JP7354195B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Conventionally, methods for predicting user behavior on the Internet have been known. For example, in Patent Document 1, with the aim of predicting user behavior with higher accuracy than before, the tendency of search queries of users on the Internet is learned, and the learned tendency of search queries and subsequent user behavior are disclosed. A technique has been proposed in which a model is generated by calculating a relevance score with a user, and this model is used to predict the behavior of other users.

Japanese Patent Application Publication No. 2016-177377

However, with the above-mentioned techniques, it is difficult to obtain certainty as to whether or not the generated information can be trusted. For example, there is a possibility that a model that produces effective results may be included, and even if an AB test is conducted, an inappropriate model may be adopted depending on the content of the test.

The present application has been made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can confirm the reliability of generated information.

The information processing device according to the present application includes a first generation section, a second generation section, a classification section, and an evaluation section. The first generation unit quantifies the relationship between the search query input by each seed user and the predetermined action based on the commonality of the search queries entered by multiple seed users who have performed the predetermined action. Generate first list information. The second generation unit quantifies the relationship between the predetermined behavior and each user based on the search query input by each user including the seed user and the first list information, and provides a value indicating the quantified relationship. Second list information is generated in which each user is ranked based on the second list information. The classification unit classifies each user into a plurality of clusters based on the commonality of the sensor information of each user. The evaluation section evaluates the reliability of the second list information using the classification results by the classification section.

According to one aspect of the embodiment, the reliability of the generated information can be verified.

FIG. 1 is a diagram illustrating an example of an information processing system according to an embodiment. FIG. 2 is a diagram illustrating an example of a user classification method and a second list information evaluation method according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of an information processing device according to an embodiment. FIG. 4 is a diagram showing an overview of first list information according to the embodiment. FIG. 5 is a diagram illustrating an overview of second list information according to the embodiment. FIG. 6 is a diagram showing an overview of sensor information according to the embodiment. FIG. 7 is a flowchart illustrating an example of a processing procedure by the information processing apparatus according to the embodiment. FIG. 8 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS An information processing apparatus, an information processing method, and an embodiment of an information processing program (hereinafter referred to as "embodiments") according to the present application will be described in detail below with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited to the embodiments described below. Furthermore, the embodiments described below can be combined as appropriate within the range that does not conflict with the processing contents. Further, in the embodiments described below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

Furthermore, in the following description, the terminal device 10 may be referred to as a seed user U-1 or a user U-2. That is, the seed user U-1 or the user U-2 can be read as the terminal device 10. Further, seed user U-1 and user U-2 may be collectively referred to as "user U."

[1. Information processing system]
FIG. 1 is a diagram illustrating an example of an information processing system according to an embodiment. As shown in FIG. 1, the information processing system SYS according to the embodiment includes a terminal device 10 and an information processing device 100. Note that the information processing system SYS is not limited to the example shown in FIG. 1, and may include multiple terminal devices 10 and multiple information processing devices 100.

The terminal device 10 and the information processing device 100 are each connected to a network N (see FIG. 3, for example) by wire or wirelessly. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (mobile phone network, fixed telephone network, etc.), a local IP (Internet Protocol) network, or the Internet. . The network N may include a wired network or a wireless network. The terminal device 10 and the information processing device 100 can communicate with each other through the network N.

A terminal device 10 shown in FIG. 1 is an information processing device used by a user U who uses various services using search queries. For example, the terminal device 10 is realized by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a PDA (Personal Digital Assistant), or the like.

The terminal device 10 also supports wireless communication networks such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation), Bluetooth (registered trademark), and wireless LAN (Local Area It is possible to connect to the network N via short-range wireless communication such as Network).

Further, the terminal device 10 can display information for using various services using a web browser or an application. Note that when the terminal device 10 receives control information for realizing information display processing from the information processing device 100 or the like, it realizes the display processing according to the control information.

