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

Abstract

To estimate a need for a commodity.SOLUTION: An information processing device includes: an acquisition unit that obtains an answer history including both a question about a commodity which is input to a model that generates an answer to an input question and an answer by the model; and an estimation unit that estimates a need for the commodity by analyzing the answer history obtained by the acquisition unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Conventionally, with the rapid spread of the Internet, for example, techniques related to analysis using various information on the Internet have been provided. For example, a technique has been proposed for extracting information related to needs for products based on a search query entered by a user in an online shopping mall (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-32776 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional techniques leave room for improvement in estimating product needs.

[0005] The present invention has been made in view of the above, and has an object to provide an information processing device, an information processing method, and an information processing program capable of estimating needs for a product. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the objective, the information processing device of the present invention includes an acquisition unit that acquires an answer history including questions about a product input to a model that generates answers to the input questions and answers from the model, and an estimation unit that analyzes the answer history acquired by the acquisition unit and estimates needs for the product. Effect of the Invention

[0007] According to the present invention, the needs for a product can be estimated with high accuracy. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of information stored in an answer history storage unit according to the embodiment. [Figure 4] FIG. 4 is an explanatory diagram of the estimation process according to the embodiment. [Diagram 5] FIG. 5 is an explanatory diagram of the estimation process according to the embodiment. [Figure 6] FIG. 6 is a flowchart illustrating an example of a processing procedure of the providing process according to the embodiment. [Figure 7] FIG. 7 is an explanatory diagram regarding the visibility of a product according to the embodiment. [Figure 8] FIG. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0010] [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that the information processing according to the embodiment is realized by an information processing device 1 shown in Fig. 1.

[0011] 1 is, for example, an information processing device that operates various online shopping malls. As described later, the information processing device 1 estimates needs for products and provides information on the estimated needs for the products to various manufacturers, sellers in the online shopping malls, etc.

[0012] The user terminal 100 shown in Fig. 1 is a terminal device owned by a user U. For example, the user U can operate the user terminal 100 to access an online shopping mall operated by the information processing device 1 and view and purchase products. Note that, although Fig. 1 illustrates an example in which the user terminal 100 is a smartphone, the user terminal 100 may be other devices such as a PC (Personal Computer).

[0013] The information providing device 200 shown in FIG. 1 has a model. The model is, for example, a sentence generation model that learns data published on the Web. For example, the model is a Generative Pre-trained Transformer (GPT) model that generates answers to questions. The model may be implemented in the information processing device 1.

[0014] By the way, such models generate answers to questions from data published on the Web. Since new data is published on the Web every day, the answers generated by the models are updated every day.

[0015] That is, even if the same question is asked, the model will generate different answers depending on the time of the question, etc., because the data that the model refers to when generating the answer differs. Also, since the model can provide detailed answers to questions in a wide range of fields, a wide variety of questions are asked of the model by the user U.

[0016] In this embodiment, focusing on this point, the needs for the product are estimated using the answer history of the model. Specifically, as shown in Fig. 1, the information providing device 200 accepts a question from a user U through the user terminal 100 (step S1), and provides an answer generated by the model to the user terminal 100 in a conversational format (step S2).

[0017] For example, in the example shown in Figure 1, user U's question is "Do they sell eyeshadow for deep-set eyelids?" and the answer is "They don't sell eyeshadow for deep-set eyelids." In other words, user U's question indicates that there is a need for "eyeshadow for deep-set eyelids," and the answer suggests that "eyeshadow for deep-set eyelids" is not sold.

[0018] The information processing device 1 acquires an answer history including questions and answers from the information providing device 200 (step S3), and estimates needs for the product by analyzing the answer history (step S4).

[0019] FIG. 1 shows a graph with two axes: the vertical axis shows the proportion of the model who answered "no" and the horizontal axis shows the "needs." The "proportion of the model who answered "no" indicates the proportion of the model's answers to questions about the corresponding product that suggest that the product does not exist. The "proportion of the model who answered "no" may include the proportion of the model who did not answer appropriately to the product. For example, in response to a question about "eyeshadow for deep-set eyelids," the model answers about "deep-set eyelids" or "eyeshadow," and the answer is not substantially related to "eyeshadow for deep-set eyelids," and the answer may be classified as "answer that does not exist." The needs on the horizontal axis shown in FIG. 1 correspond to the number of questions by user U about the corresponding product.

[0020] The information processing device 1 estimates the needs for each product by mapping the response history of each product on a graph. Figure 1 shows the estimation results for "Washing machine for leather," "Eye shadow for double eyelids," and "Eyebrow for thick eyebrows."

