Information processing device

Abstract

An information processing device 30 solves, as a so-called optimization problem, which content that is selected within a budget for content acquisition would maximize a KPI, on the basis of a causal relationship between a viewing history and the KPI. Thus, the information processing device 30 can select a combination of content to be distributed to viewers in consideration of both the index that measures the degree of achievement to performance goals by a content distributor and the cost required for preparing the content to be distributed to the viewers.

Description

Information processing device

[0001] The present invention relates to a technique for selecting content to be distributed to viewers.

[0002] In a service that distributes content to viewers via terminals such as smartphones for a fee, the selection of a content group to be distributed is extremely important. For example, Patent Literature 1 discloses a mechanism for selecting a combination of content that, when one of a plurality of pieces of content is assigned to each of a plurality of time slots, will result in a high total of viewer satisfaction levels based on scores and playback times.

[0003] Japanese Patent Application Laid-Open No. 2019-53667

[0004] It is also important for content distributors to consider the costs involved in obtaining content from content providers for distribution to viewers.

[0005] Therefore, the present invention aims to provide a system for selecting a combination of content to be distributed to viewers, taking into consideration both an indicator that measures the content distributor's degree of achievement of performance goals and the costs required to prepare the content to be distributed to viewers.

[0006] In order to solve the above problems, the present invention aims to provide an information processing device that includes: a derivation unit that uses an algorithm to derive an index that measures the degree of achievement of the performance goals of the content distributor of the content distributed to the viewer from the viewing history of the content, and derives the index when each piece of content that could be distributed is not distributed to the viewer; and a selection unit that selects a combination of content to be distributed to the viewer using the cost required to distribute each piece of content to the viewer and the index when each piece of content is not distributed to the viewer.

[0007] According to the present invention, it is possible to select a combination of content to be distributed to viewers by taking into consideration both an indicator that measures the degree of achievement of the content distributor's performance goals and the cost required to prepare the content to be distributed to viewers.

[0008] FIG. 1 is a diagram showing an example of the configuration of a communication system 1 according to an embodiment of the present invention. FIG. 2 is a schematic diagram illustrating an overview of the present embodiment. FIG. 3 is a diagram showing an example of the hardware configuration of an information processing device 30 according to the present embodiment. FIG. 4 is a diagram showing an example of the functional configuration of the information processing device 30 according to the present embodiment. FIG. 5 is a schematic diagram showing the relationship between viewing history and KPI when a multiple regression model is used in the present embodiment. FIG. 6 is a schematic diagram showing the relationship between viewing history and KPI when a LinGAM model is used in the present embodiment. FIG. 7 is a flowchart showing an example of the operation of the information processing device 30 according to the present embodiment.

[0009] [Embodiment] [Configuration] FIG. 1 is a diagram illustrating an example of the configuration of a communication system 1 according to an embodiment of the present invention. The communication system 1 is a system for acquiring various content from a content provider (not shown) for a fee and distributing the acquired content to viewers for a fee. As shown in FIG. 1, the communication system 1 includes user terminals 10 used by multiple viewers to play content, a content distribution system 20 that distributes content acquired from the content provider to the user terminals 10, and a communication network 2, including a wireless or wired communication network, that communicatively connects these. The user terminals 10 are, for example, computers capable of communication, such as smartphones, tablets, personal computers, or wearable devices. The content distribution system 20 is a system composed of multiple computers that, for example, have the function of storing content to be distributed and the function of distributing the content to the user terminals 10 via the communication network 2. The content distribution system 20 includes at least an information processing device 30, which corresponds to an example of an information processing device according to the present invention. Note that, in the present invention, content may be anything that viewers can watch or listen to (i.e., viewable), such as videos, music, animation, e-books, etc.

[0010] Generally, in a business model in which a large number of contents are distributed to a large number of viewers, a small number of specific popular contents account for the majority of the total viewing time of all the contents. For example, there are known examples in which 20% of all contents account for 80% of the total viewing time. On the other hand, there are also known examples in which viewing by a specific 20% of all viewers accounts for 80% of the total viewing time of all the contents. Viewers have a variety of preferences and requests for content, and how to select content to be distributed to viewers is an important issue for business entities that provide content distribution services (hereinafter referred to as content distributors). This embodiment optimizes what content groups should be selected for distribution within a budget for continuing to distribute content that is already being distributed, rather than within a budget for acquiring new content to be distributed from content providers.

