Information processing system, information processing method and program

Abstract

To provide an information processing system that determines the tone of item descriptions based on user preference data.SOLUTION: In an information processing system where a server device and a client device are connected via a network for communication, the server device has at least one control unit 210. The control unit 210 acquires user preference data based on an item purchase history, browsing history, retrieval history, SNS contribution content, etc. of the user. The tone of the item description is determined based on the preference data. The item description is converted based on the determined tone. The converted item description is outputted to the user.SELECTED DRAWING: Figure 2

Description

[Technical Field]

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

[0002] Patent Document 1 discloses a technology that recommends places similar to a user's favorite places by reflecting the user's explicit preferences. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-91701 Summary of the Invention [Problem to be solved by the invention]

[0004] Even if a system exists that recommends items that match a user's preferences, the descriptions of the items are uniform, and as a result, users may not select the recommended items. In Patent Document 1, places similar to the user's favorite places are recommended, but the way the recommendation is expressed does not change depending on the user. [Means for solving the problem]

[0005] According to one aspect of the present invention, there is provided an information processing system. The information processing system has at least one or more control units. The control unit acquires user preference data. The control unit determines a tone for an item description based on the preference data. The control unit converts the item description based on the determined tone. The converted item description is output to the user. [Brief explanation of the drawings]

[0006] [Figure 1]FIG. 1 is a diagram illustrating an example of a system configuration of an information processing system. [Figure 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of the server device. [Figure 3] FIG. 3 is a diagram illustrating an example of a hardware configuration of the client device. [Figure 4] FIG. 4 is a diagram showing an example of the characteristics of each tone. [Figure 5] FIG. 5 is a sequence diagram illustrating an example of information processing in the information processing system. [Figure 6] FIG. 6 is a diagram showing an example of a screen including a search box, which is displayed on a client device. [Figure 7] FIG. 7 is a diagram showing an example of a screen including an explanatory text, which is displayed on the client device. [Figure 8] FIG. 8 is a sequence diagram illustrating an example of information processing in the information processing system according to the first modification. [Figure 9] FIG. 9 is a diagram showing an example of a screen displayed on the client device. [Figure 10] FIG. 10 is a diagram showing an example of a screen displayed on the client device. [Figure 11] FIG. 11 is a diagram showing an example of a screen displayed on the client device. DETAILED DESCRIPTION OF THE INVENTION

[0007] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the accompanying drawings. Various features shown in the following embodiments can be combined with each other.

[0008] In this specification, the term "unit" may include, for example, a combination of hardware resources implemented by a circuit in the broad sense and software information processing that can be specifically realized by these hardware resources. In addition, various types of information are handled in this embodiment, and communication and calculation can be performed on a circuit in the broad sense, regardless of whether this information is represented by a high or low signal value as a binary bit collection consisting of 0 or 1, a physical numerical value of a signal value, or a quantum superposition.

[0009] In addition, a circuit in the broad sense is a circuit realized by at least appropriately combining a circuit, circuitry, a processor, a memory, etc. That is, it includes an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)), etc.

[0010] In addition, the program for realizing the software appearing in the embodiments may be implemented in a form that allows it to be downloaded from a server, the program may be executed on a cloud computer, or it may be stored on a non-volatile or volatile non-transitory storage medium and distributed.

[0011] <Embodiment 1> 1. System Configuration 1 is a diagram showing an example of the system configuration of an information processing system 1000. The information processing system 1000 includes, as its system configuration, a server device 100 and a client device 110. The server device 100 and the client device 110 are connected to each other via a network 150 so as to be able to communicate with each other. The client device 110 is a terminal device operated by a user. The user operates the client device 110 to browse a website and purchase items (goods and / or services) on the website. For simplicity of explanation, the description will be given using goods as an example. The server device 100 publishes the constructed website and executes the following processing of the first embodiment.

[0012] Here, the claimed information processing system may be composed of multiple devices or may be composed of a single device. When the claimed information processing system is composed of a single device, an example of that device is server device 100. When the claimed information processing system is composed of a plurality of devices, an example of the plurality of devices is server device 100 and client device 110, or server device 100 and another server device that can communicate with server device 100 and executes part of the processing of server device 100, etc.

