JP7675161B2 - Information processing device, method and program - Google Patents

Description

This invention relates to an information processing device, method, and program that uses events related to a product or service to perform future predictions, including future sales of the product or service.

Conventionally, when selling a particular product, a technique is known in which the past sales history data of the product is statistically analyzed to predict the future sales of the product (see, for example, Patent Document 1).

In addition, technology is known for measuring the effectiveness of events such as various exhibitions and competitions when the events are held (see, for example, Patent Document 2).

JP 2002-358402 A JP 2003-167976 A

However, the past sales history data of a product used in the technology described in Patent Document 1 reflects the economic environment at the time the product was sold in the past. For this reason, conventional analyses are not only unable to evaluate the merits and demerits of a product's value and future potential, but also unable to provide a rational and objective evaluation of future responses, such as how the product can be improved to improve its appeal, which products should be discontinued and which should be retained (improved), and whether a newly developed product has value (competitiveness).

There were no known methods of forecasting sales other than the method described in Patent Document 1, which relies solely on statistical analysis of data reflecting past economic conditions.

In addition, the technology described in Patent Document 2 can measure the effectiveness of various recently held events such as exhibitions and competitions, but no method was known for predicting sales based on the measured effectiveness of the events.

This invention was made in light of the above circumstances, and its purpose is to provide an information processing device, method, and program that uses events related to a product or service to perform future predictions, including future sales of the product or service.

In order to solve the above problem, the first aspect of the present invention is an information processing device that includes an event planning unit that sets information necessary for implementing an event for a product or service, an event announcement unit that notifies consumers of the event and acquires event participation acceptance information including information of consumers who wish to participate in the event, an incentive distribution unit that distributes incentives for the event to consumers who wish to participate in the event, an event implementation unit that acquires incentive use information including information of consumers who have used the incentive in conjunction with the implementation of the event, a VfM primary evaluation unit that generates a primary evaluation including an objective evaluation of the product or service based on reaction behavior information including the acquired event participation acceptance information and incentive use information, a market value evaluation unit that conducts research on the product or service to consumers based on the generated primary evaluation, generates a market value evaluation of the product or service based on the results of the research including the consumer's subjective evaluation, and performs a future prediction including future sales of the product or service based on the generated market value evaluation, and a VfM evaluation report unit that outputs information related to the results of the future prediction.

In a second aspect of the invention, the event planning department sets a VfM index, which is an index for any measurement item that should be focused on regarding the product or service, and the primary evaluation includes a VfM index evaluation based on the VfM index and actual values for the set arbitrary measurement item that should be focused on.

In a third aspect of the present invention, the VfM primary evaluation unit includes a hypothesis generation unit that generates hypotheses related to a market value evaluation of the product or service based at least on the VfM index evaluation, and the market value evaluation unit conducts research related to the product or service based on the generated hypotheses.

In a fourth aspect of the invention, the market value assessment unit is provided with a hypothesis correction unit that determines whether the generated hypothesis was valid based on the results of the research, and corrects the generated hypothesis if it is determined that the generated hypothesis was not valid, and the market value assessment unit conducts second or subsequent research on the product or service to consumers based on the corrected hypothesis after the correction, and generates a market value assessment of the product or service based on the results of the second or subsequent research.

In a fifth aspect of the present invention, the market value assessment unit performs at least one of an extended estimation using a simple estimation method and an extended estimation using a complex estimation method based on attribute information of each consumer who responded to the research and the research responses from the consumer, thereby performing a future forecast including the future sales.

In a sixth aspect of the present invention, the VfM index includes at least one of an index for a measurement item related to consumers who have used the incentive multiple times, an index for a measurement item related to consumers who have not used the incentive, and an index for a measurement item related to consumers who have selected a specific incentive.

According to a first aspect of the invention, in conjunction with the implementation of an event for a product or service, incentive usage information is acquired, including information on consumers who have used the incentives of the event, and a primary evaluation, including an objective evaluation of the product or service, is generated based on reaction behavior information including the incentive usage information. After that, research is conducted on consumers based on the generated primary evaluation, and a market value evaluation of the product or service is generated based on the results of the research, including a subjective evaluation from the consumer's side. A future forecast, including future sales of the product or service, is performed based on the generated market value evaluation.

Such event- and research-based market valuation and future forecasting processes can be based on data that reflects the current economic environment, rather than the economic environment of the past. This makes it possible to make such future forecasts more reliable across a wide range of forecasting fields, as compared to methods that rely solely on statistical analysis of past data.

In addition, the above future predictions can utilize consumer research as described above to reflect, for example, the subjective opinions of consumers on the buying side. By conducting the research based on the primary evaluation as described above, it is possible, for example, to reconfirm the information obtained in the primary evaluation or to perform an evaluation from a different perspective than the information obtained in the primary evaluation. This makes it possible to make such future predictions more purposeful and accurate.

Based on the results of such future predictions, it is possible to determine, for example, which products should continue to be sold and which services should continue to be provided, which products should be discontinued and which services should be discontinued, or which products and services should be improved. Furthermore, the above future predictions not only predict future sales but also reveal the value of the products, making it possible to determine production plans for how many products should be produced and plans for the scale of service provision.

According to a second aspect of the present invention, a VfM index is set, which is an index for any measurement item to be focused on with respect to the product or service. The primary evaluation includes a VfM index evaluation based on the VfM index and actual values for the set arbitrary measurement item to be focused on.

In this way, it is possible to generate the primary evaluation based on a numerically assessable index called the VfM index. Since the research is carried out based on the primary evaluation generated in this way, it is possible to make the market value evaluation and future prediction more accurate. In addition, since the VfM index can be set for any measurement item, it is possible to perform a market value evaluation and future prediction focusing on the required items.

In addition, as the event is carried out, information on the results of consumer reactions or actions can be accumulated in sequence, and the actual values for the measurement items related to the VfM index can be calculated in a chronological order from the accumulated information. The information may be accumulated continuously while the event is carried out multiple times, for example. By using the actual values calculated in a chronological order in this way, it is also possible to evaluate and analyze the trends and trends of the market value evaluation in a chronological order. By evaluating and analyzing the trends and trends of the market value evaluation in this way, it is possible to make highly accurate future predictions regarding the management of marketing activities related to the product or service, future predictions of sales related to the product or service, and future predictions regarding the development and direction of improvement and abolition of the product or service. Furthermore, since the actual values for the measurement items related to the VfM index are calculated for the VfM index, which is an index for any measurement item that should be noted for the product or service, it is also possible to apply the same VfM index to consumer reactions or actions to the product, etc., and cross-sectionally evaluate products, etc. of other companies, other industries, and other business types.

According to a third aspect of the present invention, a hypothesis is generated based at least on the VfM index evaluation. Research related to the product or service is conducted based on the generated hypothesis.

The hypotheses generated in this way are based on a numerically assessable index known as the VfM index. For example, in research conducted based on this hypothesis as described above, it is possible for the research items included in the research to be generated based on this hypothesis, and for the consumers targeted by the research to be selected based on this hypothesis. By carrying out the market value assessment generation process and future prediction process based on this research, it is possible to make future predictions more accurate.

According to a fourth aspect of the present invention, a determination is made as to whether the generated hypothesis was valid or not based on the results of the research, and if it is determined that the generated hypothesis was not valid, the generated hypothesis is corrected. After that, a second or subsequent research on the product or service is conducted on consumers based on the corrected hypothesis, and a market value assessment of the product or service is generated based on the results of the second or subsequent research.

In this way, it is possible to recursively correct the hypothesis until it becomes valid, and therefore the future prediction results derived from the corrected hypothesis after the correction can be made more reliable.

According to a fifth aspect of the present invention, in the future prediction process for the above-mentioned goods or services, the above-mentioned future prediction is performed by performing at least one of an extended estimation using a simple estimation method and an extended estimation using a complex estimation method (e.g., a Bayesian network method) based on the attribute information of each consumer who responded to the above-mentioned research and the research responses from the consumer. For example, in the extended estimation using the simple estimation method, a deductive extended estimation is performed, and in the extended estimation using the complex estimation method, a deductive or recursive extended estimation is performed.

