative review from a plurality of reviews, for example, a representative store or product may be selected from a plurality of stores or products.

  Further, FIG. 1 shows the case where the review of the selected representative is displayed to the user U2, but for example, for the products displayed in the list of the search results of the products in the shopping site, the representative products are displayed preferentially You may give priority to the products handled by the representative store. Further, the information processing method according to the embodiment is not limited to the case of applying to review display and display of search results, and may be applied to, for example, display of recommendations for recommending a product that the user U2 is likely to be interested.

  Moreover, in FIG. 1, although the first evaluation point selected a representative from the same review, for example, a review in which the first evaluation point is in the range of “4” to “5”, that is, the first evaluation point is predetermined The representative may be selected from the reviews within the scope of

  Next, the configuration of the information processing system S according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an exemplary configuration of the information processing system S according to the embodiment.

  As shown in FIG. 2, the information processing system S includes an information processing device 1, a store terminal 10, and a user terminal 100.

  The information processing device 1, the store terminal 10, and the user terminal 100 are connected via the network N. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (mobile telephone network, fixed telephone network or the like), a regional IP (Internet Protocol) network, the Internet or the like. The network N may include a wired network or may include a wireless network. As shown in FIG. 2, a plurality of store terminals 10 and a plurality of user terminals 100 may be included.

  The user terminal 100 is an information processing apparatus used by a user U (such as a purchased user U1 or a user U2 shown in FIG. 1). The user terminal 100 is, for example, a smartphone, a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), a wearable device, or the like. The user terminal 100 transmits a search request and a purchase request to the information processing apparatus 1 according to the operation by the user U.

  Further, the user terminal 100 transmits the review information to the information processing device 1 according to the operation by the user U. For example, the user terminal 100 transmits the information input by the user U on the posting page for posting a review as review information to the information processing device 1. The post page can be acquired, for example, by accessing the URL disclosed by the information processing apparatus 1 after the purchase of the product (or after the arrival of the product). That is, the review posting page is configured such that only the user who actually purchased the product can post the review.

  The store terminal 10 is an information processing apparatus used by a manager M1 (or an operator) of a store such as an online store. The store terminal 10 is, for example, a desktop PC, a notebook PC, or the like. The store terminal 10 transmits product information (such as a product identifier, a product name, a maker name, a price, an image, etc.) of a product to be sold at the EC site to the information processing apparatus 1 according to an operation by the administrator M1. Further, the store terminal 10 receives, from the information processing apparatus 1, purchase information of the product by the user U (the identifier of the product, the identifier of the purchased user U, the delivery destination, the desired delivery date and time, payment information, etc.).

  The information processing apparatus 1 is a shopping server that functions as an EC site as described above. In the present embodiment, the information processing apparatus 1 provides the function of the online mall to the user U or the store. An online mall is a site where a plurality of stores open. The information processing apparatus 1 provides the user U with the product information collected from the plurality of store terminals 10, and receives a product purchase, and the like.

  The information processing apparatus 1 is also a search server that functions as a search site. The information processing apparatus 1 as a search server provides a search service. For example, the information processing apparatus 1 as a search server receives an input of a search keyword from a user, and provides the user with a search result based on the search keyword.

  The information processing apparatus 1 is also a recommendation server having a recommendation function of recommending a product that the user U is likely to be interested in. The information processing apparatus 1 as a recommendation server acquires behavior information on the network of the user U, and recommends a product based on the behavior information.

  The information processing apparatus 1 is also a generation server that performs the above-described index generation process. As described above, in the present embodiment, an example in which one information processing apparatus 1 functions as a shopping server, a search server, a recommendation server, and a generation server will be described. However, the information processing apparatus 1 may be separated into a shopping server, a search server, a recommendation server, and a generation server.

  Next, the configuration of the information processing apparatus 1 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating an exemplary configuration of the information processing apparatus 1 according to the embodiment.

  As shown in FIG. 3, the information processing apparatus 1 includes a communication unit 2, a control unit 3, and a storage unit 4. The information processing apparatus 1 may be an input unit (for example, a keyboard or a mouse) that receives various operations from a manager or the like who uses the information processing apparatus 1 or a display unit (for example, a liquid crystal display or the like for displaying various information). ) May be provided.

  Communication unit 2 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 2 is connected to the network N in a wired or wireless manner, and transmits and receives information to and from the store terminal 10 and the user terminal 100 via the network N.

  The storage unit 4 is realized by, for example, a semiconductor memory device 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. 3, the storage unit 4 stores evaluation information 41, product information 42, store information 43, user information 44, and word information 45.

  The evaluation information 41 is information including review information on a review posted by the purchase user U1 who has purchased the item, and a second evaluation point calculated by the calculation unit 32 described later. The evaluation information 41 is updated, for example, each time a review is posted by the purchasing user U1. FIG. 4 is a diagram showing an example of the evaluation information 41. As shown in FIG. As shown in FIG. 4, the evaluation information 41 has items such as a review ID, an attribute, a product ID, a store ID, a user ID, a posting date, a first evaluation point, a second evaluation point, a sentence length, and an evaluation sentence.

