Information processing device and information processing method

Abstract

An information processing device (10) comprises: a target probability estimation unit (11) that, for each user and on the basis of information relating to an element for determining a distribution target of the message, estimates the probability that the user is a distribution target; and a subscription rate estimation unit (13) that, for each user and on the basis of at least information relating to an element for determining a service subscription and the probability that the user is a distribution target, estimates a service subscription rate which is the probability that the user will subscribe to a service related to the message.

Description

Information processing device and information processing method

[0001] The present disclosure relates to an information processing device and an information processing method.

[0002] Previously, it was possible to use machine learning in message distribution strategies to target users who were likely to subscribe to a service.

[0003] Japanese Patent Application Laid-Open No. 2022-014529

[0004] However, the data that forms the basis of conventional targeting models contains biases in the target audience due to messages having been delivered only to specific users in the past, and biases in the target audience due to users joining the service through other channels (media / routes for attracting customers). However, there has been no consideration given to building a targeting model that takes such biases into account.

[0005] Furthermore, when constructing the targeting model, user-side factors such as whether or not the user opened the message, or the user's psychological factors at the time of opening (for example, whether or not they opened the message out of interest) were not taken into consideration. In this case, the bias of recipients and user-side factors that should be considered when constructing the targeting model as described above are collectively referred to as "user bias."

[0006] Therefore, the present disclosure aims to take into account the above-mentioned user biases and obtain effective data for building a targeting model.

[0007] The information processing device according to the present disclosure includes a target probability estimation unit that estimates the probability of a message being delivered to each user based on information regarding factors that determine the recipients of the message, and a subscription rate estimation unit that estimates a service subscription rate, which is the probability that a user will subscribe to a service related to the message, for each user based on at least information regarding factors that determine service subscription and the probability of being delivered to each user.

[0008] According to the present disclosure, it is possible to take user bias into account and obtain effective data for building a targeting model.

[0009] It is a block diagram of an entire system including an information processing device It is a flow diagram showing a first pattern of processing executed by the information processing device It is a flow diagram showing a second pattern of processing executed by the information processing device It is a diagram showing an example of a hardware configuration of the information processing device.

[0010] Hereinafter, an embodiment of an information processing device and an information processing method according to the present disclosure will be described with reference to the drawings.

[0011] [Configuration of a System Including an Information Processing Device] FIG. 1 shows a configuration diagram of a system 1 including an information processing device 10 according to the present disclosure. As shown in FIG. 1, the system 1 includes the information processing device 10, an external server 30 that manages various databases (hereinafter referred to as "DBs") described below, and a mobile terminal 20 used by a user. Among these, the external server 30 manages the following DBs: a target determination factor DB 31 that stores information about factors that determine target delivery; a delivery information DB 32 that stores information about delivery; an opening determination factor DB 33 that stores information about factors that determine message opening; a service information DB 34 that stores information about service subscriptions; and a subscription determination factor DB 35 that stores information about factors that determine service subscriptions. The external server 30 may be composed of multiple servers, and these multiple servers may share the management of the above DBs 31 to 35.

[0012] Examples of the "information related to delivery" stored in delivery information DB 32 include information related to whether or not a message has been delivered, indicating whether or not various messages have been delivered to mobile terminal 20, delivery destination information and delivery time information, information related to whether or not a delivered message has been opened at mobile terminal 20, opening time information and information on the mobile terminal on which the message was opened, an estimate of the message opening rate Y1 estimated in the past by open rate estimation unit 12 (to be described later), an estimate of the probability Z of being a delivery target estimated in the past by target probability estimation unit 11 (to be described later), etc. Of these, the estimate of message open rate Y1 is used for machine learning of an estimation model for estimating the message open rate (to be described later).

[0013] Examples of the "information related to service subscription" stored in the service information DB 34 include information related to whether a user has subscribed to a certain service, information related to the subscribed user name, service name, and time of subscription procedure, and an estimated value of the service subscription rate Y2 previously estimated by the subscription rate estimation unit 13 (described later). Of these, the estimated value of the service subscription rate Y2 is used for machine learning of an estimation model for estimating the service subscription rate (described later).