By carrying out such an expanded estimation, it is possible to predict how much the limited number of consumers who are the subjects of the research, as well as the potential buyers of the product or service, will contribute to sales. Even if the distribution of attribute information of the consumers who are the subjects of the research is biased compared to the distribution of attribute information of all consumers who are potential buyers of the product or service, it is possible to make the future prediction based on the expanded estimation more accurate by, for example, appropriately weighting each attribute information to correct the distribution bias. Furthermore, by logging actual results, storing them as indexes (information), and analyzing them rather than simply making "sales forecasts," it is possible to make more accurate future predictions regarding the management of marketing activities, sales related to products or services, and the direction of development and improvement/elimination.

According to a sixth aspect of the present invention, the VfM index includes at least one of an index for a measurement item related to consumers who have used the incentive multiple times, an index for a measurement item related to consumers who have not used the incentive, and an index for a measurement item related to consumers who have selected a specific incentive.

Here, consumers who have used the incentive multiple times include, for example, consumers who rate the value of the above-mentioned product or service as high. Therefore, by setting a VfM index for the measurement items related to consumers who have used the above-mentioned incentive multiple times, it is possible to evaluate the positive aspects of the value of the above-mentioned product or service.

Furthermore, consumers who do not use incentives include, for example, consumers who wished to participate in the event but did not use the incentive, and consumers who received an incentive but did not use it. Therefore, by setting a VfM index for the measurement items related to consumers who do not use the incentive, it is possible to verify, for example, whether there is room to improve the evaluation of the product or service, or to verify what method should be used to improve the evaluation of the product or service.

Furthermore, for example, when consumers select an incentive to use from multiple types of incentives (discounts, exchanges, points, etc.), it may be desirable to obtain statistics on consumers who have selected a specific incentive. For example, the type of assessment of the value of the product or service by the consumer can be determined for each incentive selected by the consumer. Therefore, by setting a VfM index for the measurement items related to consumers who have selected the specific incentive, it is possible to assess the value of the product or service with a higher quality. In other words, by preparing multiple incentives that consumers desire and setting and analyzing a base value for measuring market value for each incentive, the accuracy of the future prediction can be improved.

By using the VfM index as described above, for example, in the primary valuation generation process, the hypothesis generation process, or the research implementation process, it is possible to make the market value assessment based on the research more accurate. Therefore, the future forecast based on the market value assessment can also be made more accurate.

According to each aspect of the present invention, it is possible to provide an information processing device, method, and program that utilizes events related to a product or service to perform future predictions, including future sales of the product or service.

1 is a schematic configuration diagram of a future prediction system according to a first embodiment of the present invention. FIG. 2 is a block diagram showing the functional configuration of a VfM marketing system in the future prediction system shown in FIG. 1 . 3 is a flow diagram showing an example of a primary evaluation generation process executed by the control unit shown in FIG. 2; 3 is a flow diagram showing an example of a future prediction process executed by the control unit shown in FIG. 2 . FIG. 4 is a diagram showing an example of a setting status based on calculation/non-calculation setting information and VfM index setting information according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a setting state based on calculation/non-calculation setting information according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of notification response log information according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of coupon issuance log information according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of coupon usage log information according to the first embodiment of the present invention. FIG. 13 is a diagram showing an example of a VfM index evaluation based on VfM indexes and actual values for any measurement item of interest, generated as part of a primary evaluation, according to the first embodiment of the present invention. FIG. 13 is a diagram showing an example of a VfM index evaluation based on VfM indexes and actual values for any measurement item of interest, generated as part of a primary evaluation, according to the first embodiment of the present invention. FIG. 13 is a diagram showing an example of a VfM index evaluation based on VfM indexes and actual values for any measurement item of interest, generated as part of a primary evaluation, according to the first embodiment of the present invention. FIG. 13 is a diagram showing an example of a VfM index evaluation based on VfM indexes and actual values for any measurement item of interest, generated as part of a primary evaluation, according to the first embodiment of the present invention. FIG. 2 shows an example pie chart illustrating coupon usage by consumer gender and age, generated as part of a primary evaluation, according to a first embodiment of the present invention. A figure showing an example of a line graph generated as part of a primary evaluation relating to the first embodiment of the present invention, which summarizes the reaction status of female consumers at each stage of their reactions or actions toward a product, etc., by age. FIG. 2 is a diagram showing an example of a pie chart showing coupon usage by consumer occupation type, generated as part of a primary evaluation, according to a first embodiment of the present invention. FIG. 4 is a diagram showing an example of a hypothesis generation table showing a correspondence relationship between detection conditions based on VfM index evaluation and generated hypotheses according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a hypothesis generation table showing a correspondence relationship between detection conditions based on VfM index evaluation and generated hypotheses according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire item according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire item according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire item according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire item according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire item according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire item according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire item according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire compilation result according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire compilation result according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire compilation result according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire compilation result according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a display screen of a questionnaire compilation result according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a result of sales forecast according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a result of sales forecast according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example of a result of sales forecast according to the first embodiment of the present invention.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
[First embodiment]
(composition)
FIG. 1 is a schematic diagram of a future prediction system according to a first embodiment of the present invention.

The future prediction system of this embodiment includes, for example, a Value for Money (VfM) marketing system 1, an operator terminal 2 which is a personal computer (PC) terminal including, for example, a smartphone or tablet type, and is operated by an operator, a consumer information database 3, an event notification system 4, an event participation acceptance system 5, an incentive management system 6, and a research system 7, which are connected via a network (NW), for example, the Internet.

The VfM marketing system 1 can generate a market value assessment as a value relative to the price for any product or service (hereinafter referred to as "product, etc."), such as a product that will soon be released for sale or a service that will soon be launched for sale, or a product or service that has already been released for sale or launched for sale, and perform future predictions, including future sales.

In more detail, the VfM marketing system 1 uses an event announcement system 4, an event participation acceptance system 5, an incentive management system 6, and a research system 7 in response to an operation signal transmitted from the operator terminal 2 to implement events such as campaigns, advertisements, or promotions for the above-mentioned products, etc., and further to conduct research on the products, etc. among consumers, and based on the results of such research, generates a market value assessment as a value relative to the price of the above-mentioned products, etc. Based on the generated market value assessment, the VfM marketing system 1 can execute future predictions including future sales for the above-mentioned products, etc.

In the following, an example will be described in which the VfM marketing system 1 implements the above-mentioned event on a product-by-product basis, as described above, and executes the above-mentioned market value assessment generation process and future prediction process on a product-by-product basis, but the market value assessment generation process and future prediction process of the product, etc. according to the present disclosure are not limited to this. For example, the event such as a campaign, advertisement, or promotion of the product, etc. may be, for example, an event such as a campaign, advertisement, or promotion related to a store or brand, etc. In this case, the VfM marketing system 1 implements an event such as a campaign, advertisement, or promotion related to a store or brand, etc., and further conducts research on consumers related to the store or brand, etc., thereby enabling the above-mentioned market value assessment generation process and future prediction process to be executed on a store or brand, etc. basis.

The consumer information database 3 stores consumer identification information, such as a consumer number, which is used by consumers to react or act on the products etc. that are the subject of the event, in association with attribute information of the consumer. The consumer identification information may be, for example, an ID for a membership service that can identify an individual and covers the majority of the population. The attribute information may also include, for example, information on consumer attributes such as the consumer's gender, age group, and residential area, as well as other personal information specific to the consumer.

The event announcement system 4, the event participation acceptance system 5, and the incentive management system 6 are each systems used to implement the above-mentioned events.

The event announcement system 4 announces the event to consumers using various media such as e-mail magazines, smartphone (mobile phone) and tablet applications, television commercial messages (TVCM), and social networking services (SNS) such as LINE (registered trademark), and collects reaction information. The event participation acceptance system 5 accepts requests to participate in the event using a website such as a special site for the event. The incentive management system 6 distributes incentives for the event to consumers who wish to participate in the event using the website, and collects incentive usage information related to the incentives as the event is held. The incentives may be, for example, coupons such as free exchange tickets or discount tickets for products, bonus points acquired by consumers when purchasing the products, or coupons such as free exchange tickets or discount tickets for other products acquired by consumers when purchasing the products.

The research system 7 conducts research on the above-mentioned products, etc., among consumers, and collects research responses from the consumers. The research is, for example, a questionnaire on the above-mentioned products, etc.