[0021] In the example shown in Figure 1, the "leather washing machine" suggests that there is little demand and that it is a product that has not yet been sold, while the "thick eyebrow pencil" suggests that there is a high demand but that it is already on sale.

[0022] It also suggests that "eye shadow for deep-set double eyelids" is a product that is in high demand but has not yet been sold. In other words, there is little demand for a "leather washing machine," so there is little benefit to selling (developing) the product, while "eyebrow products for thick eyebrows" are already on the market and already have a certain market share. On the other hand, it suggests that although "eye shadow for deep-set double eyelids" is not a product that exists, a certain demand can be expected.

[0023] For example, the information processing device 1 generates content related to a product that is in demand but not yet sold, such as "eye shadow for double eyelids," and provides the content to a business operator (manager) of an online shopping mall.

[0024] This allows operators of online shopping malls to take actions such as proposing new products and joint development to manufacturers and sellers on the online shopping mall based on such content.

[0025] For example, the information processing device 1 can propose new products that combine multiple keywords, such as "for deep-set eyes" and "eye shadow," to suggest products that are in demand but not on sale, i.e., products that have not previously captured demand.

[0026] In this way, the information processing device 1 according to the embodiment acquires an answer history including questions about a product input to a model that generates answers to input questions and answers by the model, analyzes the answer history, and estimates needs for the product. Therefore, the information processing device 1 according to the embodiment can estimate needs for a product.

[0027] In addition, since the demand for models that answer questions in a conversational format is expected to increase in the future, it is expected that the models will accumulate an even greater number of questions in the future. Therefore, the information processing device 1 can estimate the needs for a wide range of products by analyzing the response history of the models.

[0028] [2. Information Processing Device] Next, a configuration example of the information processing device 1 according to the embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in Fig. 2, the information processing device 1 includes a communication unit 2, a storage unit 3, and a control unit 4. Note that the information processing device 1 may also include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator who uses the information processing device 1, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0029] The communication unit 2 is realized by, for example, a network interface card (NIC) etc. The communication unit 2 is connected to a communication network such as 4G (4th Generation) or 5G (5th Generation) by wire or wirelessly, and transmits and receives information to and from each of the user terminal 100, the information providing device 200, etc. via the communication network.

[0030] The storage unit 3 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk.

[0031] The answer history storage unit 31 stores an answer history. The answer history is a history of questions posed to a model and answers. Fig. 3 is a diagram showing an example of information stored in the answer history storage unit 31 according to the embodiment.

[0032] 3, the answer history storage unit 31 stores information items such as "question," "answer," and "date and time" in association with each other. "Question" indicates the content of a question that the user U asked the model.

[0033] "Answer" indicates the content of the answer output by the model to the corresponding question. "Date and time" indicates the date and time when the user U asked the model a question. Note that, if information on the attributes of the user U who asked the question can be obtained, the answer history storage unit 31 may store the information on the attributes of the user U in association with the answer.

[0034] Returning to the explanation of Fig. 2, the control unit 4 will be explained. The control unit 4 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM as a working area. The control unit 4 is also, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0035] As shown in Fig. 2, the control unit 4 includes an acquisition unit 41, an estimation unit 42, and a provision unit 43, and realizes or executes the functions and actions of information processing described below. The internal configuration of the control unit 4 is not limited to the configuration shown in Fig. 2, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationship between the processing units in the control unit 4 is not limited to the connection relationship shown in Fig. 2, and may be other connection relationships.

[0036] The acquisition unit 41 acquires an answer history including questions about products input to a model that generates answers to input questions and answers by the model. For example, the acquisition unit 41 acquires the answer history from the information providing device 200 (see FIG. 1) at a predetermined period.

[0037] For example, the acquisition unit 41 acquires a question about each product sold in the online shopping mall and an answer history including the answer. The acquisition unit 41 may acquire the answer history by asking the information providing device 200 the same question about a specific product at a predetermined period and acquiring the answer.

[0038] For example, the acquisition unit 41 repeatedly asks questions previously asked by the user U or questions set by an administrator or the like at a predetermined cycle, and acquires the answer history of these. For example, in the example of Fig. 1, the acquisition unit 41 repeatedly asks the question "Do they sell eye shadow for deep-set eyelids?" asked by the user U at a predetermined cycle, and acquires the answer history of these.

[0039] The estimation unit 42 estimates needs for the product by analyzing the answer history acquired by the acquisition unit 41. For example, the estimation unit 42 estimates needs from the number of questions about the product included in the answer history, and estimates the sales status of the product from the content of the answers included in the answer history.

[0040] For example, the estimation unit 42 extracts questions and answers about each product from the answer history by a predetermined language analysis. Next, the estimation unit 42 counts the number of questions about each product, and estimates that the greater the number of questions, the greater the need for that product. Note that when counting the number of questions, the estimation unit 42 excludes questions asked by the acquisition unit 41 from the counting target.