[0013] Although FIG. 1 shows only one client device 110 included in the information processing system 1000 for the sake of simplicity, the information processing system 1000 may include multiple client devices 110.

[0014] 2. Hardware Configuration (1) Hardware Configuration of Server Device 100 2 is a diagram showing an example of the hardware configuration of the server device 100. The server device 100 includes a control unit 210, a storage unit 220, and a communication unit 230 as the hardware configuration.

[0015] The control unit 210 is a CPU (Central Processing Unit) or the like, and controls the entire server device 100 .

[0016] The storage unit 220 is any one of a read-only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), and a solid state drive (SSD), or any combination thereof, and stores a program and data used by the control unit 210 when executing processing based on the program. Examples of data used by the control unit 210 when executing processing based on the program include, for example, a collection of explanatory text data, a collection of tones, history information, and a trained model, which will be described later. The control unit 210 reads a program stored in the storage unit 220 and executes processing based on the read program, thereby realizing the functions of the server device 100 and the processing of the server device 100 in the sequence diagram shown in FIG. 4, which will be described later. The storage unit 220 is an example of a storage medium. Note that, in the present embodiment, the data used by the control unit 210 when executing processing based on the program is described as being stored in the storage unit 220, but the data may also be stored in a storage unit of another device that can communicate with the server device 100. In other words, the data may be stored in a storage unit of any device as long as the data can be referenced and / or acquired by the control unit 210.

[0017] The communication unit 230 connects the server device 100 to the network 150 or the like, and controls communication with other devices or the like. The number of hardware components of the server device 100, such as the control unit 210, is not limited to that shown in FIG. 2, and the server device 100 may include a plurality of components.

[0018] (2) Hardware Configuration of the Client Device 110 3 is a diagram showing an example of the hardware configuration of client device 110. Client device 110 includes, as its hardware configuration, a control unit 310, a storage unit 320, an input unit 330, a display unit 340, an audio output unit 350, and a communication unit 360.

[0019] The control unit 310 is a CPU or the like, and controls the entire client device 110 .

[0020] The storage unit 320 is any one of a ROM, a RAM, an HDD, an SSD, or any combination thereof, and stores programs and data used when the control unit 310 executes processing based on the programs. The control unit 310 executes processing based on the programs stored in the storage unit 320, thereby realizing functions of the client device 110. The storage unit 320 is an example of a storage medium.

[0021] The input unit 330 is a keyboard and / or a mouse, etc., and is used to input operation information from the user. The display unit 340 is a display or the like, and outputs information.

[0022] The audio output unit 350 is a speaker or the like, and outputs audio. The communication unit 360 connects the client device 110 to the network 150 or the like, and controls communication with other devices or the like.

[0023] 3. Information Processing The information processing according to this embodiment will be described below. (Processing Overview) The control unit 210 acquires user preference data from other linked systems or the storage unit 220, etc. User preference data refers to data indicating the user's preferences and interests. User preference data is data obtained from the user's item purchase history, browsing history, search history, and content posted to SNS (social networking service), etc. The control unit 210 may obtain user preference data based on the user's item purchase history, browsing history, search history, and content posted to SNS (social networking service), and store the obtained data in the storage unit 220, etc. Alternatively, the control unit 210 may obtain user preference data obtained by another system, etc. The control unit 210 determines the tone of the item description based on the preference data. Tone refers to the tone or impression given by the use of language, style, etc. In this specification, six types of tone will be described as examples: Neutral, Attractive, Humorous, Romantic, Formal, and Plain. However, this does not limit the tones, and other examples of tones may include "a style similar to that of Natsume Soseki" or "a tone similar to a specific document." FIG. 4 is a diagram showing an example of the characteristics of each tone. The control unit 210 converts the description of the item based on the determined tone. The control unit 210 outputs the description of the item converted into the determined tone to the user. According to this process, it is possible to present to the user an explanation of the item in a tone that suits the user's preferences.

[0024] (Processing details) FIG. 5 is a sequence diagram showing an example of information processing in the information processing system 1000. As shown in FIG. In sequence SQ501, the control unit 210 receives a request to display a screen from the client device 110. In sequence SQ502, control unit 210 generates a screen in response to the display request. If the requested screen is a static screen, control unit 210 may acquire a screen that has been generated and stored in advance from storage unit 220 or the like. If the requested screen is a dynamic screen, control unit 210 may generate a screen in response to the request.