In this embodiment, a VfM marketing system 1 will be described as a non-limiting example of an information processing device.
Fig. 2 is a block diagram showing the functional configuration of the VfM marketing system 1 in the future prediction system shown in Fig. 1. Note that the configuration of the VfM marketing system 1 shown in Fig. 2 is merely an example, and each component included in the VfM marketing system 1 may exist as a physically separate device in any combination.

The VfM marketing system 1 includes, as hardware components, a control unit 11, a memory unit 12, and a communication interface unit 13.

The communication interface unit 13 includes, for example, one or more wired or wireless communication interface units. The communication interface unit 13 inputs an operation signal input by the operator terminal 2 to the control unit 11. The communication interface unit 13 also outputs information output from the control unit 11 to the event notification system 4, the event participation acceptance system 5, the incentive management system 6, and the research system 7, and inputs information transmitted from the event notification system 4, the event participation acceptance system 5, the incentive management system 6, and the research system 7 to the control unit 11. Furthermore, the communication interface unit 13 outputs information related to the results of future predictions including future sales of the above-mentioned products, etc., output from the control unit 11 to, for example, the operator terminal 2 or an external output device such as a network printer (not shown).

The storage unit 12 is configured with a storage medium such as a non-volatile memory that can be written to and read from at any time, such as a hard disk drive (HDD) or solid state drive (SSD), and in order to realize this embodiment, it is equipped with a VfM index master 121, a VfM index calculation presence/absence storage unit 122, a reaction behavior log information storage unit 123, a VfM index history information storage unit 124, a primary evaluation storage unit 125, a research response log information storage unit 126, and a market value evaluation storage unit 127. The VfM index used in this embodiment is an index for any measurement item that should be noted for the above-mentioned product, etc. The actual value for the measurement item can be numerically evaluated by comparing it with the VfM index.

The VfM index master 121 stores measurement items related to, for example, consumer reactions or behavior toward the above-mentioned product, etc. The measurement items are stored in advance, for example, by an operator. The measurement items include, for example, a criterion item that indicates the number of consumers who reacted or acted in response to the above-mentioned product, etc., which can be directly tallied from each piece of information that indicates the result of the consumer's reaction or behavior toward the above-mentioned product, etc., and an item calculated by any combination of the criterion items. Such measurement items are not limited to items that measure numerical values generated in conventional campaign research, such as the number of page views of a website or survey totals. In particular, such measurement items may be items that measure numerical values calculated or analyzed from actual performance figures generated in various activities.

The VfM index calculation storage unit 122 stores calculation/non-calculation setting information and VfM index setting information. The calculation/non-calculation setting information is information indicating the setting by the operator as to whether each of the measurement items stored in the VfM index master 121 is to be a measurement item to be calculated for which a performance value is calculated in association with the implementation of the event. The VfM index setting information is information indicating the setting of a VfM index for any measurement item to be focused on with respect to the product, etc., among the measurement items to be calculated. Note that the VfM index for each measurement item set by the VfM index setting information is a target value for the measurement item, for example, a numerical value such as the number of consumers, the number of items, or the sales amount, or a numerical value obtained by expressing these as a percentage with respect to a reference value. Note that the reference value may be set in advance by the operator, or may be automatically set based on the performance value for another measurement item different from the measurement item. Note that the VfM index may be set for some of the measurement items to be calculated, or may be set for all of the measurement items to be calculated.

The reaction behavior log information storage unit 123 stores reaction behavior information, which is information on the result of a consumer's reaction or behavior to the above-mentioned product, etc. The reaction behavior information includes, for example, event announcement information including information on consumers who have been notified of the above-mentioned event, event announcement opening information including information on consumers who have opened or read the event announcement, event announcement viewing information including information on consumers who have opened or read the event announcement and, for example, viewed the event announcement page on a website, event participation acceptance information including information on consumers who wish to participate in the above-mentioned event accepted on the event announcement page, incentive distribution information including information on consumers who have been distributed the above-mentioned incentive among the participating consumers, and incentive use information including information on consumers who have used the distributed incentive in conjunction with the implementation of the above-mentioned event. The consumer information included in the reaction behavior information is, for example, the consumer number or other identification information of the consumer. The consumer information included in each of the event announcement information, event announcement opening information, event announcement viewing information, event participation acceptance information, incentive distribution information, and incentive use information related to the same consumer is linked to each other. Furthermore, the consumer information contained in each of these pieces of reaction behavior information is linked to the consumer's identification information stored in the above-mentioned consumer information database 3. For example, the consumer information contained in the incentive distribution information and the incentive usage information may include a coupon ID of the coupon as the incentive, which is issued so as to uniquely identify the consumer's identification information stored in the consumer information database 3. Furthermore, each piece of reaction behavior information may include, for example, information on the date and time when the consumer's reaction or behavior was performed, and information on the medium used by the consumer.

The VfM index history information storage unit 124 stores the actual values for the measurement items to be calculated.

The primary evaluation memory unit 125 stores primary evaluations including objective evaluations of the above-mentioned products, etc., generated under the control of the VfM primary evaluation unit 115.

The research response log information storage unit 126 stores research response information, which is information on responses to the above research from consumers.

The market value assessment storage unit 127 stores the market value assessments of the above-mentioned products, etc., generated under the control of the market value assessment unit 116.

The control unit 11 includes an event planning unit 111, an event notification unit 112, an incentive distribution unit 113, an event implementation unit 114, a VfM primary evaluation unit 115, a market value evaluation unit 116, and a VfM evaluation report unit 117 to execute the processing functions of this embodiment. The control unit 11 includes a processor such as a CPU (Central Processing Unit) and a program memory, and all of the processing functions of the above-mentioned units are realized by having the processor execute a program stored in the program memory. Note that these processing functions are not limited to those realized using a program stored in the program memory, and may be realized using a program provided over a network.

The event planning unit 111 executes a process of setting information necessary for implementing an event for a product or the like in response to an operation signal transmitted from the operator terminal 2 and received by the control unit 11. For example, the event planning unit 111 sets the purpose, target, outline, and goal of the event to be implemented. For example, the event planning unit 111 accesses the VfM index calculation/non-calculation memory unit 122 and executes a process of writing calculation/non-calculation setting information and VfM index setting information. The process of writing the calculation/non-calculation setting information sets the measurement item to be calculated. The process of writing the VfM index setting information sets a VfM index for any measurement item to be focused on in relation to the product or the like that is the subject of the event, out of the measurement items to be calculated.

The event notification unit 112 executes a process of sending an event notification instruction to the event notification system 4 to notify consumers of the event. In response to the event notification instruction, the event notification system 4 notifies consumers of the event through various advertising media. The event notification unit 112 acquires, from the event notification system 4, event notification information including information on consumers who have notified the event, and event notification opening information including information on consumers who have opened or read the event notification, and executes a process of storing the acquired event notification information and event notification opening information in the reaction behavior log information storage unit 123.

Next, the event announcement unit 112 executes a process of transmitting an event participation acceptance instruction to the event participation acceptance system 5 to accept a request to participate in the event from a consumer in response to the announcement. In response to the event participation acceptance instruction, the event participation acceptance system 5 accepts the request to participate in the event.

Then, the event notification unit 112 executes a process of acquiring event notification viewing information including information of consumers who viewed the event announcement page on a website from the event participation acceptance system 5, and storing the acquired event notification viewing information in the reaction behavior log information storage unit 123. Furthermore, the event notification unit 112 executes a process of acquiring event participation acceptance information including information of consumers who wish to participate in the event that was accepted on the event announcement page from the event participation acceptance system 5, and storing the acquired event participation acceptance information in the reaction behavior log information storage unit 123.

The incentive distribution unit 113 first executes a process of reading out the event participation acceptance information stored in the reaction behavior log information storage unit 123. Then, based on the read event participation acceptance information, the incentive distribution unit 113 executes a process of sending an incentive distribution instruction to the incentive management system 6 to distribute the incentive for the event to the consumers who wish to participate in the event. In response to the incentive distribution instruction, the incentive management system 6 distributes the incentive for the event to the consumers who wish to participate in the event. The incentive distribution unit 113 executes a process of acquiring incentive distribution information including information of the consumers to whom the incentive was distributed from the incentive management system 6, and storing the acquired incentive distribution information in the reaction behavior log information storage unit 123.