[0041] In addition, the estimation unit 42 classifies answers into answers suggesting that a corresponding product exists and answers suggesting that a corresponding product does not exist by performing a predetermined language analysis on the contents of answers included in the answer history. The estimation unit 42 estimates the sales status of the product according to the tendency of answers suggesting that a corresponding product exists and answers suggesting that a corresponding product does not exist.

[0042] For example, the sales status of a product is classified into a situation where the product is already on sale and a situation where the product is not on sale, but also includes, for example, a situation where the product is not on sale but has been decided to be sold.

[0043] The estimation unit 42 collects questions asked in a predetermined time period (for example, one week or one month) and analyzes the tendency between answers suggesting that a corresponding product exists and answers suggesting that a corresponding product does not exist. The result of such analysis indicates the change in sales status for each period.

[0044] The estimation unit 42 may estimate the time when the product was sold from a time series change in the answers to the product. For example, the estimation unit 42 estimates that the time when the ratio of answers suggesting the existence of a corresponding product started to increase is the time when the product was sold.

[0045] Fig. 4 is an explanatory diagram of the estimation process according to the embodiment. Fig. 4 shows answers about a product before and after the product is newly released. As shown in Fig. 4, the estimation unit 42 analyzes the time-series change in questions about the same product.

[0046] In the example shown in Figure 4, at time t2, the answer is "They don't sell eye shadow for deep-set eyes," and at a later time t3, the answer is "It seems that eye shadow for deep-set eyes is sold at XX (store name)."

[0047] That is, the response shown in Figure 4 indicates that the product was already on sale at time t3, and that the product was not on sale before time t2. In other words, it suggests that "eye shadow for deep-set eyelids" was on sale during the period from time t2 to time t3.

[0048] At this time, the estimation unit 42 may estimate the time when the product was sold according to the transition of the abstraction level of the answer about the product. For example, the estimation unit 42 may estimate the time when the product was sold as the time when the answer about the product changed from the presence or absence of the product to specific information about the product, such as "It seems that a new color has been released" or "It seems to be sold at XX". Note that the estimation unit 42 may estimate the time when the product was sold according to the transition of the abstraction level of the question in addition to the answer. In other words, the estimation unit 42 may estimate the time when the product was sold as the time when the question of the user U became more specific.

[0049] The estimation unit 42 can also estimate needs for products that have already been sold. Fig. 5 is an explanatory diagram of the estimation process according to the embodiment. For example, the estimation unit 42 classifies answers included in a specific product from the answer history into positive answers and negative answers.

[0050] Then, the estimation unit 42 estimates the needs for products that have already been sold according to the changes in these ratios. More specifically, as shown in Fig. 5, if the ratio of positive responses to negative responses increases over time, it is estimated that there is a risk of the future market size decreasing. On the other hand, if the ratio of negative responses to positive responses increases over time, it is estimated that there is a possibility of the future market size increasing.

[0051] The answers may be classified into categories such as "cheap" and "expensive," "dangerous" and "safe," "easy to use" and "difficult to use," "difficult to obtain" and "in stock," etc., and the estimation unit 42 may estimate the future increase or decrease in the market size based on the results of these classifications.

[0052] Returning to the explanation of Fig. 2, the providing unit 43 will be explained. The providing unit 43 provides information on products whose needs estimated by the estimation unit 42 exceed a threshold and that are not on sale. The providing unit 43 extracts products whose needs are estimated to be equal to or above a certain level and that are not yet on sale, from the estimation result on needs by the estimation unit 42.

[0053] For example, the providing unit 43 provides information on products that are in demand but are not yet available on the market to operators of online shopping malls. This enables operators of online shopping malls to propose highly original products that are differentiated from existing products.

[0054] [3. Processing flow] Next, a process procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the process procedure of the providing process according to the embodiment.

[0055] 7, the information processing device 1 acquires a response history from the information providing device 200 (step S101). Next, the information processing device 1 estimates the needs of each product from the acquired response history (step S102).

[0056] Next, the information processing device 1 extracts products that are in demand and are not on sale (step S103), and then provides content related to the extracted products (step S104).

[0057] 4. Modifications In the above embodiment, the case where the needs for a product and the sales status of the product are estimated has been described, but the present invention is not limited to this. For example, the recognition level of a product may be estimated.

[0058] Here, an example of the awareness of a product will be described with reference to Fig. 7. Fig. 7 is an explanatory diagram relating to the awareness of a product according to an embodiment. For example, the information processing device 1 asks the model a question such as "What is AAA (product name)?" a predetermined number of times and acquires a response history.

