JP6796384B2 - Dictionary construction device, information processing device, evaluation word dictionary production method, information processing method, and program - Google Patents

Description

The present invention relates to an information processing device or the like that analyzes comments such as word-of-mouth.

Conventionally, there has been a technique for analyzing the reputation of people, things, and things that are talked about on blogs (see, for example, Non-Patent Document 1). This technology is a technology that analyzes text based on a large-scale semantic dictionary, extracts reputation information according to evaluation points, and evaluates it.

"goo Reputation Analysis", [online], NTT Resonant, [Search on July 28, 2013], Internet [URL: http://blog-hyoban.goo.ne.jp/]

However, in the prior art, appropriate information processing could not be performed for comments such as word-of-mouth.

The dictionary construction device of the first invention is a comment acquisition unit that acquires comments input by one or more users with respect to an evaluation target, and one or more comments corresponding to scores from a recording medium, and one or more. From each comment of, obtain an evaluation word group consisting of two or more evaluation words that are co-occurring two or more terms and are related to evaluation, and score one or more corresponding to the comment including the evaluation word group. The evaluation information acquisition unit that determines the score corresponding to the evaluation word group and acquires one or more evaluation information having the score and the evaluation word group, and the storage unit that stores one or more evaluation information in the recording medium. It is a dictionary construction device including.

With such a configuration, a dictionary for acquiring an appropriate evaluation value for comments such as word-of-mouth can be automatically constructed.

Further, in the dictionary construction apparatus of the second invention, for the first invention, the evaluation word group includes keywords related to the evaluation of the evaluation target, characteristic words indicating the characteristics related to the keywords, and degree words indicating the degree of evaluation. It is a dictionary construction device that has.

With such a configuration, a dictionary for acquiring an appropriate evaluation value for comments such as word-of-mouth can be automatically constructed.

Further, the information processing apparatus of the third invention is an evaluation word related to evaluation of an evaluation target, and is an evaluation word having two or more evaluation information having two or more evaluation word groups having different meanings. It consists of a dictionary storage unit that stores a dictionary, a comment acquisition unit that acquires one or more comments entered by one or more users from a recording medium, and two or more evaluation words that co-occur from each of the one or more comments. An evaluation value acquisition unit that acquires an evaluation word group, applies the evaluation word group to the evaluation word dictionary, and acquires the evaluation value of the evaluation target, and an output unit that outputs the evaluation value of the evaluation target acquired by the evaluation value acquisition unit. It is an information processing device provided with.

With such a configuration, an appropriate evaluation value can be obtained for comments such as word-of-mouth.

Further, in the information processing apparatus of the fourth invention, with respect to the third invention, the evaluation word group includes keywords related to the evaluation of the evaluation target, characteristic words indicating the characteristics related to the keywords, and degree words indicating the degree of evaluation. It is an information processing device that has.

With such a configuration, an appropriate evaluation value can be obtained for comments such as word-of-mouth.

Further, the information processing apparatus of the fifth invention has an evaluation word group and a score which is an evaluation value for the evaluation information with respect to the first or second invention, and the evaluation value acquisition unit It is an information processing device that acquires two or more co-occurring evaluation words from each one or more comments, and acquires an evaluation value to be evaluated by using a score corresponding to the two or more evaluation words.

With such a configuration, an appropriate evaluation value can be obtained for comments such as word-of-mouth.

Further, in the information processing apparatus of the sixth invention, the dictionary storage unit stores an evaluation word dictionary for each of two or more evaluation targets for any one of the third to fifth inventions. The evaluation value acquisition unit further includes an evaluation target determination unit that determines the evaluation target of each one or more comments acquired by the acquisition unit, and the evaluation value acquisition unit is an evaluation word consisting of two or more evaluation words co-occurring from each one or more comments. It is an information processing device that acquires a group, applies the evaluation word group to the evaluation word dictionary corresponding to the evaluation target determined by the evaluation target determination unit, and acquires the evaluation value of the evaluation target.

With such a configuration, an appropriate evaluation value can be obtained for comments such as word-of-mouth.

Further, in the information processing apparatus of the seventh invention, the dictionary storage unit stores an evaluation word dictionary for each of two or more evaluation items for any one of the third to sixth inventions. The value acquisition unit acquires two or more evaluation word groups from each of one or more comments, determines evaluation items corresponding to each of two or more evaluation word groups, and corresponds to the evaluation items for each determined evaluation item. An information processing device that applies to an evaluation word dictionary, acquires evaluation values, and outputs the evaluation values acquired by the evaluation value acquisition unit for each evaluation item.

With such a configuration, an appropriate evaluation value can be obtained for comments such as word-of-mouth.

Further, in the information processing apparatus of the eighth invention, with respect to the third to seventh inventions, the dictionary storage unit stores an evaluation word dictionary having one or more evaluation information accumulated by the above-mentioned dictionary construction apparatus. It is an information processing device.

With such a configuration, an appropriate evaluation value can be obtained for comments such as word-of-mouth.

Further, the comment output device of the ninth invention is a comment corresponding to a receiving unit for receiving a comment output instruction and a user identifier of a user who has transmitted the output instruction, and is a comment with a score associated with the comment. The self-comment acquisition unit that acquires the above self-comment and the other comment acquisition unit that acquires one or more other comments, which are comments corresponding to the user identifier of another user different from the user and have a score. And 1 or more own user information, 1 or more own comment and information having a score corresponding to each own comment, and 1 or more other user information, 1 or more of each other user. Using other comments and one or more other information that has a score corresponding to each other comment, other information similar to the own information can be obtained for each other user so as to satisfy a predetermined condition. It is a comment output device including a similar user determination unit for determining and an output unit for outputting one or more other comments corresponding to one or more other information determined by the similar user determination unit.

With such a configuration, comments such as reviews of others similar to oneself can be appropriately seen.

Further, in the comment output device of the tenth invention, with respect to the ninth invention, the similar user determination unit is information of one or more own users, and one or more self-comments and one or more for each other user. The degree of similarity with other comments is calculated, and using the degree of similarity and the score corresponding to each comment, other information similar to the own information is determined for each other user so that a predetermined condition is satisfied. It is a comment output device.

With such a configuration, comments such as reviews of others similar to oneself can be appropriately seen.

Further, in the comment output device of the eleventh invention, with respect to the tenth invention, the similar user determination unit satisfies one or more self-comments, a score corresponding to each self-comment, and a predetermined condition. Acquire one or more other comments corresponding to the approximate score, calculate the similarity between one or more other comments and one or more own comments, and the more the similarity satisfies a predetermined condition, the more self-information It is a comment output device that determines other information similar to.

With such a configuration, comments such as reviews of others similar to oneself can be appropriately seen.

According to the information processing apparatus according to the present invention, appropriate information processing can be performed for comments such as word-of-mouth.

The figure which shows the conceptual diagram of the information system 1 in Embodiment 1. Block diagram of the information system 1 Next, a flowchart illustrating the operation of the information processing apparatus 12. Flowchart explaining the process of acquiring the evaluation value of the comment Flow chart explaining the division process Flow chart explaining the evaluation word dictionary acquisition process Diagram showing the same evaluation word dictionary Diagram showing the same evaluation word dictionary Diagram showing the same unique name information management table Diagram showing an example of the comment The figure which shows the evaluation value table by evaluation item by the comment Figure showing the number of reviews by the same evaluation value The figure which aggregated the number of effect tags attached to the review data by evaluation value Figure showing the result of the experiment Block diagram of the dictionary construction device 2 according to the second embodiment A flowchart explaining the operation of the dictionary construction device 2. Block diagram of the information system 3 according to the third embodiment Flow chart explaining the operation of the comment output device 31 Flow chart explaining the same user judgment process Flowchart explaining an example of similarity calculation processing of comments with the same score Flowchart explaining an example of similarity calculation processing of comments with the same score Diagram showing the same output example Block diagram of the computer system in the above embodiment

Hereinafter, embodiments of the information processing apparatus and the like will be described with reference to the drawings. In the embodiment, the components with the same reference numerals perform the same operation, and thus the description may be omitted again.

(Embodiment 1)

In the present embodiment, comments (reviews, reviews) are automatically evaluated using an evaluation word dictionary based on the co-occurrence of two or more terms (which may be called evaluation words), and each review is automatically evaluated. An information system including an information processing device for acquiring a score will be described. Here, the term is usually a word, but it may be a phrase or the like and is widely understood.

Further, in the present embodiment, an information system including an information processing device in which two or more co-occurring terms include three types of evaluation words, degree words, and feature words will be described.

Further, in the present embodiment, an information system in which the evaluation word dictionary includes an information processing device having a score corresponding to a comment will be described.

Further, in the present embodiment, an information system including an information processing device in which two or more evaluation targets exist and the evaluation word dictionary used differs depending on the evaluation target will be described.

Further, in the present embodiment, an information system including an information processing device in which a plurality of evaluation items exist for one evaluation target and the evaluation word dictionary used differs depending on the evaluation items will be described.

FIG. 1 is a conceptual diagram of the information system 1 according to the present embodiment. The information system 1 includes one or more external devices 11, an information processing device 12, and one or more terminal devices 13. The external device 11 is a server device that stores comments such as word-of-mouth. The comment is information entered by the user and posted to a word-of-mouth, a blog, a bulletin board, an SNS, a so-called tweeter, or the like, and may be considered to include a so-called CGM (Consumer Generated Media). Further, the information processing device 12 is a device that analyzes one or more comments and acquires an evaluation of an evaluation target. Further, the terminal device 13 is a user terminal that accesses the information processing device 12 and outputs the evaluation of the evaluation target.

FIG. 2 is a block diagram of the information system 1 according to the present embodiment.

The information system 1 includes an external device 11, an information processing device 12, and a terminal device 13.

The external device 11 includes a comment storage unit 111, an instruction receiving unit 112, and a comment transmitting unit 113.

The information processing device 12 includes a dictionary storage unit 121, a comment acquisition unit 122, an evaluation target determination unit 123, an evaluation value acquisition unit 124, a target evaluation value acquisition unit 125, and an output unit 126.

The terminal device 13 includes a terminal reception unit 131, a terminal transmission unit 132, a terminal reception unit 133, and a terminal output unit 134.

The comment storage unit 111 constituting the external device 11 stores one or more comments. As described above, the comment is information such as word-of-mouth input by one or more users, and is a so-called CGM. The comment is usually text, but its data type, data structure, etc. do not matter.

The instruction receiving unit 112 receives an instruction for transmitting a comment from the information processing device 12.

The comment transmission unit 113 acquires one or more comments from the comment storage unit 111 and transmits the comment to the information processing device 12 in response to the instruction for transmitting the comment.

The external device 11 may send a comment to the information processing device 12 without receiving the instruction.

One or two or more evaluation word dictionaries are stored in the dictionary storage unit 121 that constitutes the information processing device 12. The evaluation word dictionary has two or more evaluation information. The evaluation information has an evaluation language group. The evaluation information may have an evaluation language group and a score. The evaluation word group is two or more evaluation words. The evaluation term is a term related to the evaluation of the evaluation target. An evaluation word group is usually two or more evaluation words having different meanings. It should be noted that different meanings may be said to be different attributes. Further, the evaluation word is, for example, a keyword related to the evaluation of the evaluation target, a characteristic word indicating a feature related to the keyword, and a degree word indicating the degree of evaluation. The characteristics related to the keyword may be said to be the characteristics given to the keyword. The evaluation word group has keywords, characteristic words, and degree words. The evaluation word group has, for example, a keyword and a degree word. In addition, the keyword is a term directly related to the evaluation of the evaluation target such as, for example, a lotion, and is, for example, "moisturizing" and "moist". Characteristic terms are, for example, terms related to time, such as "continue" and "in a short time". Degree words are, for example, "a little," "quite," "very," and so on. The score is the value of evaluation. The score is, for example, a numerical value (1, 2, ..., 10 etc.), an alphabet (A, B, ...) or the like. Each of the two or more evaluation word dictionaries is associated with, for example, an evaluation target. The evaluation word dictionary is associated with, for example, an evaluation target word or an ID indicating an evaluation target. The evaluation target is a product or service to be evaluated (hereinafter, appropriately referred to as “product, etc.”). The evaluation target word is usually a unique name of the product or the like to be evaluated. Here, the evaluation target may be a type of product or the like (for example, cosmetics, skin care, lotion, face wash, milky lotion, base makeup, foundation, etc.). Further, each of the two or more evaluation word dictionaries is associated with, for example, an evaluation item. The evaluation word dictionary is associated with, for example, an evaluation item word or an ID indicating an evaluation item. The evaluation item word is a term indicating an evaluation item. The evaluation item is an evaluation item of one product or the like. The evaluation items for the product "lotion" are, for example, "moisturizing effect", "whitening effect", "pore / keratin care effect", "hypoallergenic", "aging care effect" and the like.

