Information processing device, information processing method, and information processing program

Abstract

To determine the trends of a target in selling commodities of the target in stages.SOLUTION: An information processing apparatus includes: a prediction unit which predicts a sales trend of an unreleased second sales object of a target from a sales record of a released first sales object of the target; and a determination unit which determines whether the target has caught on or not, on the basis of a result of comparing the predicted sales trend of the second sales object with a sales trend of the actually released second sales object.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] In recent years, with the remarkable spread of the Internet, for example, technologies related to analysis using various information on the Internet have been provided. For example, a technique for analyzing customers in consideration of trends over time using purchase history data and the like is known (see Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When splitting a series of objects (such as titles) of works, contents, etc. into multiple sales items and selling them step by step, for example, in developing a sales strategy, it is desired to quickly grasp whether the object is popular.

[0005] The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of determining the popularity of an object when selling the target product step by step.

Means for Solving the Problems

[0006] The information processing apparatus according to the present application includes a prediction unit that predicts the sales trend of a second unsold sales item of the target from the sales history of a first sold sales item of the target, and based on a comparison result between the predicted sales trend of the second sales item and the actual sales trend of the second sold sales item, a determination unit that determines whether the target is popular. [Effects of the Invention]

[0007] According to one embodiment, when selling the target product in stages, it is possible to determine the trend of the target product. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of information processing performed by the information processing device according to the embodiment. [Figure 2] Figure 2 is a scatter plot showing the correlation between the projected sales figures and the actual sales figures. [Figure 3] Figure 3 is a diagram illustrating an example of the operation of the information processing device shown in Figure 1. [Figure 4] Figure 4 is a diagram illustrating another example of the operation of the information processing device shown in Figure 1. [Figure 5] Figure 5 is a diagram illustrating another example of the operation of the information processing device shown in Figure 1. [Figure 6] Figure 6 shows an example of the configuration of an information processing device in an information processing system according to an embodiment. [Figure 7] Figure 7 is a flowchart showing an example of the information processing flow performed by an information processing device. [Figure 8] Figure 8 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, each embodiment can be appropriately combined as long as the processing content is not inconsistent. Also, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant explanations are omitted.

[0010] (Embodiment) [1. An example of information processing] First, an example of information processing performed by the information processing device 100 will be explained using Figure 1. Figure 1 is a diagram showing an example of information processing performed by the information processing device according to the embodiment.

[0011] In Figure 1, the information processing system 1 is a system that processes information related to the subject of sale. The subject of sale includes, for example, titles of manga, books, content, etc. The subject is a series of the same title that is divided into multiple sales items, which are sold in stages at different times. In this embodiment, an example is described where the subject is a manga title. In this case, the subsequent books (comics) that are the subject of sale are sold on different release dates, such as volume 1, volume 2, ..., volume n. "n" in volume n is an integer. In this embodiment, the sales item is described as a book, but it may also be content, etc., that is distributed in stages at different times.

[0012] Information processing system 1 can provide functions to manage sales history, sales trends, etc., for each of the multiple sales items for the title under management. Information processing system 1 can provide a function to predict the sales trends of unsold items for the title based on the sales history of already sold items for the title. Sales trends include, for example, changes in sales after an item is sold, and features such as sales by gender and age group. Information processing system 1 can provide a function to determine the popularity of a title based on the sales trends of its sales items. Sales trends include the number of sales.

[0013] [1-1. Overview of Information Processing] As shown in Figure 1, the information processing system 1 comprises a management device 10 and an information processing device 100. The management device 10 and the information processing device 100 are configured to communicate with each other via a network (not shown). The network includes, for example, a wired or wireless network. For the sake of simplicity, the following description will assume that the information processing system 1 has a one-to-one relationship with the information processing device 100 and the management device 10, but the information processing device 100 may be configured to transmit and receive data with each of multiple management devices 10.

[0014] The management device 10 is a server device capable of managing the sales schedule, sales history, etc., of the target merchandise. The management device 10 includes, for example, a computer, a dedicated device, an EC (Electronic Commerce) server, etc. The management device 10 manages sales data 500 for each target merchandise and provides the target sales data 500 in response to requests from external sources.

[0015] Sales data 500 is data that can identify the sales history, number of sales, etc. of a product. Sales data 500 includes identification information 510, post-release sales information 520, sales information by gender 530, and sales information by age group 540. Identification information 510 is set to information that can identify the product of a specific title. Post-release sales information 520 is set to information that shows the sales history of the product for each day after its release, as indicated by identification information 510. Sales information by gender 530 is set to information that shows the sales history of the product for each gender, as indicated by identification information 510. Sales information by age group 540 is set to information that shows the sales history of the product for each age group, as indicated by identification information 510.

