JP5429525B2 - Product recommendation method and product recommendation system - Google Patents

Description

  The present invention relates to a product recommendation method and a product recommendation system for recommending a specific product to a consumer.

  2. Description of the Related Art A product recommendation system that distributes recommended information of a specific product to a consumer information terminal by e-mail or a web page, for example, is known. As a prior art of such a product recommendation system, there is a product recommendation system (advertising information distribution system) that grasps the consumer's balance status and distributes the recommended product information to scenes with high advertising effects caused by changes in the balance status Exists (see, for example, Patent Document 1).

JP 2007-102820 A

  In general, there are differences in consumer personality and consumption trends, such as people who tend to consume in a relatively short time after a certain product is put on the market (so-called trends or people who jump to new products) There are people who tend to consume a product after a relatively long time since the product was put on the market (people who carefully determine the state of a new product). In such a case, it is preferable to recommend the product earlier after the product is introduced to the former, and to recommend the product later to the latter after the product is introduced. However, according to the above-mentioned prior art product recommendation system, although the consumer's income and expenditure situation is taken into consideration, the individuality and consumption trend of each consumer as described above are not taken into consideration, The product could not be recommended at the appropriate recommendation time.

  An object of the present invention is to provide a product recommendation method and a product recommendation system that can make an effective product recommendation according to the individuality and consumption trend of each consumer.

In order to achieve the above object, the product recommendation method of the first invention is a product recommendation method for recommending a specific product to a consumer, wherein a plurality of consumer identifications are performed based on operation inputs on the first information terminal on the product recommender side. A first procedure for accessing a consumer database storing information and identifying the consumer; a time when the product is first placed on the market and a specific consumer stored in the consumer database; based on consumer behavior history information having a consumption behavior timing that consumed the product, for each product, and a second step of calculating the time difference between the time the consumer behavior and the time-to-market, each product in the second procedure The time difference calculated in the above is corrected and aggregated using a first correction condition determined in advance for each product characteristic stored in the consumer database, and the standard time unique to the specific consumer A fifth step of calculating the information, based on said fifth procedure the standard time difference information calculated by the third procedure for determining at least one recommended timing of the specific products to recommend to the particular consumer And at the recommended time determined in the third procedure, the recommended information of the specific product is obtained from a recommendation database, and the recommended procedure is output to the second information terminal of the specific consumer. It is characterized by having.

  In the first invention of the present application, consumption behavior history information relating to consumption of goods by a plurality of consumers is accumulated in the consumer database. This consumption behavior history information includes the market launch time when the product is first introduced to the market and the consumer behavior time when the consumer consumes the product. When the first information terminal is operated by the product recommender, the consumer database is accessed in the first procedure, and the consumer is specified by the consumer identification information. Thereafter, in the second procedure, a time difference from the time when the product is put on the market until the specific consumer consumes is calculated for each of the plurality of products based on the time when the product is put on the market and the time of consumption behavior. Then, in the third procedure, a recommended time for each product is determined based on the time difference calculated for each product. Then, every time the recommended time of each product arrives, the recommended information of the product is output to the second information terminal of the specific consumer in the fourth procedure.

  As a result, if a product tends to be consumed in a relatively short time after being put on the market, the product is recommended earlier than the product launch date, For those who tend to consume after a long time, product recommendations can be made late after product launch. As a result, effective product recommendations can be made according to the individuality and consumption trends of each consumer.

Further, in general, the time difference until a specific consumer consumes after the time when the product is put on the market differs depending on the product characteristics in addition to the individuality of the consumer. Corresponding to this, the first invention of the present application corrects and aggregates the time difference calculated for each product for a specific consumer using the first correction condition defined for each product characteristic. Thereby, the dispersion | variation by the above merchandise characteristics is eliminated, and the effective merchandise recommendation which mainly reflected the personality and consumption trend peculiar to a specific consumer can be performed.

The product recommendation method according to a second aspect of the present invention is the above-described first aspect , wherein the standard time difference information calculated by the fifth step is determined according to a sixth step and a sixth step. And a seventh procedure for determining which of the plurality of consumer groups classified by the predetermined time width the specific consumer belongs to when the predetermined time width is determined. The third procedure is recommended to the specific consumer based on representative time difference information predetermined for the consumer group determined to belong to the specific consumer in the seventh procedure. The recommended time of the specific product is determined.

In the second invention of the present application, a plurality of consumer groups divided for each predetermined time width are prepared, and representative time difference information is preset for each consumer group. Then, in the sixth procedure, it is determined which of the plurality of consumer groups the standard time difference information calculated in the fifth procedure belongs, and in the seventh procedure, the representative time difference information corresponding to the determined consumer group is added. Based on this, a recommended time for a specific product is determined for the specific consumer. As a result, if the recommended time is set uniformly for each consumer group in advance, the recommended time is determined only by determining which consumer group the consumer belongs to according to the standard time difference information. The recommended time can be easily determined for consumers. In addition, since the number of recommended periods managed on the product recommender side can be significantly reduced as compared with the case where no consumer group is prepared, the system processing speed is improved and the database capacity is also reduced.

The product recommendation method according to a third aspect of the present invention is the first or second aspect of the invention , wherein the third step is the standard time difference information calculated for the specific consumer in the fifth step, or the sixth step. The representative time difference information associated with the specific consumer is corrected using a second correction condition determined in advance corresponding to the product characteristics of the specific product stored in the storage unit, Including a calculation procedure for each product for calculating time difference information, and a procedure for determining a recommended time of the specific product recommended for the specific consumer based on the time difference information for each product calculated in the calculation procedure for each product. It is characterized by being.

When the recommended time is determined based on the standard time difference information or representative time difference information calculated to grasp the consumer's unique personality and consumption trends, the standard time difference information and representative time difference information are uniform for each consumer. Since it is set, it is not possible to determine the recommended time corresponding to the product characteristics of each product. Accordingly, in the third invention of the present application, it is possible to determine the recommended time corresponding to the product characteristics of each product by correcting the standard time difference information or the representative time difference information using the second correction condition corresponding to the product characteristics. it can.

The product recommendation method of the fourth invention is the product recommendation method according to any one of the first to third inventions , wherein the third procedure is a plurality of recommended times for making a recommendation while gradually changing the price setting of the specific product. And the fourth procedure changes the price setting value of the specific product to the second information terminal of the specific consumer at each of the plurality of recommended times determined in the third procedure. It is characterized by being output.