Further, it is preferable that the evaluation word dictionary of the dictionary storage unit 121 is an evaluation word dictionary accumulated by the dictionary construction device 2 described in the second embodiment. However, the evaluation word dictionary may be information created manually.

Further, it is preferable that the dictionary storage unit 121 also stores hierarchical information which is information indicating the hierarchical relationship of three or more evaluation targets that are hierarchical. The hierarchical information is information indicating the hierarchical relationship of the evaluation target words, and has, for example, the ID of the evaluation target word and the ID of the evaluation target word of the parent. The hierarchical information is information indicating the hierarchical relationship of the evaluation target words, and has, for example, the ID of the evaluation target word, the ID of the evaluation target word of the parent, and the ID of one or more evaluation target words of the child. Is also good. That is, in such a case, the evaluation targets are layered, and the evaluation word dictionary exists for each layered evaluation target.

Furthermore, the evaluation targets are hierarchized, and when evaluating the evaluation target, the evaluation words corresponding to one evaluation target are not only the evaluation words corresponding to the one evaluation target, but also the higher ranks of the one evaluation target. It is preferable to evaluate the evaluation target by also using the evaluation word corresponding to the evaluation target of.

Further, the dictionary storage unit 121 may store one or more unique name information. The unique name information is information that associates a unique name with an evaluation target word, and is, for example, information having a unique name and an evaluation target word. The unique name is a product name, a person's name, a place name, etc. to be evaluated. In such a case, it can be said that the evaluation target word is information indicating the classification of the proper name. The proper name may also be regarded as an evaluation target word.

The comment acquisition unit 122 acquires one or more comments from the recording medium. The recording medium here is, for example, the recording medium of the external device 11. In such a case, the comment acquisition unit 122 receives one or more comments from the external device 11. More specifically, the comment acquisition unit 122 may, for example, transmit a comment transmission instruction to the external device 11, and receive one or more comments from the external device 11 in response to the transmission of the instruction. The comment transmission instruction may have a user identifier that identifies the user. However, the recording medium in which the comment is stored may be, for example, a local recording medium (not shown). A comment is information entered by one or more users. A comment is a comment on a product or the like to be evaluated. Comments can be called reviews and reviews.

The evaluation target determination unit 123 determines the evaluation target of each one or more comments acquired by the comment acquisition unit 122. Here, the determination of the evaluation target is usually the acquisition of the evaluation target word. It is preferable that the evaluation target determination unit 123 acquires the evaluation target word by using each one or more comments acquired by the comment acquisition unit 122 and one or more evaluation target words stored in the dictionary storage unit 121. is there. However, the evaluation target word is added to the comment acquired by the comment acquisition unit 122, and the evaluation target determination unit 123 may acquire the evaluation target word added to the comment.

It is preferable that the evaluation target determination unit 123 determines the evaluation target of each comment by also using the evaluation word. That is, the evaluation target determination unit 123 may acquire the evaluation target word corresponding to each evaluation word by using, for example, the frequency of one or more evaluation words appearing in each comment. More specifically, the evaluation target determination unit 123 acquires, for example, one or more evaluation words so that the frequency of appearance of each comment satisfies a predetermined condition, and the most of the one or more evaluation words. Acquire one evaluation target word corresponding to the evaluation word of.

Further, more specifically, when the evaluation target words are layered, the evaluation target determination unit 123 selects, for example, one or more evaluation words from each comment so that the appearance frequency satisfies a predetermined condition. Acquire and acquire the lowest evaluation target word among the evaluation target words corresponding to the evaluation word. For example, when "skin care" is a hypernym and "toner" is a hyponym, "skin care" and "toner" are the evaluation target words corresponding to the evaluation words with a high frequency of appearance that satisfy a predetermined condition. In some cases, the evaluation target determination unit 123 acquires, for example, the lowest evaluation target word “toner”.

Further, when the evaluation target words are layered and the evaluation target determination unit 123 acquires a plurality of evaluation target words, for example, the evaluation target determination unit 123 is the lowest one evaluation target word that is layered. It is preferable to obtain.

The evaluation target determination unit 123 may determine the unique name corresponding to the evaluation target of each comment by using each one or more comments acquired by the comment acquisition unit 122 and one or more unique names of the dictionary storage unit 121. Suitable. That is, for example, the evaluation target determination unit 123 acquires the unique name appearing in the comment as the evaluation target word.

It is preferable that the evaluation target determination unit 123 acquires two or more evaluation targets and two or more partial comments in association with one comment. A partial comment is a part of one comment and is a part of a comment corresponding to each of two or more evaluation targets. The evaluation target determination unit 123 divides the comment into partial comments by using clues such as line breaks and line breaks + spaces. Further, the evaluation target determination unit 123 may determine the evaluation target on a sentence-by-sentence basis and acquire as a partial comment until the evaluation target changes.

The evaluation target determination unit 123 includes one or more comments or one or more partial comments acquired by the comment acquisition unit 122, and one or more evaluation target words or one or more evaluation words stored in the dictionary storage unit 121. , Or one or more evaluation target words and one or more evaluation words are used to determine the evaluation target corresponding to each comment or each partial comment.

The evaluation value acquisition unit 124 acquires an evaluation word group consisting of two or more co-occurring evaluation words from each of one or more comments, applies the evaluation word group to the evaluation word dictionary, and determines the evaluation value to be evaluated. get. The evaluation value acquisition unit 124 may acquire an evaluation word matching the evaluation word included in the evaluation word dictionary of the dictionary storage unit 121 from the comment. The evaluation value acquisition unit 124 usually morphologically analyzes the comment and acquires the evaluation value. Since the process of acquiring the evaluation word from the comment can be performed by a known technique, detailed description thereof will be omitted. Further, two or more evaluation words that co-occur are usually evaluation words that co-occur in one sentence. However, the two or more co-occurring evaluation words may be co-occurring evaluation words in a partial comment such as one paragraph.

The evaluation value acquisition unit 124 acquires 1 or 2 or more evaluation word groups consisting of 2 or more co-occurring evaluation words from each of 1 or more comments, and 1 or 1 or 2 or more evaluation word groups corresponding to the 1 or 2 or more evaluation word groups. The evaluation value of the evaluation target is acquired by using a score of 2 or more. When the evaluation value acquisition unit 124 acquires two or more scores corresponding to two or more evaluation word groups, for example, the evaluation value of the evaluation target is calculated by an increasing function having the two or more scores as parameters. When the evaluation value acquisition unit 124 acquires two or more scores corresponding to two or more evaluation word groups, for example, the average value or the median value of the two or more scores is set as the evaluation value to be evaluated.

The evaluation value acquisition unit 124 acquires one or two or more evaluation word groups consisting of two or more co-occurring evaluation words from each of one or more comments, and determines the evaluation target for the one or two or more evaluation word groups. It is applied to the evaluation word dictionary corresponding to the evaluation target determined by the unit 123, and the evaluation value of the evaluation target is acquired. The evaluation value acquisition unit 124 may acquire the evaluation value of each comment by using the evaluation word dictionary corresponding to the evaluation target higher than the evaluation target determined by the evaluation target determination unit 123. The evaluation target at the higher level of the evaluation target can be acquired by using the hierarchical information.

The evaluation value acquisition unit 124 acquires two or more evaluation word groups from each of one or more comments, applies each of two or more evaluation word groups to the evaluation word dictionary, and evaluates each evaluation item corresponding to the evaluation item. You may get the value. More specifically, the evaluation value acquisition unit 124 acquires two or more evaluation word groups from each of one or more comments, determines evaluation items corresponding to each of two or more evaluation word groups, and determines each evaluation item. In addition, the evaluation value may be obtained by applying it to the evaluation word dictionary corresponding to the evaluation item. The evaluation word dictionary may also be an evaluation word dictionary corresponding to the evaluation target determined by the evaluation target determination unit 123. The evaluation value acquisition unit 124 operates as follows, for example. First, the evaluation value acquisition unit 124 acquires two or more evaluation word groups from each of one or more comments. Next, the evaluation value acquisition unit 124 searches an evaluation word dictionary including two or more evaluation word groups. Next, the evaluation value acquisition unit 124 acquires evaluation items (information indicating the evaluation items) corresponding to the evaluation word dictionary for each evaluation word group. Next, the evaluation value acquisition unit 124 acquires one or more scores corresponding to one or more evaluation word groups from the evaluation word dictionary for each evaluation item. Next, the evaluation value acquisition unit 124 acquires the evaluation value by using the acquired score of 1 or more for each evaluation item. The evaluation value acquisition unit 124 calculates the evaluation value of the evaluation item for each evaluation item by an increasing function using the acquired score of 1 or more as a parameter.

The target evaluation value acquisition unit 125 acquires the evaluation value of the evaluation target by using one or more evaluation values corresponding to the evaluation target for each evaluation target. In addition, the target evaluation value acquisition unit 125 usually statistically processes one or more evaluation values of the evaluation target to calculate a comprehensive evaluation value of the evaluation target. Statistical processing is, for example, calculation of an average value or a median value. It should be noted that one or more evaluation values of the evaluation target are evaluation values acquired by the evaluation value acquisition unit 124.

Further, the target evaluation value acquisition unit 125 may acquire and output the evaluation value for each evaluation target and for each evaluation item by using one or more evaluation values corresponding to the evaluation target and the evaluation item. Needless to say, the evaluation value is an evaluation value acquired by the evaluation value acquisition unit 124.

The output unit 126 outputs the evaluation value of the evaluation target acquired by the evaluation value acquisition unit 124. It is preferable that the output unit 126 outputs the evaluation value acquired by the evaluation value acquisition unit 124 for each evaluation item. Further, the output unit 126 outputs the evaluation value of the evaluation target acquired by the target evaluation value acquisition unit 125 for each evaluation target. Here, it is preferable that the output unit 126 outputs, for example, the evaluation target word and the evaluation value in association with each other. The output includes transmission to an external device such as a terminal device 13, display on a display, projection using a projector, printing by a printer, sound output, storage on a recording medium, other processing devices and other devices. It is a concept that includes delivery of processing results to a program or the like.

The terminal reception unit 131 of the terminal device 13 receives instructions and information from the user. The instruction is, for example, an evaluation acquisition instruction for acquiring the evaluation of the evaluation target. Further, the information is, for example, a comment regarding the evaluation of the evaluation target. The reception of instructions and information includes the reception of information input from input devices such as keyboards, mice, and touch panels, the reception of information transmitted via wired or wireless communication lines, optical disks, magnetic disks, and so on. It is a concept including acceptance of information and the like read from a recording medium such as a semiconductor memory.

The terminal transmission unit 132 transmits the instructions and information received by the terminal reception unit 131 to the information processing device 12, the external device 11, and the like.

The terminal receiving unit 133 receives the evaluation value from the information processing device 12 in response to the transmission of the evaluation acquisition instruction. The terminal receiving unit 133 may receive information other than the evaluation value from the information processing device 12, the external device 11, or the like.

The terminal output unit 134 outputs the information (for example, the evaluation value) received by the terminal receiving unit 133. Here, the output means display on a display, projection using a projector, printing by a printer, sound output, transmission to an external device, storage on a recording medium, storage on another processing device, another program, or the like. It is a concept that includes delivery of processing results.