[0016] In an example shown in FIG. 1, for each of the plurality of sales data 500, information indicating any one of Volume 1, Volume 2, ···, Volume n is set in the identification information 510. For each of the plurality of sales data 500, information indicating the sales history every 0 days (the day of release), 1 day, 2 days, ···, m days is set in the post-release sales information 520. "m" in m days is an integer. For each of the plurality of sales data 500, information indicating the sales history for each of male and female is set in the gender-based sales information 530. For each of the plurality of sales data 500, information indicating the sales history for each of the 20s, 30s, 40s, etc. is set in the age-based sales information 540. Note that the sales data 500 may be one data that can identify the sales history of Volume 1, Volume 2, ···, Volume n.

[0017] The information processing device 100 acquires the sales data 500 from the management device 10 and predicts the future sales trend of the target based on the sales history indicated by the sales data 500. The information processing device 100 predicts the future sales trend of the target using a prediction model 400 that is machine-learned to predict the future sales trend from the characteristics of the sales history of a plurality of sold items for the target in the past. The prediction model 400 is machine-learned to predict the sales trend of the target using, for example, not only data from Volume 1 but also data from any volume. The prediction model 400 is machine-learned to predict the sales trend of the second sold item from the input sales history data using teacher data having the sales data 500 of the first sold item and the second sold item as the learning target. For example, when the sales data 500 of the target is input, the prediction model 400 predicts the future sales trend from the sales history indicated by the sales data 500 and outputs the predicted sales trend.

[0018] Figure 2 is a scatter diagram showing the correlation between the predicted sales volume and the actual sales volume of the target. In Figure 2, scatter diagram 600 shows that the horizontal axis represents the predicted sales volume and the vertical axis represents the actual sales volume respectively. Scatter diagram 600 shows a plurality of outputs 610 and a straight line 620. The plurality of outputs 610 shows the correlation between the predicted sales volume and the actual sales volume. The straight line 620 is a straight line showing the value where the predicted sales volume and the actual sales volume match, and it represents the proportional formula of the predicted sales volume and the actual sales volume. That is, when the actual sales volume is close to the predicted sales volume, the output 610 is plotted near the straight line 620. Therefore, in scatter diagram 600, when the output 610 of the predicted sales volume and the actual sales volume swings upward from the straight line 620, it can be determined that the target is "popular". The upward swing means that the actual sales volume exceeds the predicted sales volume.

[0019] In an example shown in Figure 2, when the plots 610P-2, 610P-1 of the (n-2)th volume and the plot 610P of the nth volume of the sold items swing upward from the straight line 620, the information processing apparatus 100 can determine that the target has become popular. Note that, for example, when one plot of the latest volume swings upward from the straight line 620 by a predetermined threshold value, the information processing apparatus 100 may determine that the target has become popular. Also, for example, when the output 610 is near the straight line 620, the information processing apparatus 100 can hold the determination as to whether the target has become popular. For example, when the output 610 swings downward from the straight line 620, the information processing apparatus 100 can determine that the target is in a downtrend or that the popularity has ended.

[0020] Next, referring to Figure 1, an example of the information processing procedure of the information processing apparatus 100 in the information processing system 1 will be described below.

[0021] As shown in Figure 1, the information processing device 100 acquires the target sales data 500 from the management device 10 (step S1). For example, the information processing device 100 acquires the sales data 500 for the first sales items from volume 1 to nx of the target that have already been sold at any given time. x is an integer. The first sales item is the target that has already been sold.

[0022] The information processing device 100 predicts the sales trend of the n-volume product based on sales data 500 from volume 1 to nx (step S2). For example, the information processing device 100 inputs sales data 500 from volume 1 to nx into the prediction model 400 and predicts the sales trend of the n-volume product based on the output of the prediction model 400. For example, if n is 4 volumes, the information processing device 100 predicts the sales trend (number of units sold) of the unreleased 4 volumes based on sales data 500 from volumes 1 to 3 that have already been sold. For example, the information processing device 100 may also predict the sales trend of the unreleased products based on sales data 500 from any volume to any volume that has already been sold. This allows the information processing device 100 to accurately predict the future sales trend of the target even if the sales period of the target is long. The information processing device 100 stores prediction data showing the predicted sales trend of the n-volume product. Note that the n-volume product corresponds to the second product.

[0023] After a predetermined number of days have elapsed since the sale of n volumes of the product, the information processing device 100 acquires sales data 500 indicating the n volumes from the management device 10 (step S3). For example, the information processing device 100 stores the acquired sales data 500 for the n volumes in association with the sales data 500 for volumes 1 through nx. The information processing device 100 may also update the sales data 500 for volumes 1 through nx when acquiring the sales data 500 indicating the n volumes of the product.

[0024] The information processing device 100 determines whether the target product has become popular based on a comparison between the predicted sales trend of n volumes of the product and the actual sales trend of a second product that was sold (step S4). For example, the information processing device 100 compares the predicted sales trend of n volumes of the product with the actual sales trend and determines that the target product has become popular if the actual sales trend is higher than the predicted sales trend. For example, the information processing device 100 calculates the difference between the predicted sales trend of n volumes of the product and the actual sales trend and determines that the target product has become popular if the difference exceeds a threshold for determination. The threshold for determination can be set to, for example, a value set based on past trends, a value obtained through machine learning, etc.

