JP6894875B2 - Brand dictionary creation device, product evaluation device, brand dictionary creation method and program. - Google Patents

Description

The present invention relates to a brand dictionary creation device, a product evaluation device, a brand dictionary creation method, and a program.

Acquires a query category dictionary that stores information that associates a predetermined search query with the degree of correspondence to a predetermined search query for each content category, and a search query history that indicates past search queries sent from the user terminal. Using the search history acquisition method and the search query history, information related to the degree of correspondence to the past search query for each content category is extracted from the query category dictionary, and based on the extracted information, the user for the content category. Includes a user feature amount calculation means that calculates a user feature amount that indicates the degree of correspondence of each preference, and information that indicates content that corresponds to a search query at the time of a search request sent from a user terminal and is associated with a category. A content search result providing system including a search result acquisition means for acquiring a content search result and an output means for outputting a content search result based on a user feature amount is known (see Patent Document 1).

Japanese Unexamined Patent Publication No. 2016-11260

A query may be entered to search for a product or service (hereinafter referred to as a product, etc.) on a shopping site or the like. Since the number of search hits may affect the ranking of products on shopping sites, list multiple brand names unrelated to the product in the title or product introduction column for the purpose of increasing the number of search hits. Is being done. Such an act is called excessive SEO (Search Engine Optimization) or black hat SEO. Since excessive SEO hinders the formation of an appropriate ranking of products and the like, there is a need to discover products and the like whose sales screen is configured for the purpose of excessive SEO. In order to discover products with excessive SEO, it is desirable to create an appropriate dictionary (brand dictionary) that collects brand names. However, the conventional technique has insufficient accuracy, and there are cases where an appropriate brand dictionary cannot be created.

The present invention has been made in consideration of such circumstances, and provides a brand dictionary creation device, a product evaluation device, a brand dictionary creation method and a program capable of creating a more appropriate brand dictionary. It is one of the purposes.

One aspect of the present invention includes a query acquisition unit that acquires a query input to a sales screen for selling a product or service (hereinafter, product, etc.) via a network, and the acquired query. For each target text, an appearance count unit that counts the number of occurrences of the target text appearing at the beginning of the query and the number of appearances of the target text appearing in the query regardless of the position in the query. For each target text, an index value obtained by dividing the number of first appearances by the number of appearances is derived, and a determination unit for determining whether or not to include the target text in the brand dictionary based on the derived index value. It is a brand dictionary creation device equipped.

According to one aspect of the present invention, a more suitable brand dictionary can be created.

It is a figure which shows an example of the configuration and use environment of the sales intermediary server 200 which used the product evaluation apparatus, and the brand dictionary creation apparatus 300. It is a figure which shows an example of the sale screen IM1 of a product or the like. It is a figure which shows an example of the search result display screen IM2. It is a figure which shows an example of the product display screen IM3. This is an example of the product display screen IM4 in which excessive SEO is performed. It is a figure which shows an example of the content of the product data 220. It is a figure which shows an example of the content of ranking data 222. It is a figure which shows an example of the contents of a brand dictionary 240. It is a flowchart which shows an example of the flow of the process executed by the target word acquisition unit 230, the brand name extraction unit 232, and the attention target product etc. specific unit 234 of the sales intermediary server 200. It is a figure for demonstrating the content of processing by the appearance number counting part 312. It is a flowchart which shows an example of the flow of processing executed by the brand dictionary creation apparatus 300. It is a flowchart which shows an example of the process of S212.

Hereinafter, with reference to the drawings, the brand dictionary creation device, the product evaluation device, the brand dictionary creation method, and the embodiment of the program of the present invention will be described.

[overall structure]
FIG. 1 is a diagram showing an example of a configuration and a usage environment of a sales brokerage server 200 using a product evaluation device and a brand dictionary creating device 300. The sales brokerage server 200 is a device that is accessed by the terminal device 100 to mediate the sale of a product or service (hereinafter, product or the like), and is a device that provides a so-called shopping site or auction site. Here, the "site" includes the original data of the application screen displayed by the application program in addition to the website played by the browser. The operator of the sales brokerage server 200 is provided with product data related to the product or the like exhibited by the seller of the product or the like. Product data includes titles and detailed explanations of products.