[0014] Examples of the "information relating to factors that determine delivery targets" stored in target determination factor DB31, the "information relating to factors that determine message opening" stored in opening determination factor DB33, and the "information relating to factors that determine service subscription" stored in subscription determination factor DB35 include (1) attribute information of the user of mobile terminal 20 (information such as age, gender, model used, etc.), (2) information relating to the user's psychological attributes, (3) information relating to the amount of time various applications are used on mobile terminal 20, and (4) information relating to the location of stay, distance traveled, etc., determined based on the location information of mobile terminal 20.

[0015] Of these, (1) attribute information of the user of the mobile terminal 20 (information such as age, gender, model of device used, etc.) may be obtained in advance by the external server 30 from a subscriber information DB (not shown) that stores and manages information about various users (information such as name, address, age, occupation, contact information, annual income, etc.).

[0016] (2) Information about the user's psychological attributes may be acquired in advance by the external server 30, for example, by estimating the user's psychological attributes using existing technology from application usage log data obtained from the mobile terminal 20. For example, if it is determined from the application usage log data that a user clicked or tapped on a banner advertisement on an application screen displayed on the mobile terminal 20, information about the user's psychological attributes, such as the user's interest in the genre related to the banner advertisement, can be acquired. Specific examples of psychological attributes include the BigFive, HLC (Health Locus of Control), time discount rate (average time discount rate, magnitude effect, hyperbolic discount, sign effect), behavioral inhibition system / behavioral approach system scales (also known as BIS (behavioral inhibition system) / BAS (behavioral approach system)), empathy scales, interpersonal reactivity index (IRI), and self-consciousness scales. For example, among the five dimensions of the BigFive (openness, conscientiousness, extraversion, agreeableness, and neuroticism), the lower the conscientiousness, the more likely a user is to have a frivolous personality, making them less likely to open a message they received in the first place. However, if a user opens a message despite having a frivolous personality and low conscientiousness, it can be assumed that the user is likely to have opened the message out of interest. In this way, from "(2) Information on the user's psychological attributes," it is possible to infer the user's psychological factors at the time of opening a message (such as whether or not the user opened the message out of interest), making it possible to take the user's psychological factors into consideration.

[0017] (3) Information regarding the usage time of various applications on the mobile terminal 20 is derived, for example, by the external server 30 based on application usage log data (e.g., the start time and end time of application usage) acquired from the mobile terminal 20.

[0018] (4) Information regarding the location of stay, travel distance, etc., calculated based on the location information of the mobile device 20 is derived, for example, by the external server 30 based on the location information acquired from the mobile device 20. The location information includes information indicating the location obtained by positioning, associated with the positioning time information. Therefore, it is possible to determine whether a user has stayed at a specific location for a predetermined period of time (e.g., 30 minutes) or more from the user's location information (including the positioning time). If it is determined that the user has stayed at a specific location for a predetermined period of time or more, the specific location is estimated to be the user's location. Furthermore, the travel distance may be calculated as the linear travel distance between the pre-travel location and the post-travel location from the pre-travel location information and the post-travel location information. Alternatively, the travel distance along the actual travel route may be calculated based on the pre-travel location information and the post-travel location information, as well as the constantly changing location information during the travel.

[0019] The "information on factors that determine delivery recipients," "information on factors that determine message opening," and "information on factors that determine service subscription" include at least one of the above (1) to (4), but may all be the same. In other words, the data stored in each of the target determination factor DB 31, the opening determination factor DB 33, and the subscription determination factor DB 35 may all be the same.

[0020] The information processing device 10 includes, as components for realizing the functions according to the present disclosure, a target probability estimation unit 11, an open rate estimation unit 12, and a subscription rate estimation unit 13. The functions of each unit will be described below.