  The “review ID” is identification information that identifies the received review. The "attribute" is information indicating a target of review. “Product ID” is identification information that identifies a product purchased by the user U who has posted a review. The “store ID” is identification information that identifies a store that handles the product purchased by the user U who has posted a review. The “user ID” is identification information that identifies the user U who has posted a review. The “posting date and time” is information indicating the date and time when the review was posted. The “first evaluation point” is information indicating the evaluation score for the product or store attached by the purchasing user U1. The “second evaluation point” is information indicating the evaluation score of the product or store calculated by the calculation unit 32 described later. The “text length” is information indicating the length of the evaluation text of the review, and is represented by, for example, the number of characters. The “evaluation sentence” is information indicating text data of the evaluation sentence.

  For example, in the example of FIG. 4, the review ID of the review ID “R1” is the posting date “D1” of the user U of the user ID “US1” who purchased the product of the product ID “GD1” handled by the store A of the store ID “SD1”. It shows that it is a review with respect to Store A of store ID "SD1" contributed to "." In addition, the review of the review ID "R1" includes the first evaluation point "5" and the evaluation sentence "from purchase ..." of the sentence length "RL1", and the second evaluation point "from the evaluation sentence" It shows that 11.9 "was calculated.

  The item information 42 is information on an item registered by the store. FIG. 5 is a diagram showing an example of the product information 42. As shown in FIG. As shown in FIG. 5, the product information 42 has items such as a product ID, a product name, the number of reviews, a representative review, a first evaluation point (average value), a second evaluation point (average value), and the like.

  “Product ID” is information that identifies a product. "Product name" indicates the name of the product. The “number of reviews” is information indicating the total number of reviews submitted for a product. The “representative review” is identification information for identifying a review selected as a representative by the selecting unit 33 described later. The “first evaluation point (average value)” is an average value of the first evaluation points of reviews for products, and is a value obtained by dividing the sum of the first evaluation points of all reviews by the “number of reviews”. The “second evaluation point (average value)” is the average value of the second evaluation points calculated from the evaluation sentences of the review, and is a value obtained by dividing the total of the second evaluation points of all reviews by the “number of reviews”. .

For example, in the example illustrated in FIG. 5, the product name of the product ID “GD1” is “Nature water A”, the number of reviews is “400”, and the average value of the first evaluation points is “AVG1”, It indicates that the average value of the second evaluation points is "AVG2". Moreover, the representative review of the product of the product ID “GD1” indicates that the review is a review of the review ID “R1”.

  Although FIG. 5 shows the case where one "representative review" is selected, the number selected as the "representative review" is not limited to one, and a plurality of reviews may be selected as a representative review. Good. Also, when a plurality of representative reviews are selected, information may be included that ranks each of the plurality of representative reviews. In addition, the first evaluation point and the second evaluation point are not limited to the average value, and may be, for example, the mode or median of the distribution at the first evaluation point and the second evaluation point.

  The store information 43 is information on a store that handles products. FIG. 6 is a diagram showing an example of the store information 43. As shown in FIG. As shown in FIG. 6, the store information 43 has items such as a store ID, a store name, a sales amount, a number of reviews, a representative review, a first evaluation point (average value), a second evaluation point (average value), and the like.

  The "store ID" is identification information that identifies a store. "Store name" is the name of the store. The “sales amount” is the amount of money the store has sold during a predetermined period. Such a period is, for example, a divided period such as the latest several months. “Number of reviews” indicates the total number of reviews for the store. The “first evaluation point (average value)” is an average value of the first evaluation points of the reviews for the store, and is a value obtained by dividing the sum of the first evaluation points of all the reviews by the “number of reviews”. The “second evaluation point” is an average value of the second evaluation points calculated from the evaluation sentence of the review, and is a value obtained by dividing the sum of the second evaluation points of all the reviews by the “number of reviews”.

  For example, in the example illustrated in FIG. 6, the store with the store ID “SD1” indicates that the store name is “store A”, and the sales amount of “MN1” is sold in a predetermined period. In addition, in the store A of the store ID “SD1”, the average value of the first evaluation points in all the reviews is “AV11”, the average value of the second evaluation points is “AV21”, and the number of reviews for the store A is It is "4000", and it shows that review ID "R1" in it is a representative review.

  The user information 44 is information on the user U. The user information 44 is generated, for example, by transmitting information registered by the user U to the information processing apparatus 1 which is a shopping server. Alternatively, the user information 44 may be generated by the information processing apparatus 1 acquiring information registered in the user terminal 100. FIG. 7 shows an example of the user information 44. As shown in FIG. As shown in FIG. 7, the user information 44 has items such as a user ID, a user name, the number of reviews, a first evaluation point (average value), a second evaluation point (average value), and the like.

