Estimation device

Abstract

This estimation device constructs a first estimation model and a second estimation model. The first estimation model uses first table data composed of first data indicating attributes of each user of a first user group to estimate missing data in the first table data. The second estimation model uses the first data for a common user group in second table data and the first table data to estimate missing data for the common user group in the second table data. The estimation device uses the first estimation model and the second estimation model to estimate values of the second data for the first user group excluding the common user group.

Description

Technical Field

[0001] This disclosure relates to an estimation device.

Background Art

[0002] Patent Document 1 discloses a technique related to data completion. This technique calculates the degree of correlation with other data items when there are missing data values in a plurality of data records, and performs completion by a regression method of data values based on the data item values.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Regarding a first user group and a second user group in which some users are common users, consider integrating first table data storing first data of the first user group and second table data storing second data of the second user group. If there is missing data in the first table data and the second table data, if the missing data remains in the integrated data, the utility value of the integrated data may decrease. Also, when the first data and the second data have different data items, since there is first data and second data for the common users, it is possible to obtain integrated data for the common users. However, for example, there is no second data for a first user other than the common users, so it is difficult to obtain integrated data for such users.

[0005] This disclosure has been made in view of the above, and an object thereof is to provide an estimation device capable of accurately complementing data.

Means for Solving the Problems

[0006] The estimation device relating to this disclosure comprises a first learning unit, a second learning unit, and an estimation unit. The first learning unit constructs a first estimation model. The first estimation model estimates missing data in the first table data based on first table data consisting of first data indicating the attributes of each user in the first user group. The second learning unit constructs a second estimation model. The second estimation model estimates missing data of the common user group in the second table data based on the second table data and first data for the common user group in the first table data. The second table data has second data indicating the attributes of each user in the second user group, which is a common user group shared with a part of the first user group. The estimation unit estimates the values ​​of the second data for the first user group excluding the common user group, based on the first estimation model and the second estimation model.

[0007] In the estimation device described above, missing data in the first table data is imputed by the first estimation model, and missing data in the second table data is imputed by the second estimation model. Then, the second data for first users other than common users is imputed based on the first and second estimation models. The second estimation model, which estimates missing data in the second table data, is constructed based on the first and second data, and reflects the content of the first data. Therefore, the estimation unit that estimates data based on the first and second estimation models can accurately estimate the second data that the first table data originally did not have. [Effects of the Invention]

[0008] According to this disclosure, data can be accurately interpolated. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows the configuration of an example estimation device according to an embodiment of this disclosure. [Figure 2] Figure 2 is a diagram illustrating the contents of the first table data as an example. [Figure 3] Figure 3 is a diagram illustrating the contents of an example of the second table data. [Figure 4] Figure 4 schematically shows one example of a first estimation model. [Figure 5] Figure 5 is a diagram illustrating the contents of an example of integrated data. [Figure 6] Figure 6 schematically shows one example of a second estimation model. [Figure 7] Figure 7 shows the hardware configuration of an example estimation device. [Modes for carrying out the invention]

[0010] The embodiments of the estimation device relating to this disclosure will be described in detail below, along with the drawings. In the description of the drawings, the same elements will be denoted by the same reference numerals, and redundant explanations will be omitted.

[0011] Figure 1 shows the configuration of an example estimation device 10. This example estimation device 10 can be used in a system to supplement missing data in the integrated table data when integrating two table data sets that have different attribute data. Below, an example of integrating the first table data and the second table data will be described. The first table data consists of information of the first group of users who use the first service. The second table data consists of information of the second group of users who use the second service. In this example, the first service and the second service may be services in which points are awarded to users in accordance with their purchase of goods, etc., but the content of the first service and the second service is not limited to this. The first group of users who use the first service and the second group of users who use the second service have some common users. That is, the first group of users includes users who also use the second service (common users). In this embodiment, for the sake of simplicity of explanation, it is assumed that all of the second group of users are common users. For example, we will describe an example where the estimation device 10 is used by the company when the company operating the first service is the company itself, and the company operating the second service is a partner company, and the partner company provides second table data only for common users.