The comment storage unit 111 and the dictionary storage unit 121 are preferably non-volatile recording media, but can also be realized by volatile recording media.

The process of storing information in the comment storage unit 111 or the like does not matter. For example, the information may be stored in the comment storage unit 111 or the like via the recording medium, or the information transmitted via the communication line or the like may be stored in the comment storage unit 111 or the like. Well, or the information input via the input device may be stored in the comment storage unit 111 or the like.

The instruction receiving unit 112, the comment acquiring unit 122, and the terminal receiving unit 133 are usually realized by wireless or wired communication means, but may be realized by means for receiving broadcasts.

The comment transmission unit 113, the output unit 126, and the terminal transmission unit 132 can be usually realized by wireless or wired communication means, but may be realized by broadcasting means.

The evaluation target determination unit 123 and the evaluation value acquisition unit 124 can usually be realized from an MPU, a memory, or the like. The processing procedure of the comment acquisition unit 122 and the like is usually realized by software, and the software is recorded on a recording medium such as ROM. However, it may be realized by hardware (dedicated circuit).

The output unit 126 and the terminal output unit 134 may or may not include output devices such as displays and speakers. The output unit 126 can be realized by the driver software of the output device, the driver software of the output device, the output device, or the like.

Next, the operation of the information system 1 will be described. First, the operation of the external device 11 will be described. The instruction receiving unit 112 of the external device 11 receives a comment transmission instruction from the information processing device 12. Then, the comment transmission unit 113 acquires one or more comments from the comment storage unit 111 and transmits the comment to the information processing device 12 in response to the comment transmission instruction.

Next, the operation of the information processing device 12 will be described with reference to the flowchart of FIG.

(Step S301) The comment acquisition unit 122 acquires one or more comments. The comment acquisition unit 122 may read one or more comments from a recording medium (not shown), or may receive one or more comments from one or more external devices 11.

(Step S302) The evaluation target determination unit 123 substitutes 1 for the counter i.

(Step S303) The evaluation target determination unit 123 determines whether or not the i-th comment exists among the one or more comments acquired in step S301. If the i-th comment exists, the process goes to step S304, and if the i-th comment does not exist, the process goes to step S306.

(Step S304) The evaluation value acquisition unit 124 and the like acquire the evaluation value of the comment. The process of acquiring the evaluation value of the comment will be described with reference to the flowchart of FIG.

(Step S305) The evaluation target determination unit 123 increments the counter i by 1. Return to step S303.

(Step S306) The target evaluation value acquisition unit 125 substitutes 1 for the counter j.

(Step S307) The target evaluation value acquisition unit 125 determines whether or not the j-th evaluation target word exists among the evaluation target words temporarily stored in the buffer. If the j-th evaluation target word exists, the process proceeds to step S308, and if it does not exist, the process ends.

(Step S308) The target evaluation value acquisition unit 125 acquires one or more evaluation values corresponding to the j-th evaluation target word from the buffer. This evaluation value is the evaluation value of the comment.

(Step S309) The target evaluation value acquisition unit 125 calculates the evaluation value for the j-th evaluation target word (j-th evaluation target) by using one or more evaluation values acquired in step S308. Normally, the target evaluation value acquisition unit 125 statistically processes one or more evaluation values acquired in step S308 to calculate the jth evaluation value of the evaluation target.

(Step S310) The target evaluation value acquisition unit 125 outputs the j-th evaluation target word in association with the evaluation value (usually, the statistical processing result) acquired in step S309.

(Step S311) The target evaluation value acquisition unit 125 increments the counter j by 1. Return to step S307.

In the flowchart of FIG. 3, the evaluation value of the comment was calculated for each comment, but after acquiring all the evaluation target words of each of the plurality of comments, the evaluation value of each of the plurality of comments was calculated. Needless to say, it is sufficient to finally obtain the evaluation value corresponding to the evaluation target by a different procedure.

Further, in the flowchart of FIG. 3, it is preferable that the target evaluation value acquisition unit 125 acquires and outputs the evaluation value for each evaluation target and each evaluation item.

Further, in the flowchart of FIG. 3, the evaluation value of the comment calculated for each comment may be stored in association with the comment, transmitted to an external device, or displayed.

Further, in the flowchart of FIG. 3, the process is terminated by the power off or the interrupt of the process end.

Next, the process of acquiring the comment evaluation value in step S304 will be described with reference to the flowchart of FIG.

(Step S401) The evaluation target determination unit 123 performs a process of dividing the comment to be processed. Here, the division process is a process of dividing a comment for each evaluation target. By splitting, two or more partial comments can be obtained. In addition, here, it may not be possible to divide, and in such a case, the evaluation target of the comment is one. Further, such a division process will be described with reference to the flowchart of FIG. The evaluation target determination unit 123 may simply divide the comment to be processed into sentences.

(Step S402) The evaluation value acquisition unit 124 substitutes 1 for the counter i.

(Step S403) The evaluation value acquisition unit 124 determines whether or not the i-th partial comment exists. If the i-th partial comment exists, it goes to step S404, and if it does not exist, it goes to step S410. The first partial comment may be a comment.

(Step S404) The evaluation value acquisition unit 124 acquires the evaluation word dictionary corresponding to the i-th partial comment. The evaluation word dictionary acquisition process will be described with reference to the flowchart of FIG. In this step, the evaluation target word corresponding to the i-th partial comment is also acquired. Further, the acquisition of the evaluation word dictionary may be the determination of the evaluation word dictionary to be used.

(Step S405) The evaluation value acquisition unit 124 acquires one or two or more evaluation words appearing in the i-th partial comment by using the evaluation word dictionary acquired in step S404. Here, it is preferable that the evaluation value acquisition unit 124 acquires an evaluation word group which is two or more evaluation words from the i-th partial comment. The evaluation value acquisition unit 124 searches for the i-th partial comment using, for example, one or more evaluation words included in the evaluation word dictionary acquired in step S404, and 1 or 1 appearing in the i-th partial comment. Acquire two or more evaluation words.

(Step S406) The evaluation value acquisition unit 124 acquires a score by using one or more evaluation words acquired in step S405. For example, when the evaluation value acquisition unit 124 acquires two or more evaluation words in step S405, the evaluation value acquisition unit 124 acquires a score paired with the evaluation word group having the two or more evaluation words from the evaluation word dictionary. For example, when the evaluation value acquisition unit 124 acquires one or more evaluation words in step S405, the score (for example, 1) corresponding to the evaluation word is added to calculate the score. Further, for example, when the evaluation value acquisition unit 124 acquires one or more evaluation words in step S405, it is a negative word by +1 if the evaluation word is registered as a positive word. If it is registered as, add -1 to calculate the final score.

(Step S407) The evaluation value acquisition unit 124 acquires the evaluation item corresponding to the i-th partial comment. For example, the evaluation value acquisition unit 124 acquires the evaluation item corresponding to the evaluation word dictionary including the evaluation word group acquired in step S405. For example, the evaluation value acquisition unit 124 acquires an evaluation item word which is a term indicating an evaluation item included in the i-th partial comment. The evaluation item word may be simply referred to as an evaluation item.

(Step S408) The evaluation value acquisition unit 124 temporarily stores the evaluation target word corresponding to the i-th partial comment, the evaluation item word, and the score in the buffer in association with each other. Here, the evaluation target word or / and the evaluation item may not exist.

(Step S409) The evaluation value acquisition unit 124 increments the counter i by 1. Return to step S403.

(Step S410) The evaluation value acquisition unit 124 acquires the evaluation value of the comment by using a score of 1 or more for each evaluation target and each evaluation item. Return to higher processing. The evaluation value acquisition unit 124 acquires, for example, a score of 1 or more from the buffer for each evaluation target and each evaluation item, and an increase function (for example, a function for calculating an average value) using the score of 1 or more as a parameter. The evaluation value is calculated by a function that obtains the median value, etc.). Further, for example, when the evaluation target is determined, the evaluation value acquisition unit 124 acquires the evaluation value of the comment by using, for example, a score of 1 or more for each evaluation item.

Next, the division process of step S401 will be described with reference to the flowchart of FIG.

(Step S501) The evaluation target determination unit 123 initializes. Initialization means substituting 1 for the counter i, substituting NULL for the partial comment buffer, and substituting NULL for the evaluation target buffer. The partial comment buffer is a buffer in which partial comments are stored, and the evaluation target buffer is a buffer in which evaluation target words are stored.

(Step S502) The evaluation target determination unit 123 determines whether or not the i-th processing unit exists in the comment. If the i-th processing unit exists, the process goes to step S503, and if it does not exist, the process goes to step S506. Then, after the processing of step S506, the process returns to the higher processing. The processing unit is information that is a unit for determining whether the information is in the current partial comment or the information in the next new partial comment, and is usually a sentence. However, the processing unit may be a sentence, a phrase, a paragraph, or the like in which the subject exists.

(Step S503) The evaluation target determination unit 123 acquires the i-th processing unit from the comment.

(Step S504) The evaluation target determination unit 123 acquires the evaluation target word or the unique name from the i-th processing unit. It may not be possible to obtain the evaluation target word or proper name here. If the evaluation target word or the like cannot be obtained, it is determined that there is no change from the evaluation target word or the like in the (i-1) th processing unit. Further, the evaluation target determination unit 123 may, for example, morphologically analyze the i-th processing unit and acquire a unique name, or morphologically analyze the i-th processing unit and acquire the evaluation target word which is the subject. Alternatively, the evaluation target word appearing in the i-th processing unit may be acquired by using the evaluation target word of the dictionary storage unit 121. Further, the evaluation target determination unit 123 may acquire an evaluation target word or a unique name by combining a plurality of algorithms. Since the technique for acquiring a unique name or the like is a known technique, detailed description thereof will be omitted.

(Step S505) The evaluation target word or unique name can be acquired by the evaluation target determination unit 123 in step S504, and the acquired evaluation target word or unique name is the evaluation target word or unique name stored in the evaluation target buffer. Determine if they are the same. If the condition is satisfied, the process proceeds to step S506, and if the condition is not satisfied, the process proceeds to step S509. If the condition is satisfied, the topic (evaluation target) is changed, and if the condition is not satisfied, the topic is not changed.

(Step S506) The evaluation target determination unit 123 temporarily stores the information of the partial comment buffer and the information of the evaluation target buffer in a recording medium (not shown). This temporarily accumulated information is a comment or a partial comment for which the evaluation value is calculated. If the information in the partial comment buffer is NULL, the operation of this step is not performed.

(Step S507) The evaluation target determination unit 123 overwrites the i-th processing unit in the partial comment buffer, and overwrites the evaluation target word or the unique name acquired in step S504 in the evaluation target buffer.

(Step S508) The evaluation target determination unit 123 increments the counter i by 1. Return to step S502.

(Step S509) The evaluation target determination unit 123 adds the i-th processing unit to the partial comment buffer. Go to step S508.

Next, the evaluation word dictionary acquisition process in step S404 will be described with reference to the flowchart of FIG.

(Step S601) The evaluation value acquisition unit 124 acquires a unique name or an evaluation target word corresponding to a partial comment (which may be a comment) to be processed. The method of acquiring the proper name or the evaluation target word may be the same as the acquisition method in step S504, and the description thereof will be omitted.

(Step S602) The evaluation value acquisition unit 124 determines whether or not the information acquired in step S601 has a unique name. If it is a unique name, it goes to step S603, and if it is not a unique name, it goes to step S604.

(Step S603) The evaluation value acquisition unit 124 acquires the evaluation target word paired with the unique name acquired in step S601 from the dictionary storage unit 121.

(Step S604) The evaluation value acquisition unit 124 acquires the evaluation word dictionary corresponding to the evaluation target word acquired in step S601 or the evaluation target word acquired in step S603 from the dictionary storage unit 121. The evaluation target word used in this step is the current evaluation target word.