In the terminal device 100, a UA (User Agent) 110 such as a browser or an application program is activated. The UA 110 displays the sales screen provided by the sales intermediary server 200, and transmits a request corresponding to the input operation made by the user of the terminal device 100 to the sales intermediary server 200. The sales brokerage server 200 decides to sell the product or the like in response to the request from the UA 110.

Further, the sales brokerage server 200 is provided with a brand dictionary created by the brand dictionary creation device 300. A brand dictionary is an electronic dictionary that collects highly certain words that are the names of brands, which are brand names that should be posted on the introduction screen of a certain product in principle. In the figure, the sales brokerage server 200 and the brand dictionary creation device 300 are shown as separate bodies, but these may be integrated and realized by one hardware.

The terminal device 100, the sales brokerage server 200, and the brand dictionary creation device 300 communicate with each other via the network NW. These components include a network card for connecting to the network NW, a wireless communication module, and the like. The network NW includes, for example, the Internet, a WAN (Wide Area Network), a LAN (Local Area Network), a radio base station, a provider terminal, a dedicated line, and the like.

[Sales brokerage server]
The sales brokerage server 200 includes, for example, a sales screen providing unit 210, a ranking processing unit 212, a log collecting unit 214, a target word acquisition unit 230, a brand name extraction unit 232, and a product identification unit 234 to be noted. Be prepared. These components are realized by, for example, a processor such as a CPU (Central Processing Unit) executing a program (software). In addition, some or all of these components are realized by hardware such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), and GPU (Graphics Processing Unit). It may be done, or it may be realized by the collaboration of software and hardware.

Further, the sales mediation server 200 is stored in a storage device such as a RAM (Random Access Memory), an HDD (Hard Disk Drive), a flash memory, and a ROM (Read Only Memory), and includes product data 220, ranking data 222, log information 224, and the like. It stores data such as the brand dictionary 240. These data may be stored in NAS (Network Attached Storage) or the like that can be accessed by the sales brokerage server 200 via the network NW.

The sales screen providing unit 210 refers to the product data 220 and the ranking data 222, and provides the product sales screen to the terminal device 100. FIG. 2 is a diagram showing an example of the sales screen IM1 of a product or the like. The sales screen IM1 is provided with a query input field A1 for inputting a query for searching for a product or the like, and a search button B1 for executing a search with the input query. When a query is input to the query input field A1 and the search button B1 is operated, the screen transitions to the search result display screen IM2. Some queries are only one word, and some queries include multiple words in which multiple child queries are combined with spaces.

FIG. 3 is a diagram showing an example of the search result display screen IM2. The search result display screen IM2 includes a search result display field A2. In the search result display field A2, images and explanations of products and the like are displayed side by side in the ranking order for each query determined by the ranking processing unit 212. When an image or description of one product or the like is operated on the search result display screen IM2, the screen transitions to the product or the like display screen IM3.

FIG. 4 is a diagram showing an example of a product or the like display screen IM3. The product or the like display screen IM3 includes a product or the like image display column A3-1, a title column A3-2, a product or the like explanation column A3-3, and the like. In the title column A3-2 and the product description column A3-3, the manufacturer, the material of the product, the use, and other contents are posted. Such a content is a normal product or the like display screen IM3, but the product or the like display screen in which excessive SEO is performed shows a different mode.

FIG. 5 is an example of the product display screen IM4 in which excessive SEO is performed. On the product display screen IM4, although the manufacturer is "○○ company", the product explanation column A4-3 shows unrelated companies A, B, and C (all of the same category as company XX). Brand name) is posted. As a result, as a result of performing a search by designating any of "Company A", "Company B", or "Company C" as a query, this product, etc. is searched even though it is not such a product, etc. May hit. In order to avoid or suppress the listing of such products, the sales brokerage server 200 executes a specific process of the products to be noted using the brand dictionary 240. This will be described later.

Returning to the story, the sales screen providing unit 210 generates various display screens illustrated in FIGS. 2 to 5 based on the product data 220. FIG. 6 is a diagram showing an example of the contents of the product or the like data 220. The product data 220 includes a product category, a product image, a title, a product description, a price (standard price or bid price in the case of an auction), shipping conditions, and the like for the product ID, which is identification information of the product. Data are associated with each other.