[0012] As shown in Figure 1, an example estimation device 10 includes an input unit 11, a preprocessing unit 12, a first learning unit 13, a second learning unit 15, an estimation unit 16, and an output unit 17. The input unit 11 includes a first data input unit 11A and a second data input unit 11B. The first data input unit 11A receives the contents of a first table data containing data (first data) of a first group of users who use the first service. The first table data may be managed by the company itself. The second data input unit 11B receives the contents of data for a common group of users from the second table data. In this embodiment, since all of the second group of users constituting the second table data are common users, the contents of the second table data may be directly input to the second data input unit 11B. The second table data may be managed by a partner company. For example, the second data may be data extracted for common users from the second table data managed by a partner company.

[0013] Figure 2 shows the contents of the first table data. Figure 3 shows the contents of the second table data. In one example, the first data consists of a user ID (identifier) ​​to identify the user and attribute data for each user. The user attribute data may include basic information and behavioral information. Basic information may include static characteristics such as the user's gender, age, and place of residence. Note that the basic information may be based on contract information obtained from the user when they start using the first service. Behavioral information includes dynamic characteristics resulting from the user's actions, such as the amount of payment made by the user related to the first service. Behavioral information may include multiple behavioral histories with different characteristics. In the example in Figure 2, the age item for the user with user ID 2 and the payment amount item for the user with user ID 4 are missing data and are indicated by "-".

[0014] Furthermore, user behavior information may be obtained through an application running on the terminal device. The terminal device is, for example, a communication device operated by the user. The terminal device may be, for example, a mobile device such as a high-function mobile phone (smartphone), a mobile phone, or a personal digital assistant (PDA). Furthermore, the devices constituting the terminal device are not interpreted restrictively.

[0015] In one example, the second data set consists of a common user ID for identifying common users and data about each user's attributes. The common user ID may have the same identification code as the user ID in the first data set. Note that the user ID (common user ID) may also be personally identifiable information such as an email address or mobile phone number. In this case, users with the same user ID included in both the first and second table data can be extracted as common users. In the example shown in Figure 3, users with user IDs 2, 3, 4, and 7 among the first group of users that make up the first table data are exemplified as common users. Also, in the example shown in Figure 3, the favorite stores item for the user with common user ID 3, the residential area and favorite stores item for the user with user ID 4, and the residential area item for the user with user ID 7 are all missing data and are indicated by "-".

[0016] In the second data set, user attributes may include basic information and behavioral information. Basic information includes static characteristics such as the user's residential area. In addition to the residential area, basic information may also include gender, etc., as in the first data set. In this example, basic information that overlaps with the first data set and is included in the second table data may be deleted before being entered into the second data input unit 11B. Behavioral information includes dynamic characteristics resulting from the user's actions in the second service, such as the user's membership rank, usage points, and favorite stores.

[0017] The preprocessing unit 12 performs a process of converting the first data input to the first data input unit 11A and the second data input to the second data input unit 11B into a format that can be processed by the first learning unit 13 and the second learning unit 15. In one example, the preprocessing unit 12 may convert the string data included in the first data and the second data into numerical data.

[0018] Also, the preprocessing unit 12 represents the input table data on the graph space. FIG. 4 schematically shows an example of representing the first table data on the graph space as an example of the table data represented on the graph space. The table data in the present embodiment is composed of a user ID that identifies each user and values for each item of the data sequence associated with the user ID. Therefore, the preprocessing unit 12 represents the user and each item of the data sequence as nodes. In FIG. 4, each user ID is represented as a node 31 surrounded by a circle, and each item is represented as a node 32 surrounded by a square. The preprocessing unit 12 connects the node 31 of the corresponding user and the node 32 of the item with the value of the item as an edge 33. The preprocessing unit 12 embeds and represents the nodes 31, 32, and the edge 33 so that the user, the item, and the value are represented by vectors. Hereinafter, the vector 31a of the user generated by the embedding representation is called a feature vector, the vector 32a of the item is called a variable vector, and the vector 33a of the value is called a weight vector.

[0019] The preprocessing unit 12 represents the first table data on the graph space as preprocessing for model construction in the first learning unit 13. Also, the preprocessing unit 12 represents, as preprocessing for model construction in the second learning unit 15, table data (common table data) in which the first data and the second data for the common user group are integrated on the graph space.