Further, the user U provides sensor information to the information processing device 100 through the use of various services. The sensor information is information acquired by various sensors installed in the terminal device 10. For example, position information acquired by a position sensor, acceleration information detected by an acceleration sensor, angular velocity information detected by a gyro sensor, operation information acquired by a touch panel, illuminance information acquired by an illuminance sensor, etc. , atmospheric pressure information acquired by an atmospheric pressure sensor, sound information acquired by a microphone, and the like.

The information processing apparatus 100 shown in FIG. 1 is an information processing apparatus that provides various services using search queries. The various services provided by the information processing device 100 may include API (Application Programming Interface) services corresponding to various applications and various online services. Online services include Internet connectivity, search services, SNS (Social Networking Services), electronic commerce services, electronic payment services, online games, online banking services, online trading services, accommodation reservation services, etc. Ticket reservation services, video distribution services, music distribution services, news distribution services, map information services, route search services, route guidance services, route information services, operation information services, weather information services, etc. Services may be applicable.

Further, the information processing device 100 is an information processing device that executes information processing according to the embodiment using sensor information collected through provision of various services. The information processing device 100 is typically a server device, but may also be realized by a mainframe, a workstation, or the like.

When the information processing device 100 is implemented as a server device, it may be implemented as a single server, or may be implemented as a cloud system in which multiple server devices and multiple storage devices operate cooperatively. Note that the information processing device 100 may function as a distribution device that distributes control information to the terminal device 10 used by the user U. Here, the control information is written in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). Note that the application itself distributed from the information processing device 100 may be regarded as control information.

[2. Information processing]
An example of information processing in the information processing system SYS will be described below. In the following description, the target of information processing according to the embodiment is the user U who uses various services. Furthermore, in the following description, a group of seed users U-1 will be collectively referred to as a "user group UG-1", and a group of all users U-2 including the seed users will be collectively referred to as a "user group UG-2". Seed user U-1 is a user who has performed a predetermined action such as ``bought 〇〇,'' ``went to 〇〇,'' or ``do 〇〇,'' or a user who has specific attributes (such as interests and preferences). It corresponds to a user with a specific user context, such as a user.

Note that the information processing described below is not limited to the case where the information processing target is the user U, but can be applied to any target for which information can be collected, such as products, towns, and services. can also be applied.

First, in the example shown in FIG. 1, the information processing device 100 identifies a user group UG-1 consisting of a plurality of seed users U-1 who have taken a predetermined action. The information processing device 100 then associates the search query input by each seed user U-1 with a predetermined action based on the commonality of the search queries input by each seed user U-1 included in the user group UG-1. First list information that quantifies the relationships between the two is generated and stored.

For example, the information processing device 100 collects users who meet the conditions (titles) such as "bought XX" and "I am interested in XX" as seed users U-1, and searches for information input by the seed user U-1. First list information is created to which a score is assigned based on the commonality of the queries. Specifically, we collect seed users U-1 who say ``wear glasses,'' search query: ``70 points'' for ``eyeglasses,'' search query: ``50 points'' for ``glass cloth,'' and search query: A score such as "-50 points" is assigned to "apple" and first list information that is a combination of a search query and a score is created.

The above-described user group UG-1, which is a group of seed users U-1, can be identified using any method. For example, the information processing device 100 estimates that the user who has performed the expected behavior is the seed user U-1 based on various information such as purchase history, usage history, location history, etc. may be specified. Specifically, the user group UG-1 is identified by inputting the name of a certain predetermined store as a search query and then estimating the number of visitors (seed users U-1) who actually visited the predetermined store. You may. As another example, user group UG-1 may be identified by inputting the name of an event as a search query and then estimating the participants (seed users U-1) who actually participated in the event. good. As yet another example, the user group UG-1 is obtained by inputting the name of a certain product as a search query and then estimating the purchasers (seed users U-1) who actually purchased the product with that name. May be specified. Further, the information processing device 100 identifies the user group UG-1 by estimating the number of users (seed users U-1) who have actually used a predetermined store (for example, a store corresponding to a distributed advertisement). It's okay. Furthermore, the information processing device 100 may identify the user group UG-1 by estimating the number of viewers (seed users U-1) who have viewed content such as a predetermined advertisement, web page, movie, or music.

