Presentation device, presentation method, and presentation program

Abstract

To provide a presenting device, a presenting method, and a presenting program which present content representing an impression of an object which a user wants to know.SOLUTION: A presenting device 1 according to the present application comprises an acquisition unit 12a and a generation unit 12d. The acquisition unit 12a acquires information about a prescribed object. The generation unit 12d uses the acquired information about the object to generate content representing an impression of the object.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a presentation device, a presentation method, and a presentation program. [Background technology]

[0002] BACKGROUND ART Conventionally, there is known a technique for inputting text and presenting an impression image that represents an impression associated with the text (see Non-Patent Document 1). [Prior art documents] [Non-patent literature]

[0003] [Non-Patent Document 1] "We tried out a demo of GauGAN2, an AI that generates landscape images based on just a few words," [online], November 2021, GIGAZINE, [Retrieved January 5, 2022], Internet<URL:https: / / gigazine.net / news / 20211125-gaugan2-ai-art-responds-words / > Summary of the Invention [Problem to be solved by the invention]

[0004] However, with conventional technologies, it has been difficult to present content that expresses an impression of a tangible or intangible object that a user is interested in. For example, even if a user is interested in a brand or the atmosphere of a city and wants to know an intuitive impression rather than text, it has not been possible to present content such as an image that expresses the impression of the object.

[0005] The present application has been made in view of the above, and aims to provide a presentation device, a presentation method, and a presentation program that present content that expresses an impression of a target that a user wants to know about. [Means for solving the problem]

[0006] The presentation device according to the present application is characterized by comprising an acquisition unit that acquires information about a specified object, and a generation unit that uses the acquired information about the object to generate content that represents an impression of the object. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to provide content that expresses an impression of a subject that the user wants to know about. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of a presentation process according to the embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of the presentation device according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of target information according to the embodiment. [Figure 4] FIG. 4 is a flowchart illustrating a presentation process performed by the presentation device according to the embodiment. [Figure 5] FIG. 5 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the presentation device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, a detailed description will be given of a presentation device, a presentation method, and a presentation program (hereinafter referred to as an "embodiment") according to the present application, with reference to the drawings. Note that the presentation device, the presentation method, and the presentation program according to the present application are not limited to the embodiment. Furthermore, the same components in the following embodiments are denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0010] (Embodiment) [1. Presentation Processing] First, an example of a presentation process according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the presentation process according to the embodiment. As shown in Fig. 1, a presentation device according to the embodiment performs a presentation process in which content such as an impression image expressing an impression of a specified target such as a brand or a city is presented to a user.

[0011] 1 illustrates an example in which brand A is designated as the target. As illustrated in FIG. 1, the presentation device acquires, as information about the target, text or the like that expresses an impression of each target. For example, the presentation device collects impression information that expresses an impression of each target, such as brand A and place α, in advance by crowdsourcing or the like, and stores the information as target information 13a.

[0012] Next, when brand A is specified, the presentation device refers to the target information 13a and acquires impression information in text format, such as "bright, up-and-coming, ...," that directly or indirectly expresses the impression of brand A. The impression information may include text information that expresses shape and color. Here, the presentation device holds a model that outputs an impression image corresponding to the input text. Therefore, the presentation device inputs text that expresses the impression of brand A into the model, and presents an impression image that expresses the impression of brand A to the user.

[0013] The presentation device may also use user information including the user's attributes, characteristics, etc. to present an impression image of a target that takes into account the user's preferences. For example, the presentation device refers to the user information to obtain text information that represents the user's attributes and characteristics, such as "female, likes brand B, ...". The presentation device then inputs the text information obtained from the user information into a model in addition to the text that represents the impression obtained from the target information 13a, thereby presenting an impression image that takes into account the user's preferences. For example, for brand A, which tends to be preferred by people who like brand B, an impression image that represents a more favorable impression than when the user information is not taken into account is presented.

[0014] The presentation device can also update the model through learning using time-series changes in the impression images of the target presented to the user. In this case, the presentation device can predict the impression image of the target using the learned model. For example, the presentation device can predict the future prospects of stock prices by predicting impression images that represent stock price fluctuations using the learned model with vibrant or calm colors.