[0020] For example, the preprocessing unit 12 may generate common table data in which the first data of the common user group constituting the first table data and the second data of the common user group constituting the second table data are integrated, and represent the generated common table data on the graph space. FIG. 5 is a diagram showing the content of the common table data. An example of the common table data is composed of a user ID and data about the attributes of each user. The attributes of the user include basic information and behavior information in the first data and basic information and behavior information in the second data. In FIG. 5, for ease of understanding, the data related to the common users of the first data shown in FIG. 2 and the second data shown in FIG. 3 are directly integrated, but for each data, data converted into numerical data by the preprocessing unit 12 may be used.

[0021] The first learning unit 13 uses the first table data on the graph space processed by the preprocessing unit 12 as learning data, and utilizes deep learning techniques using a neural network (here, a graph neural network) to construct a first estimation model. For example, the first learning unit 13 updates the initial values given to the feature vector and the variable vector in the preprocessing unit 12 while repeating learning using the data of each user based on an adjacency matrix representing the positional relationship between the user node and the item node, a feature vector representing the features of the user, a variable vector representing the features of the item, and a weight vector representing the features of the value, thereby constructing a learning model for estimating the value of each item from the feature vector and the variable vector. That is, the first estimation model learned by the first learning unit 13 has a feature vector and a variable vector for estimating the value of each item in the first table data.

[0022] The second learning unit 15 uses the common table data in the graph space processed by the preprocessing unit 12 as training data and constructs a second estimation model using deep learning techniques with a neural network. The learning method in the second learning unit 15 may be the same as that of the first learning unit 13. That is, the model learned by the second learning unit 15 has feature vectors and variable vectors for estimating the values ​​of each item in the common table data.

[0023] The estimation unit 16 estimates the missing data in the first table data and generates the first table data with the missing data imputed. In one example, the estimation unit 16 may use the first estimation model constructed by the first estimation model to imputate the missing data in the first table data. That is, the estimation unit 16 may obtain the user feature vector and the item variable vector corresponding to the missing data in the first table data from the first estimation model. The estimation unit 16 may estimate the missing data in the first table data based on the obtained feature vector and variable vector. The common table data used in the second learning unit 15 described above may be generated based on the first table data with the missing data imputed by the first estimation model.

[0024] The estimation unit 16 may use the second estimation model constructed by the second estimation model to fill in the missing data in the first table data. That is, the estimation unit 16 may obtain user feature vectors and item variable vectors corresponding to the missing data in the first table data from the second estimation model. The estimation unit 16 may estimate the missing data in the first table data based on the obtained feature vectors and variable vectors. The estimation unit 16 may also use the average value of the estimated values ​​estimated by the first estimation model and the estimated values ​​estimated by the second estimation model to fill in the missing data in the first table data.

[0025] Furthermore, the estimation unit 16 estimates the missing data in the common table data and generates common table data with the missing data imputed. That is, the estimation unit 16 may obtain user feature vectors and item variable vectors corresponding to the missing data in the common table data from a second estimation model. The estimation unit 16 may estimate the missing data in the common table data based on the obtained feature vectors and variable vectors.

[0026] The estimation unit 16 estimates the second data for the first user group other than the common users in the first table data. That is, in the illustrated example, the membership rank, etc., is estimated for users with user IDs 1, 5, 6, etc. In one example, the estimation unit 16 may use the first estimation model and the second estimation model to estimate the second data for the first user group other than the common users in the first table data. The estimation unit 16 may obtain feature vectors corresponding to each of the first user group other than the common users in the first table data from the first estimation model, and obtain variable vectors of items corresponding to the second data from the second estimation model. The estimation unit 16 may estimate the second data for the first user group based on the obtained feature vectors and variable vectors.

[0027] The output unit 17 outputs integrated table data composed of first data and second data for the first user group. Missing data in the first data constituting the integrated data table may be imputed by the estimation unit 16. Missing data in the second data for common users constituting the integrated data table may be imputed by the estimation unit 16. The second data for the first user group constituting the integrated data table may be data estimated by the estimation unit 16. The output unit 17 may output the first table data with missing data imputed, or it may output the second table data with missing data imputed.

[0028] Figure 6 is a flowchart showing the operation of the estimation device 10 in one example. First, the estimation device 10 receives input data for the first table data and data for the second table data into the input unit 11 (step S1). The second table data may include users other than common users, but here it is assumed to consist only of common users.