Furthermore, the information processing device 100 can obtain the score of the search query in the first list from a behavioral model generated by machine learning as described below. For example, when the information processing device 100 takes a search query input by seed user U-1 as a positive example and takes a randomly selected search query input by a user other than seed user U-1 as a negative example, The learning model is trained to output a higher value when a positive example is input, and a lower value when a negative example is input. At this time, any method can be adopted for learning. For example, if a neural network is used as the model, it can be realized by backpropagation or the like.

Furthermore, the information processing device 100 may learn the model so that higher numerical values are output for search queries that are commonly input by the seed users U1. For example, the model may be trained to output a higher value as the number of seed users U-1 that input positive example search queries increases. Furthermore, the model may be trained to output a smaller value (negative value) as the number of other users who input negative example search queries increases. Then, the information processing device 100 generates a list of sets of each search query and a score output when the search query is input to such a learning model as "first list information." That is, the information processing device 100 calculates each search query input by the seed user U-1 who has performed a predetermined action, and the above-mentioned score (relationship between the search query and the predetermined action) corresponding to each search query. (score indicating 1) is generated as "first list information". Note that this first list information is generated by the information processing device 100 using a behavior model generated for each predetermined behavior, and first list information corresponding to each behavior is generated.

Subsequently, the information processing device 100 quantifies the relationship between the predetermined behavior and each user U-2 based on the search query input by the user group UG-2 and the first list information. Second list information in which each user U-2 is ranked based on the value indicating the relationship is generated and stored.

For example, the information processing device 100 selects each user U-2 from the user group UG-2 including the seed user U-1, and calculates the score associated with the search query input by each selected user U-2. 1 Specify from list information. Note that the information processing apparatus 100 may select each user U-2 included in the user group UG-2 at random, or may select them based on predetermined conditions. Then, the information processing device 100 generates a second list indicating the relationship between each user U-2 and a predetermined behavior set as a condition for collecting seed users U-1 from the total of the identified scores. Derive information. For example, in the second list information, user U-2 who has a high relationship with the predetermined behavior has a high score, and user U-2 who has a low relationship with the predetermined behavior has a low score.

Hereinafter, generation of the second list information by the information processing device 100 will be specifically described. For each of the plurality of search queries input by each user U-2 including the seed user U-1, the associated score is acquired from the first list information, and the total value of the acquired scores is calculated. In this way, the relationship between multiple search queries entered by each user U-2 and a predetermined behavior can be expressed numerically, which is more reliable than quantifying a single search query. It is possible to achieve high quantification of

Next, the information processing device 100 calculates the total score for each user U-2, and then ranks each user U-2 in descending order of the score, and searches input by each user U-2 in order of ranking. Second list information associated with the queries is generated. This second list information functions as a list indicating what kind of search query the user U-2 has input is strongly related to a predetermined action. This second list information is used for analyzing the relationship between a search query and a predetermined action, and for analyzing user U-2. This second list includes actions set when selecting seed user U-1 (for example, "bought 〇〇", "went to 〇〇", "doing 〇〇", etc.) It is created for each predetermined action.

By using the second list information described above, it is possible to provide information that is likely to be of interest to the user U-2. For example, the second list information corresponding to the action of visiting a certain store includes a ranking of user U-2 that is highly relevant to the action. Therefore, for example, by using the second list information, the distribution server that distributes advertisements can improve the advertisement effectiveness by providing advertisements related to the store to user U-2 who has a high ranking. It seems possible. Further, the second list information corresponding to the action of purchasing a certain product includes a ranking of user U-2 that is highly relevant to the action. Therefore, for example, the distribution server that distributes the advertisement uses the second list information to provide user U-2 with a high ranking with an advertisement regarding the product or a product related to the product. It is thought that advertising effectiveness can be improved.