  The “user ID” is identification information for identifying the user U. The “user name” is information indicating the name of the user U. The “number of reviews” is information indicating the total number of reviews submitted by the user U in the past. The “first evaluation point (average value)” is information indicating the average value of the first evaluation points assigned by the user U in the store or the product review. The “second evaluation point (average value)” is information indicating the average value of the second evaluation points calculated from the evaluation statement of the store or the product review.

  For example, in the example illustrated in FIG. 7, the user U with the user ID “US 1” posts a review whose number of reviews is “30” whose user name is “××” in the past, and the first evaluation score based on such a review Indicates that the average value of the second evaluation point is “AVU 11” and the average value of the second evaluation points is “AVU 21”.

  The word information 45 includes information for giving a weight to the words included in the evaluation sentence. The word information 45 is generated in advance, for example, by analyzing a large number of past reviews (for example, hundreds of thousands of reviews). FIG. 8 is a diagram showing an example of the word information 45. As shown in FIG. As shown in FIG. 8, the word information 45 has items such as expression attribute, word ID, word name, number of appearances, weight and the like.

  The “expression attribute” is information indicating an attribute of expression of a word, and indicates, for example, an attribute of whether the word is a positive expression or a negative expression. "Word ID" is identification information for identifying a word. The “word name” is information indicating the name of a word. The “number of occurrences” indicates the total number of occurrences in the analyzed past review. "Weight" is a value indicating the rating of a store or a product.

  For example, in the example shown in FIG. 8, the word of the word ID “T1” has the word name “polite” and the expression attribute “affirmed”, that is, a positive expression, and the number of appearances of past reviews is “ This is ST1 'times, and indicates that the weight is "W1" (positive value).

  Further, in the example shown in FIG. 8, the word of the word ID "T11" has the word name "Sorry", the expression attribute is "Negative", that is, a negative expression, and the number of appearances of past reviews is " ST11 ′ ′, which indicates that the weight is “−W11” (negative value).

  Further, in the example shown in FIG. 8, the word with the word ID “T21” is a word whose word name is “future” and whose expression attribute is “none”, that is, neither positive nor negative. The number of occurrences is “ST21” times, and the weight is “0 (zero)”.

  The “weight” of each word is determined, for example, based on the words extracted from a large number of past reviews. Specifically, first, a large number of reviews are classified into positive cases (reviews of positive evaluations) and negative cases (reviews of negative evaluations).

  For example, the review with the first evaluation score of “4” and “5” is a positive example, and the review with the first evaluation score of “1” and “2” is a negative example. Subsequently, using the past reviews classified into the positive and negative examples as learning data, a discriminator is generated which identifies whether each word of the past reviews is a positive expression or a negative expression. A support vector machine (SVM) can be used as an example of such a discriminator.

  For example, a separating line for arranging each word of the past review in a predetermined space as learning data using the past review as described above, and linearly separating the word of the positive expression and the word of the negative expression in the space Is generated as a learning result of the classifier. This determines whether the weight of each word is a positive value (i.e., a positive expression) or a negative value (i.e., a negative expression).

  Then, based on the distance from a word arranged in a predetermined space (for example, a two-dimensional space) to a separation line which linearly separates the space, the magnitude relation of the weight of each word is determined. For example, the weight of a word is increased as the distance to the separation line is longer, and the weight of the word is decreased as the distance to the separation line is shorter. This makes it possible to accurately determine the weight of words in positive or negative expressions.

  Further, the “weight” is not limited to the case where it is determined based on the classifier, and for example, a manager of the information processing apparatus 1 or the like may set it manually. When the administrator sets, for example, the word weight of the positive expression is set to “+1”, and the word weight of the negative expression is set to “−1”. As a result, since calculation at the time of calculation processing of a second evaluation point described later of the information processing apparatus 1 can be simplified, processing load of the information processing apparatus 1 in post-stage processing can be suppressed.

  Also, the "weight" may be determined based on the number of occurrences in the past review. That is, the weight of the word of the past review in the positive example is set to a positive value, and the weight is determined so as to increase as the number of occurrence increases. In addition, the weight of the word of the past review in the negative example is set to a negative value, and the weight is determined so as to increase as the number of occurrence increases.

  The above-described “weight” determination process may be performed by the information processing apparatus 1 or may be acquired as the word information 45 determined by a server apparatus (not shown). In addition, when the information processing device 1 performs the determination process, the word information 45 may be updated using the review acquired by the acquisition unit 31 as learning data.

  The control unit 3 is a controller, and for example, various programs (information processing programs) stored in a storage device inside the information processing apparatus 1 by a central processing unit (CPU), a micro processing unit (MPU) or the like. (Corresponding to an example) is realized by executing the RAM as a work area. The control unit 3 is, for example, 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 shown in FIG. 3, the control unit 3 includes an acquisition unit 31, a calculation unit 32, a selection unit 33, a determination unit 34, and a provision unit 35, and functions and functions of the information processing described below. Realize or execute. Note that the internal configuration of the control unit 3 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as it performs the information processing described later.