The event implementation unit 114 executes a process of sending an incentive collection instruction to the incentive management system 6 to collect the incentive use information related to the distributed incentive in conjunction with the implementation of the event. In response to the incentive collection instruction, the incentive management system 6 collects the incentive use information. Thereafter, the event implementation unit 114 executes a process of acquiring incentive use information including information on the consumers who used the distributed incentive from the incentive management system 6, and storing the acquired incentive use information in the reaction behavior log information storage unit 123.

Here, from the reaction behavior information such as event notification information, event notification opening information, event notification viewing information, event participation acceptance information, incentive distribution information, and incentive use information stored in the reaction behavior log information storage unit 123, actual values are calculated for the measurement items to be calculated that are set by the calculation on/off setting information. Specifically, under the control of a performance value calculation unit (not shown) included in the control unit 11, first, the calculation on/off setting information stored in the VfM index calculation on/off storage unit 122 is referenced. Then, under the control of the performance value calculation unit, reaction behavior information related to the measurement items to be calculated that are set by the referenced calculation on/off setting information is read out from the reaction behavior information stored in the reaction behavior log information storage unit 123, and the actual values for the measurement items to be calculated are sequentially calculated based on the read reaction behavior information. The calculated actual values are sequentially stored in the VfM index history information storage unit 124.

The VfM primary evaluation unit 115 generates a primary evaluation including an objective evaluation of the above-mentioned product, etc., and executes a process of storing the information of the generated primary evaluation in the primary evaluation storage unit 125. The primary evaluation includes, for example, a VfM index evaluation, a routine analysis processing result, a detailed analysis processing result, and a hypothesis.

Specifically, the VfM primary evaluation unit 115 first executes a process of reading out the VfM index for the arbitrary measurement item of interest, which is indicated by the VfM index setting information stored in the VfM index calculation presence/absence storage unit 122, and the actual value for the measurement item stored in the VfM index history information storage unit 124. The VfM primary evaluation unit 115 executes a process of generating a VfM index evaluation based on the read-out VfM index and actual value.

The VfM primary evaluation unit 115 can execute the following process according to the result of the generated VfM index evaluation. That is, the VfM primary evaluation unit 115 reads out the reaction behavior information stored in the reaction behavior log information storage unit 123, and executes a routine analysis process based on the read-out reaction behavior information, which analyzes the results of the aggregation based on preset axes such as the steps of event notification, opening of the event notification, viewing of the event notification, acceptance of event participation, distribution of incentives, and incentive use, advertising medium, time period, and consumer attributes such as age and gender. Furthermore, the VfM primary evaluation unit 115 may execute a detailed analysis process based on the read-out reaction behavior information, which analyzes using axes different from the routine analysis process. In the routine analysis process and the detailed analysis process, for example, based on the consumer's identification information such as a consumer number included in the reaction behavior information, attribute information of the consumer associated with the identification information is obtained from the consumer information database 3 and used.

The hypothesis generation unit 1151 provided in the VfM primary evaluation unit 115 executes a process of generating a hypothesis related to the market value evaluation of the above-mentioned product, etc., based at least on the generated VfM index evaluation. The generated hypothesis may be based on the results of the above-mentioned routine analysis process and the above-mentioned detailed analysis process, for example.

The market value assessment unit 116 executes the process of generating a market value assessment as a value relative to the price of the above-mentioned product, etc., and includes a research implementation management unit 1161, a hypothesis correction unit 1162, and a future prediction unit 1163.

The research implementation management unit 1161 reads out the primary evaluations stored in the primary evaluation storage unit 125, and executes a process of conducting research related to the above-mentioned products, etc. based on the read out primary evaluations. The research is, for example, a questionnaire related to the above-mentioned products, etc.

For example, the research implementation management unit 1161 reads out the hypotheses stored in the primary evaluation storage unit 125, and generates research items for the above-mentioned products, etc., based on the read out hypotheses. The research implementation management unit 1161 then executes a process of sending a research implementation instruction to the research system 7 to have the research system 7 conduct a research on consumers including the generated research items. In response to the research implementation instruction, the research system 7 conducts the above-mentioned research. The research is conducted, for example, on consumers who participated in the above-mentioned event and who were set as research targets in advance. The research implementation management unit 1161 then executes a process of acquiring research response information indicating the responses to the above-mentioned research, including the consumer's subjective evaluation, from the research system 7, and storing the acquired research response information in the research response log information storage unit 126. In addition, the consumers who are targets of the above-mentioned research can be set by expanding the model members from the profile rather than the research members.

The hypothesis correction unit 1162 executes a process of reading out the research response information stored in the research response log information storage unit 126. Next, the hypothesis correction unit 1162 executes a process of determining whether or not the hypothesis was valid based on the read research response information. The determination threshold used in the determination process is, for example, set in advance when the research item is generated. If it is determined that the hypothesis was invalid, the hypothesis correction unit 1162 executes a process of correcting the hypothesis. The research implementation process may be executed again based on the corrected hypothesis after the correction.

The market value assessment unit 116 executes a process of reading out the research response information stored in the research response log information storage unit 126. After that, the market value assessment unit 116 executes a process of generating a market value assessment of the above-mentioned product, etc. based on the research response indicated by the read research response information, and storing the generated market value assessment in the market value assessment storage unit 127.

The future prediction unit 1163 performs a process of performing a future prediction including future sales of the above-mentioned products, etc. based on the generated market value assessment, and storing information related to the results of the future prediction in the market value assessment storage unit 127.

The VfM evaluation report unit 117 reads out information related to the results of the future predictions stored in the market value evaluation memory unit 127, and executes a process of outputting the information related to the results of the future predictions, including the future sales of the products, etc., that have been read out, to, for example, the operator terminal 2 or an external output device (not shown).

(Operation)
Next, the operation of the VfM marketing system 1 configured as above will be described.
Fig. 3A is a flow diagram showing an example of a primary evaluation generation process executed by the event planning unit 111, the event notification unit 112, the incentive distribution unit 113, the event implementation unit 114, and the VfM primary evaluation unit 115 of the control unit 11 shown in Fig. 2. Fig. 3B is a flow diagram showing an example of a future prediction process executed by the market value evaluation unit 116 of the control unit 11 shown in Fig. 2.

These flow charts will be explained in detail below with reference to Figures 4A to 15C, using as an example the case of performing a future forecast including future sales of "Healthy Cafe Sweet," a special health coffee drink targeted at young women that beverage manufacturer A will launch on April 1, 2018.

(1) Primary evaluation generation process First, the primary evaluation generation process shown in the flow of Fig. 3A will be described in detail. Note that the primary evaluation generation process shown in the flow of Fig. 3A is a non-limiting embodiment, and the primary evaluation generation process of the present disclosure is not limited thereto.

In step S11, the control unit 11, under the control of the event planning unit 111, accesses the VfM index calculation/non-calculation storage unit 122 as a setting process of information necessary for implementing an event for a product, etc., and writes the calculation/non-calculation setting information and the VfM index setting information. The calculation/non-calculation setting information writing process sets the measurement items to be calculated. The VfM index setting information writing process sets the VfM index for any measurement items to be focused on regarding the product, etc., that is the target of the event, among the measurement items to be calculated. In addition, in the calculation/non-calculation setting information and VfM index setting information writing process, for example, the calculation/non-calculation and VfM index for the measurement items are stored differently for each project. As the event planning process, under the control of the event planning unit 111, for example, the planning of the event itself, the definition of the consumers to be targeted in the event, and the setting of the consumers to be notified of the event may be executed. In addition, the target consumers may be defined, for example, using the attribute information of the consumers stored in the consumer information database 3.

In the example of the product "Healthy Cafe Sweet," it is set up to take advantage of a campaign event that also serves as a promotion for that product. In addition, as an incentive for the event, it is set up so that all people who enter the campaign will be presented with a coupon that can be used at a designated convenience store for a free copy of the product "Healthy Cafe Sweet." Furthermore, women in their twenties are defined as the target consumers, and all members of a designated membership service stored in the consumer information database 3 are set as consumers to whom the event will be announced.

Figures 4A and 4B show tables showing an example of the setting status based on the calculation/non-calculation setting information and the VfM index setting information used during the campaign for the product "Healthy Cafe Sweet."