[0025] In sequence SQ503, control unit 210 transmits to client device 110 a screen corresponding to the request. When the screen is received, in sequence SQ504, control unit 310 of client device 110 displays the screen on display unit 340 or the like. FIG. 6 is a diagram showing an example of a screen 600 displayed on the client device 110, the screen 600 including a search window 610. Here, the description will be made assuming that the user of the client device 110 has performed an operation to display a screen such as that shown in FIG. 6. The screen 600 includes a search window 610. The user of the client device 110 inputs a search string or the like into the search window 610 to search for a desired item. The search window 610 is an area where the user inputs the string they wish to search for. The search window is also called a search box, search window, or search field.

[0026] In sequence SQ505, control unit 310 receives an input from the user via the screen. For example, control unit 310 receives a search character string or the like input via screen 600.

[0027] When a search string or the like is entered into the search window 610 and predetermined operation information is received, such as the Enter key being selected, in sequence SQ506, the control unit 310 generates a search query including the search string or the like and sends it to the server device 100.

[0028] In sequence SQ507, the control unit 210 acquires user behavior information on the screen displayed on the client device 110 via the screen and records it as a behavior history in the storage unit 220 or the like. The behavior information is information that indicates the user's behavior on the screen (website). The behavior information includes, for example, the screen's uniform resource locator (URL), the screen title, the time spent on the screen, the data entered and selected on the screen, the type of item purchased via the screen, the price of the item, the frequency of item purchases, etc.

[0029] In sequence SQ508, the control unit 210 acquires user behavior information from the storage unit 220 or the like. In sequence SQ509, control unit 210 determines whether the user's behavior satisfies a predetermined condition related to the item based on the acquired user behavior information. If control unit 210 determines that the user's behavior satisfies the predetermined condition related to the item, it executes the processing from sequence SQ510 onward, which will be described later. If control unit 210 determines that the user's behavior does not satisfy the predetermined condition related to the item, it skips the processing from sequence SQ510 onward, which will be described later. Here, the predetermined condition includes at least inputting item information in a search box on a website and issuing a search command. That is, control unit 210 determines whether the user inputs a character string related to the item in search box 610 on a screen such as that shown in FIG. 6 and issues a command to execute a search.

[0030] In sequence SQ510, the control unit 210 acquires user preference data from another linked system, the storage unit 220, or the like. As described above, user preference data is data that indicates the user's preferences and interests. The user preference data is data obtained from the user's item purchase history, browsing history, search history, content posted to SNS (Social Networking Service), etc. For example, the user preference data may be history data of the user's past selections or purchases of items similar to the target item (i.e., the item selected by the user or the item included in the screen the user wishes to display).

[0031] In sequence SQ511, the control unit 210 determines the tone of the item description based on the acquired preference data. For example, the control unit 210 inputs the user's preference data into a trained model. Here, the trained model is a trained model that has been trained using the user's preference data as input data and the tone of the description as output data. The control unit 210 determines the tone output from the trained model as the tone of the item description. More preferably, the trained model is trained using the tone of a description that is likely to make the user interested in the item as output data. As another example, the control unit 210 may determine the tone of the item description in a rule-based manner based on the preference data.

[0032] In sequence SQ512, control unit 210 searches for relevant items based on the search string and the like included in the search query, and acquires the items and their descriptions as search results. The items and their descriptions are assumed to be stored in storage unit 220 or the like. Control unit 210 converts the acquired item descriptions based on the determined tone. For example, control unit 210 converts the tone of the text data of the item descriptions based on the determined tone. For example, if the tone determined in sequence SQ511 is humorous, control unit 210 converts the tone of the text data of the item descriptions to a humorous tone. Furthermore, the control unit 210 may generate a prompt (command) that instructs the user to convert the description of the acquired item based on the determined tone, and input the generated prompt to an AI (Artificial Intelligence) of a large-scale language model. Then, the control unit 210 may acquire the description converted into the designated tone from the AI ​​of the large-scale language model.