The ranking processing unit 212 performs ranking processing on each of the queries input in the past according to various criteria, and generates ranking data 222. FIG. 7 is a diagram showing an example of the contents of the ranking data 222. The ranking data 222 is, for example, associated with a query by ranking of product IDs. The ranking data 222 is, for example, based on the log information collected by the log collection unit 214, in the order of the number of clicks, the order of the number of purchases, the order of high CVR (Conversion Ratio), the order of the number of favorites registered, or The ranking is high in ascending order of price or in order of score combining these. In addition, the ranking process may include randomly including products and the like in the ranking.

The log collecting unit 214 stores information including a query input in the terminal device 100, such as an action history in which pages requested by the terminal device 100 are arranged in chronological order, as log information 224.

The target word / phrase acquisition unit 230 acquires the target word / phrase for each product or the like indicated by the product or the like ID among the data included in the product or the like data 220. The target phrase may be arbitrarily defined, but for example, the phrase included in the title and the description of the product or the like is set as the target phrase.

The brand name extraction unit 232 refers to the brand dictionary 240 and extracts the brand name included in the target word / phrase acquired by the target word / phrase acquisition unit 230. More specifically, the brand name extraction unit 232 extracts a brand name that matches the category of the original product or the like from which the target phrase was acquired. FIG. 8 is a diagram showing an example of the contents of the brand dictionary 240. The brand dictionary 240 lists, for example, brand names for each category such as products.

The brand name extraction unit 232 constructs an automaton that performs pattern matching from the dictionary by performing a common prefix search (Common Prefix Search) such as the AhoCorasick method in order to utilize the search results that have already been performed, and inputs text. Achieve a linear calculation time for.

The attention target product etc. specifying unit 234 specifies the caution target product etc. based on the number of brand names extracted by the brand name extraction unit 232. For example, the attention target product identification unit 234 specifies a product or the like whose target phrase includes a brand name of a predetermined number of k or more as a caution target product or the like. For example, k = 2.

Then, the attention target product identification unit 234 displays the product ID on the display device or pays attention to the seller in order to (1) pay attention to the seller regarding the specified caution target product or the like. Is generated and transmitted, (2) the ranking of the product or the like in the ranking data 222 is lowered, or (3) the product or the like is deleted from the product or the like data 220 (the listing is canceled).

Attention The target product identification unit 234 may perform the above-mentioned processes (1) to (3) step by step according to the number of brand names specified by the brand name extraction unit 232. For example, the process of (1) for products, etc. in which two brand names are included in the target phrase, and the process of (2) for products, etc. in which three brand names are included in the target phrase, are performed in four or more. The process of (3) may be performed for a product or the like whose brand name is included in the target phrase.

In addition, the caution target product identification unit 234 counts the number of products, etc. that correspond to the caution target products, etc. for each seller, and according to the number of products, etc. that correspond to the caution target products, etc., the above (1) to The process of (3) may be performed step by step. For example, the process of (1) is applied to the seller whose number of products, etc. corresponding to the caution target product, etc. is 1 or more and less than the 2nd threshold C2, and the number of products, etc. corresponding to the caution target product, etc. The process of (2) is applied to the seller's attention target products, etc. with the second threshold C2 or more and less than the third threshold C3, and the number of products, etc. corresponding to the caution target products, etc. is the seller with the third threshold C3 or more. Note The process (3) may be performed on the target product or the like (or all the products or the like) (C1 <C2 <C3).

FIG. 9 is a flowchart showing an example of the flow of processing executed by the target word acquisition unit 230, the brand name extraction unit 232, and the attention target product and the like specific unit 234 of the sales brokerage server 200. The processing of this flowchart is started at an arbitrary timing.

First, the target word / phrase acquisition unit 230 selects one product or the like from the product or the like data 220 (S100) and acquires the target word or phrase (S102). Next, the brand name extraction unit 232 extracts the brand name from the target words and phrases acquired in S102 (S104).

Next, the product identification unit 234 to be careful determines whether or not the brand name extracted in S104 is a predetermined number k or more (S106). When the brand name extracted in S104 is a predetermined number of k or more, the caution target product or the like specifying unit 234 specifies the product or the like selected in S100 as the caution target product (S108).