[0029] Next, the first data constituting the first table data is preprocessed (step S2). That is, the preprocessing unit 12 represents the first table data in graph space. Next, the first learning unit 13 constructs a first estimation model based on the preprocessed first table data (step S3). Next, the estimation unit 16 imputes missing data in the first table data (step S4). That is, the estimation unit 16 uses the feature vector and variable vector of the first estimation model constructed by the first learning unit 13 to imputate missing data in the first table data.

[0030] Next, the common data is preprocessed (step S5). First, the preprocessing unit 12 extracts data for common users between the first table data and the second table data to generate common table data. Missing data in the first table data is imputed in step S4. Next, the preprocessing unit 12 represents the generated common table data in graph space. Subsequently, the second learning unit 15 constructs a second estimation model based on the preprocessed common table data (step S6).

[0031] Next, the estimation unit 16 imputes the missing data in the second table data (step S7). That is, the estimation unit 16 uses the feature vector and variable vector of the second estimation model constructed by the second learning unit 15 to imputate the missing data in the second table data.

[0032] Next, the estimation unit 16 re-fills the missing data in the first table data (step S8). For example, the estimation unit 16 estimates the missing data in the first table data using the feature vector of the first estimation model and the variable vector of the second estimation model, and fills in the missing data by averaging this estimated missing data with the missing data estimated in step S4. Note that the first data for common users in the first table data may be filled in using the feature vector and variable vector of the second estimation model constructed by the second learning unit 15.

[0033] Next, the estimation unit 16 estimates the second data for the first user group (step S9). That is, the estimation unit 16 estimates the second data for the first user group, excluding common users, using the feature vector of the first estimation model and the variable vector of the second estimation model.

[0034] Next, the output unit 17 outputs integrated table data in which the missing data and the second data for the first user group have been supplemented by the estimation unit 16. In one example, the missing data in the first table data portion is supplemented in step S8, the missing data in the second table data portion is supplemented in step S7, and the second data for the first user group excluding common users is estimated in step S9.

[0035] As described above, one example of an estimation device 10 includes: a first learning unit 13 that constructs a first estimation model for estimating missing data in the first table data based on the first table data; a second learning unit 15 that constructs a second estimation model for estimating missing data for the common user group in the second table data based on the second data for the common user group in the second table data and the first data for the common user group in the first table data; and an estimation unit 16 that estimates the values ​​of the second data for the first user group excluding the common user group based on the first estimation model and the second estimation model.

[0036] In the estimation device 10 described above, missing data in the first table data is imputed by the first estimation model, and missing data in the second table data is imputed by the second estimation model. Then, the second data for first users other than common users is imputed based on the first and second estimation models. The second estimation model, which estimates missing data in the second table data, is constructed based on the first and second data, and reflects the content of the first data. Therefore, the estimation unit 16, which estimates missing data based on the first and second estimation models, can accurately estimate the second data that the first table data did not originally contain.

[0037] One example of a first estimation model may estimate the value of each item corresponding to each user in the first user group from the features of each user in the first user group and the features of each item constituting the first table data. Another example of a second estimation model may estimate the value of each item corresponding to each user in the common user group from the features of each user in the common user group and the features of each item constituting the second table data. Another example of an estimation unit 16 may estimate the value of the second data for the first user group excluding the common user group based on the features of each user in the first user group used in the first estimation model and the features of each item constituting the second table data used in the second estimation model. In this configuration, when estimating the second data for the first user group, the user features reflect the data from the first table data, and the features of the items in the second data reflect the data of common users in both the first and second table data. In this case, since the user features are generated from the first table data, which consists of the first user group, which is larger in number than the common user group, bias is less likely to occur in the user features. Furthermore, since the feature vectors for the items in the second data set are generated based on the first and second data sets of the common user group, the feature vectors can be generated with greater accuracy compared to the case where the feature vectors for the items in the second data set are generated based solely on the second data set of the common user group. Therefore, the second data, which was not originally present in the first table data, can be estimated with greater accuracy based on the feature vectors of the first user and the feature vectors of the items in the second data set.

[0038] In one example, the features of each user in the first user group used in the first estimation model and the features of each item constituting the second table data used in the second estimation model may be represented as vectors. This configuration makes it easy to construct estimation models using so-called graph neural network techniques.

[0039] One example of a second estimation model may estimate missing data in the first table data based on the first and second data for a common user group. In this configuration, the missing data can be estimated more accurately than in the first estimation model as the number of items in the data column increases.