  As a result, for consumers who tend to consume a product in a relatively short time after being put on the market, the consumer's willingness to consume can be obtained by discounting the price early on the product launch date. Can be further increased. On the other hand, for those who tend to consume after a relatively long period of time since the product was introduced to the market, do not discount the price early in the product launch period, but discount later. Therefore, it is possible to perform a discount price according to the individuality and consumption trend of the consumer, thereby increasing the willingness to consume. In this way, effective product recommendations can be made according to the individuality and consumption trends of each consumer.

The product recommendation method according to a fifth aspect of the present invention is the method according to the fourth aspect , wherein the third step is calculated by the second step or the fifth step, and the time difference or the standard time difference relating to the specific consumer is a predetermined time. Including a time difference determination procedure for determining whether or not the time difference is greater than or equal to, and when the time difference determination procedure determines that the time difference or the standard time difference is greater than or equal to a predetermined time, the first recommendation among a plurality of the recommended times When the start time and the recommended end time are delayed and the recommended number of times including the first time is increased, while the time difference determination procedure determines that the time difference is less than a predetermined time, the first time among the plurality of recommended times. The recommended start time and the recommended end time are advanced earlier, and the recommended number of times including the first time is reduced.

  As a result, for those people who tend to consume in a relatively short time after a certain product is put on the market, the recommendation is started earlier on the date of product introduction and the total number of recommendations is reduced and the earlier By ending the recommendation, it is possible to make an effective product recommendation in accordance with the consumer's individuality and consumption trends. On the other hand, for those who tend to consume after a relatively long time since the product was put on the market, the recommendation was started late after the product was introduced, and the overall number of recommendations was increased. By ending the recommendation, it is possible to make an effective product recommendation in accordance with the consumer's individuality and consumption trends.

In order to achieve the above object, the product recommendation system of the sixth invention is a product recommendation system for recommending a specific product to a consumer, and consumption behavior history information related to a plurality of products by each of the plurality of consumers, A consumer database in which consumer identification information of each consumer is stored in association with each other, and a market launch in which the product is first placed in the market, which is included in the consumer behavior history information accumulated in the consumer database A time difference calculating means for calculating a time difference between the market launch time and the consumption action time for each of a plurality of products based on the time and the consumption behavior time of a specific consumer, and each product by the time difference calculation means The time difference calculated for each product is corrected using a first correction condition determined in advance for each product characteristic stored in the consumer database, and totaled. And the standard time difference information calculating means for calculating a specific standard time difference information into serial particular consumer, on the basis of the standard time difference information calculated by the standard time difference information calculation unit, the specific recommended to the particular consumer Recommended time determination means for determining at least one recommended time of a product, and at the recommended time determined by the recommended time determination means, the recommended information of the specific product is obtained from a recommendation database, and the specific consumer's And a recommended information output means for outputting to the consumer information terminal.

In the sixth invention of this application, consumption behavior history information related to consumption of products by a plurality of consumers is accumulated in the consumer database. This consumption behavior history information includes the market launch time when the product is first introduced to the market and the consumer behavior time when the consumer consumes the product. The time difference calculating means accesses this consumer database and calculates the time difference until the product for a specific consumer is consumed after the market launch time for each of the plurality of products based on the market launch time and the consumption behavior time.

Then, the recommended time calculation means determines the recommended time of the product for a specific consumer based on the calculated time difference. When the recommended time for a product arrives, the recommended information output means acquires the recommended information for the product from the recommended database and outputs it to the consumer information terminal of the specific consumer.
As a result, if a product tends to be consumed in a relatively short time after being put on the market, the product is recommended early after the product is put on the market, and a relatively long time has passed since the product was put on the market. For those who tend to consume after the product has passed, product recommendations can be made late after product launch. As a result, effective product recommendations can be made according to the individuality and consumption trends of each consumer.
Further, in general, the time difference until a specific consumer consumes after the time when the product is put on the market differs depending on the product characteristics in addition to the individuality of the consumer. Correspondingly, in the sixth invention of the present application, the time difference calculated for each product for a specific consumer is corrected and totaled using the first correction condition determined for each product characteristic. Thereby, the dispersion | variation by the above merchandise characteristics is eliminated, and the effective merchandise recommendation which mainly reflected the personality and consumption trend peculiar to a specific consumer can be performed.

  ADVANTAGE OF THE INVENTION According to this invention, the recommendation of an effective product according to each consumer's individuality and consumption trend can be performed.

It is a system configuration figure showing notionally the whole composition of the goods recommendation system of this embodiment. It is a block diagram showing the function structure of a server and a portable terminal. It is a figure showing an example of the memory content of a singing action history database. It is a figure showing an example of the correction conditions predetermined for every characteristic of music data for correcting the time difference calculated for every music data, when calculating a standard time difference peculiar to a consumer. It is a figure showing an example of the setting regarding the recommendation time which recommends specific goods with respect to the said consumer corresponding to the standard time difference for every consumer. It is a figure showing an example of the correction conditions predetermined in order to correct the determined recommendation time corresponding to the goods characteristic of the goods recommended with respect to the said consumer, and to calculate the recommended time for every goods. It is a figure showing an example of the setting regarding the recommended goods recommended with respect to the said consumer corresponding to the standard time difference for every consumer. It is a figure showing an example of the setting regarding the discount rate of the price of the recommended product recommended with respect to the said consumer corresponding to the standard time difference for every consumer. It is a figure showing an example of the recommendation information plan produced by the control part of a server. It is a flowchart showing the control content which the control part of a server performs. It is a block diagram showing the function structure of a server and a portable terminal in the modification which determines a recommendation time based on consumption action history. It is a figure showing an example of the memory content of a consumption action history database. It is a figure showing an example of the correction conditions predetermined for every characteristic of goods for amending the time difference computed for every goods, when calculating the standard time difference peculiar to consumers.

  Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

  FIG. 1 is a system configuration diagram conceptually showing the overall configuration of the product recommendation system 1 of the present embodiment.

  In FIG. 1, the product recommendation system 1 determines the personality of the consumer M from the trend of the singing behavior of the consumer M who is a karaoke user in karaoke, and estimates the consumption behavior of the product according to the personality. A specific product (hereinafter referred to as “specific product” as appropriate) is recommended to the consumer M at a corresponding timing. This product recommendation system 1 has a server 200 (first information terminal) connected to a karaoke apparatus 100 installed in a karaoke room KR via a network NW such as the Internet. A display 220, a keyboard 221, and a mouse 222 are connected to the server 200.

  The karaoke apparatus 100 includes a karaoke apparatus main body 110 that reproduces music data distributed from a music distribution company via the network NW, a display apparatus 120 that displays an image related to singing when the music data is reproduced, and a karaoke apparatus main body 110. It has a microphone 115 connected and used for singing by the consumer M.