[0033] In sequence SQ513, control unit 210 generates a screen including the items acquired as search results and the explanations converted into tones. In sequence SQ514, control unit 210 transmits the generated screen to client device 110. This process is an example of a process for outputting character data with a converted writing style to the user. When the screen including the tone-converted explanatory text is received, in sequence SQ515, control unit 310 displays the screen on display unit 340 or the like.

[0034] 7 is a diagram showing an example of a screen 600 including an explanation displayed on the client device 110. The screen 600 includes a search window 610, an item 620 obtained as a search result, an explanation 630 for the item 620, an item 640 obtained as a search result, and an explanation 650 for the item 640. The explanation 630 and the explanation 650 are tone-converted explanations.

[0035] According to the first embodiment, it is possible to present to the user an item description written in a tone that matches the user's preferences, thereby stimulating the user's interest in the item and encouraging them to consume the item.

[0036] (Variation 1) Modification 1 of Embodiment 1 will be described. In Modification 1, differences from Embodiment 1 will be described. Modification 1 is not an embodiment different from Embodiment 1, but is included in Embodiment 1.

[0037] FIG. 8 is a sequence diagram showing an example of information processing in the information processing system 1000 according to the first modification. In sequence SQ801, the control unit 210 receives a request to display a screen from the client device 110.

[0038] When the screen display request is received, in sequence SQ802, the control unit 210 acquires user behavior information from the storage unit 220 or the like. In sequence SQ803, the control unit 210 determines whether the user's behavior satisfies a predetermined condition related to the item based on the acquired user behavior information. If the control unit 210 determines that the user's behavior satisfies the predetermined condition related to the item, it executes the processing from sequence SQ804 onwards, which will be described later. If the control unit 210 determines that the user's behavior does not satisfy the predetermined condition related to the item, it skips the processing from sequence SQ804 onwards, which will be described later. Here, the predetermined condition includes an attempt to visit a website that includes a description of the item. That is, the control unit 210 determines whether the user has requested the display of a screen including a description of the item, such as that shown in FIG. 10, which will be described later.

[0039] In sequence SQ804, the control unit 210 acquires user preference data from other linked systems or the storage unit 220 or the like. In sequence SQ805, control unit 210 determines the tone of the item description based on the acquired preference data.

[0040] In sequence SQ806, control unit 210 acquires the items and item descriptions included in the screen requested to be displayed. The items and item descriptions are assumed to be stored in storage unit 220 or the like. Control unit 210 converts the acquired item descriptions based on the determined tone. For example, if the tone determined in sequence SQ805 is humorous, control unit 210 converts the item descriptions to a humorous tone. In sequence SQ807, the control unit 210 generates a screen in response to the display request. For example, the control unit 210 generates a screen as shown in FIG. 9. FIG. 9 is a diagram showing an example of a screen 900 displayed on the client device 110. Here, the description will be given assuming that the user of the client device 110 has performed an operation to display the screen as shown in FIG. 9. The screen 900 includes an item 910, a description 920 of the item 910, an item 930, and a description 940 of the item 930. The description 920 and the description 940 are description that have been converted into tones.

[0041] In sequence SQ808, the control unit 210 generates a screen including the item and the tone-converted explanatory text, and transmits it to the client device 110. When the screen including the tone-converted explanatory text is received, in sequence SQ809, control unit 310 displays the screen on display unit 340 or the like.

[0042] Modification 1 also makes it possible to present to the user an item description written in a tone that matches the user's preferences, thereby stimulating the user's interest in the item and encouraging them to consume the item.

[0043] (Variation 2) Modification 2 of Embodiment 1 will be described. In Modification 2, differences from Embodiment 1 will be described. Modification 2 is not an embodiment different from Embodiment 1, but is included in Embodiment 1.

[0044] In the second modification, the control unit 210 determines whether the user's behavior satisfies a predetermined condition related to an item based on the acquired user behavior information. In the second modification, the predetermined condition includes selecting a first item and then selecting a second item similar to the first item. That is, the control unit 210 determines whether the user performed the operation shown in FIG. 10 . FIG. 10 is a diagram illustrating an example of a screen 1010 displayed on the client device 110. The screen 1010 includes an item 1020 and an item 1040. The items 1020 and 1040 are similar items. Similar items refer to items having common attributes and / or characteristics. For example, if the items are movies, examples of similar items include movies in the same genre, movies by the same director, and movies starring the same leading actor or actress. As shown in FIG. 10 , if an item 1040 similar to the item 1020 is selected after the item 1020 is selected, the control unit 210 determines that the predetermined condition is satisfied.