[0011] First, an overview of this embodiment will be described with reference to Fig. 2. The information processing device 30 uses so-called clustering technology to classify all current viewers into multiple viewer groups based on certain conditions. The conditions here include, for example, pre-registered attribute data such as the gender and age of each viewer, or analytical data such as the hobbies and preferences of each viewer identified from their content viewing history. As a result, viewers are classified into groups with a certain degree of similarity in their content viewing tendencies.

[0012] Next, the information processing device 30 divides the multiple pieces of content currently being distributed into multiple groups (hereinafter referred to as content groups) based on at least one of the following: the title of the content, the genre to which the content belongs, the actors, characters, etc. appearing in the content, the supervisor involved in creating, editing, and directing the content, or the attributes of the content.The information processing device 30 then treats these content groups as a single unit and acquires the past viewing history of the content belonging to each content group for each of the above-mentioned viewer groups.In other words, this viewing history is the viewing history for each viewer group and each content group.

[0013] Next, the information processing device 30 analyzes the causal relationship between the viewing history of each viewer group and each content group and an indicator that measures the content distributor's achievement of its performance goals. Here, the indicator that measures the content distributor's achievement of its performance goals is, for example, called a KPI (Key Performance Indicator). Specifically, there are indicators that measure the number of active viewers per unit period (e.g., MAU: Monthly Active Users), indicators that measure the number of newly subscribed viewers (e.g., number of new users), indicators that measure the profits obtained from viewers (e.g., LTV: Life Time Value), indicators that measure viewer loyalty (e.g., NPS: Net Promoter Score), indicators that measure viewer satisfaction (e.g., customer satisfaction), and indicators that measure viewer churn (e.g., customer churn rate). In the following description, an indicator that measures the content distributor's achievement of its performance goals will be referred to as a KPI. However, in the present invention, any name may be used for the indicator as long as it measures the content distributor's achievement of its performance goals.

[0014] Based on the causal relationships analyzed as described above, the information processing device 30 solves a so-called optimization problem: what combination of content should be selected within the content acquisition budget to maximize the KPI? Strictly speaking, as described above, for all content currently being distributed, a content group is treated as a single unit, so the problem is solved as to which content group should be selected to maximize the KPI. In this case, it is desirable for the information processing device 30 to select a combination of content using weights according to the number of viewers belonging to each of the classified viewer groups. In other words, a relatively large weight is assigned to content that has a strong causal relationship with a viewer group with a relatively large number of viewers, and a relatively small weight is assigned to content that has a strong causal relationship with a viewer group with a relatively small number of viewers, thereby selecting a combination of content.

[0015] With the above-described mechanism, the information processing device 30 can select a combination of content to be distributed to viewers by taking into consideration both the indicators that measure the content distributor's degree of achievement of performance goals and the costs required to prepare the content to be distributed to viewers.

[0016] This embodiment will be described in detail below. FIG. 3 is a diagram showing the hardware configuration of an information processing device 30. The information processing device 30 is physically configured as a computer including a processor 3001, a memory 3002, a storage 3003, a communication device 3004, an input device 3005, an output device 3006, and a bus connecting these devices. Each of these devices operates using power supplied from a battery (not shown). In the following description, the term "device" can be interpreted as a circuit, device, unit, etc. The hardware configuration of the information processing device 30 may be configured to include one or more of the devices shown in FIG. 3, or may be configured without including some of the devices. Furthermore, the information processing device 30 may be configured by communicating and connecting multiple devices each having a different housing.

[0017] Each function in the information processing device 30 is realized by loading specified software (programs) onto hardware such as the processor 3001 and memory 3002, causing the processor 3001 to perform calculations, control communication via the communication device 3004, and control at least one of reading and writing data in the memory 3002 and storage 3003.

[0018] The processor 3001 controls the entire computer by running, for example, an operating system. The processor 3001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. Furthermore, for example, a baseband signal processing unit, a call processing unit, etc. may be realized by the processor 3001.

[0019] The processor 3001 reads programs (program codes), software modules, data, etc. from at least one of the storage 3003 and the communication device 3004 into the memory 3002 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 below. The functional blocks of the information processing device 30 may be implemented by a control program stored in the memory 3002 and running on the processor 3001. Various processes may be executed by one processor 3001, or may be executed simultaneously or sequentially by two or more processors 3001. The processor 3001 may be implemented by one or more chips. The programs may be transmitted to the information processing device 30 via a telecommunications line.

[0020] The memory 3002 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 3002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 3002 can store executable programs (program codes), software modules, etc. for implementing the method according to this embodiment.

[0021] Storage 3003 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 3003 may also be called an auxiliary storage device.

[0022] The communication device 3004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0023] Each device, such as the processor 3001 and the memory 3002, is connected by a bus for communicating information. The bus may be configured using a single bus, or may be configured using different buses between each device.