[0040] In one example, the second learning unit 15 may construct a second estimation model based on the first table data, in which missing data has been imputed by the first estimation model, and the second table data. In this configuration, by utilizing the first table data in which missing data has been imputed, a second estimation model with high estimation accuracy can be constructed.

[0041] Although one embodiment has been described in detail above with reference to the drawings, the specific configuration is not limited to this embodiment. For example, an example of constructing a learning model using deep learning techniques with a graph neural network has been described, but other machine learning techniques can be used as long as they can estimate the second data about the first user based on the characteristics of the first user estimated from the first estimation model and the characteristics of the items of the second data estimated from the second estimation model.

[0042] The block diagram used in the description of the above embodiment shows functional units. 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 it may be realized using two or more physically or logically separated devices that are directly or indirectly connected (for example, using wired or wireless connections). A functional block may be realized by combining the above one device or the above multiple devices with software.

[0043] Functions include, but are not limited to, judgment, decision, judgment, calculation, calculation, processing, derivation, investigation, exploration, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, assumption, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating (mapping), and assigning. For example, a functional block (configuration part) that enables transmission is called a transmitting unit or transmitter. As mentioned above, the method of implementation is not particularly limited.

[0044] For example, the estimation device 10 in one embodiment of the present disclosure may function as a computer that performs the estimation processing of the present disclosure. Figure 7 is a diagram showing an example of the hardware configuration of the estimation device 10 according to one embodiment of the present disclosure. The estimation device 10 described above may be physically configured as a computer device including a processor 1001, memory 1002, storage 1003, communication device 1004, input device 1005, output device 1006, bus 1007, etc.

[0045] In the following explanation, the term "device" can be replaced with "circuit," "device," "unit," etc. The hardware configuration of the input unit 11, preprocessing unit 12, first learning unit 13, second learning unit 15, estimation unit 16, and output unit 17 may include one or more of the devices shown in the figure, or it may be configured to omit some of the devices.

[0046] Each function in the estimation device is realized by loading predetermined software (programs) onto hardware such as the processor 1001 and memory 1002, which allows the processor 1001 to perform calculations, control communication by the communication device 1004, and control at least one of data reading and writing in the memory 1002 and storage 1003.

[0047] The processor 1001 controls the entire computer, for example, by running an operating system. The processor 1001 may be composed of a central processing unit (CPU) that includes interfaces with peripheral devices, control units, arithmetic units, registers, etc. For example, the preprocessing unit 12, first learning unit 13, second learning unit 15, estimation unit 16, etc., described above may be implemented by the processor 1001.

[0048] Furthermore, the processor 1001 reads programs (program code), 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 accordingly. The program used is one that causes the computer to execute at least a part of the operations described in the above embodiment. For example, the pre-processing unit 12 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and other functional blocks may be implemented similarly. The above-described various processes have been explained as being executed by one processor 1001, but 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 program may also be transmitted from a network via a telecommunications line.

[0049] Memory 1002 is a computer-readable recording medium and may consist of at least one of the following: ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. Memory 1002 may also be called a register, cache, main memory, etc. Memory 1002 can store executable programs (program code), software modules, etc., for carrying out the estimation method according to one embodiment of the present disclosure.

[0050] Storage 1003 is a computer-readable recording medium and may consist of at least one of the following: an optical disc such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disc, a digital multipurpose disc, a Blu-ray® disc), a smart card, flash memory (e.g., a card, a stick, a key drive), a floppy® disk, a magnetic strip, etc. Storage 1003 may also be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, server, or other suitable medium including at least one of memory 1002 and storage 1003.

[0051] The communication device 1004 is hardware (transceiver / receiver device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as a network device, network controller, network card, communication module, etc. The communication device 1004 may be configured to include high-frequency switches, duplexers, filters, frequency synthesizers, etc., in order to implement at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, the input section 11 and output section 17 described above may be implemented by the communication device 1004.

[0052] The input device 1005 is an input device that accepts input from an external source (e.g., a keyboard, mouse, microphone, switch, button, sensor, etc.). The output device 1006 is an output device that outputs to an external source (e.g., a display, speaker, LED lamp, etc.). The input device 1005 and the output device 1006 may be configured as an integrated unit (e.g., a touch panel).