  The acquiring unit 31 acquires review information regarding a review including a first evaluation score and an evaluation statement for a store or an item posted by a purchasing user U1 who has purchased an item handled by the store.

  The acquisition unit 31 may directly acquire review information from the purchasing user U1 via the user terminal 100, or may acquire review information collected by a server device (not shown).

  When acquiring review information from the server apparatus which is not shown in figure, the acquisition timing of the review information of the acquisition part 31 may be arbitrary. For example, the acquisition unit 31 may acquire review information each time the server apparatus collects new review information. In addition, the acquisition unit 31 may collectively acquire new review information when the number of new review information acquired by the server device exceeds a threshold.

  Further, the acquiring unit 31 may acquire the review information from the server device in a time zone predetermined as a time zone in which the processing load of the information processing device 1 as the shopping server decreases, for example. In addition, the acquisition unit 31 may acquire the review information from the server device when the number of accesses to the EC site falls below a threshold. As described above, by acquiring the review information under a condition where the processing load of the information processing device 1 is small, it is possible to suppress an increase in the processing load of the information processing device 1 accompanying the processing of the latter stage.

  The calculating unit 32 analyzes a word included in the evaluation sentence of the review acquired by the acquiring unit 31 to calculate a second evaluation point for the store or the product. In addition, the calculation unit 32 calculates a second evaluation point on the review information of the store or the product. For example, the calculating unit 32 determines, for each word, a weight that indicates the quality of the evaluation of the store or the product, and calculates a second evaluation point based on an integrated value obtained by integrating the weight. Here, the calculation process of the second evaluation point will be specifically described with reference to FIG.

  FIG. 9 is an explanatory diagram of a calculation process of the second evaluation point according to the embodiment. As shown in FIG. 9, the evaluation statement “Packing is necessary and sufficient, it is satisfactory. The goods are also received immediately. However, the advertisement mail comes to be received, and the delivery stop procedure becomes very troublesome and closed. Then, the case of calculating the second evaluation point from the case of being the highest ... will be described as an example. Note that the weight and the second evaluation point shown in FIG. 9 are merely examples, and any value may be set.

  As shown in FIG. 9, the calculation unit 32 first decomposes the evaluation sentence into words of the smallest unit having meaning in the language by morphological analysis. The decomposed words include nouns, verbs, particles, or combinations thereof. Then, as shown in FIG. 9, the calculation unit 32 determines the weight for each word with reference to the word information 45.

  In FIG. 9, the calculating unit 32 determines the weight of the positive value for “packing, sufficient”, “satisfying”, “immediately received”, and “highest” as the positive expression (that is, the weight is a positive value). And calculate the sum of each weight. In FIG. 9, it is assumed that "6.8" is calculated as the sum of weights of positive expressions.

  In addition, the calculation unit 32 determines negative weights for "advertisement, trouble", "closing", and "improvement" as negative expressions (that is, negative weights), and calculates the sum of the weights. . In FIG. 9, it is assumed that “−2.9” is calculated as the sum of weights of negative expressions.

  Then, the calculating unit 32 calculates an integrated value by integrating the calculated sum of weights of positive expressions and the sum of weights of negative expressions. In FIG. 9, that is, “6.8 + (− 2.9) = 3.9” is calculated as the second evaluation value. That is, the calculation unit 32 calculates the second evaluation point by subtracting the sum of the weights of the negative expression from the sum of the weights of the positive expression.

  That is, the calculation unit 32 calculates the second evaluation point to be larger as the number of positive expressions is larger, and calculates the second evaluation point to be smaller as the negative expressions are larger. Thus, the second evaluation point with high objectivity can be calculated by integrating the weights of the words of the positive expression and the negative expression to calculate the second evaluation point.

  In addition, the calculation unit 32 may calculate all the words of the positive expression and the negative expression (that is, all the words whose weights are determined) as a second evaluation point by integration, or words of the positive expression and the negative expression Among the above, only words having weights greater than or equal to a predetermined threshold may be integrated.

  That is, the calculation unit 32 calculates an integrated value by integrating only weights having a predetermined threshold value or more among the weights of the words included in the evaluation sentence. As a result, the second evaluation point can be calculated by excluding the positive expression and the negative expression close to the intermediate expression (that is, the expression attribute “absent” in FIG. 8), so that the load on the calculation process of the calculation unit 32 can be suppressed. A highly objective second evaluation point can be calculated.

  In FIG. 9, the calculation unit 32 calculates the integrated value of the weight of the word in the positive expression and the negative expression as the second evaluation point, but is not limited to this. For example, the second evaluation point is added An evaluation point may be calculated.

  For example, the calculation unit 32 may set a value obtained by summing the integrated value of the weight of the word of the positive expression and the negative expression and the first evaluation point as the second evaluation point. That is, when the first evaluation point is “5”, the second evaluation point may be calculated as “3.9 + 5 = 8.9”.