In the calculation yes/no columns in the tables of FIG. 4A and FIG. 4B, the setting status according to the calculation yes/no setting information is shown. In the calculation yes/no setting information, the measurement items with a circle in the calculation yes/no column are set as the measurement items to be calculated. Specifically, in "11. Notification", "a. Number" and "b. Notification rate" are set as the measurement items to be calculated. In "12. Open/Read", "13. View", "14. Coupon application", "21. Coupon issuance", and "31. Coupon redemption", "a. Number", "b. Notification rate", "c. Cost per result", and "d. Cost increase rate" are set as the measurement items to be calculated. In addition, "a. Number", "51. Redemption index", and "61. Cost effectiveness index" of "41. Duplicate application" are also set as the measurement items to be calculated. On the other hand, in the target value column in the table of FIG. 4A, the setting status according to the VfM index setting information is shown. The VfM index setting information sets the VfM index shown in the target value column for each of the arbitrary measurement items to be focused on for the product "Healthy Cafe Sweet" among the measurement items to be calculated. Specifically, for "11. Announcement", a target value of 76,250,000 is set as the VfM index for "a. number". For "12. Opened/Read", a target value of 22,593,750 is set as the VfM index for "a. number", and a target value of 29.63% is set as the VfM index for "b. Notification rate". For "13. View", a target value of 19,826,563 is set as the VfM index for "a. number", and a target value of 26.00% is set as the VfM index for "b. Notification rate". In "14. Coupon application", a target value of 87,500 is set as the VfM index for "a. number", and a target value of 0.11% is set as the VfM index for "b. Notification rate". In "21. Coupon issue", a target value of 70,000 is set as the VfM index for "a. number", and a target value of 0.09% is set as the VfM index for "b. Notification rate". In "31. Coupon redemption", a target value of 46,667 is set as the VfM index for "a. number", and a target value of 0.06% is set as the VfM index for "b. Notification rate".

In the table of Figure 4A, "a. Number" for "13. Views" is the total number of times the campaign application page of Company A's website was viewed, and "b. Notification rate" for "14. Coupon application,""21. Coupon issued," and "31. Coupon redemption" is the ratio of consumers who responded or took action corresponding to each item out of the number of consumers who were notified.
In the table of Figure 4B, "51. Redemption index" is calculated from "31. Coupon redemption" / "13. Viewing", and "61. Cost-effectiveness index" is calculated from "31. Coupon redemption" / "Total advertising fee".

In step S12, the control unit 11, under the control of the event notification unit 112, uses the event notification system 4 to notify consumers of an event such as a product. Thereafter, under the control of the event notification unit 112, the control unit 11 acquires, from the event notification system 4, event notification information including information on the consumer who notified the event, and event notification opening information including information on the consumer who opened or read the event notification. The acquired event notification information and event notification opening information are stored in the reaction behavior log information storage unit 123. Note that, for example, when the event notification system 4 uses a conventional advertising medium whose announcement performance is difficult to grasp, the event notification information or event notification opening information may be acquired by inputting the advertising medium used to recognize the event when the consumer wishes to participate in the event on a website.

In step S13, the control unit 11, under the control of the event announcement section 112, acquires from the event participation acceptance system 5 event announcement viewing information including information of consumers who viewed the event announcement page on a website, for example, and event participation acceptance information including information of consumers who wish to participate in the event that was accepted on the event announcement page. The acquired event announcement viewing information and event participation acceptance information are stored in the reaction behavior log information storage section 123. Note that, for example, in the case where the event participation acceptance system 5 uses a conventional announcement page whose viewing history is difficult to grasp, the event announcement viewing information may be acquired by inputting the medium on which the consumer is viewing the event announcement when expressing a desire to participate in the event.

Figure 5 is a diagram showing an example of announcement response log information for a campaign for the product "Healthy Cafe Sweet." In Figure 5, records showing "Advertisement sent" as the "Response type" correspond to event announcement information. Records showing "View" as the "Response type" correspond to event announcement viewing information. Records showing "Application" as the "Response type" correspond to event participation acceptance information.

In step S14, the control unit 11, under the control of the incentive distribution unit 113, reads out the event participation acceptance information stored in the reaction behavior log information storage unit 123, and uses the incentive management system 6 to distribute incentives for the event to consumers who wish to participate in the event based on the read event participation acceptance information. The incentive may be, for example, a coupon such as a free exchange ticket for the product or the like. Thereafter, the control unit 11, under the control of the incentive distribution unit 113, acquires incentive distribution information from the incentive management system 6, which includes information on consumers to whom the incentive has been distributed. The acquired incentive distribution information is stored in the reaction behavior log information storage unit 123.

Figure 6 shows an example of coupon issuance log information for a campaign for the product "Healthy Cafe Sweet." In Figure 6, records with "Coupon issued" as the "Response type" correspond to incentive distribution information.

Next, in step S15, the control unit 11, under the control of the event implementation unit 114, acquires incentive usage information from the incentive management system 6, including information on consumers who have used the incentive in conjunction with the implementation of the event. The acquired incentive usage information is stored in the reaction behavior log information storage unit 123.

Figure 7 shows an example of coupon usage log information for a campaign for the product "Healthy Cafe Sweet." In Figure 7, records with "Coupon Usage" shown as the "Response Type" correspond to incentive usage information.

Actual values are calculated for the measurement items to be calculated that are set by the calculation on/off setting information from reaction behavior information such as the event announcement information and event announcement opening information acquired in step S12, the event announcement viewing information and event participation acceptance information acquired in step S13, the incentive distribution information acquired in step S14, and the incentive use information acquired in step S15, and the calculated actual values are sequentially stored in the VfM index history information storage unit 124.

Next, in steps S16, S17, and S18, the control unit 11 generates a primary evaluation including an objective evaluation of the above-mentioned products, etc., under the control of the VfM primary evaluation unit 115. The primary evaluation may also include, for example, the media effect (by advertising medium, application, exchange) when announcing the event to consumers.

In step S16, the control unit 11, under the control of the VfM primary evaluation unit 115, reads out the VfM index for the arbitrary measurement item of interest stored in the VfM index calculation presence/absence memory unit 122 and the actual value for the measurement item stored in the VfM index history information memory unit 124. Then, under the control of the VfM primary evaluation unit 115, the control unit 11 generates a VfM index evaluation based on the read-out VfM index and actual value.

In step S17, the control unit 11, under the control of the VfM primary evaluation unit 115, reads out the above-mentioned reaction behavior information stored in the reaction behavior log information storage unit 123, and executes the above-mentioned standard analysis processing and detailed analysis processing based on the read-out reaction behavior information.

In step S18, the control unit 11 generates a hypothesis related to the market value evaluation of the product, etc., based at least on the generated VfM index evaluation, under the control of the hypothesis generation unit 1151 provided in the VfM primary evaluation unit 115. The generated hypothesis is an accumulation of the degree of fulfillment and achievement of the plan related to the product or service. The generated hypothesis may be based on the results of the routine analysis process and the detailed analysis process, for example.

8A, 8B, 8C, and 8D are tables showing an example of VfM index evaluation based on VfM index and actual value for any measurement item to be focused on in the campaign for the product "Healthy Cafe Sweet". In the examples of Fig. 8A, 8B, 8C, and 8D, actual values are calculated for each advertising medium for each measurement item, and further, actual values are calculated for the measurement items "14. Coupon application", "21. Coupon issuance", and "31. Coupon redemption" by target cover. In the tables of Fig. 8A, 8B, and 8C, for example, the number of consumers shown in the target column or the target value of the number of consumers shown in the target column as a reference value and the number of consumers calculated for each measurement item as a percentage of the reference value, for example, 100%, is used as the VfM index for the measurement item. In addition, in the tables of Fig. 8A, 8B, and 8C, for example, the goal achievement status is shown as the VfM index evaluation. Here, in the table of FIG. 8C, the goal achievement status of coupon redemption can be seen to be below 90% for all advertising media used. This means that the target, female office workers in their twenties, redeemed fewer coupons than expected. The "61. Cost Effectiveness Index" shown in the table of FIG. 8D is calculated based on a total advertising fee of ¥5,000,000 for advertising medium 1, ¥10,000,000 for advertising medium 2, and ¥30,000,000 for advertising medium 3.

Figure 9 shows an example of a pie chart showing the coupon usage status by consumer gender and age in the campaign for the product "Healthy Cafe Sweet," generated by the routine analysis process, which is part of the primary evaluation described above. This routine analysis process makes it possible to evaluate whether the target was covered. The total value of the product/service target demographics for each gender/year composition ratio (%) shown in Figure 9 becomes an indicator called the "target achievement rate."