[0053] Furthermore, each device, such as the processor 1001 and memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or different buses may be configured for each device.

[0054] Furthermore, the estimation device may include hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array), and some or all of the functional blocks may be implemented by such hardware. For example, processor 1001 may be implemented using at least one of these hardware components.

[0055] Information notification is not limited to the embodiments described herein and may be carried out by other means. For example, information notification may be carried out by physical layer signaling (e.g., DCI (Downlink Control Information), UCI (Uplink Control Information)), upper layer signaling (e.g., RRC (Radio Resource Control) signaling, MAC (Medium Access Control) signaling, broadcast information (MIB (Master Information Block), SIB (System Information Block))), other signals, or combinations thereof. RRC signaling may also be called RRC messages, and may be, for example, RRC Connection Setup messages, RRC Connection Reconfiguration messages, etc.

[0056] The processing procedures, sequences, flowcharts, etc., of each aspect / embodiment described herein may be reordered, provided they are consistent with each other. For example, the methods described herein present various step elements in an exemplary order and are not limited to that specific order.

[0057] Input and output information may be stored in a specific location (e.g., memory) or managed using a management table. Input and output information may be overwritten, updated, or appended to. Output information may be deleted. Input information may be transmitted to other devices.

[0058] The determination may be made by a value represented by 1 bit (0 or 1), by a boolean value (true or false), or by a numerical comparison (for example, a comparison with a predetermined value).

[0059] Each aspect / embodiment described herein may be used individually, in combination, or switched between as needed during implementation. Furthermore, notification of specific information (e.g., notification that "X is") is not limited to explicit notification, but may also be implicit (e.g., by not providing such notification).

[0060] Although the present disclosure has been described in detail above, it will be 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 intent and scope of the present disclosure as defined by the claims. Accordingly, the descriptions in the present disclosure are illustrative and not intended to be restrictive in any way.

[0061] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, and so on, whether they are called software, firmware, middleware, microcode, hardware description languages, or by any other name.

[0062] Furthermore, software, instructions, information, etc., may be transmitted and received via a transmission medium. For example, if software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cable, fiber optic cable, twisted pair, or digital subscriber line (DSL)) and wireless technologies (such as infrared or microwave), then at least one of these wired and wireless technologies is included in the definition of a transmission medium.

[0063] The information, signals, etc. described in this disclosure may be represented using any of the various different techniques. For example, the 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.

[0064] In addition, terms used in this disclosure and terms necessary for understanding this disclosure may be replaced with terms that have the same or similar meaning.

[0065] Furthermore, the information, parameters, etc., described in this disclosure may be expressed using absolute values, relative values ​​from a given value, or other corresponding information. For example, wireless resources may be indicated by an index.

[0066] As used in this disclosure, the terms “determining” and “determining” may encompass a wide variety of actions. “Determining” may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, or inquiring (e.g., searching in a table, database, or other data structure), or ascertaining. “Determining” may also include, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), inputting, outputting, or accessing (e.g., accessing data in memory). Furthermore, "judgment" and "decision" can include considering something as having been "judged" or "decided" after resolving, selecting, choosing, establishing, comparing, etc. In other words, "judgment" and "decision" can include considering something as having been "judged" or "decided" after some action. Also, "judgment (decision)" can be reinterpreted as "assuming," "expecting," or "considering."

[0067] The terms “connected,” “coupled,” or any variation thereof, mean any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are “connected” or “coupled” with each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, “connection” may be reinterpreted as “access.” As used in this disclosure, two elements may be considered to be “connected” or “coupled” with each other using at least one of one or more wires, cables, and printed electrical connections, and, in some non-limiting and non-exclusive examples, electromagnetic energy having wavelengths in the radio frequency domain, microwave domain, and optical (both visible and invisible) domain.

[0068] In this disclosure, the phrase "based on" does not mean "based solely on" unless otherwise specified. In other words, the phrase "based on" means both "based solely on" and "based at least on."

[0069] Any reference to elements using designations such as “first,” “second,” etc., as used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient way to distinguish between two or more elements. Accordingly, references to first and second elements do not imply that only two elements may be adopted, or that the first element must precede the second element in any way.