[0024] The information processing device 30 may 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 3001 may be implemented using at least one of these pieces of hardware.

[0025] 4 is a block diagram showing the functional configuration of the information processing device 30. In the information processing device 30, a processor 3001 reads a program or the like from a storage 3003 into a memory 3002 and executes the program, thereby realizing the functions of a storage unit 31, a derivation unit 32, a selection unit 33, and an output unit 34.

[0026] The storage unit 31 stores data related to each viewer and each content. The data related to each viewer includes attribute data such as the name, gender, and age of each viewer. The data related to each content includes, for example, a viewing history such as the number of times each viewer has viewed each content and the viewing time, as well as metadata such as the title of each content, the genre to which each content belongs, the actors, characters, and other characters appearing in each content, the supervisors involved in the creation, editing, and supervision of each content, and the attributes of each content. Of this data, the attribute data such as the name, gender, and age of each viewer and the viewing history such as the number of times each viewer has viewed each content and the viewing time, are used to classify viewer groups. At least one of the title, genre, characters, supervisor, and attributes of the content is used to classify content groups.

[0027] The derivation unit 32 generates and stores an algorithm for deriving KPIs for a content distributor from the viewing history of the content distributed to the viewer. In other words, this algorithm is an algorithm that shows the causal relationship between the content viewing history and the KPI, and by using, for example, machine learning represented by a multiple regression model or a causal search model called the LiNGAM model, when the viewing history of each content is, for example, X, the number of views or viewing time, the KPI is generated as a model that expresses the KPI as a linear expression or an n-th order equation of X. This algorithm is generated for each of the above-mentioned viewer groups.

[0028] FIG. 5 is a diagram illustrating the relationship between viewing history and KPIs when a multiple regression model is used in this embodiment, and FIG. 6 is a diagram illustrating the relationship between viewing history and KPIs when a LinGAM model is used in this embodiment. The multiple regression model is generated by multiple regression analysis using training data in which the content viewing history of each viewer belonging to a certain viewer group is used as an explanatory variable and the KPI related to that viewer group is used as a target variable. The content viewing history of each viewer is stored in a viewing history database (not shown) of the content distribution system 20, and this is used as training data. Furthermore, since various methods for calculating KPIs are known, the training data can be obtained by calculating them using these methods. In contrast, the LinGAM model can consider the viewing history of other content that influences the viewing history of a certain content as a causal effect.

[0029] By inputting the number of views or viewing time (viewing history) of each content included in a content group that can be distributed to viewers into the algorithm generated in this way, it is possible to output the KPIs that are likely to be achieved by distributing that content group for each viewer group. The sum of the KPIs output in this way for each viewer group becomes the KPI for all viewers. In this way, by generating an algorithm for deriving KPIs for each viewer group, it is possible to understand the causal relationship between viewing history and KPIs specific to each viewer group.

[0030] On the other hand, the reason for analyzing the causal relationship between viewing history and KPIs using viewing history for each content group is that if the total number of contents distributed by the content distribution system 20 is very large, the processing required to select the optimal content becomes enormous, and the processing burden becomes excessive for limited computer resources. For this reason, content groups that are recognized to have a certain degree of similarity are each treated as a single unit of content. However, this is just one example, and if there are sufficient computer resources, it is not necessarily necessary to use viewing history for each content group as in this embodiment.

[0031] For example, when using a multiple regression model, the y value corresponding to the KPI value in a linear formula such as the following equation is used: kpi can be expressed as:

[0032]

[0033] In this equation, β0 is a constant term, β1 to β n are coefficients corresponding to each content 1 to n, and x1 to x n is the number of views or viewing time of each content 1 to n, z1 to z n is 1 or 0 indicating whether or not each of the contents 1 to n is to be distributed (1 means distributed, 0 means not distributed). As mentioned above, each content here may be a unit of a group of contents divided according to predetermined conditions from the viewpoint of reducing the processing load, or may be a unit of each individual content (the same applies below).

[0034] In addition, when using the LinGAM model, for example, the y value corresponding to the KPI value is expressed in a linear formula as follows: kpi can be expressed as:

[0035]

[0036] In this formula, β ij is the causal effect, and x i is the number of views or viewing time (viewing history) of content i, and z i is 1 or 0 indicating whether or not each content i is distributed (1 means distributed, 0 means not distributed), and e i is the potential demand for content i, and a ij is the causal effect of the non-intervention variable i, and v i is the no-intervention variable i, and u i is the potential demand for the non-intervention variable i. The non-intervention variables here include, for example, the viewing time for each content group, the number of word-of-mouth reviews, and the amount of campaigns.