[0021] The target probability estimation unit 11 is a functional unit that estimates the probability of each user being a target for delivery based on information about factors that determine the target for delivery. For example, the target probability estimation unit 11 constructs in advance an estimation model for estimating the probability of each user being a target for delivery by machine learning, and estimates the probability Z of each user being a target for delivery based on the constructed estimation model.

[0022] Specifically, the target probability estimation unit 11 constructs, in advance, an estimation model represented by the following formula (1) through machine learning as an estimation model for probability Z of being a target for distribution: Z=X1β1+e1 (1) The objective variable in the machine learning is "probability Z of being a target for distribution" obtained from the distribution information DB 32, and the explanatory variable is "factor X1 determining the target for distribution" obtained from the target determination factor DB 31. In addition, β1 in formula (1) is a machine learning / statistical modeling parameter (e.g., regression coefficient), and e1 is an error term. In the machine learning phase, appropriate β1 and e1 are determined by machine learning a large number of combinations of explanatory variable X1 and target variable Z.

[0023] In the estimation phase, the target probability estimation unit 11 inputs the element X1 that determines the target of delivery to the constructed estimation model, thereby estimating the probability Z of each user being a target of delivery, and calculating the estimated value of the probability of being a target of delivery. In this way, the values ​​with the symbol "^" indicate predicted values.

[0024] The open rate estimation unit 12 is a functional unit that estimates a message open rate, which is the probability that a delivered message will be opened, for each user based on information about factors that determine message opening and the probability that the message will be delivered. For example, the open rate estimation unit 12 constructs in advance an estimation model for estimating the message open rate by machine learning, and estimates a message open rate Y1 for each user based on the constructed estimation model.

[0025] Specifically, the open rate estimation unit 12 takes into consideration the “estimated value of the probability Z of being a target of delivery (bias of target of delivery)” estimated by the target probability estimation unit 11, and constructs in advance, by machine learning, an estimation model expressed by the following equation (2) as an estimation model for the message open rate Y1. The objective variable in the machine learning is the "message opening rate Y1" obtained from the distribution information DB 32, and the explanatory variable is the "factor X2 determining message opening" obtained from the opening determination factor DB 33. In addition, β2 and ρ1 in formula (2) are machine learning / statistical modeling parameters (regression coefficients, etc.), and e2 is an error term. In the machine learning phase, appropriate β2, ρ1, and e2 are determined by machine learning a large number of combinations of the explanatory variable X2 and the objective variable Y1.

[0026] In the estimation phase, the open rate estimation unit 12 estimates the message open rate Y1 for each user by inputting the factor X2 that determines message open into the constructed estimation model, and calculates the estimated value of the message open rate. get.

[0027] The subscription rate estimation unit 13 is a functional unit that estimates the service subscription rate, which is the probability that a user will subscribe to a service related to a message, for each user based on at least information regarding factors that determine service subscription and the probability of being a delivery target, and further derives numerical values ​​for user targeting using the following two patterns.

[0028] In a first pattern, the subscription rate estimation unit 13 calculates an index for each user based on the message open rate and the service subscription rate as a numerical value for user targeting. Specifically, the subscription rate estimation unit 13 takes into consideration the "estimated value of the probability Z of being a delivery target (bias of delivery target)" estimated by the target probability estimation unit 11, and then constructs in advance by machine learning an estimation model expressed by the following formula (3) as an estimation model for estimating the service subscription rate Y2. The objective variable in the machine learning is the "service subscription rate Y2" obtained from the service information DB 34, and the explanatory variable is the "factor X3 determining service subscription" obtained from the subscription decision factor DB 35. In addition, β3 and ρ2 in equation (3) are machine learning / statistical modeling parameters (regression coefficients, etc.), and e3 is an error term. In the machine learning phase, appropriate β3, ρ2, and e3 are determined by machine learning a large number of combinations of the explanatory variable X3 and the objective variable Y2.