Next, the target word / phrase acquisition unit 230 determines whether or not all the products or the like to be processed this time are selected from the product or the like data 220 (S110). If all the products and the like are not selected, the process is returned to S100, and if all the products and the like are selected, the process of this flowchart ends. The loop processing illustrated in FIG. 9 may be executed in parallel by parallel computing.

In this way, according to the sales brokerage server 200 (product evaluation device), the target word acquisition unit 230 for acquiring the target word included in the introduction screen of the product sold via the network NW and the brand name are described. Based on the number of brand names extracted by the brand name extraction unit 232 and the brand name extraction unit 232 that extract the brand names included in the target words and phrases by referring to the brand dictionary 240, the products to be noted are selected. By providing the identification unit 234 for the product or the like to be specified, the product or the like to be specified can be efficiently found. An example of the "product evaluation device" is a combination of the target word acquisition unit 230, the brand name extraction unit 232, and the attention target product identification unit 234. In addition, the product identification unit 234 to be noted is an example of the “monitoring unit”.

In the above explanation, the brand dictionary 240 according to the category of the product or the like is used to specify the product or the like to be noted, but the product or the like to be noted is specified by using all the brand dictionaries 240 without specifying the category. May be specified.

[Brand dictionary creation device]
Hereinafter, the brand dictionary creating device 300 for creating the brand dictionary 240 will be described. The brand dictionary creation device 300 includes, for example, a query acquisition unit 310, an appearance number counting unit 312, a determination unit 314, and a creation unit 316. These components are realized by, for example, a processor such as a CPU executing a program (software). Further, some or all of these components may be realized by hardware such as LSI, ASIC, FPGA, GPU, or may be realized by cooperation between software and hardware.

Further, the brand dictionary creating device 300 stores data such as a query log 320 and a brand dictionary 322 being created in a storage device such as a RAM, an HDD, a flash memory, or a ROM. These data may be stored in NAS or the like accessible by the brand dictionary creation device 300 via the network NW.

The query acquisition unit 310 acquires information about the query from the log information 224 accumulated by the sales brokerage server 200, and stores it in the storage device as the query log 320. Each query included in the query log 320 is accompanied by a product or the like displayed as a result of searching using the query and its category. The categories such as products may be assigned hierarchically, but here, the categories of the hierarchy corresponding to the categories of the brand dictionary will be focused on.

The appearance count unit 312 is the text included in the query based on each query included in the query log 320, and the number of occurrences of the judgment target text (hereinafter referred to as the target text) for which it is determined whether or not to include it in the brand dictionary. To count. The target text is interpreted as a semantic unit by a predetermined logic such as morphological analysis. Further, the target text may be each of the child queries separated by a space or the like, or may be a combination of a plurality of child queries. Depending on the category, the appearance number counting unit 312 may add a limitation to the elements constituting the target text, such as limiting the target text to katakana of three or more characters.

First, the appearance number counting unit 312 extracts a query (hereinafter, target query) corresponding to the target category from the query log 320 when creating a brand dictionary of a certain category (hereinafter, target category). In the query log 320, the query and the information indicating the product or the like clicked on the search result screen of the query are stored in association with each other (click log). The appearance number counting unit 312 extracts, for example, the query to which the product or the like corresponding to the target category is most associated with the click log as the target query. For example, when the categories of products and the like associated with query A included in the query log 320 are fashion 40%, food 20%, outdoor 10%, beauty 10, and others 20%, the appearance number counting unit 312 has the highest ratio. Query A is extracted as a target query used to create a brand dictionary of "fashion", which is a high target category.

The appearance number counting unit 312 may use the query when creating a brand dictionary of the category having the highest ratio among the categories such as products associated with the query. Further, when there are a plurality of categories having a high ratio among the categories such as products associated with the query, the appearance number counting unit 312 has a high possibility that the query is used as a query having various meanings (that is,). , It is a query whose meaning is difficult to specify), and the query may be processed for brand dictionaries related to multiple target categories, or queries showing such a tendency may be excluded from the processing target in the first place. Good.

Next, the appearance number counting unit 312 counts the number of occurrences of the target text constituting the extracted target query. FIG. 10 is a diagram for explaining the content of processing by the appearance number counting unit 312. The appearance count unit 312 sets the number of times of input as a single query for each target text included in the target query to s0, the number of times of occurrence first among the queries including a plurality of target texts to s1, and the second. The number of appearances in is counted as s2, and the number of appearances after the third is counted as s3.