[0025] The information processing device 100 provides the determination result of the target epidemic (step S5). For example, if the information processing device 100 determines that the target has become epidemic, it generates determination result information that can notify the target epidemic and provides the determination result by transmitting the determination result information to the management device 10 or by having the management device 10 notify it. For example, if the information processing device 100 determines that the target has become epidemic, it generates determination result information that can notify the target epidemic and provides the determination result by registering the determination result information in the database.

[0026] Figure 3 is a diagram illustrating an example of the operation of the information processing device 100 shown in Figure 1. As shown in Figure 3, if the prediction target is the sales history for m days after the release of n volumes, the information processing device 100 obtains sales data 500 from the management device 10 showing the sales history of n volumes for m days after the release of the target. The information processing device 100 predicts the sales trend of the unsold (future) n volumes from the sales history of the already sold target, and determines that the target has become popular if the actual sales trend is higher than the predicted sales trend. The information processing device 100 generates determination data 700 indicating the determination result that the target has become popular, based on the sales history up to n-1 volumes, and provides the determination data 700.

[0027] In this way, the information processing device 100 can predict the sales trend of the unsold (future) second product from the sales history of the first product that has already been sold, and determine whether the product has become popular based on the comparison result between the predicted sales trend and the actual sales trend of the second product. As a result, when selling the product in stages, the information processing device 100 can determine whether the product is popular based on its sales trend, and thus quickly grasp whether the product is popular.

[0028] [1-2. Other processing examples] For example, the prediction results may differ when predicting the sales trend of volume 4 based on the sales trends of volumes 1 to 3, compared to predicting the sales trend of volume 23 based on the sales trends of volumes 20 to 22. Therefore, the information processing device 100 can be modified as follows.

[0029] If the information processing device 100 is predicting the sales history of n volumes for m days after their release, it obtains sales data 500 from the management device 10 showing the sales history of nx volumes for m days after their release. The "x" in x volumes specifies how many volumes prior to the sales data 500 should be used as the sales history. As the value of n increases, the accuracy of the prediction can be improved by decreasing the value of x. The information processing device 100 predicts the sales trend of unsold (future) n volumes from the sales history of the already sold nx volumes of the target, and if the actual sales trend is higher than the predicted sales trend, it can determine that the target has become popular.

[0030] The information processing device 100 can predict the sales trend of an input second product using a predictive model 400 that has been trained to predict the sales trend of a second product from input sales history data, using training data which includes the characteristics of the target to be learned and sales data 500 of the first and second products. The characteristics of the target to be learned include factors that affect the number of sales, such as the story, illustrations (images), author, publisher, and number of pages. The training data associates these characteristics with the sales data 500 as labels. As a result, the predictive model 400 can predict the sales trend of the second product according to the characteristics of the target by machine learning the sales data 500 corresponding to the characteristics.

[0031] The information processing device 100 acquires feature data that indicates the characteristics of the target, inputs the feature data and sales data 500 of the first product into the prediction model 400, and uses the output of the prediction model 400, which makes predictions based on the characteristics of the target, as a prediction of the sales trend of the second product. As a result, the information processing device 100 can improve the accuracy of determining whether the target has become popular or not based on the comparison result of the predicted sales trend with the actual sales trend of the second product.

[0032] The predictive model 400 can be a machine learning model that predicts the sales trend of the second product from the input sales history data and type, using training data that has the characteristics to be learned and sales data of the first and second products for each type of target buyer. For example, the type of buyer includes gender, age, and combinations thereof. The training data has labels that identify the gender distribution, age distribution, etc. of the target buyers, associated with the sales data 500 for machine learning. As a result, the predictive model 400 can predict the sales trend of the second product according to the type of buyer by machine learning the sales data 500 corresponding to the type of buyer.

[0033] The information processing device 100 acquires type data indicating the type of buyer to be judged, inputs the type data and sales data 500 of the first product into the prediction model 400, and uses the output of the prediction model 400, which predicts based on the type of buyer, as the prediction of the sales trend of the second product. As a result, the information processing device 100 can determine whether or not the target product has become popular among a specific type of buyer based on the comparison result between the predicted sales trend and the actual sales trend of the second product.

[0034] Figure 4 is a diagram illustrating another example of the operation of the information processing device 100 shown in Figure 1. As shown in Figure 4, if the prediction target is the sales history for m days after the release of volume n and for a predetermined gender, the information processing device 100 obtains sales data 500 from the management device 10 showing the sales history for m days after the release of volume n of the target. The information processing device 100 predicts the sales trend of unsold (future) volumes n from the sales history of the sold target for a predetermined gender, and determines that the target has become popular if the actual sales trend is higher than the predicted sales trend. In other words, the information processing device 100 can determine whether or not the target has become popular for a predetermined gender. The information processing device 100 generates determination data 700 showing the determination result that the target has become popular, given that the data used is the sales history of a predetermined gender up to volume n-1, and provides the determination data 700. For example, the information processing device 100 may determine whether or not the target has become popular for men and women separately, and provide determination data 700 showing the determination result for whether or not the target has become popular for men and women separately.