[0015] When expressing the image of an object such as a brand or a place in text, it involves various elements, which makes it time-consuming to understand and analyze changes. In contrast, a presentation device makes it possible to intuitively grasp impressions. Furthermore, by statistically analyzing the inner changes of people who use a brand or visit a place and acquiring information about impressions, it becomes possible to reflect this in impression images. Furthermore, by representing each user group, which is formed by grouping users of a service, etc., based on gender, age, interests, etc., using an impression image, it becomes possible to promote understanding of each user group.

[0016] 2. Configuration of the Presentation Device Next, the above-mentioned presentation device 1 will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of the presentation device 1 according to an embodiment. As shown in Fig. 2, the presentation device 1 includes an input / output unit 11, a control unit 12, and a storage unit 13.

[0017] (Regarding input / output unit 11) The input / output unit 11 is realized by an input device such as a microphone, a camera, a keyboard, or a mouse, and an output device such as a display or a printer. To the input / output unit 11, for example, instructions and operations by a user are input.

[0018] In addition, the presentation device 1 may have a communication unit realized by a NIC (Network Interface Card) or the like, and may send and receive information via the communication unit between a terminal device used by a user that is equipped with a microphone, camera, display, etc., or an external server, etc.

[0019] (Regarding the storage unit 13) The storage unit 13 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. As shown in Fig. 2, the storage unit 13 stores target information 13a, a model 13b, and user information 13c.

[0020] (Regarding target information 13a) The target information 13a is information about a predetermined target. FIG. 3 is a diagram showing an example of the target information according to the embodiment. As illustrated in FIG. 3, the target information 13a is information generated by associating a "target" with "impression information." The "target" is a target of the presentation process, such as a brand or a place. The "impression information" is information about each target, such as text that expresses an impression of each target. The impression information may include text that expresses the shape or color.

[0021] In the example shown in Fig. 3, the impression information "bright, up-and-coming, ..." is associated with and generated for the object "brand A." Also, the impression information "redevelopment, young people, ..." is associated with and generated for the object "place α."

[0022] The target information 13a is obtained by collecting text information expressing impressions of each target as impression information for each target in advance through crowdsourcing or the like, and storing it in the storage unit 13. This makes it possible to obtain information about impressions by statistically analyzing changes in the inner lives of people who use a brand or visit a place.

[0023] The target information 13a is generated by the acquisition unit 12a, which will be described later, by collecting impression information of each target and storing it in the storage unit 13. However, this is not limiting, and for example, the acquisition unit 12a may not store the generated target information 13a in the storage unit 13, but may immediately transmit it to a subsequent functional unit.

[0024] (About Model 13b) The model 13b is a model for outputting an impression image corresponding to input text, and is stored in advance in the storage unit 13. In the presentation process described below, an impression image is output using the impression information about the designated target of the presentation process and the model 13b.

[0025] (Regarding User Information 13c) The user information 13c is information that represents the attributes and characteristics of the user. In the presentation process described later, by inputting text information obtained from the user information 13c into the model 13b in addition to text that represents the impression obtained from the target information 13a, an impression image that takes into account the preferences of the user is output.

[0026] (Regarding the control unit 12) Returning to the explanation of Fig. 2, the control unit 12 is a controller, and is realized by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to examples of presentation programs) stored in a storage device inside the presentation device 1 using RAM as a working area. The control unit 12 is also realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0027] As shown in FIG. 2, the control unit 12 has an acquisition unit 12a, a reception unit 12b, a learning unit 12c, and a generation unit 12d, and realizes or executes the functions and actions of the presentation process described below.

[0028] (Regarding the acquisition unit 12a) The acquisition unit 12a acquires information about a predetermined target. Specifically, the acquisition unit 12a collects text information about the predetermined target. Here, the predetermined target includes at least one of a brand, a place, and a security. For example, the acquisition unit 12a collects text information expressing an impression of the target in advance by crowdsourcing or the like as impression information, and stores the collected text information in the storage unit 13.

[0029] For example, the words that are ranked highly in the results of a survey about impressions of brand A or place α are acquired as impression information. This enables the acquiring unit 12a to acquire statistical information on inner changes of people who use brand A or visit place α.