On the other hand, with respect to the second list information mentioned above, it is difficult to obtain certainty as to whether the list accurately reflects the behavior of user U-2. That is, when ranking users U-2 based on their scores, it is not actually certain as to which ranking user U-2 has a relationship with a predetermined behavior. For example, it is inferred that the higher the score, the higher the possibility of taking a certain action, but it is difficult to determine how high the score has to be related to the given action. Furthermore, it cannot be said that verification of the correlation between the high score and the high relationship with a predetermined behavior is sufficient.

Therefore, the information processing apparatus 100 according to the embodiment proposes an information processing method for confirming the reliability of the second list information through information processing described below.

First, the information processing device 100 sets a predetermined action for selecting second list information whose reliability is to be evaluated (step S1). Next, the information processing device 100 classifies each user U-2 in the second list information based on the commonality of the sensor information collected from the user group UG-2 (step S2). Hereinafter, an example of a user classification method and a second list information evaluation method will be described using FIG. 2. FIG. 2 is a diagram illustrating an example of a user classification method and a second list information evaluation method according to the embodiment. Note that the number of users ranked in the second list information shown in FIG. 2 is an example, and more users than the example shown in FIG. 2 may be included.

First, the information processing apparatus 100 selects sensor information #EX corresponding to user U-2 (hereinafter referred to as "reference user") whose score rank is first in the second list information LT (see FIG. 2). Get -1. Next, the information processing device 100 specifies the behavior pattern X by analyzing the behavior pattern of the reference user using the acquired sensor information #EX-1.

Subsequently, the information processing apparatus 100 selects a sensor corresponding to sensor information #EX-1 for a user U-2 (hereinafter referred to as a "comparison user") other than the reference user listed in the second list LT. Each piece of information is acquired, behavior pattern analysis is performed using the acquired sensor information, and a behavior pattern corresponding to each comparison user is acquired.

An example of a method for identifying behavior patterns by the information processing apparatus 100 will be described below. For example, the information processing device 100 acquires a position history and a message transmission history such as SNS as sensor information EX-1. Furthermore, the information processing device 100 identifies a location where the user has stayed for a predetermined period of time or more from the location history. Further, the information processing apparatus 100 searches the message transmission history for a transmission message corresponding to the recording date and time of the specified position. Then, the information processing device 100 matches the content of the message with the location where it has been staying for a predetermined time or longer, and if the transmitted message is "Hamburger is delicious", the information processing device 100 corresponds to the location where it has been staying for a predetermined time. It is estimated that it was located at a hamburger shop in the area. In this way, the information processing device 100 can identify the chronological behavior pattern of the reference user by connecting the behaviors identified based on the location history and message transmission history one by one. Note that the information processing apparatus 100 can similarly identify behavior patterns for comparison users.

The information processing device 100 then compares the reference user's behavior pattern X and the comparison user's behavior pattern, and based on the similarity of the behavior patterns (whether or not the comparison user's behavior pattern is similar to the behavior pattern X). and perform clustering. For example, as shown in FIG. 2, the information processing device 100 sorts comparison users whose behavior patterns are similar to behavior pattern X into cluster X-1, and classifies comparison users whose behavior patterns are not similar to behavior pattern X into cluster X-2. Allocate to.

Then, the information processing device 100 evaluates the reliability of the second list information LT based on the classification results of each user U-2 associated with a predetermined action. For example, the information processing device 100 derives the ratio at which each user U-2 located in a predetermined rank layer in the second list information LT is assigned to the same cluster, and based on the derived ratio, Evaluate the reliability of Note that the predetermined ranking layer in the second list information LT can be arbitrarily set by the operator of the information processing device 100.

Specifically, the information processing device 100 determines the rate at which each user U-2 whose score rank is located in a ranking layer from 1st to 10th is assigned to cluster X-1 in the second list information LT. Calculate the distribution rate. Next, for example, if the information processing device 100 determines that the calculated distribution rate is equal to or higher than a predefined reliability determination threshold, the information processing device 100 determines that the score ranking is from 1st to 10th in the second list information LT. A determination result is derived that determines that the relationship between each user U-2 located in the ranking layer of and a predetermined action is reliable.