[0035] Figure 5 is a diagram illustrating another example of the operation of the information processing device 100 shown in Figure 1. As shown in Figure 5, if the prediction target is the sales history for m days after the release of volume n and is within a predetermined time period, the information processing device 100 obtains sales data 500 from the management device 10 showing the sales history for m days after the release of volume n of the target. The information processing device 100 predicts the sales trend of unsold (future) volume n products from the sales history of the sold products of the target for a predetermined time period, and determines that the target is not popular if the actual sales trend is not higher than the predicted sales trend. In other words, the information processing device 100 can determine whether or not the target was popular in a predetermined time period. The information processing device 100 generates determination data 700 showing the determination result that the target is not popular, given that the data used is the sales history for a predetermined time period up to volume n-1, and provides the determination data 700. For example, the information processing device 100 may determine whether or not the target was popular for each different time period and provide determination data 700 showing the determination results for each different time period.

[0036] The above-described process is merely an example, and the information processing system 1 and the information processing device 100 may determine whether or not the target has become popular in various ways. For example, the information processing device 100 may calculate the upward deviation rate of the sales trend (number of sales) of n volumes of the product and use the upward deviation rate and a determination threshold to determine whether or not the target has become popular. In other words, the information processing device 100 may predict the sales trend of the product using a calculation program or the like without using a machine learning model and determine whether or not the target has become popular. For example, the information processing device 100 may determine that the target has become popular if the actual sales trend of the product is exponentially higher than expected. For example, the information processing device 100 may predict the total number of sales of the latest product and the total number of sales of past products and compare it with the actual total to determine whether or not the target has become popular.

[0037] [2. Configuration of the Information Processing System] Information processing system 1 is a system that determines a target trend based on target sales data 500. Figure 6 is a diagram showing an example configuration of the information processing device 100 of information processing system 1 according to an embodiment. As shown in Figure 6, information processing system 1 includes a management device 10, a terminal device 20, and an information processing device 100. The management device 10, the terminal device 20, and the information processing device 100 are connected via a network N so as to be able to communicate by wired or wireless means. Note that information processing system 1 shown in Figure 6 may include multiple management devices 10, multiple terminal devices 20, and multiple information processing devices 100. In addition, information processing system 1 may include various computers used to determine the target trend.

[0038] The management device 10 can provide a function to manage sales data 500 for multiple targets. The management device 10 can provide a function to provide sales data 500 for targets specified by the information processing device 100. For each of the multiple targets, the management device 10 constructs the aforementioned volume-by-volume sales data 500 as a database. For example, if volumes 1 through 3 of a target are being sold, the management device 10 generates, updates, etc., the sales data 500 for each of volumes 1 through 3. When the information processing device 100 specifies a target, the management device 10 extracts the sales data 500 for that target from the database and transmits it to the information processing device 100. The management device 10 can be any device as long as it can implement the processing in the embodiment.

[0039] Terminal device 20 is a device used by the user. Terminal device 20 is used by the user to access various types of information. Terminal device 20 can be implemented as, for example, a smartphone, a tablet, a notebook PC (Personal Computer), a desktop PC, a mobile phone, or a PDA (Personal Digital Assistant). For example, terminal device 20 requests the information processing device 100 to provide various types of data. For example, terminal device 20 accepts input from the user and transmits the received data to the information processing device 100. Terminal device 20 displays the various types of data provided by the information processing device 100 using an application or browser. When terminal device 20 receives a target epidemic determination, it requests the information processing device 100 to perform the epidemic determination. Terminal device 20 can be any device as long as it can implement the processing in the embodiment.

[0040] The information processing device 100 according to this embodiment is a computer that acquires target sales data 500 from the management device 10 and predicts the sales trends of unsold (future) products based on the sales data 500. The information processing device 100 can provide a function to determine whether or not the target product has become popular based on a comparison between the predicted sales trends of the target product and the actual sales trends.

[0041] Although the information processing system 1 is configured to include an information processing device 100 and a management device 10, the information processing device 100 and the management device 10 may be implemented as a single device, such as a computer.

[0042] [3. Configuration of the Information Processing Device] The following describes an example of the functional configuration of the information processing device 100 described above. As shown in Figure 6, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130. The information processing device 100 may also have an input unit (e.g., a keyboard or mouse) for receiving various operations from the administrator of the information processing device 100, and a display unit (e.g., a liquid crystal display) for displaying various information.