  As described above, the karaoke apparatus main body 110 and the server 200 are connected to each other via the network NW so as to be able to communicate with each other, and singing action history information related to reproduction of each piece of music data by each consumer M in the karaoke room KR. Is stored in the server 200. The server 200 is also connected to the base station 300 via the network NW, and the recommendation of a specific product that is output from the server 200 to the consumer M at a timing based on the singing behavior history information of each consumer M. Information can be transmitted by wireless communication to the mobile terminal 400 carried by each consumer M via the base station 300.

  As the mobile terminal 400 (second information terminal, consumer information terminal), for example, a mobile phone or the like is used. In addition, an information terminal such as a PDA (Personal Digital Assistant) may be used. The portable terminal 400 includes a display unit 401 such as a liquid crystal display for performing various displays, an operation unit 402 including numeric keys and operation buttons for the consumer M to perform various operation inputs, and wireless communication with the base station 300. And an antenna 410 for transmitting and receiving information through the network.

  FIG. 2 is a block diagram illustrating functional configurations of the server 200 and the mobile terminal 400.

  In FIG. 2, the server 200 includes a network NW among a control unit 201 that controls the entire server 200, a storage unit 210 configured by an HDD (Hard Disk Drive), and the karaoke apparatus main body 110 and the base station 300. A communication control unit 202 that performs control of information communication performed via the network, an output control unit 203 that performs control regarding output of a video signal to the display 220, and a control regarding input of information via the keyboard 221 and the mouse 222. And an input control unit 204 for performing the above.

  The storage unit 210 (storage means) stores the singing action history information (consumption action history information) related to a plurality of music data (products) by each of a plurality of consumers M, and a consumer ID as consumer identification information. It has a singing action history database 211 (consumer database) stored in association with each other. The singing action history information includes, for each consumer M, for each piece of music data, the distribution start time (market introduction time) when the music data was first distributed to the market by the music distribution company, and the consumer M The singing action time (consumption action time) at which the music data is first reproduced in the karaoke room KR is included (see FIG. 3 described later).

  The storage unit 210 also has a product database 212 (recommendation database) that stores recommendation information (for example, information about products such as product names, product contents, prices, and appearance images) for recommending various products, and a karaoke room KR. To identify the personality of the consumer M from the trend of the singing behavior of the consumer M in Japan, to estimate the consumer behavior of the product according to the personality, and to recommend the specific product to the consumer M at the timing according to this And a program storage area 213 for storing various programs such as a product recommendation program for executing a product recommendation method (see FIG. 10 described later).

  The control unit 201 is a so-called microcomputer, and although not shown, the control unit 201 includes a central processing unit such as a CPU, a ROM, a RAM, and the like. Signal processing is performed according to various programs stored in the area 213.

  The portable terminal 400 includes a display unit 401, an operation unit 402, an antenna 410, a wireless communication control unit 403 that controls information communication performed through wireless communication with the base station 300, and the entire portable terminal 400. And a control unit 404 that performs the above control. When the controller 404 receives recommended information on a specific product from the server 200 via the network NW and the base station 300, the controller 404 causes the display 401 to display the recommended information.

  FIG. 3 is a diagram illustrating an example of the stored contents of the singing action history database 211.

  As shown in FIG. 3, in the singing action history database 211, for each consumer M, the consumer ID and singing action history information related to a plurality of pieces of music data sung by the consumer M are associated with each other. Is remembered. The singing action history information includes, for each piece of music data, the name of the music, the type of music, the distribution start time when the music data was first distributed to the market by the music distribution company, and the consumer M at the karaoke room KR. The singing action time when the music data was first reproduced is included.

  The control unit 201 of the server 200 calculates a time difference between the distribution start time and the singing action time for each piece of music data for a specific consumer M. In the example illustrated in FIG. 3, the consumer M whose consumer ID is “ID1” has a time difference of 7 days (1 week), 1 day, and 22 days for each piece of music data “music 1 to 3”. For the consumer M with the person ID “ID2”, the time differences for the music data “music4-6” are 36 days, 83 days, and 76 days, respectively. That is, the former has a relatively short time difference between the distribution start time and the singing action time, and the latter has a relatively long time difference between the distribution start time and the singing action time. In this example, the type of music is divided into two types, “Japanese music” and “Western music”, but other than this, for example, whether it is a young singer or an elderly singer, whether it is a single music or a medley music, etc. The music may be classified according to other types.

  FIG. 4 shows an example of correction conditions predetermined for each characteristic of music data for correcting the time difference calculated for each piece of music data when calculating a standard time difference unique to the consumer M. FIG.

  FIG. 4A is a graph showing general product characteristics of two types of music data, “Japanese music” and “Western music”. As shown in FIG. 4 (a), the number of distributions for “Japanese music” rises relatively early from the start of distribution, while the number of distributions for “Western music” increases from the start of distribution. Has a relatively long product characteristic. In the present embodiment, as shown in FIG. 4A, the time required for the characteristic curve M2 of “Western music” to reach the maximum value is approximately the time required for the characteristic curve M1 of “Japanese music” to reach the maximum value. Since it is 5 times, as shown in FIG. 4B, the correction condition for the time difference is 1 time for “Japanese music” and 0.2 times for “Western music”. Thereby, the dispersion | variation in the time difference by the said characteristic based on the kind of music can be eliminated. Information regarding the correction condition (first correction condition) is stored in advance in an appropriate area of the storage unit 210.

  In the example shown in FIG. 4, the correction condition is determined based on the maximum value of the two characteristic curves M1 and M2. However, the present invention is not limited to this. For example, the median value and average value of the characteristic curves M1 and M2 are determined. Alternatively, the correction condition may be determined based on the standard deviation or the like.

  Based on the correction conditions, the standard time difference inherent to the consumer M is specifically obtained as follows. For example, for the consumer M whose consumer ID is “ID1” shown in FIG. 3 above, “music1” and “music2” are “Japanese music”, and therefore, after correction by multiplying by 1 times the above correction condition The time difference is 7 days (1 week) and 1 day, and “music3” is “Western music”. Therefore, the time difference is 4.4 days by multiplying by 0.2 times the correction condition. Therefore, the standard time difference is the average of these (7 + 1 + 4.4) /3≈4.1 days. Further, for example, for the consumer M whose consumer ID is “ID2” shown in FIG. 3, since “music 4 to 6” are all “Japanese music”, they are multiplied by 1 times that is the above correction condition, and are corrected. The time differences are 36 days, 83 days, and 76 days, respectively. Therefore, the standard time difference is the average of these, (36 + 83 + 76) / 3≈65 days.