(Step S605) The evaluation value acquisition unit 124 determines whether or not to acquire the evaluation word dictionary by using the hierarchical information. If the hierarchical information is used, the process goes to step S606, and if the hierarchical information is not used, the process returns to the higher processing. It is assumed that whether or not to use the hierarchical information is determined in advance.

(Step S606) The evaluation value acquisition unit 124 determines whether or not the parent of the current evaluation target word exists by using the hierarchical information. If the parent exists, the process proceeds to step S607, and if the parent does not exist, the process returns to the higher processing.

(Step S607) The evaluation value acquisition unit 124 acquires an evaluation word dictionary corresponding to the evaluation target word of the parent of the current evaluation target word from the dictionary storage unit 121.

(Step S608) The evaluation value acquisition unit 124 sets the current evaluation target word as the parent evaluation target word. Return to step S606.

In the flowchart of FIG. 6, the evaluation value acquisition unit 124 determines an evaluation item from one or more evaluation words included in the partial comment (which may be a comment) to be processed, and the evaluation word corresponding to the evaluation item. You may get a dictionary. In such a case, for example, correspondence information between one or more evaluation words and evaluation items is stored in a storage unit (not shown).

Next, the operation of the terminal device 13 will be described. The terminal reception unit 131 of the terminal device 13 receives an evaluation acquisition instruction from the user. The evaluation acquisition instruction is an instruction to acquire the evaluation. Next, the terminal transmission unit 132 transmits the evaluation acquisition instruction received by the terminal reception unit 131 to the information processing device 12. Then, the terminal receiving unit 133 receives the evaluation value from the information processing device 12 in response to the transmission of the evaluation acquisition instruction. It is preferable that the evaluation value is an evaluation value for each evaluation item. Further, it is preferable that the evaluation value is an evaluation value for each evaluation target and each evaluation item. The terminal output unit 134 outputs the evaluation value received by the terminal receiving unit 133. The evaluation acquisition instruction usually includes an evaluation target word. Further, the terminal receiving unit 133 receives, for example, an evaluation value corresponding to the evaluation target word included in the evaluation acquisition instruction from the information processing device 12. Further, the terminal receiving unit 133 may receive the evaluation value for each comment. In such a case, the terminal output unit 134 outputs an evaluation value for each comment.

Hereinafter, the specific operation of the information system 1 in the present embodiment will be described. The conceptual diagram of the information system 1 is FIG.

Now, the dictionary storage unit 121 stores the evaluation word dictionaries shown in FIGS. 7 and 8. The evaluation word dictionary has one or more evaluation information. The evaluation information has a "score" and a "evaluation superfamily" here. That is, the evaluation word dictionary stores one or two or more evaluation information having a score for each evaluation word group. In addition, the "evaluation word group" has one or more types of information among "degree words", "characteristic words", and "keywords". Further, the "characteristic word" here is mainly information indicating the length of time that the state of the "keyword" continues. Further, the evaluation word dictionary of FIG. 7 corresponds to the evaluation item word "moisture". Further, the evaluation word dictionary of FIG. 8 corresponds to the evaluation item word “pore / keratin”.

Further, the dictionary storage unit 121 stores the unique name information management table shown in FIG. The unique name information management table stores one or more records having "ID", "unique name", and "evaluation target word". This record is unique name information. It can be said that the evaluation target word corresponding to the proper name indicates the classification of the proper name.

Further, the comment storage unit 111 of the external device 11 stores the comment shown in FIG. The comment in FIG. 10 is a comment for the evaluation target “Toner A”. The plurality of comments shown in FIG. 10 may be those stored in one external device 11, or may be a collection of those stored in two or more external devices 11. ..

In such a situation, for example, the information system 1 operates as follows. Here, a process in which the information processing apparatus 12 outputs the evaluation value for each evaluation item of each comment and the evaluation value of the evaluation target word or the unique name will be described.

First, the comment acquisition unit 122 of the information processing device 12 transmits a comment transmission instruction to one or more external devices 11.

Then, the instruction receiving unit 112 of one or more external devices 11 receives the transmission instruction. Then, the comment transmission unit 113 of one or more external devices 11 reads one or more comments from the comment storage unit 111 and transmits them to the information processing device 12.

Next, the comment acquisition unit 122 of the information processing device 12 receives one or two or more comments from one or two or more external devices 11. FIG. 10 shows a set of comments received by the comment acquisition unit 122.

Next, the evaluation target determination unit 123 and the like process each comment in FIG. 10 in order as follows.

First, the evaluation target determination unit 123 processes the first comment. That is, the evaluation target determination unit 1231 substitutes NULL for the partial comment buffer and substitutes NULL for the evaluation target buffer. Then, the evaluation target determination unit 1231 analyzes the first sentence of the first comment, "When this lotion A is used, the skin becomes considerably moisturized and continues to be considerably moisturized." For example, the subject is analyzed. Acquire the phrase "Toner A" that composes. Here, the evaluation target word "cosmetics" that is paired with the subject "skin water A" of the sentence is acquired from the unique name information management table of FIG.

Next, the evaluation value acquisition unit 124 acquires an evaluation word dictionary (here, FIGS. 7 and 8) corresponding to the evaluation target word “cosmetics”.

Next, the evaluation value acquisition unit 124 morphologically analyzes the first sentence of the first comment, acquires one or more independent words, and acquires the original form of each independent word. Then, the evaluation value acquisition unit 124 acquires one or more evaluation words in the evaluation word dictionaries of FIGS. 7 and 8 in the original form of each acquired independent word. Then, the evaluation value acquisition unit 124 acquires "quite", "moist", "quite", "moisturizes", and "continue" from the first sentence of the first comment.

Next, the evaluation value acquisition unit 124 acquires the score by using the acquired five evaluation words. That is, the evaluation value acquisition unit 124 acquires the score “7” paired with “quite” and “moist” from the five evaluation words acquired from the evaluation word dictionary of FIG. In addition, the evaluation value acquisition unit 124 acquires a score "8" paired with "quite", "moisturizing", and "continue" from the evaluation word dictionary of FIG. 7 among the five acquired evaluation words.

Next, the evaluation value acquisition unit 124 acquires the evaluation item "moisture" corresponding to the evaluation word dictionary of FIG. 7. Then, the evaluation value acquisition unit 124 associates the evaluation item "moisture" with the score "7" and the evaluation item "moisture" with the score "8" and temporarily stores them in a buffer (not shown). Here, the evaluation value acquisition unit 124 may also temporarily store the evaluation target word “cosmetics” in a buffer (not shown) in association with the evaluation item and the score.

Next, the evaluation value acquisition unit 124 morphologically analyzes the second sentence of the first comment, acquires one or more independent words, and acquires the original form of each independent word. Then, the evaluation value acquisition unit 124 acquires one or more evaluation words in the evaluation word dictionaries of FIGS. 7 and 8 in the original form of each acquired independent word. Then, the evaluation value acquisition unit 124 acquires "short time" and "removal" from the second sentence of the first comment.

Next, the evaluation value acquisition unit 124 acquires a score using the two acquired evaluation words. That is, the evaluation value acquisition unit 124 acquires the score "8" paired with the two acquired evaluation words "short time" and "removal" from the evaluation word dictionary of FIG.

Next, the evaluation value acquisition unit 124 acquires the evaluation item “pores / keratin” corresponding to the evaluation word dictionary of FIG. Then, the evaluation value acquisition unit 124 associates the evaluation item “pores / keratin” with the score “8” and temporarily stores them in a buffer (not shown). Here, the evaluation value acquisition unit 124 may also temporarily store the evaluation target word “cosmetics” in a buffer (not shown) in association with the evaluation item and the score.

Next, the evaluation value acquisition unit 124 morphologically analyzes the third sentence of the first comment, acquires one or more independent words, and acquires the original form of each independent word. Then, the evaluation value acquisition unit 124 acquires one or more evaluation words in the evaluation word dictionaries of FIGS. 7 and 8 in the original form of each acquired independent word. Then, the evaluation value acquisition unit 124 acquires "for a long period of time", "at all", and "inconspicuous" from the third sentence of the first comment.

Next, the evaluation value acquisition unit 124 acquires the score by using the acquired three evaluation words. That is, the evaluation value acquisition unit 124 acquires the score "9" paired with the three acquired evaluation words "over a long period of time", "at all", and "inconspicuous" from the evaluation word dictionary of FIG.

Next, the evaluation value acquisition unit 124 acquires the evaluation item “pores / keratin” corresponding to the evaluation word dictionary of FIG. Then, the evaluation value acquisition unit 124 associates the evaluation item “pores / keratin” with the score “9” and temporarily stores them in a buffer (not shown). Here, the evaluation value acquisition unit 124 may also temporarily store the evaluation target word “cosmetics” in a buffer (not shown) in association with the evaluation item and the score.

Next, the evaluation value acquisition unit 124 acquires the evaluation value of the comment by using the information in the buffer and using a score of 1 or more for each evaluation item. That is, the evaluation value acquisition unit 124 has the evaluation item "moisture" and the score "7", and the evaluation item "moisture" and the score "8", and the score for the evaluation item "moisture" of the first comment is "7. 5 ”is calculated. Then, the evaluation value acquisition unit 124 stores the evaluation item “moisture” and the score “7.5” in association with each other in a buffer (not shown). The score "7.5" is the average value of the two scores "7" and "8". In addition, the evaluation value acquisition unit 124 has the evaluation item "pore / keratin" and the score "8", and the evaluation item "pore / keratin" and the score "9", and the evaluation item "pore / keratin" of the first comment. The score for is calculated as "8.5". Then, the evaluation value acquisition unit 124 stores the evaluation item “pore / keratin” and the score “8.5” in association with each other in a buffer (not shown). The score "8.5" is the average value of the two scores "8" and "9".

Next, the evaluation target determination unit 123 processes the second comment. First, the evaluation target determination unit 123 acquires the evaluation target word “cosmetics” in the same manner as the processing of the first comment.

Next, the evaluation value acquisition unit 124 morphologically analyzes the first sentence of the second comment, acquires one or more independent words, and acquires the original form of each independent word. Then, the evaluation value acquisition unit 124 acquires one or more evaluation words in the evaluation word dictionaries of FIGS. 7 and 8 in the original form of each acquired independent word. Then, the evaluation value acquisition unit 124 acquires "momentary" and "moisturizing" from the first sentence of the second comment.

Next, the evaluation value acquisition unit 124 acquires the score "3" paired with the two acquired evaluation words "momentary" and "moisturizing" from the evaluation word dictionary of FIG. 7.

Next, the evaluation value acquisition unit 124 acquires the evaluation item "moisture" corresponding to the evaluation word dictionary of FIG. 7. Then, the evaluation value acquisition unit 124 associates the evaluation item "moisture" with the score "3" and temporarily stores them in a buffer (not shown). Here, the evaluation value acquisition unit 124 may also temporarily store the evaluation target word “cosmetics” in a buffer (not shown) in association with the evaluation item and the score.

Next, the evaluation value acquisition unit 124 morphologically analyzes the second sentence of the second comment, acquires one or more independent words, and acquires the original form of each independent word. Then, the evaluation value acquisition unit 124 acquires one or more evaluation words in the evaluation word dictionaries of FIGS. 7 and 8 in the original form of each acquired independent word. Then, the evaluation value acquisition unit 124 acquires "quite" and "blocking" from the second sentence of the second comment.

Next, the evaluation value acquisition unit 124 acquires a score using the two acquired evaluation words. That is, the evaluation value acquisition unit 124 acquires the score "7" paired with the two acquired evaluation words "quite" and "closed" from the evaluation word dictionary of FIG.

Next, the evaluation value acquisition unit 124 acquires the evaluation item “pores / keratin” corresponding to the evaluation word dictionary of FIG. Then, the evaluation value acquisition unit 124 associates the evaluation item “pores / keratin” with the score “7” and temporarily stores them in a buffer (not shown). Here, the evaluation value acquisition unit 124 may also temporarily store the evaluation target word “cosmetics” in a buffer (not shown) in association with the evaluation item and the score.

Next, the evaluation target determination unit 123 processes the third comment. First, the evaluation target determination unit 123 acquires the evaluation target word “cosmetics”. It is assumed that the third comment corresponds to the evaluation target word "cosmetics".