  In addition, the calculation unit 32 analyzes whether the words included in the evaluation sentence are positive expressions or negative expressions, and the ratio of the number of words of the other expression to the number of words of one expression is It may be calculated as a second evaluation point. This makes it possible to calculate an objective second evaluation point.

  Returning to FIG. 3, the selection unit 33 will be described. The selection unit 33 sets the second evaluation point calculated by the calculation unit 32 from among a plurality of first evaluation points acquired by the acquisition unit 31 within a predetermined range for at least one of the store, the product, and the review. Select a representative based on it.

  For example, the selection unit 33 selects one of a plurality of stores (or products or reviews) whose “first evaluation point (average value)” of the store information 43 is within a predetermined range, based on the second evaluation point. Select a representative (or a product or review).

  For example, the selecting unit 33 selects a store having the highest second evaluation point as a representative of the high evaluation store from among a plurality of stores in which the first evaluation point is in the range of “4” to “5”. Further, the selection unit 33 selects a store with the lowest second evaluation point as a representative of the low evaluation store from among a plurality of stores in which the first evaluation point is in the range of “1” to “2”.

  That is, the selection unit 33 selects a representative from the range of the extreme first evaluation points where the evaluation of the purchasing user U1 is easy to concentrate. Thereby, even if the first evaluation point is extremely biased, it is possible to select an appropriate store (or a product or a review) from among them.

  The selecting unit 33 is not limited to the case where one store is selected as a representative from a plurality of stores, and a plurality of stores may be selected as a representative. For example, the selection unit 33 selects a plurality of stores with the second evaluation point ranked high (for example, 1 to 10). Thereby, it is possible to appropriately select a plurality of stores with high evaluation (or low evaluation) from stores whose first evaluation point is within the predetermined range.

  Furthermore, the selection unit 33 may select a representative from among those having the same first evaluation point, for example, without being limited to the case where the first evaluation point is within the predetermined range. Such a selection method is suitable when selecting a review.

  That is, the selection unit 33 selects a representative review based on the second evaluation points from a plurality of reviews having the same first evaluation point based on the evaluation information 41. For example, when the selection unit 33 requests the user U to read the high evaluation review in one store, the selection unit 33 has the highest second evaluation score among a plurality of reviews having the same first evaluation score in one store. Select a review as a representative of a high rating review.

  Alternatively, when the selection unit 33 requests the user U to read the low evaluation review in one store, the second evaluation point is the lowest among a plurality of reviews having the same first evaluation point in one store. Select a review as a representative for a low rating review.

  The selection unit 33 is not limited to selecting one review as a representative, and may select a plurality of reviews as a representative. Specifically, the selection unit 33 selects, as a representative, a plurality of reviews in which the second evaluation point is within a predetermined range from the reviews in one store. When a plurality of reviews are selected as a representative by the selection unit 33, the determination unit 34 described later performs ranking for each of the plurality of reviews.

  When the selecting unit 33 selects a plurality of reviews, the determining unit 34 ranks each of the plurality of reviews. For example, for the plurality of reviews selected by the selection unit 33, the determination unit 34 determines the order of the plurality of reviews based on the length of the evaluation sentence of each review.

  For example, the determination unit 34 sets the rank higher as the evaluation sentence length is longer. More specifically, the determination unit 34 ranks, according to the length of the evaluation sentence, a plurality of reviews in which the second evaluation point selected by the selection unit 33 is within a predetermined range. For example, when there are a plurality of reviews having the same second evaluation point, the determination unit 34 ranks higher as the number of words is larger, that is, the length of the evaluation sentence is longer.

  Alternatively, when the range of the second evaluation points of the plurality of selected reviews is relatively narrow, the determination unit 34 ranks only by the length of the evaluation sentence regardless of the second evaluation points. That is, if the second evaluation point is within the above-mentioned range and one review has a lower second evaluation point than the other reviews, if the evaluation sentence is longer in length than the other reviews, the one review does not Ranked higher than the review.

  Thereby, when the range of the second evaluation point is relatively narrow, the providing unit 35 described later can provide the user U with a long review of the evaluation sentence by ranking only by the length of the evaluation sentence. , A user U can be provided with a more informative review.

  In addition, although the determination part 34 determined the order of the review so that it might become higher as the length of the evaluation sentence is longer, for example, even if the second evaluation point is normalized by the length of the evaluation sentence and then ranked Good. Specifically, the determination unit 34 normalizes the second evaluation point of each of the plurality of reviews selected by the selection unit 33 with the length of the evaluation sentence, and determines the order based on the normalized second evaluation point. .

  For example, the determination unit 34 determines the order based on a ratio value obtained by dividing the second evaluation point by the length of the evaluation sentence. For example, the determination unit 34 ranks the higher the review in which the percentage value (corresponding to the normalized second evaluation point) is high.

  As described above, since the determination unit 34 can perform ranking regardless of the length of the evaluation sentence by normalizing the second evaluation point with the length of the evaluation sentence, the providing unit 35 described later transmits to the user U It is possible to provide highly rated reviews that do not depend on the length of the evaluation statement.