  FIG. 5 is a diagram illustrating an example of a setting related to a recommended time for recommending a specific product to the consumer M, corresponding to the standard time difference for each consumer M.

  As shown in FIG. 5, a recommended time for recommending a specific product is set in advance according to the calculated standard time difference. Note that the setting information regarding the recommended time is stored in advance in an appropriate area of the storage unit 210. In the present embodiment, by determining whether or not the standard time difference is a predetermined time width, it is determined which of the three consumer groups the consumer M belongs to each predetermined time width. In the example shown in FIG. 5, when the standard time difference is one week or more and less than one month, the consumer M is a consumer group “standard” whose standard time difference is a standard length, and the standard time difference is less than one week. If the standard time difference is one month or more, the consumer group is classified as “small”, and if the standard time difference is one month or more, the consumer group is classified as “large”. Information (representative time difference information) regarding the recommended time is set in advance for the group. This recommended time information is composed of items such as a start time for starting the first recommendation, an end time for ending the first recommendation, the recommended number of times, a single recommended period, and an interval until the next recommendation. In addition, “the day” shown in the figure indicates the date (release date, announcement date, etc.) when the recommended product is put on the market.

  In this example, for the consumer M belonging to the consumer group “small”, a person who tends to sing in karaoke in a relatively short time after a certain piece of music data is distributed to the market, that is, a certain product enters the market. Since it is considered that people tend to consume after a relatively short period of time since its introduction, the recommendation period is recommended earlier than the date of product introduction compared to consumer M of the consumer group “Standard” In addition, the number of recommended times is reduced, and the recommended period and the recommended interval are shortened, and the entire recommendation is finished early. For example, the consumer M having the consumer ID “ID1” shown in FIG. 3 described above corresponds to the consumer M belonging to the consumer group “small” because the standard time difference is 4.1 days as described above. .

  On the other hand, for the consumer M belonging to the consumer group “large”, a person who tends to sing in karaoke after a lapse of a relatively long time since a certain piece of music data is distributed to the market, that is, a certain product is in the market. Since it is considered that people tend to consume after a relatively long time since it was launched, the recommendation period is recommended later than the consumer M of the consumer group “standard”. In addition to increasing the total number of recommendations, it is decided to extend the recommendation period and the recommendation interval once and finish the overall recommendation later. For example, the consumer M whose consumer ID is “ID2” shown in FIG. 3 corresponds to the consumer M belonging to the consumer group “large” because the standard time difference is 65 days as described above.

  FIG. 6 is determined in advance to calculate the recommended time (product-specific time difference information) for each product by correcting the determined recommended time in accordance with the product characteristics of the product recommended for the consumer M. It is a figure showing an example of correction conditions.

  In the example shown in FIG. 6, correction conditions are defined corresponding to four price ranges as product characteristics. For products with a product price of 5,000 yen or less, the recommended time is doubled and the product price is 5,000 yen or more. For those with a high price of 10,000 yen or less, the recommended time is doubled. For those with a product price higher than 10,000 yen but less than 50,000 yen, the recommended time is tripled. For things, the recommended time is multiplied by 5. In this way, the higher the price, the larger the magnification is set because the consumer generally tends to spend more time considering whether or not to purchase the higher the price of the product. Information regarding the correction condition (second correction condition) is stored in advance in an appropriate area of the storage unit 210.

  Specifically, for example, when recommending a product of 40,000 yen to the consumer M belonging to the consumer group “small”, the recommended condition is three times, so the consumer shown in FIG. Three times the recommended period for consumer M belonging to the group “Small”, that is, the start time is 4 days, the end time is 13 days, the recommended number is 9, the recommended period is 9 days, the next recommended period The interval until the period is 3 days. In this case, the calculation method of the start time is 2 days × 3 = 6 days for the consumer group “small” because the consumer group “standard” is 2 days earlier than the current day. Since it is shifted six days later from the setting shown in FIG. 5 (two days ago), it is four days after the product introduction date. The calculation method of the end time is that the recommended period of setting shown in FIG. 5 is 3 days and the recommended period after correction is 3 days × 3 = 9 days as described above. It will be 13 days after 4 days.

  In the example shown in FIG. 6, the correction condition is set as the product characteristic according to the product price. However, the correction condition is not limited to this. For example, the product type (whether the product is a book or a car), and the product is durable. Correction conditions may be set in accordance with other product characteristics such as whether the product is a consumable product or a product individuality (for example, a difference between products in the same product).

  FIG. 7 is a diagram illustrating an example of settings related to recommended products recommended for the consumer M, corresponding to the standard time difference for each consumer M.

  As shown in FIG. 7, information related to recommended products to be recommended to the consumer M is set in advance according to the calculated standard time difference. Note that the setting information related to the recommended product is stored in advance in an appropriate area of the storage unit 210. In the example illustrated in FIG. 7, the information related to recommended products includes items of the ratio of new products and old products, the ratio of trendy products and non-fashionable products, and the number of recommended products. In this example, the consumer M who belongs to the consumer group “small” is a person who tends to sing in karaoke in a relatively short time after a certain piece of music data is distributed to the market, that is, a fashion or a new product. Since it is considered that the person jumps immediately, the recommended product is determined so that the ratio of new products and trendy products is larger than that of the consumer M who belongs to the consumer group “standard”. In addition, since the curiosity is expected and the property is expected to be interested in various products, the recommended number of products compared to the number of products (for example, two) of the consumer M of the consumer group “standard”. Recommended products are determined so as to increase (for example, four).

  On the other hand, the consumer M who belongs to the consumer group “Large” is a person who tends to sing in karaoke after a relatively long time since a certain piece of music data is distributed to the market, that is, a state of a new product. Since it is considered that the person is a type of person who carefully examines, the recommended product is determined so that the ratio of new products and trendy products is smaller than that of the consumer M who belongs to the consumer group “standard”. In addition, since it is expected that the product is only interested in limited products, the number of recommended products is smaller than the number of products (for example, two) of the consumer M in the consumer group “standard”. The recommended product is determined as follows (for example, one).

  FIG. 8 is a diagram illustrating an example of a setting related to the discount rate of the recommended product recommended for the consumer M, corresponding to the standard time difference for each consumer M.