Next, the evaluation value acquisition unit 124 morphologically analyzes the first sentence of the third comment, acquires one or more independent words, and acquires the original form of each independent word. Then, the evaluation value acquisition unit 124 acquires one or more evaluation words in the evaluation word dictionaries of FIGS. 7 and 8 in the original form of each acquired independent word. Then, the evaluation value acquisition unit 124 acquires "moisturizing", "quite", and "continue" from the first sentence of the second comment.

Next, the evaluation value acquisition unit 124 acquires the score "8" paired with the three acquired evaluation words "moisturize", "quite", and "continue" from the evaluation word dictionary of FIG. 7.

Next, the evaluation value acquisition unit 124 acquires the evaluation item "moisture" corresponding to the evaluation word dictionary of FIG. 7. Then, the evaluation value acquisition unit 124 associates the evaluation item “moisture” with the score “8” and temporarily stores them in a buffer (not shown). Here, the evaluation value acquisition unit 124 may also temporarily store the evaluation target word “cosmetics” in a buffer (not shown) in association with the evaluation item and the score.

Next, the evaluation value acquisition unit 124 morphologically analyzes the second sentence of the third comment, acquires one or more independent words, and acquires the original form of each independent word. Then, the evaluation value acquisition unit 124 could not acquire one or more evaluation words in the evaluation word dictionaries of FIGS. 7 and 8 in the original forms of the acquired independent words, so that the processing of the third comment was performed. To finish.

Then, it is assumed that the evaluation value acquisition unit 124 performs the same processing for the fourth and subsequent comments, and acquires the evaluation value table for each evaluation item shown in FIG. The evaluation value table for each evaluation item for each comment is a table for managing the evaluation value for each evaluation item for each comment.

As described above, in this specific example, the evaluation value acquisition unit 124 was able to acquire the evaluation values of two or more evaluation items for one comment. Further, even in the comments of the same evaluation target (here, lotion A), the evaluation items to which the evaluation values are automatically given differ depending on the comments.

Further, in this specific example, the target evaluation value acquisition unit 125 may calculate the evaluation value for each evaluation item of the evaluation target (here, the lotion A) from the evaluation values corresponding to two or more comments. Here, the target evaluation value acquisition unit 125 may take the average of the evaluation values of the evaluation item "moisture" corresponding to two or more comments and use it as the evaluation value of the evaluation item "moisture" of the lotion A. Needless to say, the method of calculating the evaluation value of the evaluation item "moisture" corresponding to two or more comments is not limited to the average. The target evaluation value acquisition unit 125 calculates the evaluation value of the evaluation item "moisture" of the lotion A by an increasing function having two or more evaluation values of the evaluation item "moisture" corresponding to two or more comments as parameters. In addition, the target evaluation value acquisition unit 125 uses an increasing function with two or more evaluation values of the evaluation item "pores / keratin" corresponding to two or more comments as parameters to determine the evaluation item "pores / keratin" of the lotion A. Calculate the evaluation value.

Further, in this specific example, the target evaluation value acquisition unit 125 may calculate the overall evaluation value of the evaluation target (here, the lotion A) from the evaluation values corresponding to two or more comments.
(Experiment)

Evaluation based on the co-occurrence of keywords (which may be called terms) In order to verify the validity of the scoring method (the method of the information processing device 1, which is called the proposed method) using the expression dictionary, the actual data is used. A scoring experiment was performed using this. First, in order to confirm the target data, 5000 cases were randomly extracted from the review data (comments) regarding "toner" posted on the cosmetics sales site and analyzed. FIG. 12 shows the number of reviews by evaluation value in the extracted 5000 review data. Further, FIG. 13 shows the total number of effect tags attached to each review data for each evaluation value. From FIG. 13, it was found that the posters who gave high evaluation values tended to attach many tags related to the effect.

The experimental method will be described below. Here, the method of the scoring experiment for the actual review data is shown. Ten review data randomly selected from the above-mentioned 5000 review data on "toner" were used. This experiment is carried out by comparing the two methods shown below. The first is a manual scoring method (correct answer data) that does not use a dictionary, and the second is a scoring method (proposal method) that uses an evaluation expression dictionary based on the co-occurrence of keywords.

In manual scoring, the subjects actually read the review text without using a dictionary and scored (stars) in the range of 0 to 7 for each of the 10 preset evaluation axes. Considering individual differences, 14 women (university students and working adults) in their 20s to 30s were asked to score as subjects. In the scoring using the evaluation expression dictionary, which is the proposed method, scoring was performed using the evaluation expression dictionary (evaluation word dictionary) based on the co-occurrence of keywords created in advance. Similar to manual scoring, scoring was performed in the range of 0 to 7 for each of 10 preset evaluation axes. The 10 evaluation axes (evaluation items) of the "toner" set in this experiment are as follows.
・ Cost performance ・ Moisture / Penetration / Whitening / UV
・ Pore ・ Keratin care / High cleansing ・ Refreshing feeling / Prevention of facial shine ・ Smooth ⇔ Toro Toro ・ Hypoallergenic ・ Rough skin measures ・ Aging care ・ Fragrance

The results of the above experiments are shown below. FIG. 14 shows the results of manual scoring for 10 reviews and the results of scoring with a dictionary based on the co-occurrence of the created keywords. According to FIG. 14, the average value (number of stars) of all items of manual scoring is 4.92, and the average value of all items of the proposed method (dictionary-based scoring) is 4.73. there were. The mean absolute error (MAE) was 0.72. As an overall tendency, manual scoring tends to have a slightly higher evaluation value than the proposed method (dictionary-based scoring), but the evaluation value ranges from 0 to 7. On the other hand, the mean absolute error is 0.72, and it can be said that the scoring is close to the correct answer data. In addition, the total number of evaluation axes that could be scored was 48 by hand, while it was 39 by dictionary scoring, and about 81% of the correct answer data was scored. I was able to do it. Considering that it was about 5% in the preliminary experiment using the phrase dictionary, the result showed the effectiveness of the evaluation expression dictionary based on the co-occurrence of keywords.

As described above, according to the present embodiment, an appropriate evaluation value can be obtained for comments such as word-of-mouth.

Further, according to the present embodiment, the evaluation value can be automatically acquired for each evaluation item for comments such as word-of-mouth.

Further, according to the present embodiment, the evaluation value can be automatically acquired for each comment such as word-of-mouth, for each evaluation target and each evaluation item.

Further, the processing in the present embodiment may be realized by software. Then, this software may be distributed by software download or the like. Further, this software may be recorded on a recording medium such as a CD-ROM and disseminated. It should be noted that this also applies to other embodiments herein. The software that realizes the information processing device in this embodiment is the following program. That is, in this program, the recording medium accessible to the computer is an evaluation word related to the evaluation of the evaluation target, and has two or more evaluation information having two or more evaluation word groups having different meanings. It is provided with a dictionary storage unit for storing an evaluation word dictionary, and co-occurs from a comment acquisition unit that acquires one or more comments input by one or more users from a recording medium and each of the above one or more comments. An evaluation value acquisition unit that acquires an evaluation word group consisting of two or more evaluation words, applies the evaluation word group to the evaluation word dictionary, and acquires an evaluation value of the evaluation target, and the evaluation value acquisition unit This is a program for functioning as an output unit that outputs the acquired evaluation value of the evaluation target.

In the above program, it is preferable that the evaluation word group has a keyword related to evaluation for the evaluation target, a characteristic word indicating a feature related to the keyword, and a degree word indicating the degree of evaluation.

In the above program, the evaluation information has an evaluation word group and a score which is an evaluation value, and the evaluation value acquisition unit acquires two or more co-occurring evaluation words from each of the one or more comments. However, it is preferable that the program operates a computer to acquire the evaluation value of the evaluation target by using the scores corresponding to the two or more evaluation words.

In the above program, the dictionary storage unit stores an evaluation word dictionary for each of two or more evaluation targets, and an evaluation target determination unit that determines the evaluation target of one or more comments acquired by the comment acquisition unit. Further, the evaluation value acquisition unit acquires an evaluation word group consisting of two or more co-occurring evaluation words from each of the one or more comments, and the evaluation target determination unit determines the evaluation word group. It is preferable that the program applies to the evaluation word dictionary corresponding to the evaluation target and operates the computer to acquire the evaluation value of the evaluation target.

In the above program, the dictionary storage unit stores an evaluation word dictionary for each of two or more evaluation items, and the evaluation value acquisition unit stores two or more evaluation word groups from each of the one or more comments. Acquire, determine the evaluation items corresponding to each of the two or more evaluation word groups, apply each of the determined evaluation items to the evaluation word dictionary corresponding to the evaluation item, acquire the evaluation value, and obtain the evaluation value. Is a program that operates a computer so as to output the evaluation value acquired by the evaluation value acquisition unit for each evaluation item.

In the above program, it is preferable that the dictionary storage unit is a program that operates a computer assuming that the dictionary construction device 2 stores an evaluation word dictionary having one or more evaluation information accumulated.

(Embodiment 2)

In the present embodiment, a dictionary construction device that automatically generates an evaluation word dictionary (evaluation word dictionary of the dictionary storage unit 121 of the first embodiment) based on the co-occurrence of two or more terms will be described.

In the present embodiment, the co-occurrence of two or more terms includes, for example, three types of keywords, degree words, and feature words.

FIG. 15 is a block diagram of the dictionary construction device 2 according to the present embodiment.

The dictionary construction device 2 includes a dictionary storage unit 121, a reception unit 21, a comment acquisition unit 22, an evaluation information acquisition unit 23, and a storage unit 24.

The dictionary storage unit 121 may store one or more evaluation word dictionaries. Further, one or more evaluation words may be stored in the dictionary storage unit 121. Further, the dictionary storage unit 121 may store one or more evaluation word groups.

The reception unit 21 receives instructions, information, and the like. The instruction, information, etc. are, for example, a dictionary construction instruction. The input means for instructions and information may be any means such as a keyboard, a mouse, or a menu screen. The reception unit 21 can be realized by a device driver for input means such as a keyboard, control software for a menu screen, or the like.

The comment acquisition unit 22 acquires one or more comments having a score corresponding to the evaluation target from the recording medium. The comment is usually a comment entered by the user. The comment acquisition unit 22 may perform the same processing as the comment acquisition unit 122.

The evaluation information acquisition unit 23 acquires one or two or more evaluation language groups from each of the one or more comments acquired by the comment acquisition unit 22, and uses one or more scores corresponding to the comments including the evaluation language group. , The score corresponding to the evaluation word group is determined, and one or more evaluation information having the score and the evaluation word group is acquired. The evaluation term is a term related to evaluation. The evaluation word group is two or more co-occurrence evaluation words. The evaluation word group has, for example, a keyword related to the evaluation of the evaluation target, a characteristic word indicating the characteristics of the keyword, and a degree word indicating the degree of evaluation.

The evaluation information acquisition unit 23 performs one of the following first to third operations, for example. First, in a situation where one or more evaluation word groups are stored in the dictionary storage unit 121, a score corresponding to each one or more evaluation word groups is calculated using one or more comments with a corresponding score. It is a process of constructing one or more evaluation information having an evaluation language group and a score. The second is a dictionary in which one or more evaluation words are stored in the dictionary storage unit 121, and two or more evaluation words co-occur in the comments using one or more comments with corresponding scores. An evaluation word group consisting of two or more evaluation words stored in the storage unit 121 and a score corresponding to the evaluation word group are acquired, and one or more evaluation information having the acquired evaluation word group and a score is configured. It is a process. Third, using one or more comments with scores associated with each other, two or more terms that co-occur in the comment are acquired as evaluation words, and the evaluation word group consisting of the two or more evaluation words and the evaluation word It is a process of acquiring a score corresponding to a group and forming one or more evaluation information having the acquired evaluation word group and a score.