The graph in Figure 9 shows that fewer women in their 20s are redeeming coupons than expected. The graph in Figure 9 also shows that the product "Healthy Cafe Sweets" is generally popular among a wide range of women in their 20s to 40s, with women in their 30s making the largest percentage of coupon redemptions. It also shows that there is a certain demand for the product "Healthy Cafe Sweets" among men in their 20s to 40s, although not as much as women.

Figure 10 shows an example of a line graph that shows the reaction or behavioral status of female consumers at each stage of the reaction or behavior toward the product "Healthy Cafe Sweet" by age group, generated by the detailed analysis process that is part of the primary evaluation described above, in a campaign for the product "Healthy Cafe Sweet."

The graph in Figure 10 shows that the most views of the campaign application page on Company A's website for the product "Healthy Cafe Sweet" were from women in their 20s, but the application rate for women in their 20s was lower than that for women in their 30s and 40s.

Figure 11 shows an example of a pie chart showing coupon usage by consumer occupation type in a campaign for the product "Healthy Cafe Sweets," generated by the detailed analysis process that is part of the primary evaluation described above.

The graph in Figure 11 shows that the highest proportion of people using coupons for the Healthy Cafe Sweets product are office workers and assistants, but the proportion of people using coupons in professional and technical occupations is also high.

From the tables and graphs shown in Figures 8A to 11, hypotheses regarding the market value assessment of the product "Healthy Cafe Sweet" are generated.

For example, since the number of views by the target women in their twenties is high but the number of applications is low, it is conceivable that they stop applying after checking the product introduction on the website. In this case, under the control of the hypothesis generation unit 1151, a hypothesis is generated that the content of the campaign announcement does not match the tastes of women in their twenties. The generated hypothesis may be output, for example, from the VfM marketing system 1 to an external display unit (not shown), and the display on the display unit may be reviewed by an operator before being confirmed.

It can also be seen that the number of coupon usages is high among women in their 20s to 40s who work at desks, but also among men in their 20s to 40s. In this case, under the control of the hypothesis generation unit 1151, a hypothesis is generated that people who do not usually exercise much purchase the product for health reasons. The generated hypothesis may be output, for example, from the VfM marketing system 1 to an external display unit (not shown), and the display on the display unit may be reviewed by an operator before being confirmed.

The hypothesis may be generated based on the VfM index evaluation as follows:

12A and 12B are diagrams showing an example of a hypothesis generation table showing the correspondence between detection conditions based on VfM index evaluation and hypotheses to be generated. The hypothesis generation table may be set by an operator when registering a project in step S11, for example. In the example of the hypothesis generation table in FIG. 12A and FIG. 12B, under the control of the hypothesis generation unit 1151, when the VfM index evaluation satisfies a certain detection condition in the hypothesis generation table, a hypothesis corresponding to the detection condition is generated. In the examples of FIG. 8A, FIG. 8B, and FIG. 8C, the goal achievement status as the VfM index evaluation corresponding to each measurement item satisfies the detection conditions No. 13 and No. 15, and a hypothesis corresponding to the detection condition is generated. Note that the hypothesis generation tables shown in FIG. 12A and FIG. 12B are merely examples, and for example, the detection conditions in the hypothesis generation table may be arbitrarily combined with VfM index evaluations based on arbitrary VfM indexes.

Alternatively, for a VfM index for each measurement item, a hypothesis may be set in advance to be generated when the actual value for that measurement item does not satisfy the numerical value associated with that VfM index. The hypothesis may be set, for example, by the operator when registering the project in step S11. When there is a VfM index for which the actual value for the measurement item does not satisfy the numerical value associated with the VfM index, a hypothesis corresponding to that VfM index is generated under the control of the hypothesis generation unit 1151.

(2) Future Prediction Processing Next, the future prediction processing shown in the flow of Fig. 3B will be described in detail. Note that the future prediction processing shown in the flow of Fig. 3B is a non-limiting embodiment, and the future prediction processing of the present disclosure is not limited thereto.

In step S21, the control unit 11, under the control of the research implementation management unit 1161 included in the market value evaluation unit 116, conducts research on the above-mentioned products, etc., among consumers based on the hypothesis generated in step S18. The research is, for example, a questionnaire on the above-mentioned products, etc., among consumers.

In the implementation process of the research, for example, under the control of the research implementation management unit 1161, research items such as the above-mentioned product are generated based on the above-mentioned hypothesis, and information related to the generated research items is output to a research system 7 outside the VfM marketing system 1. The research system 7 conducts a research including the generated research items, targeting consumers who have participated in the campaign and who have been set as research targets in advance. Thereafter, under the control of the research implementation management unit 1161, the control unit 11 acquires research response information indicating the responses to the research, including the consumer's subjective evaluation, from the research system 7. Note that the generated research items may be output, for example, from the VfM marketing system 1 to an external display unit (not shown), and the display on the display unit may be reviewed by an operator before being confirmed. In addition, the consumers who are the targets of the research may be set by expanding the model members from the profile of the research members. In this way, the research may be conducted after the research items and research targets are extracted.

In addition, in the process of conducting research based on the above hypothesis, the research may be conducted recursively. For example, the research may be conducted recursively on consumers who are set as research targets in advance but are in a range other than the current research range, or on consumers selected based on the information of consumers included in the above reaction behavior information related to the above hypothesis. Alternatively, research may be conducted recursively including new research items that are regenerated, or added, modified, or deleted based on the hypothesis. In this way, it is possible to increase the accuracy of future predictions by expanding or reducing the consumers who are the targets of the research and conducting the research recursively.

In the above, an example was described as one embodiment of the process for conducting hypothesis-based research, in which research items are generated based on a hypothesis, and research including the generated research items is conducted for consumers who have been set in advance as research targets. However, the process for conducting hypothesis-based research is not limited to this. For example, research with research items set in advance may be conducted for consumers selected based on consumer information included in the reaction behavior information related to the hypothesis. Alternatively, research including research items generated based on a hypothesis may be conducted for consumers selected based on consumer information included in the reaction behavior information related to the hypothesis.

In the above description, a hypothesis is generated based on the VfM index evaluation in step S18, and research is conducted based on the generated hypothesis. However, the hypothesis generation process in step S18 is not a required configuration. For example, research may be conducted using any combination of the VfM index evaluation generated in step S16 and the results of the standard analysis process and the detailed analysis process executed in step S17.

13A to 13G are diagrams showing an example of a display screen of questionnaire items generated based on a hypothesis in the example of the product "Healthy Cafe Sweets". The questionnaire items shown in Figs. 13A and 13B are questionnaire items that can be used for sales forecasting. The questionnaire items shown in Fig. 13C are questionnaire items generated based on the above hypothesis that the campaign announcement content does not match the tastes of women in their twenties. The questionnaire items shown in Figs. 13D and 13E are questionnaire items generated based on the above hypothesis that people who do not usually exercise much purchase it for health reasons. Furthermore, the questionnaire items shown in Figs. 13F and 13G are questionnaire items generated based on the above hypothesis associated with the detection condition No. 15 in the example of Figs. 12A and 12B. For example, the questionnaire items are previously associated with a hypothesis, and as described above, the questionnaire items associated with the hypothesis are generated based on the hypothesis. Furthermore, as the targets of the research, from among the consumers who have been set as the research targets in advance, for example, women in their twenties who applied for a campaign for the product "Healthy Cafe Sweets" but did not use a coupon, and consumers in their twenties to forties who used a coupon may be selected.

In step S22, the control unit 11, under the control of the hypothesis correction unit 1162 included in the market value evaluation unit 116, determines whether or not the hypothesis is valid based on the research response information. The registration of the determination threshold used in the determination process is set, for example, during the processing of step S11.

Figures 14A to 14E are diagrams showing examples of display screens of the results of a survey of women in their twenties who viewed the product "Healthy Cafe Sweets" but did not use a coupon, and consumers in their twenties to forties who did use a coupon. The survey results shown in Figures 14A to 14E correspond to the survey items shown in Figures 13C to 13G, respectively.