[0045] Then, the control unit 210 generates a screen including a detailed description 1050 of the item 1040. The description 1050 is a description converted into a tone that matches the user's preferences. The client device 110 displays the screen as shown in FIG. 11 transmitted from the server device 100. FIG. 11 is a diagram showing an example of a screen 1100 displayed on the client device 110.

[0046] Modification 2 also makes it possible to present to the user an explanation of an item written in a tone that matches the user's preferences, thereby stimulating the user's interest in the item and encouraging them to consume the item.

[0047] (Variation 3) Modification 3 of Embodiment 1 will be described. Modification 3 will be described in terms of differences from Embodiment 1. Modification 3 is not an embodiment different from Embodiment 1, but is included in Embodiment 1.

[0048] The control unit 210 of the third modification converts the audio data of the item description based on the determined tone. For example, the control unit 210 converts the intonation of the audio data of the item description based on the determined tone. If the determined tone is humorous, the control unit 210 converts the intonation of the audio data of the item description to a humorous tone. The control unit 210 transmits the converted audio data to the client device 110. This process is an example of a process of outputting audio data with the converted intonation to the user. The control unit 310 of the client device 110 outputs the converted audio data from the audio output unit 350.

[0049] According to the third modification, it is also possible to output to the user an explanation of an item in a tone that matches the user's preferences, thereby stimulating the user's interest in the item and encouraging consumption of the item.

[0050] (Variation 4) Modification 4 of Embodiment 1 will be described. Modification 4 will be described in terms of differences from Embodiment 1. Modification 4 is not an embodiment different from Embodiment 1, but is included in Embodiment 1.

[0051] The control unit 210 of the fourth modification acquires the description of an item included in a screen requested by the client device 110. Then, the control unit 210 determines the tone of the description of the item based on the description of the item and the preference data. For example, the control unit 210 inputs the description of the item and the user's preference data into a trained model. Here, the trained model is a trained model that has been trained using the description of the item and the user's preference data as input data and the tone of the description as output data. The control unit 210 determines the tone output from the trained model as the tone of the description of the item. As another example, the control unit 210 may determine the tone of the description of the item based on a rule base based on the description of the item and the user's preference data. The control unit 210 converts the description of the item based on the determined tone.

[0052] According to the fourth modification, the tone of the item description can be determined based on the item description and the user's preference data.

[0053] (Variation 5) Modification 5 of Embodiment 1 will be described. Modification 5 will be described in terms of differences from Embodiment 1. Modification 5 is not an embodiment different from Embodiment 1, but is included in Embodiment 1.

[0054] The control unit 210 of the fifth modification acquires characteristic data of an item included in a screen requested by the client device 110. More specifically, the control unit 210 acquires the characteristic data of the item from another linked system, the storage unit 220, or the like. Here, the characteristic data of an item is data indicating the nature and / or capabilities of the item. Examples of the characteristic data of an item include data on the use of the item, the function of the item, the durability of the item, the safety of the item, and the reliability of the item.

[0055] The control unit 210 determines the tone of the item description based on the item characteristic data and the user preference data. For example, the control unit 210 inputs the item characteristic data and the user preference data into a trained model. Here, the trained model is a trained model that has been trained using the item characteristic data and the user preference data as input data and the tone of the description as output data. The control unit 210 determines the tone output from the trained model as the tone of the item description. As another example, the control unit 210 may determine the tone of the item description in a rule-based manner based on the item characteristic data and the user preference data. The control unit 210 converts the description of the item based on the determined tone.

[0056] According to the fifth modification, the tone of the description of the item can be determined according to the item's characteristic data and the user's preference data.

[0057] (Variation 6) Modification 6 of Embodiment 1 will be described. Modification 6 will be described in terms of differences from Embodiment 1. Modification 6 is not an embodiment different from Embodiment 1, but is included in Embodiment 1. The control unit 210 of the sixth modification executes the following process.