[0029] In the estimation phase, the subscription rate estimation unit 13 estimates the service subscription rate Y2 for each user by inputting the factor X3 that determines service subscription into the constructed estimation model, and calculates the estimated value of the service subscription rate Y2. Furthermore, the subscription rate estimation unit 13 calculates the following weighted average or geometric mean for each user as an "index based on message opening rate and service subscription rate." Note that w1 and w2 are weights, and may or may not be w1 + w2 = 1. If the open rate and subscription rate are both considered to be equally important indicators, then for example, w1 = w2 = 0.5 is set, and if the subscription rate is considered to be a more important indicator than the open rate, then for example, w1 = 0.1 and w2 = 0.9 is set.

[0030] As described above, by calculating the weighted average or geometric mean for each user as an "index based on message opening rate and service subscription rate," it is possible to obtain effective data for building a targeting model that takes into account user bias and takes into account both message opening and service subscription.

[0031] In the second pattern, the subscription rate estimation unit 13 estimates a service subscription rate Y2 as a numerical value for user targeting. In this case, to estimate the service subscription rate Y2, the subscription rate estimation unit 13 uses a likelihood function weighted by the estimated value of the message open rate or a loss function weighted by the estimated value of the message open rate as follows: That is, the subscription rate estimation unit 13 estimates parameters such as regression coefficients for predicting the service subscription rate Y2 while taking into account the probability of being a recipient (bias of the recipient), and constructs a service subscription rate estimation model.

[0032] Taking into account the bias of the target recipients, the predicted message open rate is calculated by weighting the data of users with a high predicted message open rate, which is considered important, while the data of users with a low predicted message open rate is considered less important and weighted less, to construct a service subscription rate estimation model.In the following, the root mean squared error (RMSE) is used as an example of the loss function. In addition, p(X3|β3) in the above formula (6) represents a probability distribution such as a normal distribution. For example, in the case of a normal distribution, it becomes the following formula (8). In the above formula (8), the normal distribution random variable is Y2, and the average of the normal distribution parameters is X3β3. Therefore, if the distribution is normal, the loss function is the same as when it is RMSE. Note that unnecessary constants are omitted in the above formula (8).

[0033] In the estimation phase, the subscription rate estimation unit 13 estimates the service subscription rate Y2 taking into consideration the message opening rate Y1 for each user based on the above formula (6) or (7), and calculates the estimated value of the service subscription rate get.

[0034] As described above, by calculating an estimated service subscription rate Y2 for each user that takes into account the message open rate Y1 for each user, it is possible to obtain effective data for building a targeting model that takes into account both message opening and service subscription, taking into account user bias.

[0035] [Regarding the processing executed in the information processing device] The processing executed in the information processing device 10 (processing related to the information processing method of the present disclosure) will be described below with reference to the flow diagrams of Figures 2 and 3. Of the two patterns of index derivation by the subscription rate estimation unit 13 described above, the processing of the first pattern is shown in Figure 2, and the processing of the second pattern is shown in Figure 3. These will be described in order below. It is assumed that the estimation model shown in the above-mentioned equations (1) to (3) has been constructed in advance.

[0036] In the first pattern shown in FIG. 2, first, the target probability estimation unit 11 estimates the probability Z of each user being a target of distribution by inputting the factor X1 that determines the target of distribution into a pre-constructed estimation model of the probability of being a target of distribution, Z=X1β1+e1 (1) (Step S1 in FIG. 2).

[0037] Next, the open rate estimation unit 12 calculates a message open rate estimation model that is constructed in advance while taking into account the estimated value of the probability Z of being a target of delivery (bias of target of delivery). By inputting the factor X2 that determines message opening, the message opening rate Y1 for each user is estimated, and the estimated value of the message opening rate is is obtained (step S2).

[0038] Next, the subscription rate estimation unit 13 calculates a service subscription rate estimation model that is constructed in advance while taking into consideration the probability of being a distribution target (bias of distribution target). Based on this, the service subscription rate Y2 for each user is estimated, and the estimated value of the service subscription rate (Step S3).