[0070] Where the terms “include,” “including,” and their variations are used in this disclosure, these terms are intended to be inclusive, as is the term “comprising.” Furthermore, the term “or” as used in this disclosure is not intended to mean exclusive OR.

[0071] In this disclosure, if articles are added by translation, such as a, an, and the in English, this disclosure may include the fact that the noun following these articles is plural.

[0072] In this 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 "combine" may be interpreted similarly to "different."

[0073] The estimation device of this disclosure has the following configuration. [1] A first learning unit constructs a first estimation model that estimates missing data in the first table data based on first table data consisting of first data representing the attributes of each user in the first user group, A second table data having second data showing the user attributes of a second user group, which is a common user group shared with a portion of the first user group, and a second learning unit that constructs a second estimation model for estimating missing data of the common user group in the second table data based on the first data for the common user group in the first table data. An estimation device comprising: an estimation unit that estimates the values ​​of the second data for the first user group excluding the common user group, based on the first estimation model and the second estimation model. [2] The first estimation model estimates the value of each item corresponding to each user in the first user group from the feature quantities of each user in the first user group and the feature quantities of each item constituting the first table data, The second estimation model estimates the value of each item corresponding to each user in the common user group from the feature quantities of each user in the common user group and the feature quantities of each item constituting the second table data, The estimation device according to [1], wherein the estimation unit estimates the values ​​of the second data for the first user group excluding the common user group, based on the feature quantities of each user of the first user group used in the first estimation model and the feature quantities of each item constituting the second table data used in the second estimation model. [3] The estimation apparatus described in [2], wherein the features of each user in the first user group used in the first estimation model and the features of each item constituting the second table data used in the second estimation model are represented as vectors. [4] The estimation device according to any one of [1] to [3], wherein the second estimation model estimates missing data in the first table data based on the first and second data for the common user group. [5] The estimation apparatus according to any one of [1] to [4], wherein the second learning unit constructs the second estimation model based on the first table data and the second table data, from which the missing data has been imputed by the first estimation model. [Explanation of symbols]

[0074] 10... Estimation device, 11... Input unit, 11A... First data input unit, 11B... Second data input unit, 12... Preprocessing unit, 13... First learning unit, 15... Second learning unit, 16... Estimation unit, 17... Output unit, 1001... Processor, 1002... Memory, 1003... Storage, 1004... Communication device, 1005... Input device, 1006... Output device, 1007... Bus.

Claims

1. A first learning unit constructs a first estimation model that estimates missing data in the first table data based on first table data consisting of first data representing the attributes of each user in the first user group, A second table data having second data showing the user attributes of a second user group, which is a common user group shared with a part of the first user group, and a second learning unit that constructs a second estimation model for estimating missing data of the common user group in the second table data based on the first data for the common user group in the first table data. An estimation device comprising: an estimation unit that estimates the values ​​of the second data for the first user group excluding the common user group, based on the first estimation model and the second estimation model.

2. The first estimation model estimates the value of each item corresponding to each user in the first user group from the feature quantities of each user in the first user group and the feature quantities of each item constituting the first table data, The second estimation model estimates the value of each item corresponding to each user in the common user group from the feature quantities of each user in the common user group and the feature quantities of each item constituting the second table data, The estimation device according to claim 1, wherein the estimation unit estimates the values ​​of the second data for the first user group excluding the common user group, based on the feature quantities of each user of the first user group used in the first estimation model and the feature quantities of each item constituting the second table data used in the second estimation model.

3. The estimation apparatus according to claim 2, wherein the feature quantities of each user in the first user group used in the first estimation model and the feature quantities of each item constituting the second table data used in the second estimation model are represented as vectors.

4. The estimation apparatus according to claim 1, wherein the second estimation model estimates missing data in the first table data based on the first and second data for the common user group.

5. The estimation apparatus according to claim 1, wherein the second learning unit constructs the second estimation model based on the first table data and the second table data, from which the missing data has been imputed by the first estimation model.

6. A first learning unit constructs a first estimation model that estimates missing data in the first table data based on first table data consisting of first data representing the attributes of each user in the first user group, An estimation device comprising: a second table data having second data indicating the user attributes of a second user group, which is a common user group shared with a part of the first user group; and a second learning unit that constructs a second estimation model for estimating the missing data of the common user group in the second table data based on the first data for the common user group in the first table data, from which the missing data has been imputed by the first estimation model.

Images