[0030] The acquiring unit 12a collects and generates impression information of each target and stores it in the storage unit 13, but is not limited to this. For example, the acquiring unit 12a may immediately transmit the impression information of each target to the generating unit 12d without storing it in the storage unit 13.

[0031] (Regarding the reception unit 12b) The reception unit 12b receives a target to be provided to a user. For example, the reception unit 12b receives an operation by a user to specify a target for the presentation process described below via the input / output unit 11. Alternatively, the reception unit 12b may estimate a target that the user is interested in based on the user's search history, and receive the estimated target as a target for the presentation process.

[0032] (Regarding learning section 12c) The learning unit 12c learns the model 13b using time-series changes in the impression image. Specifically, the learning unit 12c updates the model 13b through learning using time-series changes in the impression image of the target generated by the generating unit 12d (described later) and presented to the user. By using the trained model 13b in this way, the generating unit 12d (described later) can predict the impression image of the target. For example, by predicting an impression image that represents the fluctuation phase of the stock price with the vividness or calmness of colors, it becomes possible to predict the future prospects of the stock price.

[0033] (Regarding the generation unit 12d) The generation unit 12d uses information about the acquired object to generate content that represents an impression of the object. For example, the generation unit 12d uses the model 13b to generate an impression image that represents an impression of the acquired object. Specifically, the generation unit 12d outputs an impression image for the object accepted by the acceptance unit 12b using the impression information about the accepted object and the model 13b. The generation unit 12d presents the output impression image to the user via, for example, the input / output unit 11.

[0034] For example, when a user designates "Brand A," the generation unit 12d refers to the target information 13a to acquire text information "bright, up-and-coming, ..." as impression information of "Brand A," and inputs the text information into the model 13b. As a result, the generation unit 12d outputs an impression image of Brand A, as illustrated in FIG. 1.

[0035] The generation unit 12d may generate content that expresses an impression of a target by taking the user information 13c into consideration. That is, the generation unit 12d may generate content that expresses an impression of a target by using the user information 13c and the acquired information about the target for the accepted target.

[0036] For example, the generation unit 12d refers to the user information 13c to acquire text information such as "female, likes brand B, ..." that represents the attributes and characteristics of the user. Then, the generation unit 12d inputs the text information acquired from the user information into the model 13b in addition to the text information representing the impression acquired from the target information 13a. This enables the generation unit 12d to output an impression image that takes into account the preferences of the user. For example, if brand A tends to be preferred by people who like brand B, it is possible to output an impression image that expresses a more favorable impression of brand A than when the user information is not taken into account.

[0037] Furthermore, when the learning unit 12c updates the model 13b through learning, the generation unit 12d predicts an impression image that expresses the impression of the target using the learned model 13b. This enables the generation unit 15d to predict the future prospects of stock prices, for example, by predicting an impression image that expresses the fluctuation phase of stock prices with vibrant or calm colors.

[0038] [3. Processing Procedure] Next, a processing procedure executed by the presentation device 1 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a flowchart showing a presentation processing procedure executed by the presentation device 1 according to the embodiment.

[0039] 4, in the presentation device 1, first, when a user inputs a processing target via the input / output unit 11, the receiving unit 12b receives the input (step S1). Alternatively, the receiving unit 12b estimates a target that the user is interested in based on the user's search history, and receives the input as a target for presentation processing.

[0040] The acquiring unit 12a acquires information about the target (step S2). For example, the acquiring unit 12a collects target information 13a about each target in advance, and the generating unit 12d refers to the target information 13a to acquire information about the target, such as text that expresses an impression of the accepted target.

[0041] Then, the generation unit 12d generates content that expresses an impression of the object using the acquired information about the object (step S3). For example, the generation unit 12d inputs text that expresses an impression about the object into the model 13b, thereby generating an impression image that expresses the impression of the object. The generation unit 12d also presents the generated content to the user via the input / output unit 11 (step S4). This completes a series of presentation processes.

[0042] [4. Effects] As described above, the presentation device 1 according to the embodiment includes the acquisition unit 12a and the generation unit 12d. The acquisition unit 12a acquires information about a predetermined target. The generation unit 12d uses the acquired information about the target to generate content that expresses an impression of the target. This makes it possible to present content such as images that express an intuitive impression of a target that the user wants to know about.