[0043] (Communications Department 110) The communication unit 110 is implemented, for example, by a NIC (Network Interface Card). The communication unit 110 is connected to the network N by wire or wireless connection and transmits and receives information with various other devices.

[0044] (Storage unit 120) The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) or flash memory, or by a storage device such as a hard disk or optical disc. The storage unit 120 includes a sales data storage unit 121, a prediction model storage unit 122, and a judgment data storage unit 123. However, the storage unit 120 may store various types of information, not limited to those described above.

[0045] (Sales data storage unit 121) The sales data storage unit 121 stores sales data 500 for multiple items. The sales data storage unit 121 stores one or more sales data 500 acquired from the management device 10, etc., associating them with an item. For example, the sales data storage unit 121 stores the above-mentioned sales data 500 in the order of the volumes sold, thereby constructing a database that can identify the sales history from volume 1 to volume n. For example, the sales data storage unit 121 stores the sales data 500 from volume 1 to n-1 as past sales history, and the sales data 500 for volume n as the sales history for the latest volume. The sales data storage unit 121 is not limited to the above and may store various types of information depending on the purpose.

[0046] (Predictive model memory unit 122) The prediction model storage unit 122 stores machine-learned model data, such as the prediction model 400 described above. The prediction model storage unit 122 stores model data, such as the prediction model 400, obtained from, for example, a server device, a machine learning device, etc. The prediction model 400 is a learning model that uses the target sales data 500 and ground truth data contained in the training data to extract the characteristics, regularities, patterns, etc. of sales volume shown in the sales data, and predicts the future sales trend of the target by machine learning the relationship with the ground truth data.

[0047] The prediction model 400 performs machine learning using, for example, a neural network, and has an input layer, a hidden layer, and an output layer. For example, when sales data 500 from volume 1 to n-1 volumes is input to the input layer of the prediction model 400, the hidden layer predicts the sales trend of n volumes, and the output layer outputs the predicted sales trend. For example, when sales data 500 from volume 1 to n-1 volumes and target feature data are input to the input layer of the prediction model 400, the hidden layer predicts the sales trend of n volumes based on the past sales history of products similar to the target features, and the output layer outputs the predicted sales trend. For example, when sales data 500 from volume 1 to n-1 volumes and target buyer type data are input to the input layer of the prediction model 400, the hidden layer predicts the sales trend of n volumes based on the past sales history of the type, and the output layer outputs the predicted sales trend.

[0048] (Decision data storage unit 123) The judgment data storage unit 123 stores the judgment data 700 described above. The judgment data storage unit 123 stores the judgment data 700, which indicates the result of the control unit 130 of the information processing device 100 determining the trend of the target, in association with the target. In this embodiment, the judgment data storage unit 123 can store judgment data 700 associated with multiple different targets. The judgment data 700 may include the data used for the determination, or it may be associated with the data used for the determination.

[0049] (Control unit 130) The control unit 130 is a controller, and is implemented, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs (an example of an information processing program) stored in the memory device inside the information processing device 100 using RAM as the working area. Alternatively, the control unit 130 is a controller and can be implemented, for example, by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0050] As shown in Figure 6, the control unit 130 includes an acquisition unit 131, a prediction unit 132, a determination unit 133, and a provision unit 134, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in Figure 6, and other configurations are also acceptable as long as they perform the information processing described later.

[0051] (Acquisition part 131) The acquisition unit 131 acquires various types of data. The acquisition unit 131 acquires target sales data 500 from the management device 10 via the communication unit 110, associates the acquired sales data 500 with the target, and stores it in the storage unit 120. The acquisition unit 131 acquires model data such as the prediction model 400 via the communication unit 110 and stores it in the storage unit 120. If the acquired target sales data 500 is stored in the storage unit 120, the acquisition unit 131 updates the sales data 500. The acquisition unit 131 acquires request data for predicting the target sales trend from the terminal device 20, etc., via the communication unit 110.

[0052] (Prediction unit 132) The prediction unit 132 predicts the sales trend of the unsold second product of the target based on the sales history of the first product that has already been sold. The prediction unit 132 predicts the sales trend of the input second product using a prediction model 400 that has been machine-trained to predict the sales trend of the second product from the input sales history data, for example, using training data that has the sales data of the first and second products to be learned. The prediction unit 132 predicts the sales trend of the input second product using a prediction model 400 that has been machine-trained to predict the sales trend of the target second product from the input sales history data, for example, using training data that has the characteristics of the target and the sales data 500 of the first and second products to be learned.

[0053] (Judgment unit 133) The determination unit 133 determines whether the target product became popular based on the comparison result between the predicted sales trend of the second product and the actual sales trend of the second product. The determination unit 133 determines that the target product became popular if the degree of agreement between the predicted sales trend of the second product and the actual sales trend of the second product exceeds a predetermined threshold. The determination unit 133 determines that the target product became popular if the actual number of second products sold is greater than the number of second products sold, and the difference exceeds a predetermined threshold. The determination unit 133 determines whether the target product became popular among different types of buyers based on the comparison result between the predicted sales trend of the second product and the actual sales trend of the second product. The determination unit 133 stores the determination data 700, which allows for the identification of the determination result of whether the target product became popular or not, in the storage unit 120.

