Information processing device

The information processing device addresses the lack of personalized explanations in recommendation systems by using user style and behavioral data to generate and present tailored explanations, improving user engagement through a combination of style selection and explanatory text generation units.

WO2024247399A1PCT designated stage expired Publication Date: 2024-12-05NTT DOCOMO INC
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
PCT/JP2024/006103
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-26
Filing Date
2024-02-20
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

Conventional recommendation systems do not provide personalized and appealing explanations for recommended content to users, failing to consider user-specific style information and behavioral data.

Method used

An information processing device that includes a style selection unit to choose user style information based on attribute and behavioral data, an explanatory text generation unit to create personalized explanations, and a presentation unit to display these explanations, using reinforcement learning to optimize the selection and generation of recommendation explanations.

Benefits of technology

Generates and presents more personalized and appealing recommendation explanations to individual users by integrating user style information and behavioral data into the recommendation process, enhancing user engagement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure JP2024006103_05122024_PF_FP_ABST
    Figure JP2024006103_05122024_PF_FP_ABST
Patent Text Reader

Abstract

This information processing device (10) comprises: a style selection unit (11) that selects style information relating to a user on the basis of user information including at least one of user attribute information and behavior information; an explanatory sentence generation unit (12) that generates a recommendation explanation sentence on the basis of a recommendation basis obtained in advance about content to be recommended and the style information selected by the style selection unit (11); and a presentation unit (13) that presents the recommendation explanation sentence generated by the explanatory sentence generation unit (12) to the user.
Need to check novelty before this filing date? Find Prior Art

Description

Information processing device

[0001] The present disclosure relates to an information processing device that presents recommended content along with a recommendation reason to a user. Note that the term "content" here broadly includes various products (e.g., video works, books, etc.) and various services (e.g., provision of video works, sales of books, etc.).

[0002] Recommendation systems that present recommended content to users have been known for some time. However, such recommendation systems generally do not present the reason for the recommendation to the user. Therefore, a technology has been proposed that presents the recommended content to the user along with a description of the reason for the recommendation based on the content's meta information (see Patent Literature 1).

[0003] Japanese Patent Application Laid-Open No. 2006-309751

[0004] However, no consideration has been given to generating and presenting to individual users more personalized and appealing recommendation reason explanations based on user style information (such as attribute information for each user and behavioral information according to the user's preferences).

[0005] Therefore, an object of the present disclosure is to generate a recommendation reason explanation that is more personalized and appealing to each individual user and present it to the user.

[0006] The information processing device according to the present disclosure includes a style selection unit that selects style information of a user based on user information including at least one of attribute information and behavioral information of the user, a description generation unit that generates a recommendation description based on a predetermined recommendation basis for the content to be recommended and the style information of the user selected by the style selection unit, and a presentation unit that presents the recommendation description generated by the description generation unit to the user.

[0007] In the information processing device, the style selection unit selects the user's style information based on user information including at least one of the user's attribute information and behavior information, the explanation generation unit generates a recommendation explanation based on a predetermined recommendation reason for the content to be recommended and the selected user's style information, and the presentation unit presents the generated recommendation explanation to the user. In this way, the recommendation explanation is generated and presented to the user based not only on the recommendation reason for the content to be recommended but also on the style information selected based on the user information. This makes it possible to generate and present to the user a recommendation reason explanation that is more personalized and appealing to each individual user.

[0008] According to the present disclosure, it is possible to generate and present to an individual user a recommendation reason explanation that is more personalized and appealing to the user.

[0009] FIG. 1 is a functional block configuration diagram of an information processing device. FIG. 2 is a diagram explaining data for learning by an explanation generation unit. FIG. 3 is a diagram explaining learning by an explanation generation unit. FIG. 4 is a diagram explaining data for learning by a style selection unit. FIG. 5 is a diagram explaining learning by a style selection unit. FIG. 6 is a diagram explaining learning by a style selection unit. FIG. 7 is a flow diagram showing processing executed by an information processing device after learning is completed. (a) is a diagram showing an example of a presentation of a recommendation reason explanation, and (b) is a diagram showing another example of a presentation of a recommendation reason explanation. FIG. 8 is a diagram showing an example of a hardware configuration of an information processing device.

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following embodiments, it is assumed that content to be recommended to a target user has already been selected using publicly known technology, and the basis for the recommendation has been previously determined using publicly known eXplainable AI (XAI) technology.

[0011] As shown in FIG. 1, the information processing device 10 in the embodiment includes, as functional blocks for realizing the functions related to the present disclosure, a style selection unit 11 that selects style information of a user based on user information including at least one of attribute information and behavioral information of the user, an explanation generation unit 12 that generates a recommendation explanation based on a pre-determined recommendation basis for the content to be recommended and the user's style information selected by the style selection unit 11, and a presentation unit 13 that presents the generated recommendation explanation to the user.