[0059] The information processing device 1 classifies the answers included in the answer history into a plurality of categories, and obtains, for example, the histogram shown in Fig. 7. Note that Fig. 7 shows a case where the answers of the model are classified into categories F1 to F5, and it is assumed that recognition increases from category F1 to category F5.

[0060] In the example shown in Figure 7, the proportion of category F3 is the highest, indicating that the current awareness of "AAA" corresponds to the level of category F3, and that the current awareness is at the third stage.

[0061] In this way, the information processing device 1 classifies each answer into each category and estimates the awareness of the product according to the ratio of these categories. This makes it possible to appropriately estimate the awareness. Note that the information processing device 1 may also ask the model a question such as "Which demographic (user attribute) is it popular with?"

[0062] The information processing device 1 may also compare the answers of multiple models trained with different data sources to estimate needs. For example, the same question is asked to each of the multiple models at the same time, and the answers are compared to estimate needs. That is, in this case, if one model and the other model give the same answer, it can be estimated that the level of understanding is low or that there are pros and cons, and if both models give the same answer, it can be estimated that it has become common knowledge. Note that both models may be trained using data sources with different user demographics, for example.

[0063] The information processing device 1 may estimate the awareness of a product according to the degree of dispersion of answers to the same model. In other words, it can be estimated that the more the answers are dispersed, the lower the level of understanding is, or that there are mixed opinions, and that the more the answers are converged, the more common knowledge is obtained.

[0064] Furthermore, in the above-described embodiment, the model outputs text as an answer. However, the output by the model may be other content such as an image, music, or video.

[0065] 5. Effects The information processing device 1 according to the embodiment includes an acquisition unit 41 that acquires a response history including questions about a product input to a model that generates responses to the input questions and responses from the model, and an estimation unit 42 that analyzes the response history acquired by the acquisition unit 41 and estimates needs for the product.

[0066] The estimation unit 42 estimates the needs from the number of questions about the product included in the answer history, and estimates the sales status of the product from the contents of the answers included in the answer history. The information processing device 1 also includes a provision unit 43 that provides information about products whose needs estimated by the estimation unit 42 exceed a threshold and are not on sale.

[0067] Furthermore, the estimation unit 42 classifies the answers included in the answer history into positive answers and negative answers, and estimates future needs for the product from changes in the trends between the positive answers and the negative answers.

[0068] By performing any one or a combination of the above-described processes, the information processing device according to the present application can estimate the needs for a product.

[0069] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0070] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0071] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0072] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 8, the output devices and the input devices are collectively referred to as "input / output devices") via an input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0073] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0074] For example, when the computer 1000 functions as an information processing device according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0075] [7. Other] Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. The above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0076] Furthermore, among the processes described in the above embodiments, 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 a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0077] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0078] For example, the above-mentioned information processing device may be realized using multiple server computers, and depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0079] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0080] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0081] 1. Information processing device 2. Communications Department 3 Storage section 4. Control section 31 Answer history memory section 41 Acquisition Department 42 Estimation part 43 Providing Department 100 user terminals 200 Information provision device

Claims

1. an acquisition unit that acquires a question about a product input to a model that generates an answer to the input question and an answer history including the answer generated by the model; an estimation unit that analyzes the response history acquired by the acquisition unit and estimates needs for the product; An information processing device comprising:

2. The estimation unit is The needs are estimated from the number of questions about the product included in the answer history, and the sales status of the product is estimated from the contents of the answers included in the answer history.

2. The information processing apparatus according to claim 1,

3. The estimation unit is Inferring the time when the product was sold from the time series changes in the responses to the product 2. The information processing apparatus according to claim 1,

4. The estimation unit is and estimating the need for the product according to the degree of dispersion of the answers included in the answer history.

2. The information processing apparatus according to claim 1,

5. a provision unit that provides information on products whose needs estimated by the estimation unit exceed a threshold and that are not on sale; To be prepared 2. The information processing apparatus according to claim 1,

6. The estimation unit is Classifying the answers included in the answer history into positive answers and negative answers, and estimating future needs for the product from changes in trends between the positive answers and the negative answers.

2. The information processing apparatus according to claim 1,

7. 1. A computer-implemented information processing method, comprising: An acquisition step of acquiring an answer history including questions about a product input to a model that generates answers to input questions and answers generated by the model; an estimation step of estimating needs for the product by analyzing the response history acquired by the acquisition step; 13. An information processing method comprising:

8. An acquisition step of acquiring an answer history including questions about products input to a model that generates answers to input questions and answers generated by the model; an estimation step of estimating needs for the product by analyzing the response history acquired by the acquisition step; An information processing program characterized by causing a computer to execute the above.

Images