[0054] (Provider 134) The provisioning unit 134 provides various data. The provisioning unit 134 provides various data by transmitting various data to external devices via the communication unit 110. The provisioning unit 134 provides the judgment data 700 stored in the storage unit 120 to the terminal device 20, external devices, etc. The provisioning unit 134 provides the terminal device 20 with judgment data 700 that can identify whether or not the target has become prevalent.

[0055] [4. Processing Procedure] Next, using Figure 7, the procedure for information processing performed by the information processing device 100 according to the embodiment will be described. Figure 7 is a flowchart showing an example of the flow of information processing performed by the information processing device.

[0056] As shown in Figure 7, the information processing device 100 acquires the target sold sales data 500 from the management device 10 (step S101). For example, the information processing device 100 acquires the target sold sales data 500 from the management device 10 via the communication unit 110, associates the sales data 500 with the target, and stores it in the storage unit 120. When the processing in step S101 is completed, the information processing device 100 proceeds to step S102.

[0057] The information processing device 100 predicts the sales trend of unsold items from the sales history of the target items (step S102). For example, the information processing device 100 inputs the target sales data 500 into the prediction model 400, and when the prediction model 400 outputs the predicted sales trend of the target unsold items, the information processing device 100 obtains the sales trend as a prediction result. For example, the information processing device 100 may use a prediction program to predict (calculate) the sales trend of the target unsold items from the target sales data 500. When the processing in step S102 is completed, the information processing device 100 proceeds to step S103.

[0058] The information processing device 100 determines whether or not to perform a trend determination on the target product (step S103). For example, the information processing device 100 determines to perform a trend determination on the target product when it detects that a predetermined number of days have passed since the product to be determined was put on sale, or when a trend determination is requested from an external source. If the information processing device 100 determines not to perform a trend determination on the target product (No in step S103), it returns to step S103 and continues processing. If the information processing device 100 determines to perform a trend determination on the target product (Yes in step S103), it proceeds to step S104.

[0059] The information processing device 100 obtains the latest sales data 500 of the target from the management device 10 (step S104). For example, the information processing device 100 obtains the latest sales data 500 of the target that has been sold from the management device 10 via the communication unit 110, associates the sales data 500 with the target, and stores it in the storage unit 120. In other words, the information processing device 100 obtains sales data 500 that shows the sales history of the latest sales item of the target for determination, for a predetermined number of days after it was released. When the processing in step S104 is completed, the information processing device 100 proceeds to step S105.

[0060] The information processing device 100 determines whether or not the target has become popular (step S105). For example, the information processing device 100 compares the actual sales trend shown by the latest sales data 500 of the target with the sales trend of the target predicted in step S102, and determines that the target has become popular if the actual sales trend is higher than the predicted sales trend. When the processing in step S105 is completed, the information processing device 100 proceeds to step S106.

[0061] The information processing device 100 notifies the determination data 700 (step S106). For example, the information processing device 100 generates determination data 700 indicating the determination result of step S105 based on sales data 500, etc., and executes a notification process to notify the determination data 700. The notification process includes at least one process, such as sending the determination data 700 via the communication unit 110 to notify, displaying the determination data 700 on a display device, or registering the determination data 700 in a database, etc. When the process of step S106 is completed, the information processing device 100 terminates the processing procedure shown in Figure 7.

[0062] In the processing procedure shown in Figure 7, steps S101 to S102 and steps S104 to S106 may be different processing procedures.

[0063] [5. Variations] The information processing device 100 described above may be implemented in various other forms besides those described above. Therefore, other embodiments of the information processing device 100 will be described below.

[0064] The information processing device 100 can predict sales trends not only using sales data 500 from volume 1, but also using data from any volume to any volume. The information processing device 100 may be configured to predict sales trends and future trends for volumes sold over a certain period in the future, rather than predicting sales trends for a specific volume in the future.

[0065] The information processing device 100 has been described in a case where it predicts the sales trends of unsold target products based on the sales history of target products, but it is not limited to this. For example, the information processing device 100 may predict the sales trends of unsold target products from the sales history of similar products that have similar characteristics to the target product.

[0066] The information processing system 1 has been described as comprising a management device 10 and an information processing device 100, but is not limited to this configuration. For example, the information processing device 100 may be incorporated into the management device 10, terminal device 20, etc.

[0067] [6. Program] Furthermore, the information processing device 100 according to the above-described embodiment is realized by a computer 1000 having a configuration as shown in Figure 8. Figure 8 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a cache 1040, a memory 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0068] The arithmetic unit 1030 operates based on programs stored in the cache 1040 and memory 1050, as well as programs read from the input device 1020, and executes various processes. The cache 1040 is a memory device, such as RAM, that temporarily stores data used by the arithmetic unit 1030 for various calculations. The memory 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is implemented using ROM (Read Only Memory), HDD (Hard Disk Drive), flash memory, etc.