As shown in Fig. 14A to Fig. 14E, each answer option for a questionnaire item reflects the consumer's subjective opinion regarding the hypothesis related to the questionnaire item. Therefore, for example, by comparing the proportion of answers to each option for the questionnaire item "Q14. Please tell us why you did not apply for the "Healthy Cafe Sweet" campaign" shown in Fig. 14A with a preset judgment threshold, it is possible to determine whether the hypothesis that the campaign announcement content does not match the tastes of women in their twenties is valid or not. By similar processing, it is possible to determine whether the hypothesis that people who do not usually exercise much purchase it for health reasons is valid or not from the proportion of answers to each option for the questionnaire items shown in Fig. 14B and Fig. 14C. Also, it is possible to determine whether the hypothesis generated when the detection condition No. 15 described above in relation to the example of Fig. 12A and Fig. 12B is satisfied is valid or not from the proportion of answers to each option for the questionnaire items shown in Fig. 14D and Fig. 14E.

The process of determining whether a hypothesis is valid may be performed using, for example, Structural Equation Modeling (SEM). In such a determination process, for example, for a model that is a hypothesis related to consumer purchases, the model fitness is calculated from the survey results of the research items that correspond to the observed variables, and the model fitness is compared with a determination threshold to determine whether the hypothesis is valid.

If it is determined in step S22 that the above hypothesis is invalid, the process branches from step S23 to step S24.

In step S24, the control unit 11 corrects the hypothesis under the control of the hypothesis correction unit 1162, and then the process from step S21 is executed again. In the hypothesis correction process, for example, the hypothesis is corrected based on the difference between the evaluation (generated by the system) from the event log (expected value) and the result (actual value).

In addition, in the hypothesis correction process, when multiple hypotheses are generated as in the above example, for example, a hypothesis determined to be invalid from among the multiple hypotheses may be removed. In addition, in the case where hypotheses are generated based on detection conditions as in the examples of Figures 12A and 12B, the hypothesis correction process may, for example, modify the detection conditions and the hypotheses associated with the detection conditions, and then regenerate a hypothesis associated with the detection conditions that the VfM index evaluation satisfies. Furthermore, in the case where the validity of a hypothesis is determined using structural equation modeling as described above, the hypothesis correction process may customize the hypothesis using a mathematical technique such as factor analysis.

On the other hand, if it is determined in step S22 that the above hypothesis is valid, the process branches from step S23 to step S25.

In step S25, the control unit 11 generates a market value evaluation of the above-mentioned product, etc., based on the research response indicated by the research response information, under the control of the market value evaluation section 116. The market value evaluation is a value that can be called market satisfaction (a numerical value that can be benchmarked), and is a final index group consisting of the degree of satisfaction with product/service planning items (objectives), the total value of additions and subtractions thereof, and the affirmative (purchase) probability by consumer attribute. If the product is a food product, for example, the market value evaluation is expressed as follows:
Σ(rating x weight) = taste 5 x 10% + quantity 3 x 5% +...

In step S26, under the control of the future prediction section 1163 of the market value evaluation section 116, the control unit 11 executes a future prediction including future sales of the above-mentioned product, etc., based on the market value evaluation generated in step S25. In the future prediction process, for example, based on the attribute information of each consumer included in the research response information and the research response from the consumer indicated by the research response information, the future prediction is executed by executing at least one of an extended estimation using a simple estimation method and an extended estimation using a complex estimation method, for example, a Bayesian network method. Note that the extended estimation using the Bayesian network method may be executed by setting a purchase probability between the answer options for each item of the research, and using the purchase probability indicated by the research response information. The purchase probability may be set by an operator, for example, when generating or confirming a research item.

15A, 15B, and 15C are diagrams showing an example of the sales forecast result of the product "Healthy Cafe Sweets" in the example of the product "Healthy Cafe Sweets". The sales forecast in FIG. 15A, 15B, and 15C can be performed, for example, based on the aggregated results of consumer responses to the questionnaire items shown in FIG. 13A and FIG. 13B. FIG. 15A shows the result of a sales forecast based on a simple estimation from the market sales volume. FIG. 15B shows the result of a sales forecast based on a simple estimation by consumer attributes. FIG. 15C shows the result of a sales forecast based on an expanded estimation using a Bayesian network method. Note that, as the campaign response coefficient in the examples of FIG. 15A, 15B, and 15C, a coefficient set in advance may be used, or a coefficient derived based on the consumer responses to the corresponding questionnaire items may be used.

In step S27, under the control of the VfM evaluation report unit 117, the control unit 11 outputs information regarding the results of the future prediction performed in step S26, including future sales of the above-mentioned products, etc., to an external output device (not shown).

(effect)
(1) First, under the control of the event planning unit 111, calculation/non-calculation setting information and VfM index setting information are written to the VfM index calculation/non-calculation storage unit 122. The calculation/non-calculation setting information write process sets the measurement items to be calculated. The VfM index setting information write process sets the VfM index for any measurement item to be focused on for the product or the like that is the target of the event, among the measurement items to be calculated. Under the control of the event announcement unit 112, the incentive distribution unit 113, and the event implementation unit 114, the event announcement system 4, the event participation acceptance system 5, and the incentive management system 6 are used to implement an event for a product or the like, and incentive use information including information on consumers who have used the incentive for the event is acquired in conjunction with the implementation of the event. Under the control of the VfM primary evaluation unit 115, a primary evaluation including an objective evaluation of the product or the like is generated based on the reaction behavior information including the acquired incentive use information. In the process of generating the primary evaluation, under the control of the VfM primary evaluation unit 115, a VfM index evaluation is generated based on the VfM index for the arbitrary measurement item of interest indicated by the VfM index setting information and the actual value for the measurement item, and under the control of the hypothesis generation unit 1151, a hypothesis related to a market value evaluation of the product, etc. is generated based at least on the generated VfM index evaluation. Thereafter, under the control of the research implementation management unit 1161, research on the product, etc. is conducted on consumers based on the generated hypothesis. Under the control of the market value evaluation unit 116, a market value evaluation of the product, etc. is generated based on responses to the conducted research. Under the control of the future prediction unit 1163, a future prediction including future sales of the product, etc. is executed based on the generated market value evaluation.

Such event- and research-based market valuation and future forecasting processes can be based on data that reflects the current economic environment, rather than the economic environment of the past. This makes it possible to make such future forecasts more reliable across a wide range of forecasting areas, as compared to sales forecasts that rely solely on statistical analysis of past data.

In addition, the above future predictions can utilize consumer research as described above to reflect, for example, the subjective opinions of consumers on the buying side. By conducting the research based on the primary evaluation as described above, it is possible, for example, to reconfirm the information obtained in the primary evaluation or to perform an evaluation from a different perspective than the information obtained in the primary evaluation. This makes it possible to make such future predictions more purposeful and accurate.

As described above, the primary evaluation can be generated based on a numerically assessable index called the VfM index. Since the research is carried out based on the primary evaluation generated in this way, the market value evaluation and future forecast can be made more accurate. Furthermore, since the VfM index can be set for any measurement item, it is possible to perform a market value evaluation and future forecast focusing on the required items.

In addition, as the event is carried out, information on the results of consumer reactions or actions can be accumulated in sequence, and the actual values for the measurement items related to the VfM index can be calculated in a chronological order from the accumulated information. The information may be accumulated continuously while the event is carried out multiple times, for example. By using the actual values calculated in a chronological order in this way, it is also possible to evaluate and analyze the trends and trends of the market value evaluation in a chronological order. By evaluating and analyzing the trends and trends of the market value evaluation in this way, it is possible to make highly accurate future predictions regarding the management of marketing activities related to the product or service, future predictions of sales related to the product or service, and future predictions regarding the development and direction of improvement and abolition of the product or service. Furthermore, since the actual values for the measurement items related to the VfM index are calculated for the VfM index, which is an index for any measurement item that should be noted for the product or service, it is also possible to apply the same VfM index to consumer reactions or actions to the product, etc., and cross-sectionally evaluate products, etc. of other companies, other industries, and other business types.

Furthermore, the generated hypothesis is based on a numerically evaluable index called the VfM index. For example, in research conducted based on the hypothesis as described above, it is possible for the research items included in the research to be generated based on such a hypothesis, and for the consumers targeted by the research to be selected based on such a hypothesis. By performing the market value evaluation generation process and future prediction process based on such research, it is possible to make future predictions more accurate.

Based on the results of such future predictions, it is possible to determine, for example, which products should continue to be sold and which services should continue to be provided, which products should be discontinued and which services should be discontinued, or which products and services should be improved. Furthermore, the above future predictions not only predict future sales but also reveal the value of the products, making it possible to determine production plans for how many products should be produced and plans for the scale of service provision.