First, an example of the first operation of the evaluation information acquisition unit 23 will be described. First, the evaluation information acquisition unit 23 morphologically analyzes a comment or a partial comment (for example, a sentence in the comment), acquires one or more independent words, and makes each one or more independent words into the original form. Then, the evaluation information acquisition unit 23 searches the dictionary storage unit 121 for an evaluation word group that matches a set of one or more independent words (combination of independent words) in the original form. Then, the evaluation information acquisition unit 23 temporarily stores the searched evaluation language group and the score corresponding to the comment having the evaluation word group in a buffer (not shown). Then, the evaluation information acquisition unit 23 performs the above processing for all comments, and a set of two or more evaluation word groups and a score is temporarily stored in a buffer (not shown). Then, the evaluation information acquisition unit 23 calculates the final score corresponding to the evaluation word group by using one or more scores corresponding to the evaluation word group. Then, the evaluation information acquisition unit 23 obtains information (evaluation information) of a set of the evaluation word group and one score. The evaluation information acquisition unit 23 usually calculates the final score by an increasing function having a score of 1 or more corresponding to the evaluation word group as a parameter.

Next, an example of the second operation of the evaluation information acquisition unit 23 will be described. First, the evaluation information acquisition unit 23 morphologically analyzes a comment or a partial comment (for example, a sentence in the comment), acquires one or more independent words, and makes each one or more independent words into the original form. Then, the evaluation information acquisition unit 23 searches the dictionary storage unit 121 for an evaluation word that matches one or more independent words in the original form. Next, the evaluation information acquisition unit 23 corresponds to an evaluation word group (there may be one evaluation word) which is a set of one or more evaluation words acquired by the search and a comment having the one or more evaluation words. The score is temporarily stored in a buffer (not shown). Then, the evaluation information acquisition unit 23 performs the above processing for all comments, and a set of two or more evaluation word groups and a score is temporarily stored in a buffer (not shown). Then, the evaluation information acquisition unit 23 calculates the final score corresponding to the evaluation word group by using one or more scores corresponding to the evaluation word group. Then, the evaluation information acquisition unit 23 obtains information (evaluation information) of a set of the evaluation word group and one score. The evaluation information acquisition unit 23 usually calculates the final score by an increasing function having a score of 1 or more corresponding to the evaluation word group as a parameter.

Next, an example of the third operation of the evaluation information acquisition unit 23 will be described. First, the evaluation information acquisition unit 23 morphologically analyzes a comment or a partial comment (for example, a sentence in the comment), acquires one or more independent words, and makes each one or more independent words into the original form. Then, the evaluation information acquisition unit 23 acquires the evaluation word related to the evaluation from one or more independent words. The evaluation information acquisition unit 23 may remove proper nouns from one or more independent words, for example. Further, the evaluation information acquisition unit 23 may acquire, for example, an independent word that appears more than or more than the threshold value as the evaluation word. Further, the evaluation information acquisition unit 23 may use, for example, all independent words as evaluation words. Further, the evaluation information acquisition unit 23 may select an evaluation word from one or more independent words by another method. Next, the evaluation information acquisition unit 23 includes an evaluation word group (there may be one evaluation word) which is a set of one or more evaluation words, and a score corresponding to a comment having the one or more evaluation words. Is temporarily stored in a buffer (not shown). Then, the evaluation information acquisition unit 23 performs the above processing for all comments, and a set of two or more evaluation word groups and a score is temporarily stored in a buffer (not shown). Then, the evaluation information acquisition unit 23 calculates the final score corresponding to the evaluation word group by using one or more scores corresponding to the evaluation word group. Then, the evaluation information acquisition unit 23 obtains information (evaluation information) of a set of the evaluation word group and one score. The evaluation information acquisition unit 23 usually calculates the final score by an increasing function having a score of 1 or more corresponding to the evaluation word group as a parameter.

The storage unit 24 stores one or more evaluation information acquired by the evaluation information acquisition unit 23 in the recording medium.

The comment acquisition unit 22, the evaluation information acquisition unit 23, and the storage unit 24 can usually be realized from an MPU, a memory, or the like. The processing procedure of the comment acquisition unit 22 and the like is usually realized by software, and the software is recorded on a recording medium such as ROM. However, it may be realized by hardware (dedicated circuit).

Next, the operation of the dictionary construction device 2 will be described with reference to the flowchart of FIG.

(Step S1601) The comment acquisition unit 22 acquires one or more comments corresponding to the scores from the recording medium.

(Step S1602) The evaluation information acquisition unit 23 substitutes 1 for the counter i.

(Step S1603) The evaluation information acquisition unit 23 determines whether or not the i-th comment exists in the comments acquired in step S1601. If the i-th comment exists, the process goes to step S1604, and if the i-th comment does not exist, the process goes to step S1615.

(Step S1604) The evaluation information acquisition unit 23 acquires the score corresponding to the i-th comment.

(Step S1605) The evaluation information acquisition unit 23 performs a process of dividing the comment. The division process may be the process of the flowchart in FIG. 5 or the process of dividing the comment into sentences. That is, the partial comment may be a sentence.

(Step S1606) The evaluation information acquisition unit 23 substitutes 1 for the counter j.

(Step S1607) The evaluation information acquisition unit 23 determines whether or not the j-th partial comment exists in the i-th comment. If the j-th partial comment exists, the process goes to step S1608, and if the j-th partial comment does not exist, the process goes to step S1614.

(Step S1608) The evaluation information acquisition unit 23 acquires one or more evaluation word groups from the j-th partial comment. Since the method of acquiring the evaluation word group from the partial comment such as a sentence has been described in the first to third operations described above, the description thereof will be omitted here.

(Step S1609) The evaluation information acquisition unit 23 substitutes 1 for the counter k.

(Step S1610) The evaluation information acquisition unit 23 determines whether or not the k-th evaluation word group exists in the one or more evaluation word groups acquired in step S1608. If the k-th evaluation word group exists, the process goes to step S1611, and if the k-th evaluation word group does not exist, the process goes to step S1613.

(Step S1611) The evaluation information acquisition unit 23 accumulates the score acquired in step S1604 in association with the k-th evaluation word group. The evaluation information acquisition unit 23 may accumulate the k-th evaluation word group and the score as a pair, or may accumulate the score in association with the accumulated k-th evaluation word group. ..

(Step S1612) The evaluation information acquisition unit 23 increments the counter k by 1. Return to step S1610.

(Step S1613) The evaluation information acquisition unit 23 increments the counter j by 1. Return to step S1607.

(Step S1614) The evaluation information acquisition unit 23 increments the counter i by 1. Return to step S1603.

(Step S1615) The evaluation information acquisition unit 23 substitutes 1 for the counter l.

(Step S1616) The evaluation information acquisition unit 23 determines whether or not the l-th evaluation word group with which the score corresponds exists among the evaluation word groups accumulated in step S1611. If the l-th evaluation word group exists, the process proceeds to step S1617, and if the l-th evaluation word group does not exist, the process ends. The l-th evaluation word group to which the score is associated is the l-type evaluation word group to which the score is associated. (Step S1617) The evaluation information acquisition unit 23 acquires one final score by using the score of 1 or 2 or more corresponding to the l-th evaluation word group.

(Step S1618) The evaluation information acquisition unit 23 constitutes evaluation information having the l-th evaluation word group and the final score. The storage unit 24 stores the evaluation information in the dictionary storage unit 121.

(Step S1619) The evaluation information acquisition unit 23 increments the counter l by 1. Return to step S1616.

By the operation of the dictionary construction device 2, for example, an evaluation word dictionary as shown in FIG. 7 or 8 is automatically constructed from a set of comments with scores in FIG. The score corresponding to the comment may be one, or two or more for each evaluation item. When the comment is associated with two or more scores for each evaluation item, the dictionary construction device 2 can construct two or more evaluation word dictionaries for each evaluation item.

As described above, according to the present embodiment, it is possible to automatically construct a dictionary for acquiring an appropriate evaluation value for comments such as word-of-mouth. The dictionary constructed by the dictionary construction device 2 can be used by the information processing device 12 in the first embodiment.

The software that realizes the information processing device in this embodiment is the following program. That is, this program includes a comment acquisition unit that acquires one or more comments that are comments input by one or more users with respect to the evaluation target of the computer and have a score corresponding to the evaluation target, and one or more comments. From each comment, an evaluation word group consisting of two or more evaluation words that are co-occurring two or more terms and are related to evaluation is acquired, and a score of one or more corresponding to the comment including the evaluation word group is obtained. The evaluation information acquisition unit that determines the score corresponding to the evaluation word group and acquires one or more evaluation information having the score and the evaluation word group, and the one or more evaluation information as a recording medium. It is a program to function as a storage unit for storage.

Further, in the above program, it is preferable that the evaluation word group has a keyword related to evaluation for the evaluation target, a characteristic word indicating a feature related to the keyword, and a degree word indicating the degree of evaluation.

(Embodiment 3)

In the present embodiment, an information system including a comment output device that determines a user similar to oneself from comments with a score and outputs the comment of the user will be described.

In the present embodiment, an information system including a comment output device that inspects both the score and the content of the comment and determines a user similar to oneself will be described.

FIG. 17 is a block diagram of the information system 3 according to the present embodiment. The information system 3 includes an external device 11, a comment output device 31, and a terminal device 13.

The comment output device 31 includes a reception unit 311, a self-comment acquisition unit 312, another comment acquisition unit 313, a similar user determination unit 314, and an output unit 315.

The receiving unit 311 constituting the comment output device 31 receives the comment output instruction from the terminal device 13.

The self-comment acquisition unit 312 acquires one or more self-comments. The self-comment is a comment corresponding to the user identifier of the user who sent the output instruction. In addition, comments are associated with scores. In addition, the comment may have a score corresponding to each evaluation item. It is assumed that the comment corresponds to the user identifier of the user who posted the comment. The user identifier may be any information that can identify the user, such as an ID, an email address, and a telephone number. The self-comment acquisition unit 312 may acquire one or more self-comments from a recording medium (not shown), or may receive one or more self-comments from the external device 11. Further, the one or more self-comments acquired by the self-comment acquisition unit 312 may be a part of the self-comments or all the comments. For example, it may be a comment for the evaluation target corresponding to the output instruction, or a comment for the evaluation target included in the evaluation target category corresponding to the output instruction.

The other comment acquisition unit 313 acquires one or more other comments. The other comment is a comment corresponding to a user identifier of another user different from the user. One or more other comments may be some comments or all comments in other comments. The other comment of 1 or more may be, for example, a comment for the evaluation target corresponding to the output instruction, or a comment for the evaluation target included in the evaluation target category corresponding to the output instruction.

The similar user determination unit 314 determines another user similar to himself / herself from the score and the content of the comment by using one or more own comments and one or more other comments of each other user.

The similar user determination unit 314 is, for example, information of one or more own users, information of one or more own comments and information having a score corresponding to each comment, and information of one or more other users. , Each other user's one or more other comments and one or more other information that has a score corresponding to each other comment are used, and each other user satisfies a predetermined condition. Determine other information that is similar to the information.

The similar user determination unit 314 is, for example, information of one or more own users, calculates the similarity between one or more own comments and one or more other comments for each other user, and corresponds to the similarity and each comment. Using the attached score, other information similar to the own information is determined for each other user so as to satisfy a predetermined condition.

The similar user determination unit 314 acquires, for example, one or more own comments, a score corresponding to each comment, and one or more other comments corresponding to scores that are close enough to satisfy a predetermined condition, and one or more. The similarity between the other comment and one or more self-comments is calculated, and the more the similarity satisfies a predetermined condition, the more similar other information is determined to the self-information. The score here may be a score of 2 or more for each evaluation item. It goes without saying that the similar user determination unit 314 uses the score corresponding to the same evaluation item when comparing or calculating (for example, calculating the difference) the score corresponding to the own comment and the score corresponding to the other comment. No.