[0012] Although details will be described later, the style selection unit 11 learns a probability function regarding which style information is likely to be selected for which user, based on user information and user behavior results (e.g., click logs) regarding content corresponding to recommendation descriptions linked to previously selected style information, using a reinforcement learning approach, and selects style information for the user using the probability function obtained by learning. In other words, when user information is input, the style selection unit 11 learns a probability function using a reinforcement learning approach so as to select style information that maximizes the reward related to the user's degree of response to the content, and selects style information for the user using the probability function obtained by learning.

[0013] In addition, the description generation unit 12 performs learning using style information and a recommendation description (a recommendation description that reflects the recommendation basis) generated based on the recommendation basis as explanatory variables, and a recommendation description that takes the style information into account as a target variable, and generates a recommendation description based on the learning results obtained by learning.

[0014] Here, learning in the explanatory sentence generation unit 12 will be described with reference to Figures 2 and 3. As shown in Figure 2, in order to acquire learning data for individual training in the explanatory sentence generation unit 12, the explanatory sentence generation unit 12 collects correspondences between product groups in the world and catchphrases, and creates text annotations. Specifically, the target sentence is divided into "reason for inference" and "style information." For example, the target sentence "Why not take a break with a slice-of-life anime?" is divided into "reason for inference (assumed) = genre (slices-of-life anime)" and "'1' flag corresponding to 'calm atmosphere' in the style information category."

[0015] As shown in FIG. 3 , the description generator 12 performs learning using the style information and the recommendation description (recommendation description reflecting the recommendation basis) generated based on the recommendation basis as explanatory variables, and the recommendation description taking the style information into consideration as the objective variable. In the example of FIG. 3 , learning is performed using the style information of "calm atmosphere" and the recommendation basis of "genre (slices of life anime)" as explanatory variables, and the "recommendation description taking the style information into consideration" of "Why not take a break with a slice of life anime?" as the objective variable. Note that as a learning method for generating descriptions that conditionally use style information, a method such as Prefix Tuning (see https: / / arxiv.org / abs / 2101.00190), which is known to be capable of high-performance learning even with small amounts of data, may be used.

[0016] The explanation generator 12 generates a recommendation explanation based on the learning results obtained through the above-described learning. Generating a recommendation explanation based on the learning results in this way can contribute to generating a recommendation reason explanation that is more personalized and appealing to each individual user.

[0017] Next, learning in the style selection unit 11 will be described with reference to FIGS. 4 to 6. As shown in FIG. 4, the style selection unit 11 collects, for learning purposes, "correspondence data between style-converted text and product groups," i.e., data on which style information-based descriptions are best for the same product group. In the example of FIG. 4, when description A generated based on a certain recommendation basis (recommendation basis A) and style A was presented to a user, it was clicked by the user. However, when description B generated based on the same recommendation basis (recommendation basis A) and style B, and description C generated based on the same recommendation basis (recommendation basis A) and style C were presented to the same user, they were not clicked by the user. Such data is collected.

[0018] Next, the selection of style information by the style selection unit 11 will be described with reference to Figures 5 and 6. As described above, when user information is input, the style selection unit 11 learns a probability function relating to which style is likely to be selected for which user using a reinforcement learning approach, so as to select style information that maximizes the reward related to the degree of user response to content, and selects style information for the user using the probability function obtained by learning. In the above learning phase, for example, the style selection unit 11 calculates a user context vector from the input user information. As shown in Figure 5, we create a user context vector is mainly composed of "behavioral information" and "demographic information." Among these, behavioral information includes information such as usage time, number of times of usage, time of usage, and time since last usage, while demographic information includes information such as age, gender, place of residence, and content (genre) preference information. Furthermore, other information (information related to external factors) such as seasonal information and popular content (genre) information can also be included. This information serves as reference information when the style selection unit 11 selects a style.

[0019] In the learning phase, as shown in FIG. 6, the style selection unit 11 calculates a probability function (probability function) regarding which style is likely to be selected for which user based on the explanation and the click log of the corresponding product. This is learned using a reinforcement learning approach. This learning can be expressed mathematically as follows:

[0020] In the inference phase after the completion of learning, the style selection unit 11 uses the probability function obtained by learning For example, assuming LinUCB (Linear Upper Confidence Bounds) as a typical contextual bandit technique, the style information is selected by the following formula (2). In this way, by using a probability function obtained through learning using a reinforcement learning approach to select user style information, it is possible to contribute to generating more personalized and appealing recommendation reason explanations for individual users.

[0021] Next, the processing after the completion of learning will be described with reference to the flow diagram of Fig. 7. First, the style selection unit 11 receives user information (including behavioral information, demographic information, and other information) input from the outside (step S1), and calculates the probability function obtained by learning. Using the above formula (2), the style information of the user is selected (step S2).