(2) Under the control of the hypothesis correction unit 1162, it is determined whether or not the hypothesis was valid based on the research response information indicating the responses to the conducted research. If it is determined that the hypothesis was invalid, the hypothesis is corrected under the control of the hypothesis correction unit 1162. Thereafter, the processing under the control of the research implementation management unit 1161 described above is executed again.

In this way, it is possible to recursively correct the hypothesis until it becomes valid, and therefore the future prediction results derived from the corrected hypothesis after the correction can be made more reliable.

(3) In the future prediction process for the above-mentioned products, etc., the above-mentioned future prediction is performed, for example, by performing at least one of an extended estimation using a simple estimation method and an extended estimation using a complex estimation method (e.g., a Bayesian network method) based on the attribute information of each consumer included in the above-mentioned research response information and the research response from the consumer indicated by the above-mentioned research response information. For example, in the extended estimation using the simple estimation method, a deductive extended estimation is performed, and in the extended estimation using the complex estimation method, a deductive or recursive extended estimation is performed.

By carrying out such an expanded estimation, it is possible to predict how much the limited number of consumers who are the subjects of the research, as well as the potential buyers of the product or service, will contribute to sales. Even if the distribution of attribute information of the consumers who are the subjects of the research is biased compared to the distribution of attribute information of all consumers who are potential buyers of the product or service, it is possible to make the future prediction based on the expanded estimation more accurate by, for example, appropriately weighting each attribute information to correct the distribution bias. Furthermore, by logging actual results, storing them as indexes (information), and analyzing them rather than simply making "sales forecasts," it is possible to make more accurate future predictions regarding the management of marketing activities, sales related to products or services, and the direction of development and improvement/elimination.

[Other embodiments]
The present invention is not limited to the above embodiment. For example, in the above first embodiment, an example in which one type of incentive such as a coupon is used as the incentive has been mainly described. However, multiple types of incentives may be used simultaneously as incentives, such as multiple types of coupons such as free exchange tickets and discount tickets, bonus points acquired by a consumer when purchasing a product, and multiple types of coupons such as free exchange tickets and discount tickets for other products acquired by a consumer when purchasing a product. In this case, the incentive distribution information and incentive use information described above may include, for example, information indicating the type of incentive acquired and used by a consumer. In addition to the above-mentioned incentive management system, an incentive management system for managing each incentive may be used.

The VfM index may also include at least one of an index for a measurement item related to consumers who have used an incentive multiple times, an index for a measurement item related to consumers who have not used an incentive, and an index for a measurement item related to consumers who have selected a specific incentive.

Here, consumers who have used the incentive multiple times include, for example, consumers who rate the value of the above-mentioned product or service as high. Therefore, by setting a VfM index for the measurement items related to consumers who have used the above-mentioned incentive multiple times, it is possible to evaluate the positive aspects of the value of the above-mentioned product or service.

Furthermore, consumers who do not use incentives include, for example, consumers who wished to participate in the event but did not use the incentive, and consumers who received an incentive but did not use it. Therefore, by setting a VfM index for the measurement items related to consumers who do not use the incentive, it is possible to verify, for example, whether there is room to improve the evaluation of the product or service, or to verify what method should be used to improve the evaluation of the product or service.

Furthermore, for example, when consumers select an incentive to use from multiple types of incentives (discounts, exchanges, points, etc.), it may be desirable to obtain statistics on consumers who have selected a specific incentive. For example, the type of assessment of the value of the product or service by the consumer can be determined for each incentive selected by the consumer. Therefore, by setting a VfM index for the measurement items related to consumers who have selected the specific incentive, it is possible to assess the value of the product or service with a higher quality. In other words, by preparing multiple incentives that consumers desire and setting and analyzing a base value for measuring market value for each incentive, the accuracy of the future prediction can be improved.

In this way, by using the VfM index as described above, for example, in the primary valuation generation process, the hypothesis generation process, or the research implementation process, it is possible to make the market value assessment based on the research more accurate. Therefore, the future forecast based on the market value assessment can also be made more accurate.

In the first embodiment, an example was described in which a VfM index evaluation is generated based on the VfM index and actual value for any measurement item of interest. Here, for example, for each measurement item to be calculated that is set by the calculation on/off setting information, a period during which reaction behavior information related to the measurement item can be acquired is set, and if the actual value for the measurement item during that period does not satisfy the value related to the VfM index, it may be determined whether or not a reminder needs to be sent to the consumer based on the remaining period of that period and the VfM index and actual value for that measurement item, and a reminder may be sent in accordance with the determination.

In addition, in the first embodiment, an example was described in which the reaction behavior information includes consumer identification information such as a consumer number. In such an example, as described above, the attribute information of the consumer related to the reaction behavior information is obtained by utilizing the correspondence between the consumer identification information stored in the consumer information database and the attribute information of the consumer. However, the reaction behavior information may include the consumer attribute information itself in addition to the consumer identification information such as the consumer number as described above.

In the first embodiment, the hypothesis is mainly corrected when it is determined that the hypothesis is invalid. However, if the hypothesis is invalid, a new hypothesis may be obtained.

In addition, the configuration of the VfM marketing system and the data structures stored in the VfM index master, VfM index calculation/non-calculation memory unit, reaction behavior log information memory unit, VfM index history information memory unit, primary evaluation memory unit, research response log information memory unit, and market value evaluation memory unit can be modified in various ways without departing from the spirit of this invention.

In short, this invention is not limited to the above-described embodiment as it is, and in the implementation stage, the components can be modified and embodied without departing from the gist of the invention. Furthermore, various inventions can be formed by appropriately combining multiple components disclosed in the above-described embodiment. For example, some components may be deleted from all the components shown in the embodiment. Furthermore, components from different embodiments may be appropriately combined.

1...VfM marketing system, 11...control unit, 111...event planning section, 112...event announcement section, 113...incentive distribution section, 114...event implementation section, 115...VfM primary evaluation section, 1151...hypothesis generation section, 116...market value evaluation section, 1161...research implementation management section, 1162...hypothesis correction section, 1163...future prediction section, 117...VfM evaluation report section, 12...storage unit, 121...VfM index master, 122...VfM index Marking calculation presence/absence memory unit, 123...Reaction behavior log information memory unit, 124...VfM index history information memory unit, 125...Primary evaluation memory unit, 126...Research response log information memory unit, 127...Market value evaluation memory unit, 13...Communication interface unit, 2...Operator terminal, 3...Consumer information database, 4...Event announcement system, 5...Event participation acceptance system, 6...Incentive management system, 7...Research system, NW...Communication network

Claims (6)

Conducting consumer research on the goods or services based on a hypothesis regarding the market value of said goods or services;
generating a market value assessment of the goods or services based on the results of the research, including the subjective assessments of the consumers;
causing a computer to perform a future forecast, including future sales, for said goods or services based on said generated market valuation;
performing the future forecast including the future sales includes performing at least one of an extended estimation using a simple estimation method and an extended estimation using a complex estimation method based on attribute information of each consumer who responded to the research and the research responses from the consumer;
Computer program. The computer program of claim 1, wherein the market value assessment represents a value relative to the price of the goods or services. The computer program further comprises:
Based on the results of the research, determine whether the hypothesis was valid or not, and if it is determined that the hypothesis was not valid, correct the hypothesis;
Conducting second or subsequent research on the consumer related to the product or service based on the revised hypothesis;
3. The computer program product of claim 1, further comprising: a computer program for causing a computer to generate a market value assessment of the goods or services based on the results of the second or subsequent research. The computer program further comprises:
The computer program product according to claim 1 , further comprising: a computer program that causes a computer to execute the steps of: outputting information relating to a result of the future prediction. An information processing method executed by an information processing device,
Conducting consumer research on the goods or services based on a hypothesis regarding the market value of said goods or services;
generating a market value assessment of the goods or services based on the results of the research, including the subjective assessments of the consumers;
performing future projections, including future sales, for said goods or services based on the generated market valuation ;
performing the future forecast including the future sales includes performing at least one of an extended estimation using a simple estimation method and an extended estimation using a complex estimation method based on attribute information of each consumer who responded to the research and the research responses from the consumer;
Information processing methods. Memory,
a processor coupled to the memory,
An information processing apparatus, wherein the processor is configured to execute a computer program according to claim 1 , the computer program being stored in the memory.