In the example shown in FIG. 2, the reliability determination threshold is set to a content rate of 90%, and each user U-2 whose score rank is located in a ranking layer from 1st to 10th is assigned to cluster X-1. A case where the ratio (distribution rate) is 90% is shown. Therefore, the information processing device 100 determines that the relationship between each user U-2 located in the 1st to 10th ranking layer of the second list information LT and the predetermined behavior is reliable. This will be derived.

On the other hand, in the example shown in FIG. 2, the proportion (distribution rate) of each user U-2 whose score ranks are located in the 11th to 20th ranks is 60%. It is shown. Therefore, the information processing device 100 determines that the relationship between each user U-2 located in the 11th to 20th ranking layer of the second list information LT and the predetermined behavior is unreliable. This will be derived.

Further, the information processing device 100 may use a plurality of behavioral patterns to classify each user U-2 into a plurality of clusters for each behavioral pattern. Then, the information processing device 100 derives, for each of the plurality of behavior patterns, the proportion at which each user U-2 located in a predetermined rank layer in the second list information LT is assigned to the same cluster, and each of the derived proportions. The reliability of the second list information LT may be evaluated by comprehensively considering the following.

For example, as shown in FIG. 2, the information processing device 100 uses the sensor information #EX-2 acquired from the reference user to perform pattern analysis of the reference user's behavior. Pattern Y is further specified.

Next, the information processing device 100 acquires sensor information corresponding to sensor information #EX-2 for each comparison user, performs behavioral pattern analysis based on the acquired sensor information, and determines the behavior corresponding to each comparison user. Get each pattern.

Subsequently, as in the case of the behavior pattern X, the information processing device 100 compares the behavior pattern Y of the reference user and the behavior pattern of the comparison user, and performs clustering based on the similarity of the behavior patterns. For example, as shown in FIG. 2, the information processing device 100 sorts comparison users whose behavior patterns are similar to behavior pattern Y into cluster Y-1, and classifies comparison users whose behavior patterns are not similar to behavior pattern Y into cluster Y-2. Allocate to.

Then, the information processing device 100 derives, for each of the behavior pattern The reliability of the second list information LT is evaluated by comprehensively considering each derived ratio.

In the example shown in FIG. 2, the proportion (distribution rate) at which each user U-2 whose score rank ranks from 1st to 10th is assigned to cluster X-1 is 90%, and A case is shown in which the ratio of allocation to Y-1 is 90%. In this case, the information processing device 100 determines that the distribution rate of the comparison user satisfies the reliability determination threshold for both the behavior pattern X and the behavior pattern Y, so that the information processing device 100 determines that A determination result indicating that the relationship between each user U-2 located in the top 10 ranks and a predetermined action is reliable is derived.

On the other hand, in the example shown in FIG. 2, the proportion (distribution rate) of each user U-2 whose score ranks are located in the 11th to 20th ranks is 60%, and , a case is shown in which the ratio of allocation to cluster Y-1 is 80%. In this case, the information processing device 100 determines that the distribution rate of the comparison user does not satisfy the reliability determination threshold for both the behavior pattern X and the behavior pattern Y, so the information processing device 100 determines that A determination result is derived that there is no reliability regarding the relationship between each user U-2 located in the top 20 ranks and a predetermined action.

Note that the information processing device 100 is not limited to classifying each user U-2 in the second list information based on the similarity between the reference user's behavior pattern and the comparison user's behavior pattern. For example, the information processing device 100 individually identifies the behavior patterns of each user U-2 located in each ranking layer based on sensor information corresponding to each user U-2. The information processing device 100 may then perform a round-robin comparison of the identified behavior patterns and classify the users U-2 whose behavior patterns are similar to each other into the same cluster. In this case, the information processing apparatus 100 may automatically set parameters during classification so that the ranks included in each cluster are unified. For example, if the number of ranks classified into each cluster (i.e., the number of users) is below a predetermined lower threshold, the information processing device 100 sets a lower threshold for determining the similarity between behavior patterns. Readjust the value. In addition, when the number of ranks (i.e., the number of users) classified into each cluster exceeds a predetermined upper threshold, the information processing device 100 sets a higher threshold for determining the similarity between behavior patterns. Readjust the value.