  The providing unit 35 provides the user U with at least one of the store, product or review selected as a representative by the selecting unit 33. For example, the providing unit 35 provides the store or the product selected as the representative by the selecting unit 33 based on the behavior of the user U on the network N.

  More specifically, when there is a search request for searching for a product from user U, providing unit 35 generates a search result in which the product selected as a representative is preferentially displayed, and provides the same to user U. . More specifically, the providing unit 35 provides the user U with a search result including only the product selected as a representative, and a search result displayed above the list display.

  Further, when there is a search request for searching for a product from the user U, the providing unit 35 generates a search result in which the product handled by the store selected as a representative is preferentially displayed, and provides the same to the user U. It is also good. Note that a screen example of a search result will be described later with reference to FIG.

  Further, the providing unit 35 gives priority to the user U with respect to the product selected as a representative in the recommendation function of proposing a product that the user U is likely to be interested based on the user U's behavior on the network N. It may be recommended.

  Further, when there is a request for viewing a review in one store from the user U, the providing unit 35 provides the user U with the review selected as a representative by the selecting unit 33. Note that a display example of the review will be described later with reference to FIG.

  Next, the provision processing of the provision unit 35 will be further described using FIG. 10 and FIG. 10 and 11 are explanatory diagrams of the provision processing of the provision unit 35 according to the embodiment. FIG. 10 shows an example screen of a review display in one store, and FIG. 11 shows an example screen of a search result. The screens shown in FIGS. 10 and 11 are generated by, for example, the providing unit 35 and transmitted to the user terminal 100.

  First, a screen example of the review display will be described using FIG. In FIG. 10, a screen example in the case where a plurality of reviews including the review RV1 and the review RV2 are selected as a representative by the selection unit 33 will be described. In FIG. 10, it is assumed that the rank determined by the determination unit 34 is higher in the review RV1 than in the review RV2, and the second evaluation point is also higher.

  That is, as shown in the screen example of FIG. 10, the providing unit 35 displays the plurality of representative reviews RV1 and RV2 selected by the selecting unit 33 in the order determined by the determining unit 34. To provide.

  Thus, by displaying the review in the order determined based on the second evaluation points by the determination unit 34, even if the first evaluation points as shown in FIG. 10 are the same "5", the order is appropriate. Since the review display can be performed, it can be facilitated that the user U accurately determines the quality of the store (store A).

  In FIG. 10, although a plurality of reviews RV1 and RV2 are selected as representatives and displayed as a review, only the review RV1 ranked highest may be displayed as a review. Thereby, it is possible to prevent the user U from being lost in judgment of good or bad by reading a plurality of reviews RV1 and RV2.

  Further, in the screen of FIG. 10, it is possible to display a review selected as a representative of the low evaluation by clicking (or touch operation) “★ Review 1 here”. As a result, the user U can easily switch between and view the high rating review (★ 5 reviews) and the low rating review.

  Next, a screen example of a search result will be described using FIG. In FIG. 11, the screen of the search result with respect to the search request | requirement containing a search keyword "natural water" is shown. As shown in the screen example in Fig. 11, the screen of the search results displays "Saturated water" with only stores with an average value of 4.5 or more, in the order of high evaluation of the store review statement. An additional explanation of "is displayed.

  That is, when the first evaluation point is 4.5 or more, the providing unit 35 selects a plurality of stores that handle natural water products as a representative, and the plurality of stores are listed in the search results in descending order of the second evaluation point. Generate search results to be displayed.

  That is, the providing unit 35 does not display the search results in the order of the subjectively assigned first evaluation points, and the high evaluation store is substantially equal when the first evaluation points are equal to or more than a predetermined value (4.5 or more). The search results are sorted by the second evaluation point. As a result, a store that is truly evaluated is preferentially displayed in the search results, so that it is possible to facilitate the user U's judgment of the quality of the store.

  Note that if you want to browse products in stores other than the store where user U is selected as a representative, click (or touch operation) "Click here to see" Natural water "in all stores. , Search results that match "natural water" are displayed for products handled by all stores.

  Next, a procedure of processing performed by the information processing device 1 according to the embodiment will be described with reference to FIG. FIG. 12 is a flowchart illustrating the procedure of processing performed by the information processing device 1 according to the embodiment.

  As shown in FIG. 12, first, the acquiring unit 31 acquires review information on a review including a first evaluation point and an evaluation sentence for a store or an item posted by a purchasing user U1 who has purchased an item handled by the store (Steps S101).

  Subsequently, the calculating unit 32 analyzes the words included in the review acquired by the acquiring unit 31 and calculates a second evaluation point for the store or the product (step S102). Subsequently, the selection unit 33 calculates the second calculated by the calculation unit 32 from among a plurality of first evaluation points acquired by the acquisition unit 31 within a predetermined range for at least one of the store, the product, and the review. A representative is selected based on the evaluation point (step S103), and the process ends.