[0022] The explanation generator 12 receives the externally input content information (the basis for recommending the content) and the style information selected by the style selector 11 (step S3), and generates a recommendation explanation based on the learning results obtained by the learning (step S4). Furthermore, the presenter 13 presents the explanation generated by the explanation generator 12 to the user (step S5).

[0023] According to the embodiment described above, a recommendation explanation is generated and presented to a user based not only on the recommendation grounds for the recommended content but also on style information selected based on user information. This allows a recommendation explanation that is more personalized and appealing to each individual user to be generated and presented to the user.

[0024] As specific examples, FIGS. 8( a) and 8(b) show examples of explanatory sentences presented to the user. The upper section of FIG. 8(a) shows an explanatory sentence such as, "Why not watch something you haven't seen in a while? A nostalgic '90s anime'?" This explanatory sentence is generated based on the "era of the work" and taking into account the user attribute of "40s," an age group that nostalgically enjoys '90s anime. The lower section of FIG. 8(a) shows an explanatory sentence such as, "Sometimes I just want to watch a slice-of-life anime!" This explanatory sentence is generated based on the "genre of the work" and taking into account the user attribute of "I don't usually watch slice-of-life anime, but I often watch action movies, and I binge-watch this genre during long vacations." FIG. 8(b) shows examples of intentionally controlling explanatory sentences using appropriate style information based on the target user and the recommended content (product) through sentence generation rather than fill-in-the-blanks, such as, "When it's cold, you want to wear warm clothes," and "Stay stylish even in the hot summer!"

[0025] Further, examples of descriptions generated by reflecting style information are given below. (1) When the recommendation is based on the genre "battle" and the style information "for those who haven't used the service in a while" is reflected, the description "Experience the feeling of being engrossed in a battle anime for the first time in a while! This is the perfect work for reusing the service!" is generated. (2) When the recommendation is based on the performer "voice actor A" and the style information "for big fans" is reflected, the description "These works are full of charm that even big fans of "voice actor A" will be satisfied with!" is generated. (3) When the recommendation is based on the viewed work "Work B" and the style information "winter-like," the description "Heartwarming stories are perfect for the cold winter! Work B is filled with stories that we want to share with you who have seen it." is generated. (4) When the recommendation is based on the genre "wizard" and the style information "exciting," the description "Anime featuring wizards is the classic fantasy! What if you could use magic?" is generated. (5) If the recommendation basis is the genre "mystery" and the style information "serious feel" is reflected, a description such as "Immerse yourself in a detailed story. A serious work with an incredible sense of tension, perfect for mystery lovers!" is generated. Note that the style information "exciting feel" and "serious feel" in (4) and (5) above can be obtained by utilizing behavioral information related to user preferences, such as the type of content (video works, books, etc.) that the user normally watches, as basic information for style selection. As is clear from the various examples above, in this embodiment, a more personalized and appealing recommendation reason description can be generated for each individual user and presented to the user.

[0026] The gist of the present disclosure lies in the following [1] to [4]. [1] An information processing device comprising: a style selection unit that selects style information of a user based on user information including at least one of attribute information and behavior information of the user; an explanation generation unit that generates a recommendation explanation based on a recommendation basis determined in advance for content to be recommended and the style information of the user selected by the style selection unit; and a presentation unit that presents the recommendation explanation generated by the explanation generation unit to the user. [2] The information processing device according to [1], wherein the explanation generation unit performs learning using the style information and a recommendation explanation that is generated based on the recommendation basis and reflects the recommendation basis as explanatory variables, and a recommendation explanation that takes the style information into consideration as a target variable, and generates the recommendation explanation based on a learning result obtained by learning. [3] The information processing device according to [1] or [2], wherein the style selection unit learns a probability function relating to which style information is likely to be selected for which type of user, based on the user information and a behavioral result of the user regarding content corresponding to a recommendation description linked to previously selected style information, using a reinforcement learning approach, and selects the style information of the user using the probability function obtained by learning. [4] The information processing device according to [3], wherein the style selection unit learns the probability function using a reinforcement learning approach so as to select style information that maximizes a reward related to a degree of response of the user regarding the content when the user information is input, and selects the style information of the user using the probability function obtained by learning.

[0027] (Explanation of terms, explanation of hardware configuration (Figure 9), etc.) Note that the block diagrams used in the explanation of the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically coupled, or may be realized using two or more devices that are physically or logically separated and connected directly or indirectly (for example, using wires, wirelessly, etc.) and these multiple devices. A functional block may be realized by combining software with the one device or the multiple devices.

[0028] Functions include, but are not limited to, judgment, determination, assessment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs transmission is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how these functions are implemented.