Furthermore, the information processing device 100 is not limited to classifying each user U-2 into a plurality of clusters based on the similarity of behavioral patterns identified using sensor information, but also based on the commonality of the sensor information itself. Accordingly, each user U-2 may be classified into a plurality of clusters. For example, the information processing device 100 can process acceleration information detected by an acceleration sensor, tilt information detected by a gyro sensor, operation information obtained by a touch panel, illuminance information obtained by an illuminance sensor, and atmospheric pressure sensor. Each user U-2 may be classified into a plurality of clusters based on commonalities such as atmospheric pressure information acquired by the microphone and sound information acquired by the microphone.

Further, the information processing device 100 may classify each user U-2 into a plurality of clusters using sensor information that is related to a predetermined behavior. For example, if the predetermined action is to visit a predetermined store, each user U-2 may be classified into multiple clusters using image information taken on the day of visiting the predetermined store. . Furthermore, if the predetermined action is to visit a predetermined store, each user U-2 may be classified into a plurality of clusters using sound information recorded on the day of visiting the predetermined store. . Further, the information processing device 100 may use sensor information that is related to a predetermined behavior when identifying a behavior pattern. In other words, the information processing device 100 may classify each user U-2 into a plurality of clusters based on the similarity of behavior patterns identified using sensor information that is related to a predetermined behavior.

Further, the information processing device 100 may classify each user U-2 into a plurality of clusters using information regarding each user U-2 estimated from the sensor information. To explain an example of information estimated from sensor information, for example, the information processing device 100 may collect information about operating states estimated from acceleration information and angular velocity information, and environment (location) estimated from environmental sounds extracted from sound information. ) information, weather and altitude information estimated from atmospheric pressure information, etc. The information processing device 100 may classify each user U-2 into a plurality of clusters based on the commonality of these pieces of information.

Note that the information processing apparatus 100 may visually provide the operator with information indicating the evaluation result of the reliability of the second list information. At this time, the information processing apparatus 100 can also provide sensor information used to classify each user U-2 included in the second list information and information on behavior patterns based on the sensor information.

[3. Configuration of information processing device]
The configuration of the information processing device 100 according to the embodiment will be described using FIG. 3. FIG. 3 is a diagram illustrating a configuration example of an information processing device according to an embodiment.

As shown in FIG. 3, the information processing device 100 includes a communication section 110, a storage section 120, and a control section 130. Note that FIG. 3 shows an example of the configuration of the information processing apparatus 100, and the information processing apparatus 100 is not limited to the configuration shown in FIG. 3, and may have a configuration including other functional units other than those shown in FIG.

(Communication Department 110)
The communication unit 110 is connected to the network N by wire or wirelessly, for example, and transmits and receives information to and from other devices such as the terminal device 10 via the network N. The communication unit 110 is realized by, for example, a NIC (Network Interface Card), an antenna, or the like. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (such as a mobile phone network or a fixed telephone network), a local IP (Internet Protocol) network, or the Internet. . The network N may include a wired network or a wireless network.

The communication unit 110 receives information such as captured images from the terminal device 10. Furthermore, the communication unit 110 transmits proposal information to the terminal device 10.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 stores programs and data for implementing information processing executed by each unit of the control unit 130.

As shown in FIG. 3, the storage section 120 includes a first list information storage section 121, a second list information storage section 122, and a user information storage section 123.

(First list information storage unit 121)
The first list information storage unit 121 stores first list information in an arbitrary format. The first list information quantifies the relationship between the search query entered by each seed user and the predetermined action, based on the commonality of the search queries entered by multiple seed users who performed the predetermined action. It is information. FIG. 4 is a diagram showing an overview of first list information according to the embodiment.