  The information processing apparatus 1 according to the embodiment described above is realized by, for example, a computer 1000 having a configuration as shown in FIG. FIG. 13 is a hardware configuration diagram showing an example of a computer 1000 for realizing the function of the information processing apparatus 1 according to the embodiment. The computer 1000 includes 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.

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

  The HDD 1400 stores a program executed by the CPU 1100, data used by the program, and the like. The communication interface 1500 receives data from another device via the network N and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to the other device via the network N.

  The CPU 1100 controls an output device such as a display or a printer and an input device such as a keyboard or a mouse via the input / output interface 1600. The CPU 1100 acquires data from an input device via the input / output interface 1600. The CPU 1100 also 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 the CPU 1100 with the program 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 digital versatile disc (DVD) or a phase change rewritable disc (PD), a magneto-optical recording medium such as a magneto-optical disk (MO), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the information processing apparatus 1 according to the embodiment, the CPU 1100 of the computer 1000 realizes the function of the control unit 3 by executing a program loaded on the RAM 1200. Further, data in the storage unit 4 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the network N.

  As described above, the information processing apparatus 1 according to the embodiment includes the acquisition unit 31, the calculation unit 32, and the selection unit 33. The acquiring unit 31 acquires review information regarding a review including a first evaluation score and an evaluation statement for a store or an item posted by a purchasing user U1 who has purchased an item handled by the store. The calculating unit 32 analyzes a word included in the evaluation sentence of the review acquired by the acquiring unit 31 to calculate a second evaluation point for the store or the product. The selection unit 33 sets the second evaluation point calculated by the calculation unit 32 from among a plurality of first evaluation points acquired by the acquisition unit 31 within a predetermined range for at least one of the store, the product, and the review. Select a representative based on it.

  Thereby, since the representative can be selected objectively, the representative can be appropriately selected as compared with the case where the representative is selected subjectively as in the prior art.

  In addition, in the information processing device 1 according to the embodiment, the selection unit 33 selects a representative from among a plurality of the same first evaluation points.

  As a result, even if the first evaluation points are the same, it is possible to facilitate the user U to accurately determine the quality of the store (store A).

  The information processing apparatus 1 according to the embodiment also includes a providing unit 35. The providing unit 35 provides the store or the product selected as the representative by the selecting unit 33 based on the behavior of the user U on the network N.

  As a result, a store that is truly evaluated is preferentially displayed on the search result screen or the recommendation screen, so that the user U can easily judge the quality of the store.

  The information processing apparatus 1 according to the embodiment also includes a providing unit 35. The providing unit 35 provides the user U with the review selected as a representative by the selecting unit 33 when there is a request for viewing a review in one store from the user U.

  Thereby, since the selected review can be displayed in an objective evaluation, it is possible to facilitate the user U to accurately determine the good or bad based on the review of the store or the product.

  In addition, the information processing apparatus 1 according to the embodiment includes the determination unit 34. When the selection unit 33 selects a plurality of reviews, the determination unit 34 determines the order of the plurality of reviews based on the length of the evaluation sentence. The selection unit 33 selects, from the reviews in one store, a plurality of reviews having the second evaluation point within a predetermined range as a representative review. The providing unit 35 provides the user U with a plurality of representative reviews selected by the selecting unit 33 in the order determined by the determining unit 34.

  Thereby, for example, since a review sentence etc. can exclude a short review etc., a review including more useful information can be provided to user U.

  In addition, in the information processing device 1 according to the embodiment, the determination unit 34 ranks higher as the evaluation sentence length is longer.

  Thereby, for example, when the range of the second evaluation point is relatively narrow, the providing unit 35 can provide the user U with a long review of the evaluation sentence by ranking only by the length of the evaluation sentence. A more informative review can be provided to the user U.

  In addition, in the information processing device 1 according to the embodiment, the determination unit 34 normalizes the second evaluation point of each of the plurality of reviews with the length of the evaluation sentence, and the higher the normalized second evaluation point, the higher the rank Make it

  As a result, since the ranking can be performed regardless of the length of the evaluation sentence, the providing unit 35 can provide the user U with a review of high evaluation (or low evaluation) that does not depend on the length of the evaluation sentence.

  In addition, in the information processing device 1 according to the embodiment, the calculation unit 32 determines, for each word, a weight indicating the quality of the evaluation of the store or the product, and the second evaluation point is calculated based on the integrated value obtained by integrating the weight. calculate.

  As a result, the second evaluation point can be calculated by integrating the weight of the word of the positive expression and the negative expression, so that the second evaluation point with high objectivity can be calculated.

  In addition, in the information processing device 1 according to the embodiment, the calculating unit 32 calculates an integration value by integrating weights of a predetermined threshold or more among the weights of the words included in the evaluation sentence.

  As a result, since the second evaluation point can be calculated excluding the positive expression and the negative expression close to the intermediate expression, the second evaluation point with high objectivity can be calculated while suppressing the load applied to the calculation process of the calculation unit 32.