  As shown in FIG. 8, information related to the discount rate of the recommended product price to be recommended to the consumer M according to the calculated standard time difference is set in advance. The setting information regarding the discount rate is stored in advance in an appropriate area of the storage unit 210. In the example shown in FIG. 8, the information related to the discount rate is set so that the price setting varies stepwise according to the recommended number of times. In this example, the consumer M who belongs to the consumer group “small” is considered to be a person who tends to consume in a relatively short time after a certain product is put on the market as described above. The discount rate is determined so that the price is discounted earlier than the consumer M who belongs to the group “standard”. On the other hand, the consumer M belonging to the consumer group “Large” is considered to be a person who tends to consume after a relatively long time since a certain product was put on the market as described above. The discount rate is determined so that the price is discounted later than the consumer M who belongs to the group “standard”.

  In the above description, the discount rate is set according to the recommended number of times. However, the present invention is not limited to this, and the discount rate may be set according to a period (elapsed time after starting distribution).

  FIG. 9 is a diagram illustrating an example of a recommended information plan created by the control unit 201 of the server 200. In FIG. 9, it is assumed that the price of recommended specific products is within 5,000 yen, and the release date of these products is January 1, 2009.

  FIG. 9A is an example of a recommended information plan for the consumer M who belongs to the consumer group “small”. As shown in FIG. 5 described above, the recommended time for the consumer M belonging to the consumer group “small” is that the recommended start time is 2 days before the release date, the recommended period is 3 days, the recommended frequency is 3 times, and the interval Since the price of the products A, B, C, and D is within 5,000 yen, the correction condition is 1 time magnification as shown in FIG. 6, and the recommended period shown in FIG. 5 is applied as it is. The As for the setting related to the recommended product, as shown in FIG. 7 described above, the number of products of the consumer M belonging to the consumer group “small” is four. As for the discount rate of the consumer M belonging to the consumer group “small”, as shown in FIG. 8, the first time is 10%, the second time is 5%, and the third time is no discount. From the above, the recommended information plan as shown in FIG. In accordance with this recommended information plan, the control unit 201 of the server 200 recommends specific products A, B, C, and D to the mobile terminal 400 of the corresponding consumer M every time when all three recommended times arrive. Is output.

  FIG. 9B is an example of a recommended information plan for the consumer M who belongs to the consumer group “large”. As shown in FIG. 5 above, the recommended time of the consumer M belonging to the consumer group “Large” is that the recommended start time is one week after the release date, one recommended period is one week, the recommended number of times is five times, Since the interval is 5 days and the price of the merchandise A is within 5,000 yen, the correction condition is 1 magnification as shown in FIG. 6, and the recommended period shown in FIG. 5 is applied as it is. As for the setting related to the recommended product, as shown in FIG. 7 described above, the number of products of the consumer M belonging to the consumer group “large” is one. As for the discount rate of the consumer M belonging to the consumer group “Large”, as shown in FIG. 8 described above, there is no discount for the first to third times, 5% for the fourth time, and 10% for the fifth time. From the above, the recommended information plan as shown in FIG. The control unit 201 of the server 200 outputs the recommended information of the specific product A to the mobile terminal 400 of the corresponding consumer M every time when all five recommended times come according to the recommended information plan.

  FIG. 10 is a flowchart showing the control contents executed by the control unit 201 of the server 200. This flow is started, for example, when a server administrator (product recommender) inputs a processing start command using the keyboard 221 or the mouse 222 in the server 200.

  In step S <b> 5, the control unit 201 accesses the singing action history database 211 stored in the storage unit 210 based on an operation input instructing to specify the consumer ID of the consumer M in the server 200, and becomes a product recommendation target. The consumer ID of the consumer M is specified.

  In step S10, the control unit 201 selects one piece of music data among a plurality of pieces of music data included in the singing action history information of the consumer ID specified in step S5, and starts distribution related to the selected music data. The time difference between the time and the singing action time is calculated.

  In step S15, the control unit 201 reads a correction condition predetermined for each characteristic of the music data from the storage unit 210, and corrects the time difference calculated in step S10 using the correction condition. In the present embodiment, as shown in FIG. 4 described above, based on the characteristics of “Japanese music” and “Western music”, the time difference for “Japanese music” is multiplied by 1 and for “Western music” is multiplied by 0.2.

  In step S20, the control unit 201 determines whether or not the processing in steps S10 and S15 has been completed for all of the plurality of pieces of music data included in the singing action history information of the consumer ID specified in step S5. To do. If the process has not ended, the determination is not satisfied and the process returns to the previous step S10 to select the next music data among the plurality of music data included in the singing behavior history information of the consumer ID, and the selection The time difference related to the music data is calculated, and correction according to the music characteristics is performed. On the other hand, if the process has been completed, the determination is satisfied, and the routine goes to Step S25.

  In step S25, the control unit 201 calculates a standard time difference unique to the consumer M specified in step S5. Specifically, the corrected time difference for all music data included in the singing behavior history information of the corresponding consumer ID calculated by repeating the above steps S10 to S20 is added, and divided by the number of music data. Thus, an average value of a plurality of corrected time differences is calculated. This average value corresponds to the standard time difference.

  In step S30, the control unit 201 determines whether or not the standard time difference calculated in step S25 is a predetermined time width. When it is determined that the standard time difference is less than one week, the process proceeds to step S35, and the control unit 201 determines that the consumer M belongs to the consumer group “small”. Thereafter, the process proceeds to step S50 described later. On the other hand, when it is determined in step S30 that the standard time difference is not less than one week and less than one month, the process proceeds to step S40, and the control unit 201 determines that the consumer M belongs to the consumer group “standard”. Thereafter, the process proceeds to step S50 described later. On the other hand, when it is determined in step S30 that the standard time difference is one month or more, the process proceeds to step S45, and the control unit 201 determines that the consumer M belongs to the consumer group “large”. Thereafter, the process proceeds to step S50 described later.

  In step S50, the control unit 201 uses the recommended time preset for each consumer group shown in FIG. 5 according to the consumer group determined in any of the above steps S35, S40, and S45. The recommended time for the person M is determined. In the present embodiment, as described above, for the consumer M belonging to the consumer group “small”, the recommended time is compared with the date of product introduction compared to the consumer M belonging to the consumer group “standard”. It is determined that the recommendation is started earlier, the total number of recommendations is reduced, the recommendation period and the recommendation interval are shortened, and the entire recommendation is finished earlier. On the other hand, for the consumer M belonging to the consumer group “Large”, the recommendation period is started later than the introduction of the product compared to the consumer M belonging to the consumer group “Standard”. In addition to increasing the number of times, it is determined that the recommended period and the recommended interval of one time are lengthened and the entire recommendation is finished later.

  In step S55, the control unit 201 corrects the recommended time set in step S50 according to the characteristics of the recommended product, and calculates the recommended time for each specific product. In the present embodiment, as shown in FIG. 6 described above, the higher the product price, the larger the correction magnification is set. By multiplying the recommended time set in step S50 by the correction magnification, each specific product Calculate the recommended time.