[0037] Returning to the explanation of FIG. 4, the derivation unit 32 uses the above algorithm to derive the KPI when each of the contents that can be distributed is not distributed to the viewer. Specifically, the derivation unit 32 calculates the KPI when each of the contents is not distributed (i.e., z1 to z2) in each of the above formulas. n or z = 0) kpi is derived for every combination of content currently being distributed. In other words, the derivation unit 32 performs a process of calculating a KPI for every combination of multiple content that can be distributed, assuming that the presence / absence data of content that is assumed not to be distributed indicates no distribution, thereby deriving a KPI when each of the content that can be distributed is not distributed to the viewer.

[0038] The selection unit 33 selects a combination of contents to be distributed to the viewer by using the cost required to distribute each content to the viewer and an index when each content is not distributed to the viewer. Here, the cost y required to distribute the content to the viewer cost (i.e., the cost when a content distributor acquires content from a content provider for a fee) is expressed by the following formula: In this formula, C i is the cost required to distribute content i (the cost of acquiring content i), and z i is 1 or 0 indicating whether or not each content i is distributed (1 means distributed, 0 means not distributed), Di is the cost per unit number of times or per unit playback time when a fee is paid to a content provider according to the number of times or duration of playback of the content, and x i is the number of views or viewing time (viewing history) of content i, and n is the number of contents. When paying a fee to a content provider according to the number of times or duration of content playback, C i = 0 (D i ≠0), otherwise D i = 0 (C i ≠0).

[0039] The selection unit 33 selects y costAmong the content groups for which the KPI falls within a desired range (for example, a predetermined range based on the budget, such as 95% to 100% of the total budget required to acquire the content), the content group that maximizes the KPI is selected as the content group to be distributed to viewers. This involves solving an optimization problem known as the knapsack problem, which can be solved using a linear solver when a multiple regression model is used, or by quantum annealing when a LiNGAM model is used. In this case, the selection unit 33 assigns a relatively large weight to content that has a strong causal relationship with a viewer group with a relatively large number of viewers, and a relatively small weight to content that has a strong causal relationship with a viewer group with a relatively small number of viewers, thereby selecting the content group to be distributed to viewers.

[0040] The output unit 34 outputs the result of derivation by the derivation unit 32 and the result of selection by the selection unit 33, for example, y cost A list of content groups that maximize the KPI among content groups that fall within the desired range, cost The output unit 34 outputs the result of the selection by the selection unit 33, for example, y cost A list of a predetermined number of content groups in descending order of the KPI from the content groups whose y falls within a desired range, cost The KPI may also be output.

[0041] [Operation] Next, the operation of the information processing device 30 will be described with reference to Fig. 7. Note that in the following description, when the information processing device 30 is described as the subject of processing, this specifically means that the processing is executed by loading predetermined software (programs) onto hardware such as the processor 3001 and memory 3002, causing the processor 3001 to perform calculations and controlling communication via the communication device 3004 and reading and / or writing of data from the memory 3002 and storage 3003. It is assumed that by the time the processing shown in Fig. 7 starts, the derivation unit 32 has generated and stored an algorithm for deriving KPIs for the content distributor from the viewing history of the content distributed to the viewer.

[0042] The derivation unit 32 derives a KPI when each of the contents that can be distributed is not distributed to the viewer (step S11).

[0043] The selection unit 33 selects a combination of contents to be distributed to the viewer using the cost required to distribute each content to the viewer and an indicator of what would happen if each content was not distributed to the viewer (step S11).

[0044] The output unit 34 outputs the derivation result by the derivation unit 32 and the selection result by the selection unit 33 .

[0045] According to the embodiment described above, it is possible to select a combination of content to be distributed to viewers by taking into consideration both an indicator that measures the degree to which the content distributor has achieved its performance goals and the costs required to prepare the content to be distributed to viewers.

[0046] [Modifications] The present invention is not limited to the above-described embodiment. The above-described embodiment may be modified as follows. Furthermore, two or more of the following modifications may be combined and implemented.

[0047] [Variation 1] The derivation unit 32 preferably derives KPIs using not only past viewing history but also future viewing history predicted from the past viewing history. Specifically, the derivation unit 32 calculates the number of viewings or viewing time of content for a predetermined period, such as each month or each week, and predicts the number of viewings or viewing time using a time series prediction model, such as ARIMA (Auto Regressive Integrated Moving Average). In this case, a time series prediction model is prepared according to the genre or attribute of the content. For example, classic movies are content that does not see a significant increase in the number of views in a specific period but can be expected to see a certain number of views. Christmas movies are content that sees an increase in views during a specific season. News is content that sees a sudden increase in the number of views but then converges. For this reason, the derivation unit 32 stores time series prediction models according to the genre or attribute of the content, and uses the time series prediction model corresponding to the genre or attribute of the content when deriving the KPI.