[0058] Let U be the set of users and I be the set of items. For a target item i∈I to be recommended, a description r is given as text. We assume that the description can be decomposed into content and tone. Therefore, if c(r) and t(r) are the content and tone of description r, respectively, then the description is defined as r = (i,c(r),t(r)). Various methods can be used to represent content and tone, for example, using topic vectors to represent content. For simplicity, in this specification, we use a finite set C i Assume that the content and tone are prepared in advance by and T, where C i Let be the set of texts describing item i from various perspectives, and T be the set of tones such as formal and humorous. For simplicity, let c:=c(r)∈C i and define t:=t(r)∈T.

[0059] The goal of our problem is to find the best possible combination of content and tone R when recommending an item i∈I to a user u∈U. i :={(i,c,t)|c∈C i , t∈T}, the most attractive explanation r for user u * , i.e., the description r that is most likely to interest user u in item i. * This explanation is that after a recommendation item i is determined by any system, R i In this specification, the original description before conversion is called C i The utility value of user u for description r is defined as f(u,r)∈R, and the higher this utility value, the more likely user u is to be involved in the item. When recommending item i to user u, iPredict the utility value f(u,r) for each of the explanations r with the highest utility value based on historical data. * Present the following.

[0060] Based on our assumption that the description depends on the content and tone as r = (i,c,t), we define the utility value f(u,r) of description r as the utility value f of the content. content (u,c) and the tone utility value f tone (u,t) and expressed as follows:

[0061] f(u,r)=(1-α u )(f content (u,c)+b c )+α u (f tone (u,t)+b i t ) (1)

[0062] where b c ∈R and b i t ∈R is the bias term, and α u ∈[0,1] denotes a parameter that adjusts the importance of content and tone. The bias term b c represents the average popularity of content c, and the bias term b i t represents the bias of tone t in item i. The bias term b i t The reason this is item-dependent is that some tones may not be suitable for certain items. For example, a humorous tone may be suitable for a comedy film, but not for a serious human drama.

[0063] Content utility value f content (u,c) and the tone utility value f tone (u,t) are based on matrix decomposition method and are respectively f content (u,c)=W u T X c and f tone (u,t)=W u T V tHere, W u ,X c , and V t are k-dimensional embedding vectors for user u, content c, and tone t, respectively. Therefore, θ=({W u},{X c},{V t},{α u},{b c},{b t i}) are the parameters of the model. To clarify that the utility model depends on θ, we denote it as f(u,r;θ).

[0064] The model parameters f(u,r;θ) are estimated using the maximum likelihood method with a logit selection model. i ={r j >ur ' j |j=1,...,|D i |}, where r j , r j ′ ∈R i ,r j ≠r ' j The pairwise comparison data for all items is D = UiD i In each pairwise comparison, r> u r ' The probability that

[0065] TIFF2025173967000002.tif968

[0066] The model parameters θ are optimized by minimizing the cross-entropy loss function for the data D. Specifically, the loss function is formulated as follows:

[0067] TIFF2025173967000003.tif2081

[0068] where: TIFF2025173967000004.tif47 means the L2 norm, which is a regularization term to prevent overfitting. Also, λ w ,λ x ,λ v represents the weight parameter of the regularization term, and U i C i denotes the set of original descriptions to consider for all items. Furthermore, it may be provided in the following aspects.

[0069] (1) An information processing system having at least one control unit, wherein the control unit acquires user preference data, determines the tone of an item description based on the preference data, converts the item description based on the determined tone, and outputs the converted item description to the user.

[0070] (2) In the information processing system described in (1) above, the control unit acquires a description of the item, determines a tone of the description of the item based on the description of the item and the preference data, and converts the description of the item based on the determined tone.

[0071] (3) In the information processing system described in (1) above, the control unit acquires item characteristic data, determines the tone of the item description based on the item characteristic data and the preference data, and converts the item description based on the determined tone.

[0072] (4) In the information processing system described in any one of (1) to (3) above, the control unit converts the tone of the text data of the item description based on the determined tone, and outputs the text data in the converted tone to the user.

[0073] (5) In the information processing system described in any one of (1) to (3) above, the control unit converts the intonation of the audio data of the item description based on the determined tone, and outputs the audio data in the converted intonation to the user.