  In step S60, the control unit 201 sets setting information related to recommended products preset for each consumer group shown in FIG. 7 according to the consumer group determined in any of steps S35, S40, and S45. Based on this, a product recommended for the consumer M is determined. In the present embodiment, as described above, the ratio of new products and trendy products is greater for the consumer M belonging to the consumer group “small” than the consumer M belonging to the consumer group “standard”. Thus, the recommended product is finally determined so that the recommended number of products is increased. On the other hand, for the consumer M belonging to the consumer group “large”, the number of recommended products is such that the ratio of new products and trendy products is smaller than the consumer M belonging to the consumer group “standard”. Decide to be less. Further, based on the recommended time determined in step S50 and step S55, products for which the recommended time has already passed are excluded from the recommended products.

  In step S65, the control unit 201 sets the setting information relating to the discount rate set in advance for each consumer group shown in FIG. 8 according to the consumer group determined in any of steps S35, S40, and S45. Based on this, the discount rate of the product price recommended for the consumer M is determined. In the present embodiment, as described above, the price discount is performed earlier for the consumer M belonging to the consumer group “small” than the consumer M belonging to the consumer group “standard”. To determine the discount rate. On the other hand, for the consumer M belonging to the consumer group “large”, the discount rate is determined so that the price is discounted later after the introduction of the product than the consumer M belonging to the consumer group “standard”. .

  In step S70, the control unit 201 creates a recommended information plan for the corresponding consumer M based on the determinations made in steps S50 to S65. As shown in FIG. 9, the recommended information plan includes information such as a recommended time, a recommended product, a discount rate, and the like.

  In step S75, the control unit 201 acquires recommended information (including information such as a discount rate) of the specific product from the product database 212 every time the recommended time comes according to the recommended information plan created in step S70. The recommended information is output to the mobile terminal 400 of the corresponding consumer M. Thereby, the received recommendation information is displayed on the display unit 401 of the mobile terminal 400 of the consumer M. Thus, this flow is finished.

  In the above, step S5 corresponds to the first procedure for specifying the consumer described in the claims, and steps S10 and S20 are the second procedure for calculating the time difference between the market entry time and the consumption action time. In addition, the time difference calculating means for calculating the time difference between the market entry time and the consumption action time is configured. Steps S30, S50, and S55 correspond to a third procedure for determining the recommended time, A recommended time determining means for determining at least one recommended time for a specific product recommended for a consumer is configured, and step S75 corresponds to the fourth procedure for outputting recommended information, and recommended information for a specific product is recommended. The recommended information output means is obtained from the database and output to the consumer information terminal of a specific consumer.

  Steps S15, S20, and S25 correspond to a fifth procedure for calculating standard time difference information unique to a specific consumer, and step S30 determines whether or not the standard time difference information has a predetermined time width. Step S35, Step S40, and Step S45 are the seventh steps for determining which of a plurality of consumer groups a specific consumer belongs to every predetermined time width. Corresponds to the procedure. Furthermore, step S55 corresponds to a product-specific calculation procedure for calculating product-specific time difference information.

  Step S30 corresponds to a time difference determination procedure for determining whether or not the time difference or standard time difference relating to a specific consumer is equal to or greater than a predetermined time, in addition to the sixth procedure. In this case, a time segment of one week or more and less than one month, which is a standard time difference classified into the consumer group “standard”, corresponds to the predetermined time.

  In the embodiment described above, singing action history information related to singing in the karaoke room KR by a plurality of consumers M is accumulated in the singing action history database 211 of the storage unit 210 of the server 200. The singing action history information includes a distribution start time when the music data is first distributed to the market and a singing action time when the consumer M first reproduces the music data in the karaoke room KR. Then, when the server administrator operates and inputs a processing start command using the keyboard 221 or the mouse 222 in the server 200, the control unit 201 of the server 200 accesses the singing action history database 211 and selects the consumer M by the consumer ID. Identify. Thereafter, after the distribution start time of the music data, the time difference until the specific consumer M reproduces the music data and sings is calculated for each of the plurality of music data based on the distribution start time and the singing action time. Then, based on the time difference calculated for each piece of music data, a recommended time for each product recommended for the consumer M is determined. And whenever the recommendation time of each goods comes, the recommendation information of the goods is outputted to the portable terminal 400 of the specific consumer M.

  As a result, people who tend to sing in a relatively short period of time after a certain piece of music data is distributed to the market are regarded as people who are jumping to the so-called fashion and new products, and the products are released earlier than the product launch date. For those who tend to sing after a relatively long period of time since the music data was distributed to the market, they are considered to be the type of person who carefully examines the state of the new product, and the product is delayed Can make recommendations. As a result, effective product recommendations can be made according to the individuality and consumption trends of each consumer M.

  In this embodiment, in particular, the time difference calculated for each piece of music data for a specific consumer M is corrected and corrected using correction conditions determined for each product characteristic of the music data. In other words, in general, the time difference until the specific consumer M sings after the distribution start time of the music data is not limited to the individual personality of the consumer, but the product characteristic (whether the music is Japanese music or Western music in the above embodiment). It depends on the type. Therefore, in the present embodiment, the above-described variation due to the product characteristics is eliminated, and effective product recommendation mainly reflecting a specific consumer-specific personality and consumption trend is performed. Can do.

  Further, in the present embodiment, in particular, a plurality of consumer groups divided for each time width of a predetermined standard time difference are prepared, and a recommended time is preset for each consumer group. Then, it determines which of the plurality of consumer groups the calculated standard time difference belongs to, and recommends a specific product to the specific consumer M based on the recommended time information corresponding to the determined consumer group Decide when. Thus, if the recommended time is set uniformly for each consumer group in advance, the recommended time is determined only by determining which consumer group the consumer M belongs to according to the standard time difference. The recommended time can be easily determined for the consumer M. In addition, since the number of recommended times managed on the product recommender side can be significantly reduced as compared with the case where a consumer group is not prepared, the processing speed in the server 200 can be improved and the capacity of the storage unit 210 can be reduced.

  In the present embodiment, the recommended time determined based on the standard time difference is particularly corrected using the correction condition corresponding to the product characteristics (the magnification for each price range in the above embodiment). That is, when the recommended time is determined based on the standard time difference calculated for grasping the consumer-specific personality and consumption trends, the recommended time is set uniformly for each consumer M. Therefore, it is impossible to determine the recommended time corresponding to the product characteristics of each product. Therefore, the correction time corresponding to the product characteristics of each product can be determined by correcting as described above.