[0069] Output IF1060 is an interface for transmitting information to be output to output devices 1010, which output various types of information such as monitors and printers. It is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). Input IF1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, and scanners. It is implemented using, for example, USB.

[0070] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), tape media, magnetic recording media, or semiconductor memory. Furthermore, the input device 1020 may also be an external storage medium such as a USB memory stick.

[0071] Network IF1080 receives data from other devices via network N and sends it to the arithmetic unit 1030, and also transmits data generated by the arithmetic unit 1030 to other devices via network N.

[0072] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or memory 1050 onto the cache 1040 and executes the loaded program.

[0073] For example, when computer 1000 functions as an information processing device 100, the arithmetic unit 1030 of computer 1000 realizes the functions of the control unit 130 by executing a program loaded on the cache 1040.

[0074] [7. Other] Furthermore, among the processes described in the above embodiments and modifications, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0075] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0076] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0077] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit.

[0078] [8. Effects] The information processing device 100 according to the above-described embodiment 1 includes a prediction unit 132 that predicts the sales trend of an unsold second product of the target based on the sales history of a first product of the target that has already been sold, and a determination unit 133 that determines whether or not the target has become popular based on a comparison result between the predicted sales trend of the second product of the target and the sales trend of the second product of the target that has actually been sold.

[0079] In this way, the information processing device 100 can predict the sales trend of the unsold (future) second product from the sales history of the first product that has already been sold, and determine whether the product has become popular based on the comparison result between the predicted sales trend and the actual sales trend of the second product. As a result, when selling the product in stages, the information processing device 100 can determine whether the product is popular based on its sales trend, thus enabling a quick understanding of whether the product is popular.

[0080] Furthermore, in embodiment 2, the information processing device 100 described in embodiment 1 has a prediction unit 132 that uses training data having sales data 500 of the first and second products to be learned, and uses a prediction model 400 that has been trained to predict the sales trend of the second product from input sales history data to predict the sales trend of the second product.

[0081] As described above, the information processing device 100 according to embodiment 2 can predict the sales trend of a second product by inputting the sales data 500 of the first product into the prediction model 400. As a result, the information processing device 100 can improve the accuracy of predicting the sales trend of the second product, which is predicted from the sales data 500 of the target first product, and thus can also improve the accuracy of determining whether or not the target product is trending.

[0082] Furthermore, in embodiment 3, the information processing device 100 described in embodiment 2 has a prediction unit 132 that uses training data having the characteristics of the learning target and sales data 500 of the first and second products to predict the sales trend of the second product using a prediction model that has been trained to predict the sales trend of the second product from the input sales history data.

[0083] Thus, the information processing device 100 according to embodiment 3 can predict the sales trend of the second product by using an appropriate prediction model 400 that has been machine-trained considering the characteristics of the target product. As a result, the information processing device 100 can further improve the accuracy of predicting the sales trend of the second product, which is predicted from the sales data 500 of the target first product, and thus can also improve the accuracy of determining whether or not the target product is trending.

[0084] Furthermore, in embodiment 4, the information processing device 100 described in embodiment 2 or 3 determines that the target product has become popular if the sales trend of the second product actually sold exceeds the predicted sales trend of the second product.

[0085] Thus, the information processing device 100 according to embodiment 4 can determine whether or not a product has become popular simply by comparing the sales trends of the second product that has actually been sold with the predicted sales trends of the second product. As a result, when selling the product in stages, the information processing device 100 can easily determine whether or not a product has become popular based on the sales trends of the products that have already been sold.

[0086] Furthermore, the information processing device 100 described in any one of embodiments 2 to 4, in embodiment 5, is a model trained to predict the sales trend of the second product from input sales history data and type, using training data which has the characteristics of the target to be learned and the sales data of the first product and the second product for each type of target purchaser; the prediction unit 132 uses the prediction model 400 to predict the sales trend of the unsold second product for each type of target purchaser; and the determination unit 133 determines whether the target product was popular among the purchaser type based on the comparison result between the predicted sales trend of the second product and the sales trend of the second product that was actually sold.

[0087] Thus, the information processing device 100 according to embodiment 5 can determine whether or not a target product has become popular simply by comparing the sales trends of the second product actually sold with the predicted sales trends of the second product for each type of purchaser. As a result, when selling the target product in stages, the information processing device 100 can easily determine the popularity of the target product for each type of purchaser based on the sales trends of the target product already sold.

[0088] Furthermore, in the information processing device 100 described in any one of embodiments 1 to 5, embodiment 6 is defined as follows: the target is a product consisting of multiple volumes; the prediction unit 132 predicts the number of sales of the second product from the number of sales of the first product already sold; and the determination unit 133 determines that the target has become popular if the actual number of sales of the second product is greater than the predicted number of sales of the second product, and the difference exceeds a predetermined threshold.