[0074] (6) In the information processing system described in any one of (1) to (5) above, the control unit acquires behavioral information indicating user behavior on a website, and when the behavioral information satisfies predetermined conditions related to an item, determines the tone of the item description based on the preference data.

[0075] (7) In the information processing system described in (6) above, the predetermined conditions include at least one of the following: entering item information in a search box on a website and instructing a search; attempting to visit a website that includes a description of the item; and selecting a first item and then selecting a second item that is similar to the first item.

[0076] (8) In the information processing system described in any one of (1) to (7) above, the user preference data is history data of the user's past selections or purchases of items similar to the target item.

[0077] (9) In the information processing system described in (8) above, the control unit inputs the user's preference data into a trained model, which is trained using the user's preference data as input data and tones that are likely to make the user interested in an item as output data, and determines the tone output from the trained model as the tone of the description of the target item.

[0078] (10) An information processing method executed by an information processing system, which acquires user preference data, determines the tone of an item description based on the preference data, converts the item description based on the determined tone, and outputs the converted item description to the user.

[0079] (11) A program for causing a computer to function as the information processing system according to any one of (1) to (9) above. Of course, this is not the case.

[0080] For example, the above-described embodiments and modifications may be combined in any manner.

[0081] Finally, while various embodiments of the present invention have been described, these are presented by way of example only and are not intended to limit the scope of the invention. The novel embodiments may be embodied in various other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. The embodiments and their modifications are intended to be included within the scope and spirit of the invention, as well as within the scope of the inventions and their equivalents as defined in the appended claims. [Explanation of symbols]

[0082] 100: Server device 110: Client device 150: Network 210: Control unit 220: Storage section 230: Communications Department 310: Control unit 320: Storage section 330: Input section 340: Display section 350: Audio output section 360: Communications Department 600:screen 610: Search window 620: Item 630:Description 640: Item 650:Description 900:screen 910: Item 920: Description 930: Item 940: Description 1000: Information Processing Systems 1010: Screen 1020: Item 1040: Item 1050:Description 1100: Screen

Claims

1. An information processing system, having at least one or more control units, The control unit Obtaining user preference data, determining a tone for the item description based on the preference data; converting a description of the item based on the determined tone; outputting the converted description of the item to the user; Information processing system.

2. 2. The information processing system according to claim 1, The control unit Obtain a description of the item; determining a tone of the item description based on the item description and the preference data; converting a description of the item based on the determined tone; Information processing system.

3. 2. The information processing system according to claim 1, The control unit Get the item's characteristic data, determining a tone of the description of the item based on the item characteristic data and the preference data; converting a description of the item based on the determined tone; Information processing system.

4. 2. The information processing system according to claim 1, The control unit converting the tone of the text data of the item description based on the determined tone; outputting the character data in the converted style to the user; Information processing system.

5. 2. The information processing system according to claim 1, The control unit converting the tone of the audio data of the description of the item based on the determined tone; outputting the converted voice data to the user; Information processing system.

6. 2. The information processing system according to claim 1, The control unit Obtaining behavioral information indicating user behavior on the website; determining a tone of a description of the item based on the preference data when the behavioral information satisfies a predetermined condition related to the item; Information processing system.

7. 7. The information processing system according to claim 6, The predetermined conditions include at least: Entering item information into the search box on the website and instructing a search; You are about to visit a website that contains the item's description, selecting a first item and then selecting a second item similar to the first item; It includes any of the following: Information processing system.

8. 2. The information processing system according to claim 1, The user's preference data is history data of the user's past selection or purchase of items similar to the target item. Information processing system.

9. 9. The information processing system according to claim 8, The control unit Inputting the user's preference data into a trained model; The trained model is a trained model trained using the user's preference data as input data and a tone that is likely to indicate the user's interest in an item as output data, The tone output from the trained model is determined as the tone of the description of the target item. Information processing system.

10. An information processing method executed by an information processing system, Obtaining user preference data, determining a tone for the item description based on the preference data; converting a description of the item based on the determined tone; outputting the converted description of the item to the user; Information processing methods.

11. A program, Computer, A program for causing the information processing system according to any one of claims 1 to 9 to function.

Images