Also, the appearance count unit 312, the target text included in the target query, the number of times that appeared in the data collection period (i.e., the sum of S0 to S3) for counting the total number of occurrences n _t is. The data collection period is a period (target period) that the brand dictionary creation device 300 targets for one process. The brand dictionary creation device 300 performs a brand dictionary creation process based on the query log 320 collected during that period. The data collection period is, for example, a period of about one year.

Also, the appearance count unit 312, the target text included in the target query counts together appearance days c _t is the emerging (observed) the number of days in the data collection period. In the example of FIG. 10, with respect to the target text “aaa”, since it appears once at the first time and appears once alone, 1 is given to s0 and s1 respectively.

The determination unit 314 determines whether or not to include in the brand dictionary based on some or all of the following conditions for the target query for which the above various indicators are counted for the data collection period by the appearance number counting unit 312. judge.

(Condition 1)
Determination unit 314, as shown by the conditional expression (1), the top number of occurrences of the target text (i.e., s1) and derives an index value r obtained by dividing the total number of occurrences n _t of the target text. Judging unit 314, the derived index value r is greater than the first threshold th _r, if other conditions are satisfied for at the judges that include target text brand dictionary. Wherein, r is an index value r, th _r is a first threshold value _{th r (0 <th r <} 1, more preferably, th _r about 0.5).
r> th _r ... (1)

The index value r focuses on the frequency of occurrence of the first occurrence of a query containing a plurality of target texts, which is a rule suitable for a fashion category. This is because it is known in advance that when performing a query search in a fashion category, the brand name is often entered first. As a result, the determination unit 314 can more appropriately include the target text, which is likely to be a brand name, in the brand dictionary.

(Condition 2)
As shown in the conditional expression (2), the determination unit 314 has _{a value in which the total number of occurrences n t} of the target text is larger than a predetermined threshold value (for example, _{a value obtained by multiplying the second threshold value th n} by the number of days in the data collection period). If it is large and other conditions are met, it is determined that the target text is included in the brand dictionary. In the formula, n _t is the total number of occurrences n _t . D is the number of days in the data collection period, and th _n is the second threshold value th _n (1 <th _n , preferably about 10 to 100).
n _t > th _n × D ... (2)

Target text the total number of occurrences n _t has not reached the predetermined threshold value, for example, is likely to be a minor words that are not much search as a query. As a result, the determination unit 314 can include the target text, which is a target text other than a minor word and is likely to be a brand name, in the brand dictionary. Here, the number of days of the target section is an example of the "unit period", the value obtained by multiplying the number of days of the second threshold th _n and data collection period, in one example of the "ratio of the length of the number of unit periods" is there.

(Condition 3)
Determination unit 314, as shown by the conditional expression (3), the appearance of days c _t a query is observed including the target text in the data collection period, a predetermined threshold (e.g., occurrence days with a third threshold value th _c If it is larger than (value multiplied by), and if other conditions are met, it is determined that the target text is included in the brand dictionary. Wherein, _{c t} is the appearance days _{c t,} D is the number of days of data collection period, th _c is a third threshold value _{th c (0 <th c <} 1, more preferably, th _c Is about 0.5 to 0.9).
n _t > th _n × D ... (2)

Target text the appearance days c _t has not reached the predetermined threshold value, for example, is likely to be a large number retrieved text in connection with the buzzword (buzzwords). As a result, the determination unit 314 can include the target text, which is likely to be a brand name that is constantly used, in the brand dictionary.

The creation unit 316 creates a brand dictionary by collecting the target texts determined to be included in the brand dictionary as a result of the determination by the determination unit 314. The brand dictionary is provided to, for example, the sales brokerage server 200.

Hereinafter, the flow of processing executed by the brand dictionary creation device 300 will be described with reference to a flowchart. FIG. 11 is a flowchart showing an example of the flow of processing executed by the brand dictionary creating device 300.

First, the brand dictionary creation device 300 determines the target category (S200). The target category is determined based on, for example, an instruction from the outside (including the operator). Next, the determination unit 314 extracts the query corresponding to the target category from the query log 320 (S202).