  In addition, in this embodiment, especially for people who tend to sing in a relatively short time after a certain piece of music data is distributed to the market (so-called fashion or people who jump to new products immediately) Discount prices early. Thereby, the consumer's willingness to consume can be further increased. On the other hand, for those who tend to sing after a relatively long period of time since the music data was distributed to the market (people who carefully determine the state of the new product) Do not give a discount, give a discount later. Thereby, the discount price according to the individuality and consumption trend of the consumer M can be performed, and the willingness to consume can be increased. In this way, effective product recommendations can be made according to the individuality and consumption trends of each consumer M.

  In addition, in this embodiment, especially for people who tend to sing in a relatively short time after a certain piece of music data is distributed to the market (so-called fashion or people who jump to new products immediately) By starting the recommendation early, reducing the total number of recommendations, and ending the recommendation early, it is possible to recommend an effective product in accordance with the individuality and consumption trend of the consumer M concerned. On the other hand, for those who tend to sing after a relatively long period of time since the music data was distributed to the market (persons who carefully determine the state of the new product), recommend it later By starting and increasing the total number of recommendations and ending the recommendation late, it is possible to recommend effective products that match the consumer's personality and consumption trends.

  In the present embodiment, in particular, the individuality of the consumer M as a consumer is determined from the trend of singing behavior in karaoke, the consumption behavior of the article product is estimated according to the individuality, and the article product at a timing according to this. Advertise That is, it is possible to perform comprehensive advertising activities in a form that combines seemingly different consumption modes of singing and purchasing. Further, as a result, even if the purchase history data of the merchandise item for each consumer M is not accumulated, as long as the singing history data of the music data for each consumer M is accumulated, this can be used for the merchandise item. There is also an effect that effective advertising in sales can be executed.

  The present invention is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and technical idea of the present invention. Hereinafter, such modifications will be described in order.

(1) When the recommended time is determined based on the consumption behavior history In the above embodiment, the individuality of the consumer M is determined from the trend of the singing behavior of the consumer M in karaoke, and the consumption behavior of the product is estimated according to the individuality. However, the example of recommending a specific product to the consumer M at the timing according to this has been described. However, the present invention is not limited to this. Actual consumer behavior (purchasing goods, staying at a hotel, amusement park, etc.) (Including receiving services such as playing on the Internet), identifying consumer personality, estimating the consumer behavior of the product according to that personality, and recommending specific products to the consumer at the appropriate timing May be performed.

  FIG. 11 is a block diagram illustrating functional configurations of the server 200 and the mobile terminal 400 according to this modification, and corresponds to FIG. 2 described above. The same parts as those in FIG.

  The storage unit 210 of the server 200 of the present modified example stores a consumption behavior history database 214 (consumer database) in which consumption behavior history information and consumer IDs related to a plurality of products by a plurality of consumers M are stored in association with each other. have. The consumption behavior history information includes, for each consumer M, for each purchased product, the sales start time (market launch time) when the product was first sold, and the date when the consumer M purchased the product. The consumption action period is included (see FIG. 12 described later). Information on the consumption behavior period of each consumer M is supplied from, for example, a credit company. The system configuration other than the above is the same as that of the above-described embodiment.

  FIG. 12 is a diagram illustrating an example of the contents stored in the consumption behavior history database 214.

  As shown in FIG. 12, in the consumer behavior history database 214, for each consumer M, the consumer ID and consumer behavior history information relating to a plurality of products purchased by the consumer M are associated with each other. Is remembered. The consumption behavior history information includes, for each product, a product name, a product type, a sales start time when the product is first sold, and a consumer behavior time when the consumer M first purchases the product. It is.

  The control unit 201 of the server 200 calculates a time difference between the sales start time and the consumption behavior time for each product for a specific consumer M. In the example shown in FIG. 12, the consumer M whose consumer ID is “ID3” has a time difference of 1 day, 4 days, and 56 days for each product “book1, 2” and “car1”. For the consumer M whose ID is “ID4”, the time difference for each product “book 3 to 5” is 32 days, 46 days, and 57 days, respectively. That is, the former has a relatively short time difference between the sales start time and the consumption behavior time, and the latter has a relatively long time difference between the sales start time and the consumption behavior time.

  FIG. 13 is a diagram illustrating an example of correction conditions predetermined for each characteristic of a product for correcting the time difference calculated for each product when calculating a standard time difference unique to the consumer M. is there.

  FIG. 13A is a graph showing general product characteristics of two types of products “book” and “car”. As shown in FIG. 13 (a), the sales volume of “books” rises relatively early from the start of distribution, while the sales of “cars” increase from the sales start time until the sales increase. Has a relatively long product characteristic. This is because consumers generally tend to spend more time considering whether or not to purchase a product as the price of the product is higher. In the present embodiment, as shown in FIG. 13A, the time required for the “car” characteristic curve M4 to reach the maximum value is approximately the time required for the “book” characteristic curve M3 to reach the maximum value. Since it is 10 times, as shown in FIG. 13B, the correction condition for the time difference is set to 1 time for the “book” and 0.1 times for the “car”. Thereby, the dispersion | variation in the time difference by the said characteristic based on the classification of goods can be eliminated. Information regarding the correction condition (first correction condition) is stored in advance in an appropriate area of the storage unit 210.

  Based on the correction conditions, the standard time difference inherent to the consumer M is specifically obtained as follows. For example, for the consumer M whose consumer ID is “ID3” shown in FIG. 12 above, “book1” and “book2” are “books”, and after correction by multiplying by the above correction condition of 1 × The time differences are 1 day and 4 days, and “car1” is “car”, so the time difference is 5.6 days by multiplying by 0.1 times the correction condition. Therefore, the standard time difference is the average of these, (1 + 4 + 5.6) /3≈3.5 days. Further, for example, for the consumer M whose consumer ID is “ID4” shown in FIG. 12, since “books 3 to 5” are all “books”, they are multiplied by 1 times as the correction condition and corrected. The time differences are 32 days, 46 days, and 57 days, respectively. Therefore, the standard time difference is the average of these, (32 + 46 + 57) / 3 = 45 days.

  In the above example, only two product types, “book” and “car”, have been described for the sake of simplicity, but other than these, correction conditions according to product characteristics are set for various products. The standard time difference is calculated using these correction conditions.