[0039] Furthermore, the subscription rate estimation unit 13 calculates and outputs the following weighted average or geometric mean for each user as an index based on the message opening rate and the service subscription rate (step S4). Note that "output" in this case can take various forms, such as display output, print output, or data transmission to an external device of the information processing device 10. Regarding the weights w1 and w2, if both the open rate and the subscription rate are considered to be equally important indicators, then for example, w1 = w2 = 0.5 is set, and if the subscription rate is considered to be a more important indicator than the open rate, then for example, w1 = 0.1 and w2 = 0.9 is set.

[0040] By processing the first pattern described above, the weighted average or geometric mean can be obtained for each user as an index based on the message opening rate and service subscription rate, and an effective method of using this can be adopted, for example, by targeting users in descending order of the obtained index.

[0041] In the second pattern shown in Fig. 3, steps S1 to S2 are the same as those in Fig. 2 (processing of the first pattern), and therefore a duplicated explanation will be omitted. In step S3A following step S2, the subscription rate estimation unit 13 estimates the message opening rate as a numerical value for user targeting. Further based on this, the service subscription rate Y2 is estimated and output as follows (step S3A).

[0042] As described above, the subscription rate estimation unit 13 uses a likelihood function weighted by the estimated message open rate or a loss function weighted by the estimated message open rate to estimate the service subscription rate Y2 as follows. That is, the subscription rate estimation unit 13 estimates parameters such as regression coefficients for predicting the service subscription rate Y2 while weighting the likelihood function or loss function with the estimated message open rate, taking into account the probability of being a recipient (bias of recipients), and constructs a service subscription rate estimation model. More specifically, with regard to the predicted message open rate taking into account the bias of recipients, data of users with high predicted message open rates is considered important data and weighted heavily, while data of users with low predicted message open rates is considered less important data and weighted lightly, thereby constructing the service subscription rate estimation model. Hereinafter, the root mean squared error (RMSE) is used as an example of the loss function. In addition, p(X3|β3) in the above formula (6) represents a probability distribution such as a normal distribution. For example, in the case of a normal distribution, it becomes the following formula (8). In the above formula (8), the normal distribution random variable is Y2, and the average of the normal distribution parameters is X3β3. Therefore, if the distribution is normal, the loss function is the same as when it is RMSE. Note that unnecessary constants are omitted in the above formula (8).

[0043] In step S3A of FIG. 3, the subscription rate estimation unit 13 estimates the service subscription rate Y2 taking into consideration the message opening rate Y1 for each user based on the above formula (6) or formula (7) that has been constructed in advance, and calculates the estimated service subscription rate for each user. Obtain and output.

[0044] By processing the second pattern described above, an estimated service subscription rate that takes into account the message opening rate Y1 can be obtained for each user, allowing for an effective usage method such as targeting users in descending order of estimated service subscription rate.

[0045] 1 does not necessarily have to include the open rate estimation unit 12. For example, the information processing device 10 may be configured without the open rate estimation unit 12, and the subscription rate estimation unit 13 may use a service subscription rate estimation model that is previously constructed in consideration of the probability of being a distribution target (bias of distribution target) described above. Based on this, the service subscription rate Y2 for each user is estimated, and the estimated value of the service subscription rate obtained is may be obtained as valid data for building a targeting model that takes user bias into account.