Next, the determination unit 314 selects one of the queries extracted in S202 (S204) and divides the query into target texts (S206). Next, the determination unit 314, for each target text, the number of occurrences each occurrence position, the counts up the total number of occurrences _{n t} and appearance days _{c t} (S208).

Then, the determination unit 314 determines whether or not all the queries have been selected in S204 (S210). If all queries are not selected, the process is returned to S204.

When all the queries are selected, the determination unit 314 determines whether or not to include the target text in the brand dictionary based on the various conditions described above (S212). The details of the processing of S212 will be described later. The creation unit 316 includes the target text determined to be included in the brand dictionary as a brand name in the dictionary of the target category as a result of the determination by the determination unit 314 (S214). The loop processing of S204 to S210 illustrated in FIG. 11 may be executed in parallel by parallel computing.

FIG. 12 is a flowchart showing an example of the processing of S212. In S212, the determination unit 314 determines whether or not the target text is composed of three or more characters of katakana (S300). If the target text is not composed of three characters of katakana, the determination unit 314 determines that the target text is not included in the brand dictionary, and ends the process.

Determination unit 314, when the target text is the katakana least three characters, index values r of the target text, determines greater or not than the first threshold th _r (Condition 1) (S302). Judging unit 314, the index value r of the target text is less than or equal the first threshold th _r, is determined not include the target text brand dictionary, the process ends.

When the index value r of the _{target text is larger than the first threshold value th r} , the determination unit 314 determines that the total number of appearances n _t of the target text is the value obtained by multiplying the second threshold value th _n by the number of days in the data collection period. (Condition 2) (S304). _{If the total number of appearances n t} of the target text is not larger than the value obtained by multiplying the second threshold value th _n by the number of days of the data collection period, the determination unit 314 determines that the target text is not included in the brand dictionary and processes it. To finish. When the total number of appearances n _t of the target text is larger than the value obtained by multiplying the second threshold value th _n by the number of days in the data collection period, the determination unit 314 observes a query including the target text during the data collection period. occurrences days _{c t} is judged greater or not than the value obtained by multiplying the occurrence days with a third threshold value th _c (S306).

Judging unit 314, the appearance of days c _t a query is observed including the target text in the data acquisition period is not greater than the value obtained by multiplying the occurrence days with a third threshold value th _c, the target text brand Dictionary It is determined that it is not included in, and the process is terminated. Judging unit 314, the appearance of days c _t a query is observed including the target text in the elephant period is greater than the value obtained by multiplying the occurrence days with a third threshold value th _c (i.e., the condition 1-3 If it is satisfied), it is determined that the target text is included in the brand dictionary, and the process proceeds to S214.

The method of dividing the query into the target text is not limited to the above method. For example, there may be a case where "aaa bbb" included in the query "aaa bbb ccc" is widely used as a brand name. On the other hand, the brand dictionary creating device 300 simply performed morphological analysis and the like from "aaaa bbb ccc" to "aaa", "bbb", "ccc", "aaaa bbb", and "bbbb ccc". In some cases, it may be treated as one target text including words that are two or more target texts. In this case, for example, when both "aaa" and "aaa bbb" have passed through the narrowing down and remain, the one with the larger value on the left side of the conditional expression (3) may be adopted and the smaller one may be excluded. This is because when "aaaa bb" has a higher public awareness than "aaa", it is better to register "aaaa bb" to detect excessive SEO appropriately.

Further, the brand dictionary creation process of the creation unit 316 may be a process of updating an existing brand dictionary (for example, the brand dictionary 240). For example, when the target text determined not to be included in the brand dictionary by the determination unit 314 is included in the brand dictionary 240, the creation unit 316 excludes the target text from the brand dictionary 240 and adds the target text to the brand dictionary by the determination unit 314. If the target text determined to be included is not included in the brand dictionary 240, the brand dictionary 240 may be updated by including the target text in the brand dictionary 240.

According to the brand dictionary creating device 300 described above, the query acquisition unit 310 that acquires the query input to the sales screen for selling the product or the like via the network NW, and the target included in the acquired query. For each text, the appearance count unit 312 that counts the number of occurrences of the target text appearing at the beginning of the query and the number of appearances of the target text appearing in the query regardless of the position in the query, and the target text Each time, an index value r obtained by dividing the number of first appearances by the total number of appearances n _t is derived, and based on the derived index value r, a determination unit 314 for determining whether or not to include the target text in the brand dictionary is provided. Allows you to create a more appropriate brand dictionary.