[0029] For example, an information processing device according to an embodiment of the present disclosure may function as a computer that executes the processes of the present disclosure. Fig. 9 is a diagram illustrating an example of a hardware configuration of an information processing device 10 according to an embodiment of the present disclosure. The information processing device 10 described above may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, etc.

[0030] In the following description, the term "apparatus" can be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the information processing device 10 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0031] Each function of the information processing device 10 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0032] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0033] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. While the various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0034] The memory 1002 is a computer-readable recording medium and may be configured by, for example, at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0035] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0036] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc. The communication device 1004 may be configured to include a high-frequency switch, a duplexer, a filter, a frequency synthesizer, etc. to realize at least one of frequency division duplex (FDD) and time division duplex (TDD).

[0037] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (e.g., a touch panel).

[0038] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0039] The information processing device 10 may also be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0040] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. Furthermore, the RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0041] Each aspect / embodiment described in the present disclosure may be implemented using any of the following standards: LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), 6th generation mobile communication system (6G), xth generation mobile communication system (xG) (xG (x is, for example, an integer or a decimal number)), FRA (Future Radio Access), NR (new Radio), New radio access (NX), Future generation radio access (FX), W-CDMA (registered trademark), GSM (registered trademark), CDMA2000, UMB (Ultra Mobile Broadband), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.17 (WiMAX (registered trademark)), IEEE 802.19 (WiMAX (registered trademark)), IEEE 802.20 (WiMAX (registered trademark)), IEEE 802.21 (Wi-Fi (registered trademark)), IEEE 802.22 (WiMAX (registered trademark)), IEEE 802.23 (WiMAX (registered trademark)), IEEE 802.24 (WiMAX (registered trademark)), IEEE 802.25 (WiMAX (registered trademark)), IEEE 802.26 (WiMAX (registered trademark)), IEEE 802.27 (WiMAX (registered trademark)), IEEE 802.28 (WiMAX (registered trademark)), IEEE 802.29 (WiMAX (registered trademark)), IEEE 802.30 (WiMAX (registered trademark)), IEEE 802.31 (Wi-Fi (registered trademark)), IEEE 802.32 (WiMAX (registered trademark)), IEEE 802.33 (WiMAX (registered trademark)), IEEE 802.34 ( The present invention may be applied to at least one of systems using 802.20, UWB (Ultra-Wide Band), Bluetooth (registered trademark), or other suitable systems, and next-generation systems that are extended, modified, created, or defined based on these systems. The present invention may also be applied to a combination of multiple systems (e.g., a combination of LTE and / or LTE-A with 5G).

[0042] The order of the procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0043] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0044] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0045] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0046] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0047] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0048] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0049] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0050] Note that terms described in this disclosure and terms necessary for understanding this disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). Furthermore, a signal may be a message. Furthermore, a component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, etc.

[0051] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0052] Furthermore, the information, parameters, etc. described in the present disclosure may be expressed using absolute values, may be expressed using relative values ​​from a predetermined value, or may be expressed using other corresponding information. For example, a radio resource may be indicated by an index.

[0053] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the mathematical expressions using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0054] As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judged" or "decided." In other words, "judgment" and "decision" can include regarding some action as having been "judged" or "decided." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0055] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0056] As used in this disclosure, any reference to an element using a designation such as "first," "second," etc. does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0057] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0058] In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0059] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0060] 10...information processing device, 11...style selection unit, 12...explanatory sentence generation unit, 13...presentation unit, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. An information processing device comprising: a style selection unit that selects style information of a user based on user information including at least one of the user's attribute information and behavioral information; an explanation generation unit that generates a recommendation explanation based on a predetermined recommendation basis for the content to be recommended and the user's style information selected by the style selection unit; and a presentation unit that presents the recommendation explanation generated by the explanation generation unit to the user.

2. The information processing device described in claim 1, wherein the explanation generation unit performs learning using the style information and a recommendation explanation generated based on the recommendation basis and reflecting the recommendation basis as explanatory variables, and a recommendation explanation taking into account the style information as an objective variable, and generates the recommendation explanation based on the learning results obtained by learning.

3. The information processing device of claim 1, wherein the style selection unit learns a probability function regarding which style information is likely to be selected for which user based on the user information and the user's behavioral results regarding content corresponding to recommendation descriptions linked to previously selected style information, using a reinforcement learning approach, and selects the style information for the user using the probability function obtained by learning.

4. The information processing device described in claim 3, wherein the style selection unit learns the probability function using a reinforcement learning approach so as to select style information that maximizes the reward related to the degree of response of the user to the content when the user information is input, and selects the style information of the user using the probability function obtained by learning.

Citation Information

Patent Citations

  • Recommendation copywriting generation method and device, electronic equipment and readable storage medium

    CN110765273A

  • Program, method, information processing device, and system

    JP2022145991A