[0046] The gist of the present disclosure lies in the following [1] to [7]. [1] An information processing device comprising: a target probability estimation unit that estimates, for each user, a probability that the user will be a target for delivery based on information about factors that determine target delivery of a message; and a subscription rate estimation unit that estimates, for each user, a service subscription rate that is the probability that the user will subscribe to a service related to the message, based on at least information about factors that determine service subscription and the target delivery probability. [2] The information processing device further comprises: an open rate estimation unit that estimates, for each user, a message open rate that is the probability that the user will open a delivered message, based on information about factors that determine message opening and the target delivery probability, wherein the subscription rate estimation unit calculates a numerical value for user targeting based on the message open rate and the service subscription rate. [3] The information processing device according to [2], wherein the numerical value is an index based on the message open rate and the service subscription rate. [4] The information processing device according to [2] or [3], wherein the subscription rate estimation unit calculates the numerical value by weighting the message open rate based on a weighting coefficient related to the message open rate and the service subscription rate based on a weighting coefficient related to the service subscription rate. [5] The information processing device according to [2], wherein the subscription rate estimation unit estimates the service subscription rate as a numerical value for user targeting based on the estimated message open rate. [6] The information processing device according to [5], wherein the subscription rate estimation unit uses a likelihood function weighted by the message open rate or a loss function weighted by the message open rate to estimate the service subscription rate. [7] The information processing device according to any one of [2] to [6], wherein at least one of the information on factors determining delivery targets, the information on factors determining message opening, and the information on factors determining service subscription includes information on user psychological attributes.[8] An information processing method comprising: a step in which an information processing device estimates, for each user, the probability that the message will be delivered based on information about factors that determine who will receive the message; and a step in which the information processing device estimates, for each user, a service subscription rate that is the probability that the user will subscribe to a service related to the message based on at least information about factors that determine service subscription and the probability that the message will be delivered.

[0047] [Explanation of Terms, Explanation of Hardware Configuration (FIG. 4), etc.] The block diagrams used in the description 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 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 (e.g., wired, wireless, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0048] 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.

[0049] 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. 4 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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).

[0057] 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).

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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, Ultra-Wideband (UWB), Bluetooth, or other suitable systems, and next-generation systems that are extended, modified, created, or defined based on these systems. It may also be applied to a combination of multiple systems (e.g., a combination of LTE and / or LTE-A with 5G).

[0062] 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.

[0063] 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 sent to another device.

[0064] 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).

[0065] 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).

[0066] 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.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] As used in this disclosure, the terms "system" and "network" are used interchangeably.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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."

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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."

[0080] 1...system, 10...information processing device, 11...target probability estimation unit, 12...opening rate estimation unit, 13...subscription rate estimation unit, 20...mobile terminal, 30...external server, 31...target determination factor DB, 32...distribution information DB, 33...opening determination factor DB, 34...service information DB, 35...subscription determination factor DB, 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 target probability estimation unit that estimates the probability of a message being delivered to each user based on information about factors that determine the recipients of the message; and a subscription rate estimation unit that estimates a service subscription rate, which is the probability that a user will subscribe to a service related to the message, for each user based on at least information about factors that determine service subscription and the probability of the message being delivered to each user.

2. The information processing device of claim 1, further comprising: an open rate estimation unit that estimates a message open rate, which is the probability that a delivered message will be opened, for each user based on information regarding factors that determine message opening and the probability of being the target of delivery; and the subscription rate estimation unit that calculates a numerical value for user targeting for each user based on the message open rate and the service subscription rate.

3. The information processing device according to claim 2, wherein the numerical value is an index based on the message opening rate and the service subscription rate.

4. The information processing device according to claim 2, wherein the subscription rate estimation unit calculates the numerical value by weighting the message opening rate based on a weighting coefficient related to the message opening rate and the service subscription rate based on a weighting coefficient related to the service subscription rate.

5. The information processing device according to claim 2, wherein the subscription rate estimation unit estimates the service subscription rate as a numerical value for user targeting based on the estimated message opening rate.

6. The information processing device according to claim 5, wherein the subscription rate estimation unit uses a likelihood function weighted by the message opening rate or a loss function weighted by the message opening rate to estimate the service subscription rate.

7. An information processing device as described in claim 2, wherein at least one of the information relating to factors determining the recipients of the delivery, the information relating to factors determining the opening of the message, and the information relating to factors determining the subscription to the service includes information relating to the psychological attributes of the user.

8. An information processing method comprising: a step in which an information processing device estimates, for each user, the probability that the message will be delivered based on information about factors that determine who will receive the message; and a step in which the information processing device estimates, for each user, a service subscription rate, which is the probability that the user will subscribe to a service related to the message, based on at least information about factors that determine service subscription and the probability that the message will be delivered.

Images