[0089] Thus, the information processing device 100 according to embodiment 6 can determine whether or not a product has become popular simply by comparing the number of second products actually sold with the number of second products predicted to be sold. As a result, when selling a product in stages, the information processing device 100 can easily determine the popularity of the product from the number of products already sold.

[0090] The information processing method according to the above-described embodiment 7 is an information processing method performed by a computer, which includes predicting the sales trend of an unsold second product of the subject from the sales history of a first product of the subject that has already been sold, and determining whether or not the subject has become popular based on the result of comparing the predicted sales trend of the second product with the sales trend of the second product that was actually sold.

[0091] Thus, the information processing method according to Embodiment 7 allows a computer to predict the sales trend of an unsold (future) second product from the sales history of a first product that has already been sold, and to determine whether the product has become popular based on a comparison between the predicted sales trend and the actual sales trend of the second product. As a result, when the product is sold in stages, the information processing method can determine whether the product is popular based on its sales trend, thus enabling a quick assessment of whether the product is popular.

[0092] The information processing program according to the above-described embodiment 8 causes the computer to perform the following: predict the sales trend of the unsold second product of the target based on the sales history of the first product of the target that has already been sold; and determine whether or not the target has become popular based on the comparison result between the predicted sales trend of the second product of the target and the sales trend of the second product that was actually sold.

[0093] Thus, the information processing program according to embodiment 8 can predict the sales trend of the unsold (future) second product from the sales history of the first product that has already been sold, and determine whether the product has become popular based on the comparison result between the predicted sales trend and the actual sales trend of the second product. As a result, when the product is sold in stages, the information processing program can determine whether the product has become popular from its sales trend, and can quickly grasp whether the product is popular.

[0094] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention. [Explanation of Symbols]

[0095] 1. Information Processing System 10 Management device 20 Terminal devices 100 Information Processing Devices 110 Communications Department 120 Storage section 121 Sales data storage unit 122 Predictive Model Memory Unit 123 Judgment Data Storage Unit 130 Control Unit 131 Acquisition Department 132 Prediction Section 133 Judgment section 134 Provision Department 400 Predictive Models 500 Sales Data 600 scatter plot 700 judgment data N Network

Claims

1. A prediction unit that predicts the sales trend of the unsold second product based on the sales history of the first product that has already been sold, A determination unit that determines whether the target product became popular based on a comparison of the predicted sales trend of the second product and the actual sales trend of the second product, Equipped with, The prediction unit uses training data containing sales data for the first and second products to be learned, and uses a prediction model that has been machine-trained to predict the sales trend of the second product from the input sales history data to predict the sales trend of the second product. An information processing device characterized by the following:

2. The prediction unit uses training data having the characteristics of the learning target and sales data of the first and second products to predict the sales trend of the second product using the prediction model which has been machine-trained to predict the sales trend of the second product from the input sales history data. The information processing apparatus according to feature 1.

3. The determination unit determines that the target product has become popular if the sales trend of the second product actually sold exceeds the sales trend of the second product predicted above. The information processing apparatus according to feature 2.

4. The prediction model is a machine learning model that predicts the sales trend of the second product from the input sales history data and the type, using training data which includes the characteristics of the target and the sales data of the first and second products for each type of target purchaser. The prediction unit uses the prediction model to predict the sales trends of the unsold second product for each type of target buyer. The determination unit determines whether the target product was popular among the types of buyers based on the comparison result between the predicted sales trend of the second product and the actual sales trend of the second product. The information processing apparatus according to feature 1.

5. The aforementioned subject is a product consisting of multiple volumes, The prediction unit predicts the number of sales of the second product from the number of sales of the first product already sold. The determination unit determines that the target product has become popular if the actual number of the second product sold is greater than the predicted number of the second product sold, and the difference exceeds a predetermined threshold. The information processing apparatus according to feature 1.

6. A method of information processing performed by a computer, Based on the sales history of the first product already sold, predict the sales trend of the second product, which has not yet been sold. Based on the comparison of the predicted sales trend of the second product with the actual sales trend of the second product, it is determined whether or not the subject became popular. Includes, Using training data containing sales data for the first and second products to be learned, a predictive model trained on machine learning to predict the sales trend of the second product from the input sales history data is used to predict the sales trend of the second product. An information processing method characterized by the following:

7. Based on the sales history of the first product already sold, predict the sales trend of the second product, which has not yet been sold. Based on the comparison of the predicted sales trend of the second product with the actual sales trend of the second product, it is determined whether or not the subject became popular. Have the computer run it, Using training data containing sales data for the first and second products to be learned, a predictive model trained on machine learning to predict the sales trend of the second product from the input sales history data is used to predict the sales trend of the second product. An information processing program characterized by the following features.

Images