Although the embodiments for carrying out the present invention have been described above using the embodiments, the present invention is not limited to these embodiments, and various modifications and substitutions are made without departing from the gist of the present invention. Can be added.

1 ... 100 ... terminal device, 200 ... sales brokerage server, 210 ... sales screen providing unit, 212 ... ranking processing unit, 214 ... log collecting unit, 220 ... product data, 222 ... ranking data, 224 ... log information, 230 ... Target phrase acquisition unit, 232 ... Brand name extraction unit, 234 ... Caution Target product identification unit, 240 ... Brand dictionary, 300 ... Brand dictionary creation device, 310 ... Query acquisition unit, 312 ... Appearance count unit, 314 ... Judgment unit , 316 ... creating unit, 320 ... query logs 322 ... brand dictionary, C1, th r _... first threshold value, C2, th n _... second threshold, C3, th c _... third threshold, c t _... occurrence days, k ... Predetermined number, _nt ... total number of appearances, r ... index value

Claims (10)

A query acquisition unit that acquires a query entered for a sales screen for selling a product or service (hereinafter, product, etc.) via a network, and a query acquisition unit.
For each target text included in the acquired query, the number of occurrences of the target text appearing at the beginning of the query and the number of occurrences of the target text appearing in the query regardless of the position in the query are calculated. The number of appearances to be counted
For each target text, an index value obtained by dividing the number of first appearances by the number of appearances is derived, and a determination unit for determining whether or not to include the target text in the brand dictionary based on the derived index value.
A brand dictionary creation device equipped with. When the index value is larger than the first threshold value, the determination unit determines that the target text is included in the brand dictionary.
The brand dictionary creating device according to claim 1. The determination unit further determines whether or not to include the target text in the brand dictionary based on the ratio of the number of occurrences to the data collection period during the observed period.
The brand dictionary creating device according to claim 1 or 2. The determination unit further puts the target text into the brand dictionary based on the ratio of the number of unit periods in which the query containing the target text was observed during the data collection period to the length of the data collection period. Determine whether to include,
The brand dictionary creating device according to any one of claims 1 to 3. The determination unit determines that the target text is not included in the brand dictionary when the target text is not composed of three or more characters of katakana.
The brand dictionary creating device according to any one of claims 1 to 4. The brand dictionary creating device according to any one of claims 1 to 5.
The target phrase acquisition unit that acquires the target phrase included in the introduction screen of the product or service (hereinafter, product, etc.) sold via the network,
A brand name extraction unit that extracts the brand name included in the target phrase by referring to the brand dictionary, and
A monitoring unit that identifies products to be noted based on the number of brand names extracted by the brand name extraction unit, and
Product evaluation device equipped with. When the number of brand names extracted by the brand name extraction unit is equal to or greater than a predetermined number, the monitoring unit identifies the acquisition source product or the like from which the target phrase has been acquired as the caution target product or the like.
The product evaluation device according to claim 6. Based on the number of brand names extracted by the brand name extraction unit, the monitoring unit performs stepwise processing on the seller who has put up the product or the like to be noted.
The product evaluation device according to claim 6 or 7. The computer
Get the query entered for the sales screen to sell a product or service (hereinafter, product, etc.) via the network.
For each target text included in the acquired query, the number of occurrences of the target text appearing at the beginning of the query and the number of occurrences of the target text appearing in the query regardless of the position in the query are counted. And
For each target text, an index value obtained by dividing the number of first appearances by the number of appearances is derived, and based on the derived index value, it is determined whether or not the target text is included in the brand dictionary.
How to create a brand dictionary. On the computer
Get the query entered for the sales screen for selling products or services (hereinafter, products, etc.) via the network.
For each target text included in the acquired query, the number of occurrences of the target text appearing at the beginning of the query and the number of occurrences of the target text appearing in the query regardless of the position in the query are counted. Let me
For each target text, an index value obtained by dividing the number of first appearances by the number of appearances is derived, and based on the derived index value, it is determined whether or not the target text is included in the brand dictionary.
program.

Images