  The subsequent procedure is the same as that of the above-described embodiment. That is, the control unit 201 determines which of the three consumer groups (see FIG. 5) the standard time difference belongs to, and recommends the recommended time based on the information regarding the recommended time set for each consumer group. To decide. In this example, since the consumer M whose consumer ID is “ID3” belongs to the consumer group “small”, the recommended time is earlier than the consumer M of the consumer group “standard” after product introduction. The recommendation is started, the total number of recommendations is reduced, the recommendation period and the recommendation interval are shortened, and the entire recommendation is finished early. On the other hand, since the consumer M with the consumer ID “ID4” belongs to the consumer group “Large”, the recommended time is recommended later than the consumer M of the consumer group “standard”. Is started, the total number of recommendations is increased, one recommendation period and a recommendation interval are lengthened, and the whole recommendation is finished later.

  Then, the determined recommended time is corrected corresponding to the product characteristics of the product recommended for the consumer M (see FIG. 6), the recommended time for each product is calculated, and the standard for each consumer M is calculated. A recommended product / discount rate is determined according to the time difference (see FIGS. 7 and 8), and a recommended information plan is created. In accordance with this recommended information plan, recommended information of a specific product is output to the mobile terminal 400 of the corresponding consumer M every time the determined recommended time comes.

  Also in the modified examples described above, the same effects as in the above embodiment can be obtained.

(2) Others In the above, the standard time difference specific to each consumer M is calculated using the correction conditions defined for each product characteristic with respect to the time difference calculated for each product (including music data; the same applies hereinafter). However, it is not always necessary to calculate this standard time difference. Instead of this, for example, the time difference calculated for each product of the consumer M may be compared with a predetermined threshold value, and the recommended time may be determined according to the comparison result.

  In the above description, the recommended time determined for each consumer M is corrected using the correction condition, and the recommended time (product time difference information) for each product is calculated. However, the present invention is not limited to this. For example, the standard time difference calculated for each consumer M may be corrected using the correction condition to calculate the standard time difference for each product, and the recommended time may be determined based on the standard time difference for each product.

  In addition, in the above, the arrow shown in each figure of FIG.1, FIG.2, FIG.11 shows an example of the flow of a signal, and does not limit the flow direction of a signal. In addition, the flowchart shown in FIG. 10 does not limit the present invention to the procedure shown in the above flow, and even if the procedure is added / deleted or the order is changed without departing from the spirit and technical idea of the invention. Good.

  In addition to those already described above, the methods according to the above-described embodiments and modifications may be used in appropriate combination.

  In addition, although not illustrated one by one, the present invention is implemented with various modifications within a range not departing from the gist thereof.

1 Product recommendation system 200 server (first information terminal)
210 Storage section (storage means)
211 Singing behavior history database (consumer database)
212 Product database (recommended database)
214 Consumer Behavior History Database (Consumer Database)
400 Mobile terminal (second information terminal, consumer information terminal)
M consumers

Claims (6)

In product recommendation methods that recommend specific products to consumers,
A first procedure for accessing the consumer database storing a plurality of pieces of consumer identification information based on an operation input in the first information terminal on the product recommender side, and identifying the consumer;
Based on the consumption behavior history information accumulated in the consumer database, including the market entry time when the product was first put on the market and the consumption behavior time when the specific consumer consumed the product, for each product, A second procedure for calculating a time difference between the market launch time and the consumption behavior time;
The time difference calculated for each product in the second procedure is corrected and aggregated using a first correction condition predetermined for each product characteristic stored in the consumer database, and the specific consumer A fifth procedure for calculating standard time difference information specific to
A third procedure for determining at least one recommended time of the specific product recommended for the specific consumer based on the standard time difference information calculated in the fifth procedure ;
And a fourth procedure for obtaining recommended information of the specific product from a recommendation database and outputting the recommended information to the second information terminal of the specific consumer at the recommended time determined in the third procedure. Product recommendation method characterized by A sixth procedure for determining whether or not the standard time difference information calculated by the fifth procedure has a predetermined time width;
When it is determined by the sixth procedure that the time period is a predetermined time width, it is determined whether the specific consumer belongs to a plurality of consumer groups divided for each predetermined time width. Further comprises a procedure,
The third procedure includes
Based on representative time difference information predetermined for the consumer group determined to belong to the specific consumer in the seventh procedure, a recommended time of the specific product recommended for the specific consumer is determined. The product recommendation method according to claim 1 , wherein the product recommendation method is determined. The third procedure includes
The standard time difference information calculated for the specific consumer in the fifth procedure or the representative time difference information associated with the specific consumer in the seventh procedure is stored in the consumer database. Correction using a second correction condition determined in advance corresponding to the product characteristics of the specific product, and calculating a product-specific time difference information,
The procedure according to claim 1 or 2, wherein the recommended timing of the specific product recommended for the specific consumer is determined based on the time difference information for each product calculated in the calculation procedure for each product. Item 2 recommended method. The third procedure includes
Determine the recommended time for multiple times to make a recommendation while gradually changing the pricing of the specific product,
The fourth procedure includes
The price setting value of the specific product is changed and output to the second information terminal of the specific consumer at each of the plurality of recommended times determined in the third procedure. The product recommendation method according to any one of claims 1 to 3 . The third procedure includes
A time difference determination procedure for determining whether the time difference or the standard time difference relating to the specific consumer calculated in the second procedure or the fifth procedure is equal to or greater than a predetermined time;
When the time difference or the standard time difference is determined to be greater than or equal to a predetermined time in the time difference determination procedure, the recommended number of times including the first time while delaying the initial recommended start time and the recommended end time among the plurality of recommended times On the other hand,
When the time difference is determined to be less than the predetermined time in the time difference determination procedure, the recommended start time and the recommended end time for the first time out of the plurality of recommended times are advanced and the recommended number including the first time is reduced. The product recommendation method according to claim 4 . A product recommendation system that recommends specific products to consumers,
A consumer database that stores consumption behavior history information related to a plurality of products by each of the plurality of consumers and consumer identification information of each consumer in association with each other;
Each of a plurality of products based on the market launch time when the product was first introduced to the market and the consumer behavior time of the specific consumer included in the consumer behavior history information accumulated in the consumer database In addition, a time difference calculating means for calculating a time difference between the market launch time and the consumption behavior time;
The time difference calculated for each product by the time difference calculation means is corrected and aggregated using a first correction condition predetermined for each product characteristic stored in the consumer database, and the specific consumer Standard time difference information calculating means for calculating standard time difference information specific to
Based on the standard time difference information calculated by the standard time difference information calculating means, a recommended time determining means for determining at least one recommended time of the specific product recommended for the specific consumer;
In the recommended time determined by the recommended time determining means, it has recommended information output means for obtaining recommended information of the specific product from a recommendation database and outputting it to the consumer information terminal of the specific consumer. Featured product recommendation system.

Images