The output unit 315 outputs one or more other comments corresponding to the one or more other information determined by the similar user determination unit 314. The output unit 315 may output one or more scores included in one or more other information determined by the similar user determination unit 314. Further, the output unit 315 has a score calculated by using one or more scores included in one or more other information determined by the similar user determination unit 314 (for example, the average value or the center of the scores of other users similar to oneself). Value etc.) may be output. Here, the output is usually a transmission to an external device such as a terminal device 13. However, output is a concept that includes display on a display, projection using a projector, printing with a printer, sound output, storage on a recording medium, and delivery of processing results to other processing devices or other programs. Is.

The receiving unit 311 can usually be realized by a wireless or wired communication means, but may be realized by a means for receiving a broadcast.

The self-comment acquisition unit 312, the other comment acquisition unit 313, and the similar user determination unit 314 can usually be realized from an MPU, a memory, or the like. The processing procedure of the self-comment acquisition unit 312 and the like is usually realized by software, and the software is recorded on a recording medium such as ROM. However, it may be realized by hardware (dedicated circuit).

The output unit 315 can usually be realized by wireless or wired communication means, but may be realized by broadcasting means.

Next, the operation of the comment output device 31 constituting the information system 3 will be described with reference to the flowchart of FIG.

(Step S1801) The receiving unit 311 determines whether or not a comment output instruction has been received from the terminal device 13. If the comment output instruction is received, the process proceeds to step S1802, and if the comment output instruction is not received, the process returns to step S1801.

(Step S1802) The self-comment acquisition unit 312 acquires one or more self-comments corresponding to the user identifier of the user who sent the output instruction. In addition, the score is attached to the self-comment. Further, the self-comment acquisition unit 312 acquires, for example, one or more self-comments stored in a recording medium (not shown).

(Step S1803) The similar user determination unit 314 substitutes 1 for the counter i.

(Step S1804) The similar user determination unit 314 determines whether or not the i-th other user exists. If the i-th other user exists, the process goes to step S1805, and if the i-th other user does not exist, the process goes to step S1810.

(Step S1805) The other comment acquisition unit 313 acquires one or more other comments of the i-th other user. Scores are associated with other comments. Further, the other comment acquisition unit 313 acquires, for example, one or more other comments stored in a recording medium (not shown).

(Step S1806) The similar user determination unit 314 determines whether or not the user who has transmitted the comment output instruction is similar to the i-th other user, and stores the determination result in a buffer (not shown). The similar user determination process will be described with reference to the flowchart of FIG.

(Step S1807) If the determination result in step S1806 is determined that the user who has sent the comment output instruction is similar to the i-th other user, the output unit 315 proceeds to step S1808 and determines that they are not similar. In the case of, the process proceeds to step S1809.

(Step S1808) The output unit 315 temporarily stores other comments paired with the user identifier of the i-th other user in a buffer (not shown). It is assumed that the comment corresponds to the user identifier. The other comments temporarily stored in the buffer are comments to be transmitted.

(Step S1809) The similar user determination unit 314 increments the counter i by 1. Return to step S1804.

(Step S1810) The output unit 315 transmits one or more other comments in a buffer (not shown) to the terminal device 13 that has transmitted the comment output instruction. Return to step S1801.

In the flowchart of FIG. 18, the process ends when the power is turned off or an interrupt for the end of the process occurs.

Next, the similar user determination process in step S1806 will be described with reference to the flowchart of FIG.

(Step S1901) The similar user determination unit 314 substitutes 1 for the counter j.

(Step S1902) The similar user determination unit 314 determines whether or not the j-th evaluation target exists. If the j-th evaluation target exists, the process goes to step S1903, and if the j-th evaluation target does not exist, the process goes to step S1909.

(Step S1903) The similar user determination unit 314 substitutes 1 for the counter k.

(Step S1904) The similar user determination unit 314 determines whether or not the k-th evaluation item exists for the j-th evaluation target. If the k-th evaluation item exists, the process goes to step S1905, and if the k-th evaluation item does not exist, the process goes to step S1910.

(Step S1905) The similar user determination unit 314 tries to acquire the self-comment of the k-th evaluation item of the j-th evaluation target from the acquired one or more self-comments, and from the acquired one or more other comments. Attempts to obtain comments other than the kth evaluation item of the jth evaluation target. Here, it is assumed that both the self-comment and the other comment correspond to the evaluation target and the evaluation item. Corresponding to the evaluation target and the evaluation item means that the information that identifies the evaluation target (for example, the evaluation target word) and the information that identifies the evaluation item (for example, the evaluation item word) are associated. In addition, it is assumed that both self-comments and other comments have scores. In addition, the comment does not have to correspond to the evaluation item because the evaluation target has a heavy rain king.

(Step S1906) In step S1905, the similar user determination unit 314 determines whether or not both the own comment and the other comment can be acquired. If both the self-comment and the other comment can be acquired, the process goes to step S1907, and if both the self-comment and the other comment cannot be acquired, the process proceeds to step S1908.

(Step S1907) The similar user determination unit 314 determines the degree of similarity between the scored self-comment of the k-th evaluation item of the j-th evaluation target and the scored other comment of the k-th evaluation item of the j-th evaluation target. Calculated and temporarily stored in a buffer (not shown). The similarity calculation process of the scored comment will be described with reference to the flowcharts of FIGS. 20 and 21.

(Step S1908) The similar user determination unit 314 increments the counter k by 1. Return to step S1904.

(Step S1909) The similar user determination unit 314 determines whether or not the user who sent the output instruction is similar to the i-th other user by using the similarity of 1 or more calculated in step S1907. The judgment result is stored in a buffer (not shown).

(Step S1910) The similar user determination unit 314 increments the counter j by 1. Return to step S1902.

In the flowchart of FIG. 19, the similarity was calculated for each evaluation target and each evaluation item (step S1907). However, one evaluation item may be used for each evaluation target. Moreover, the evaluation target is one, and it may be decided in advance. When there is one evaluation target and one evaluation item, the similar user judgment process usually determines whether or not the own user and another user are similar from one self-comment with a score and another comment with a score. To do.

Next, a first example of the similarity calculation process of the scored comment in step S1907 will be described with reference to the flowchart of FIG.

(Step S2001) The similar user determination unit 314 calculates the difference between the score corresponding to the own comment and the score corresponding to the other comment.

(Step S2002) The similar user determination unit 314 determines whether or not “the difference <= threshold value calculated in step S2001” or “the difference <threshold value calculated in step S2001” is satisfied. If the above conditions are satisfied, the process proceeds to step S2003, and if the above conditions are not satisfied, the process proceeds to step S2007.

(Step S2003) The similar user determination unit 314 acquires one or more evaluation words from each of the self-comment and the other comment. It should be noted that one or more evaluation word candidates may exist in a storage unit (not shown) of the comment output device 31. Further, the similar user determination unit 314 may morphologically analyze the self-comment and the other comment and acquire one or more independent words as evaluation words. Further, the similar user determination unit 314 morphologically analyzes the self-comment and the other comment, and acquires the self-supporting word satisfying a predetermined condition (for example, not a proper noun) among one or more self-supporting words as an evaluation word. You may.

(Step S2004) The similar user determination unit 314 acquires the degree of similarity between the own comment and the other comment. In addition, the similar user determination unit 314 has a degree of similarity between the own comment and the other comment based on the number of matching one or more evaluation words of the own comment and one or more evaluation words of the other comment acquired in step S2003. May be obtained.

The similar user determination unit 314 may acquire the degree of similarity between the self-comment, which is a set of one or more sentences, and another comment, which is a set of one or more sentences. There can be various methods for obtaining the similarity between a set of sentences, and the method does not matter. Further, since the technique for acquiring the similarity between sentence sets is a known technique, detailed description thereof will be omitted.

(Step S2005) The similar user determination unit 314 determines whether or not “the degree of similarity acquired in step S2004 <= threshold value” or “the degree of similarity acquired in step S2004 <threshold value” is satisfied. If the above conditions are satisfied, the process proceeds to step S2006, and if the above conditions are not satisfied, the process proceeds to step S2007.

(Step S2006) The similar user determination unit 314 substitutes 1 for the degree of similarity.

(Step S2007) The similar user determination unit 314 substitutes 0 for the degree of similarity.

Next, a second example of the similarity calculation process of the scored comment in step S1907 will be described with reference to the flowchart of FIG.

(Step S2101) The similar user determination unit 314 calculates the difference between the score corresponding to the own comment and the score corresponding to the other comment.

(Step S2102) The similar user determination unit 314 calculates the degree of similarity between the self-comment, which is a set of sentences, and another comment, which is a set of sentences. There can be various methods for obtaining the similarity between such sets of sentences, and the method does not matter. Further, since the technique for acquiring the similarity between sentence sets is a known technique, detailed description thereof will be omitted.

(Step S2103) The similar user determination unit 314 calculates the similarity between the scored self-comment and the scored other comment by using the difference calculated in step S2101 and the similarity calculated in step S2102. Return to higher processing. The similar user determination unit 314 has a scored self-comment and a scored others so that the smaller the difference calculated in step S2101, the larger the similarity, and the larger the similarity calculated in step S2102, the larger the similarity. Calculate the similarity with the comment. That is, the similar user determination unit 314 is usually a decreasing function using the difference calculated in step S2101 as a parameter, and an increasing function using the similarity calculated in step S2102 as a parameter to make a self-comment with a score and another comment with a score. Calculate the similarity with.

The comment output device 31 may have an evaluation value acquisition unit (not shown). Then, the evaluation value acquisition unit uses only one or more scores corresponding to other comments of other users determined to be similar by the similar user determination unit 314, and determines that the similar user determination unit 314 is not similar to the other user. The score to be evaluated may be calculated without using the score corresponding to other comments. In such a case, the evaluation value acquisition unit calculates the score to be evaluated by, for example, an increasing function having one or more scores corresponding to other comments of other users determined to be similar by the similar user determination unit 314 as a parameter. The evaluation value acquisition unit calculates the score for each evaluation target and / or for each evaluation item, using only one or more scores corresponding to other comments of other users judged to be similar by the similar user determination unit 314. You may.

Then, in such a case, the output unit 315 may output a score calculated by using only one or more scores corresponding to other comments of other users determined to be similar by the similar user determination unit 314.

Hereinafter, the specific operation of the information system 3 in the present embodiment will be described. The conceptual diagram of the information system 3 is the same as that of FIG.

It is assumed that the receiving unit 311 of the comment output device 31 has received the comment output instruction from the user "Kyosan Hanako" of the terminal device 13. It is assumed that the output instruction includes the user identifier "001" of Hanako from Kyoto.

Then, it is assumed that the self-comment acquisition unit 312 has acquired the self-comment with a score paired with the user identifier "001" from the external device 11. It is assumed that the self-comment with a score is shown in FIG. 11, for example. In FIG. 11, it is assumed that “ID” is an identifier of an evaluation target (here, cosmetics, etc.).

Next, the other comment acquisition unit 313 acquires another comment with a score of 1 or more from the external device 11 for each other user.

Then, the similar user determination unit 314 calculates the difference between the score of the own user and the score of the other user for each of the same evaluation target and the same evaluation item. Then, the similar user determination unit 314 calculates the degree of similarity between the self-comment and the other comment for each of the same evaluation target and each of the same evaluation items.

Next, the similar user determination unit 314 uses the difference between the score of the own user and the score of the other user and the similarity between the comments acquired for each of the same evaluation targets and the same evaluation items as described above. It is determined whether or not the own user and another user are similar by the algorithm and the like. Such processing is performed for all other users.

Next, the similar user determination unit 314 acquires one or more other comments of another user similar to the own user.

Next, the output unit 315 transmits the acquired one or more other comments to the terminal device 13 of "Kyosan Hanako".

Further, the evaluation value acquisition unit (not shown) calculates the score to be evaluated for each evaluation item by using only one or more scores corresponding to other comments of other users judged to be similar by the similar user determination unit 314.

Then, in such a case, the output unit 315 also obtains a score for each evaluation item calculated by using only one or more scores corresponding to other comments of other users judged to be similar by the similar user determination unit 314. It is transmitted to the terminal device 13 of "Hanako".

Next, the terminal receiving unit 133 of the terminal device 13 of "Kyosan Hanako" receives one or more other comments, a score for each evaluation item to be evaluated, and the like from the comment output device 31.