  In addition, in the information processing device 1 according to the embodiment, the calculation unit 32 analyzes whether the word included in the evaluation sentence is a positive expression or a negative expression, and calculates the number of words in one expression. The ratio of the number of words in the other expression is calculated as a second evaluation point.

  This makes it possible to calculate an objective second evaluation point.

  Although some of the embodiments of the present application have been described above in detail based on the drawings, these are only examples, and various modifications can be made based on the knowledge of those skilled in the art, including the aspects described in the section of the description of the invention. It is possible to implement the invention in other improved forms.

  Further, among the processes described in the above embodiment, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of them can be performed automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

  Further, each component of each device illustrated is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the distribution and integration of each device is not limited to the illustrated one, and all or a part thereof may be functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured.

  In addition, the processes described in the above-described embodiment can be appropriately combined within the range in which the process contents do not contradict each other.

  Also, the "section (module, unit)" described above can be read as "means" or "circuit". For example, the calculation unit 32 can be read as a calculation unit or a calculation circuit.

DESCRIPTION OF SYMBOLS 1 information processing apparatus 2 communication part 3 control part 4 storage part 10 store terminal 31 acquisition part 32 calculation part 33 selection part 34 determination part 35 provision part 41 evaluation information 42 goods information 43 store information 44 user information 45 word information 100 user terminal

Claims (13)

An acquisition unit for acquiring review information on a review posted by the purchasing user who has purchased the item handled by the store or a first evaluation point and an evaluation statement for the item;
A calculation unit that analyzes a word included in the evaluation sentence of the review acquired by the acquisition unit to calculate a second evaluation point for the store or the product;
With regard to the second evaluation point calculated by the calculation unit from among a plurality of the first evaluation points acquired by the acquisition unit being within a predetermined range for at least one of the store, the product, and the review An information processing apparatus comprising: a selection unit which selects a representative based on the selected information. The calculation unit
The information processing apparatus according to claim 1, wherein a second evaluation point of the store or the review information of the product is calculated based on the review acquired by the acquisition unit. The selection unit is
The information processing apparatus according to claim 2, wherein the representative is selected from a plurality of the first evaluation points being the same. The information processing apparatus according to claim 3, further comprising: a providing unit configured to provide the store selected as the representative by the selection unit or the product based on an action of the user on the network. The information processing apparatus further comprising: a providing unit that provides the user with the review selected as the representative by the selection unit when the user requests viewing of the review in one of the stores. The information processing apparatus according to 3. The system further includes a determination unit that determines the order of the plurality of reviews based on the length of the evaluation sentence when a plurality of the reviews are selected by the selection unit.
The selection unit is
Among the reviews in the one store, the plurality of reviews having the second evaluation point within a predetermined range are selected as the representative review.
The providing unit is
The information processing apparatus according to claim 5, wherein the plurality of representative reviews selected by the selection unit are provided to the user in the order determined by the determination unit. The determination unit is
The information processing apparatus according to claim 6, wherein the order is higher as the length of the evaluation sentence is longer. The determination unit is
The second rank of each of the plurality of reviews is normalized by the length of the evaluation sentence, and the rank is ranked higher as the normalized second rank is higher. Information processing equipment. The calculation unit
The weight which shows the quality of evaluation with respect to the said store or the said goods is determined for every said word, The said 2nd evaluation point is calculated based on the integrated value which integrated the said weight. The information processing apparatus according to any one. The calculation unit
The information processing apparatus according to claim 9, wherein the integrated value is calculated by integrating the weights having a predetermined threshold value or more among the weights of the words included in the evaluation sentence. The calculation unit
It is analyzed whether the words included in the evaluation sentence are positive expressions or negative expressions, and the ratio of the number of words in the other expression to the number of words in one expression is the The information processing apparatus according to any one of claims 1 to 10, wherein it is calculated as a second evaluation point. An information processing method executed by the information processing apparatus;
An acquisition step of acquiring review information on a review posted by the purchase user who has purchased the item handled by the store or a review including the first evaluation point and the evaluation statement for the item;
A calculation step of analyzing a word included in the evaluation sentence of the review acquired by the acquisition step to calculate a second evaluation point for the store or the product;
The second evaluation point calculated by the calculation step is selected from among a plurality of the first evaluation points acquired by the acquisition step within a predetermined range for at least one of the store, the product, and the review A selection step of selecting a representative based on the information processing method. An acquisition procedure for acquiring review information on a review posted by the purchasing user who has purchased the item handled by the store or a first evaluation point and an evaluation statement for the item;
A calculation procedure for analyzing a word included in the evaluation sentence of the review acquired by the acquisition procedure to calculate a second evaluation point for the store or the product;
For at least one of the store, the product, and the review, the second evaluation point calculated by the calculation procedure out of a plurality of the first evaluation points acquired by the acquisition procedure being within a predetermined range An information processing program causing a computer to execute a selection procedure of selecting a representative based on the information processing program.

Images