[0048] [Variation 2] The selection unit 33 may select a combination of content by excluding KPIs derived for a certain specific viewer group. The certain specific viewer group here refers to, for example, a very small number of viewer groups.

[0049] [Variation 3] For example, multiple users, such as family members or friends, may use the same account to view content. The viewing history of such a user terminal 10 may show an extremely long viewing time or an extremely large number of viewings compared to when a single user uses a single account. Therefore, for example, a threshold value for the viewing time or number of viewings may be set, and for accounts exceeding the threshold, it may be assumed that multiple users are viewing content using the same account. In this case, the derivation unit 32 derives a KPI for an account that is assumed to be used by multiple viewers, which is lower than that for an account used by a single viewer.

[0050] [Other Modifications] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wires, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or the multiple devices.

[0051] Functions include, but are not limited to, judgment, determination, judgment, 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.

[0052] For example, the information processing device 30 according to an embodiment of the present disclosure may function as a computer that performs the processing of the present disclosure.

[0053] Each aspect / embodiment described in the present disclosure may be applied to at least one of systems using LTE (Long Term Evolution), LTE-Advanced (LTE-A), SUPER 3G, IMT-Advanced, 4G (4th generation mobile communication system), 5G (5th generation mobile communication system), FRA (Future Radio Access), NR (New Radio), 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 802.20, UWB (Ultra-Wide Band), Bluetooth (registered trademark), or other suitable systems, and next-generation systems enhanced based on these. Furthermore, a combination of multiple systems (e.g., a combination of at least one of LTE and LTE-A with 5G, etc.) may also be applied.

[0054] 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.

[0055] 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.

[0056] 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).

[0057] 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.

[0058] Software, whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise, should 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. Additionally, software, instructions, information, etc. may 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 such wired and / or wireless technologies are included within the definition of a transmission medium.

[0059] 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 voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof. 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.

[0060] Furthermore, the information, parameters, etc. described in this 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.

[0061] 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."

[0062] 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.

[0063] The "unit" in the configuration of each of the above devices may be replaced with "means," "circuit," "device," etc.

[0064] 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.

[0065] 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.

[0066] 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."

[0067] 1: Communication system, 2: Communication network, 10: User terminal, 1001: Processor, 1002: Memory, 1003: Storage, 1004: Communication device, 1005: Input device, 1006: Output device, 20: Content providing system, 30: Information processing device, 31: Storage unit, 32: Derivation unit, 33: Selection unit, 34: Output unit, 3001: Processor, 3002: Memory, 3003: Storage, 3004: Communication device.

Claims

1. An information processing device comprising: a derivation unit that uses an algorithm to derive an index that measures the degree of achievement of the content distributor's performance goals from the viewing history of the content distributed to the viewer, and derives the index when each piece of content that could be distributed is not distributed to the viewer; and a selection unit that selects a combination of content to be distributed to the viewer using the cost required to distribute each piece of content to the viewer and the index when each piece of content is not distributed to the viewer.

2. The information processing device described in claim 1, characterized in that the derivation unit uses a formula including a term that multiplies the viewing history of each content by presence / absence data indicating whether each content is distributed, and calculates the index by treating the presence / absence data of content that is assumed not to be distributed as indicating non-distribution, for all combinations of multiple content that may be the subject of distribution, thereby deriving the index when each content that may be the subject of distribution is not distributed to the viewer.

3. The information processing device according to claim 1, characterized in that the viewing history is divided into a plurality of groups, the derivation unit derives the index using the viewing history with each of the groups as a unit, and the selection unit selects a combination of content to be delivered to the viewer with each of the groups as a unit.

4. The information processing device described in claim 3, characterized in that the viewers are classified into multiple viewer groups, the derivation unit derives the index using viewing histories for each of the viewer groups as a unit, and the selection unit selects a combination of content using weights according to the number of viewers belonging to each of the viewer groups.

5. The information processing device according to claim 3, wherein the selection unit selects a combination of content by excluding the index derived for a certain viewer group.

6. The information processing device according to claim 1, wherein the derivation unit derives the index using not only past viewing histories but also future viewing histories predicted from the past viewing histories.

7. The information processing device according to claim 1, characterized in that the derivation unit derives the index to be a lower value for an account that is estimated to be used by multiple viewers compared to an account that is used by a single viewer.

Images