[0043] The presentation device 1 according to the embodiment further includes a storage unit 13. The storage unit 13 stores a model 13b that outputs an impression image corresponding to input text. In this case, the acquisition unit 12a collects text information related to a predetermined object. The generation unit 12d uses the model 13b to generate an impression image that represents the impression of the acquired object. This makes it possible to present an impression image that reflects, for example, statistical information related to the object.

[0044] The presentation device 1 according to the embodiment further includes a receiving unit 12b. In this case, the storage unit 13 stores user information 13c including at least one of information representing the user's attributes and characteristics. The receiving unit 12b receives an object to be provided to the user. The generating unit 12d generates content representing an impression of the received object using the user information 13c and the acquired information about the object. This makes it possible to present content representing an impression taking into account the user's preferences.

[0045] In addition, in the presentation device 1 according to the embodiment, the predetermined object includes at least one of a brand, a place, and a security, which makes it easy to grasp an intuitive impression of an object that is not easy to understand through text.

[0046] The presentation device 1 according to the embodiment further includes a learning unit 12c. The learning unit 12c learns the model 13b using time-series changes in the impression image. In this case, the generation unit 12d predicts an impression image representing an impression of the target using the learned model 13b. This makes it easy to intuitively predict the future prospects of the target.

[0047] [5. Hardware Configuration] The presentation device 1 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in Fig. 5. Fig. 5 is a hardware configuration diagram showing an example of the computer 1000 that realizes the functions of the presentation device 1 according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0048] The CPU 1100 operates and controls each unit based on programs 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 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0049] 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 the network N and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0050] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the 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.

[0051] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. 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.

[0052] For example, when the computer 1000 functions as the presentation device 1 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 12. In addition, the HDD 1400 stores data in the storage unit 13. 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.

[0053] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0054] [6. Other] 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 using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0055] Furthermore, the components of each device shown in the figure are conceptual functional components and do 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 depending on various loads, usage conditions, etc.

[0056] Furthermore, the processes described in the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the process contents.

[0057] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, the reception unit 12b can be read as reception means or reception circuit. [Explanation of symbols]

[0058] 1 Presentation device 11 Input / output section 12 Control Unit 12a Acquisition part 12b Reception 12c Learning Department 12d generator 13 Storage section 13a Target Information 13b model 13c User information

Claims

1. an acquisition unit that acquires information about a predetermined target; a generation unit that generates content expressing an impression of the object using the acquired information about the object; a storage unit that stores a model that outputs an impression image corresponding to an input text; Equipped with the acquisition unit collects text information related to the predetermined subject; the generation unit generates an impression image representing the obtained impression of the object using the model; a learning unit that learns the model using time-series changes in the impression image; Furthermore, The generation unit predicts an impression image representing an impression of the subject using the trained model. A presentation device characterized by:

2. a storage unit that stores user information including at least one of information representing attributes or characteristics of a user; A reception unit that receives an object to be provided to a user, The generation unit generates content expressing an impression of the received object using the user information and the acquired information about the object. The presentation device according to claim 1 .

3. The presentation device according to claim 1 , wherein the predetermined object includes at least one of a brand, a place, and a security.

4. 1. A computer-implemented presentation method comprising: an acquisition step of acquiring information related to a predetermined subject; a generating step of generating content representing an impression of the object using the acquired information about the object; Including, A model for outputting an impression image corresponding to the input text is stored in a storage unit; The acquiring step collects text information related to the predetermined subject, the generating step generates an impression image representing the obtained impression of the object using the model; a learning step of learning the model using time-series changes in the impression image; further comprising The generating step predicts an impression image representing an impression of the subject using the trained model. A presentation method characterized by:

5. an acquisition procedure for acquiring information about a predetermined subject; a generation step of generating content representing an impression of the object using the acquired information about the object; on the computer, A model for outputting an impression image corresponding to the input text is stored in a storage unit; The obtaining step collects text information related to the predetermined subject; the generating step uses the model to generate an impression image representing the obtained impression of the object; a learning procedure for learning the model using time-series changes in the impression image; Then, the computer executes The generation procedure uses the trained model to predict an impression image representing the impression of the subject. A presentation program characterized by:

Images