Next, the terminal output unit 134 outputs one or more other comments received by the terminal receiving unit 133, a score for each evaluation item to be evaluated, and the like. An example of such output is shown in FIG. 2201 of FIG. 22 is a tab for outputting comments of similar other users. Now, this tab is selected and other comments of similar users are output. Further, 2202 in FIG. 22 is an evaluation value for each evaluation item using only one or more scores of one or more similar other users. Further, 2203 in FIG. 22 is an evaluation value for each evaluation item corresponding to each other comment.

As described above, according to the present embodiment, it is possible to appropriately see comments such as word-of-mouth of others similar to oneself. It can be said that another person who is similar to himself is usually a person who has a similar evaluation score and comment for the same evaluation target.

The software that realizes the information processing device in this embodiment is the following program. That is, in this program, the computer is a comment corresponding to a receiving unit that receives a comment output instruction and a user identifier of a user who has transmitted the output instruction, and is a comment with a score associated with one or more self. A self-comment acquisition unit that acquires a comment, a comment that corresponds to a user identifier of another user different from the user, and a comment that has a score associated with the comment, and another comment acquisition unit that acquires one or more other comments. The information of one or more own users, the information of one or more own comments and the information having a score corresponding to each comment, and the information of one or more other users, one or more of each other user. Using other comments and one or more other information that has a score corresponding to each other comment, other information similar to the own information can be obtained for each other user so as to satisfy a predetermined condition. This is a program for functioning as an output unit for outputting a similar user determination unit to be determined and one or more other comments corresponding to one or more other information determined by the similar user determination unit.

Further, in the above program, the similar user determination unit is information on the one or more own users, and calculates the degree of similarity between the one or more own comments and the one or more other comments for each other user. It is a program that makes a computer function by using the similarity and the score corresponding to each comment to determine other information that is similar to its own information so that it satisfies a predetermined condition for each other user. That is preferable.

Further, in the above program, the similar user determination unit makes one or more other comments corresponding to the one or more self-comments and the score corresponding to each comment and the score corresponding to a predetermined condition. It is assumed that the degree of similarity between the one or more other comments and the one or more own comments is calculated, and the more the similarity satisfies a predetermined condition, the more similar the other information is to the own information. It is preferable that the program operates the computer.

Further, the appearance of a computer that executes the program described in the present specification to realize the information processing apparatus and the like of the various embodiments described above is 11, 12, 13 and the like in FIG. The above embodiments can be realized in computer hardware and computer programs running on it. 11, 12, 13 and the like in FIG. 1 are overview views of the computer system 300, and FIG. 23 is a block diagram of the system 300.

In 11, 12, 13 and the like of FIG. 1, the computer system includes, for example, a computer including a CD-ROM drive, a keyboard, a mouse, and a monitor.

In FIG. 23, in addition to the CD-ROM drive 3012, the computer 301 includes an MPU 3013, a bus 3014 connected to the MPU 3013 and the CD-ROM drive 3012, a ROM 3015 for storing a program such as a bootup program, and an MPU 3013. It includes a RAM 3016 for temporarily storing the instructions of the application program and providing a temporary storage space, and a hard disk 3017 for storing the application program, the system program, and data. Although not shown here, the computer 301 may further include a network card that provides a connection to the LAN.

The program for causing the computer system 300 to execute the functions of the information processing apparatus and the like according to the above-described embodiment may be stored in the CD-ROM 3101, inserted into the CD-ROM drive 3012, and further transferred to the hard disk 3017. Alternatively, the program may be transmitted to the computer 301 via a network (not shown) and stored on the hard disk 3017. The program is loaded into RAM 3016 at run time. The program may be loaded directly from the CD-ROM3101 or network.

The program does not necessarily include an operating system (OS) that causes the computer 301 to execute functions such as the information processing apparatus of the above-described embodiment, or a third-party program or the like. The program need only include a portion of the instruction that calls the appropriate function (module) in a controlled manner to obtain the desired result. It is well known how the computer system 300 works, and detailed description thereof will be omitted.

In the above program, in the step of transmitting information and the step of receiving information, processing performed by hardware, for example, processing performed by a modem or interface card in the transmission step (performed only by hardware). Processing) is not included.

Further, the number of computers that execute the above program may be singular or plural. That is, centralized processing may be performed, or distributed processing may be performed.

Further, it goes without saying that in each of the above embodiments, the two or more communication means existing in one device may be physically realized by one medium.

Further, in each of the above-described embodiments, each process may be realized by centralized processing by a single device, or may be realized by distributed processing by a plurality of devices.

It goes without saying that the present invention is not limited to the above embodiments, and various modifications can be made, and these are also included in the scope of the present invention.

As described above, the information processing device according to the present invention has an effect of being able to appropriately process information in response to comments such as word-of-mouth, and is useful as a server device for websites and the like.

1, 3 Information system 2 Dictionary construction device 11 External device 12 Information processing device 13 Terminal device 21 Reception unit 22, 122 Comment acquisition unit 23 Evaluation information acquisition unit 24 Storage unit 31 Comment output device 111 Comment storage unit 112 Instruction reception unit 113 Comment Transmitter 121 Dictionary storage unit 123 Evaluation target determination unit 124 Evaluation value acquisition unit 125 Target evaluation value acquisition unit 126, 315 Output unit 131 Terminal reception unit 132 Terminal transmission unit 133 Terminal reception unit 134 Terminal output unit 311 Reception unit 312 Self-comment acquisition Department 313 Other comment acquisition department 314 Similar user determination department

Claims (10)

A comment acquisition unit that acquires one or more comments that are comments input by one or more users and have a score corresponding to the evaluation target from the recording medium.
From each of the above 1 or more comments, an evaluation word group consisting of 2 or more co-occurring terms and 2 or more evaluation words that are related to the evaluation was acquired, and the comments including the evaluation word group were corresponded to. An evaluation information acquisition unit that determines a score corresponding to the evaluation word group using a score of 1 or more and acquires one or more evaluation information having the score and the evaluation word group.
A storage unit for accumulating one or more evaluation information on a recording medium is provided.
The evaluation word group is
Keywords related evaluation of the evaluation object, a dictionary construction apparatus having a degree word indicating characteristic word indicating a characteristic related to the keyword, and the extent of the evaluation. A dictionary storage unit that stores an evaluation word dictionary having two or more evaluation information having two or more evaluation word groups that are evaluation words related to the evaluation of the evaluation target and having different meanings.
A comment acquisition unit that acquires one or more comments input by one or more users from a recording medium, and
From each of the above 1 or more comments, an evaluation word group consisting of two or more co-occurring evaluation words is acquired, the evaluation word group is applied to the evaluation word dictionary, and the evaluation value of the evaluation target is acquired. Acquisition department and
It is provided with an output unit that outputs the evaluation value of the evaluation target acquired by the evaluation value acquisition unit.
The evaluation word group is
Keywords related evaluation of the evaluation object, characteristic word indicating a characteristic related to the keyword, and an information processing apparatus having a degree word indicating the degree of evaluation. The evaluation information is
It has an evaluation language group and a score that is an evaluation value.
The evaluation value acquisition unit
The information processing according to claim 2 , wherein two or more co-occurrence evaluation words are acquired from each of the one or more comments, and the evaluation value of the evaluation target is acquired by using the score corresponding to the two or more evaluation words. apparatus. The dictionary storage unit is
An evaluation word dictionary is stored for each of the two or more evaluation targets, and an evaluation target determination unit for determining the evaluation target of each of the one or more comments acquired by the comment acquisition unit is further provided.
The evaluation value acquisition unit
From each of the above 1 or more comments, an evaluation word group consisting of two or more co-occurring evaluation words is acquired, and the evaluation word group is applied to the evaluation word dictionary corresponding to the evaluation target determined by the evaluation target determination unit. The information processing apparatus according to claim 2 or 3 , wherein the evaluation value of the evaluation target is acquired. The dictionary storage unit is
An evaluation word dictionary is stored for each of two or more evaluation items, and the evaluation value acquisition unit is
Two or more evaluation word groups are acquired from each of the above one or more comments, evaluation items corresponding to the two or more evaluation word groups are determined, and evaluations corresponding to the evaluation items are determined for each of the determined evaluation items. Apply to the word dictionary, get the evaluation value,
The output unit
The information processing apparatus according to any one of claims 2 to 4, which outputs the evaluation value acquired by the evaluation value acquisition unit for each evaluation item. The dictionary storage unit is
The information processing device according to any one of claims 2 to 5, which stores an evaluation word dictionary having one or more evaluation information accumulated by the dictionary construction device according to claim 1. It is a production method of the evaluation word dictionary realized by the comment acquisition unit, the evaluation information acquisition unit, and the storage unit.
A comment acquisition step in which the comment acquisition unit acquires one or more comments that are comments input by one or more users and have a score corresponding to the evaluation target from the recording medium.
The evaluation information acquisition unit acquires an evaluation word group consisting of two or more evaluation words that are co-occurring two or more terms and are related to evaluation from each of the one or more comments, and the evaluation word group. An evaluation information acquisition step of determining a score corresponding to the evaluation word group using one or more scores corresponding to comments including, and acquiring one or more evaluation information having the score and the evaluation word group. ,
The storage unit includes a storage step of storing one or more evaluation information in a recording medium.
The evaluation word group is
Keywords related evaluation of the evaluation object, characteristic word indicating a characteristic related to the keyword, and a method of producing evaluation dictionary having a degree word indicating the degree of evaluation. The recording medium is
It is provided with a dictionary storage unit for storing an evaluation word dictionary having two or more evaluation information having an evaluation word group which is an evaluation word related to evaluation for an evaluation target and is two or more evaluation words having different meanings.
An information processing method realized by a comment acquisition unit, an evaluation value acquisition unit, and an output unit.
A comment acquisition step in which the comment acquisition unit acquires one or more comments input by one or more users from a recording medium.
The evaluation value acquisition unit acquires an evaluation word group consisting of two or more co-occurring evaluation words from each of the one or more comments, applies the evaluation word group to the evaluation word dictionary, and applies the evaluation word group to the evaluation word dictionary. Evaluation value acquisition step to acquire evaluation value and
It is provided with an output step for outputting the evaluation value of the evaluation target acquired by the output unit.
The evaluation word group is
Keywords related evaluation of the evaluation object, an information processing method having a degree word indicating a degree of characteristic words, and evaluation indicating characteristics related to the keyword. Computer,
A comment acquisition unit that acquires one or more comments that are comments input by one or more users and have a score corresponding to the evaluation target from the recording medium.
From each of the above 1 or more comments, an evaluation word group consisting of 2 or more co-occurring terms and 2 or more evaluation words that are related to the evaluation was acquired, and the comments including the evaluation word group were corresponded to. An evaluation information acquisition unit that determines a score corresponding to the evaluation word group using a score of 1 or more and acquires one or more evaluation information having the score and the evaluation word group.
A program for functioning as a storage unit for accumulating one or more evaluation information on a recording medium.
The evaluation word group is
Keywords related evaluation of the evaluation object, characteristic word indicating a characteristic related to the keyword, and having a degree word indicating the degree of evaluation program. Computer-accessible recording media
It is provided with a dictionary storage unit for storing an evaluation word dictionary having two or more evaluation information having an evaluation word group which is an evaluation word related to evaluation for an evaluation target and is two or more evaluation words having different meanings.
Computer,
A comment acquisition unit that acquires one or more comments input by one or more users from a recording medium, and
From each of the above 1 or more comments, an evaluation word group consisting of two or more co-occurring evaluation words is acquired, the evaluation word group is applied to the evaluation word dictionary, and the evaluation value of the evaluation target is acquired. Acquisition department and
It is a program for functioning as an output unit which outputs the evaluation value of the evaluation target acquired by the evaluation value acquisition unit.
The evaluation word group is
Keywords related evaluation of the evaluation object, characteristic word indicating a characteristic related to the keyword, and having a degree word indicating the degree of evaluation program.