As shown in FIG. 4, the first list information is provided for each predetermined action that is set in advance when the first list information is created. The first list information includes a "search query" item and a "score" item. These items included in the first list information are associated with each other.

The "search query" item stores information on a search query input by a seed user who has performed a predetermined action. Further, in the "Score" item, score information indicating the relationship between the search query and a predetermined action is stored.

(Second list information storage unit 122)
The second list information storage unit 122 stores second list information in an arbitrary format. The second list information is a value that quantifies the relationship between a predetermined action and each user based on the search query input by each user other than the seed user and the first list information, and indicates the quantified relationship. This is information that ranks each user based on. FIG. 5 is a diagram illustrating an overview of second list information according to the embodiment.

As shown in FIG. 5, the second list information is provided for each predetermined action that is set in advance when the first list information is created. Further, as shown in FIG. 5, the second list information includes a "rank" item, a "user ID" item, and a "search query" item. These items included in the second list information are associated with each other.

In the "rank" item, for each of the multiple search queries entered by users other than the seed user, the associated score is obtained from the first list information, and the ranking is determined based on the total value of the obtained scores. information is stored.

The "user ID" stores identification information that is individually assigned to each user by the information processing apparatus 100 in order to identify users who use various services when providing various services. It should be noted that, without being limited to the example shown in FIG. 5, a plurality of user IDs having the same rank may be stored in the "user ID" item.

The "Search Query" item stores information on a search query input by each user that is associated with the identification information stored in the "User ID" item.

(User information storage unit 123)
The user information storage unit 123 stores user information such as sensor information provided by each user in an arbitrary format. FIG. 6 is a diagram showing an overview of user information according to the embodiment.

As shown in FIG. 6, the user information includes items such as "user ID" and "sensor information."

The “user ID” item stores identification information given to a user who is a provider of sensor information. The identification information stored in the "User ID" item corresponds to the identification information stored in the "User ID" item in the second list information illustrated in FIG.

The "sensor information" item stores sensor information provided by each user. Note that the sensor information stored in the "sensor information" item may be raw data provided by each user, or may be information processed such as normalization to make it easier to process. Good too.

Note that the user information storage unit 123 may store information estimated from the sensor information in association with an item such as "user ID".

(Control unit 130)
The control unit 130 shown in FIG. 3 is a controller that controls the information processing device 100. The control unit 130 uses a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), etc. to execute various programs (for example, information processing programs) stored in a storage device inside the information processing device 100. This is realized by executing using RAM as a work area. Further, the control unit 130 may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 130 includes a first generation unit 131, a second generation unit 132, a classification unit 133, and an evaluation unit 134. The control unit 130 uses these units to realize or execute information processing functions and operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it performs information processing to be described later. Further, the connection relationship between the respective units included in the control unit 130 is not limited to the connection relationship shown in FIG. 3, and may be other connection relationships.

(First generation unit 131)
The first generation unit 131 quantifies the relationship between the search query input by each seed user and the predetermined behavior based on the commonality of the search queries input by the plurality of seed users who have performed the predetermined behavior. first list information is generated.

(Second generation unit 132)
The second generation unit 132 quantifies the relationship between the predetermined behavior and each user based on the search query input by each user other than the seed user and the first list information, and indicates the quantified relationship. Second list information is generated that ranks each user based on the value (score).

(Classification unit 133)
The classification unit 133 classifies each user associated with a predetermined behavior into a plurality of clusters based on the commonality of each user's sensor information. For example, the classification unit 133 can classify each user into a plurality of clusters based on the similarity of the behavior patterns of each user identified using sensor information. Further, for example, the classification unit 133 can classify each user into a plurality of clusters for each behavior pattern using a plurality of behavior patterns. Furthermore, for example, the classification unit 133 can classify each user into a plurality of clusters using sensor information that is related to a predetermined behavior. Further, for example, the classification unit 133 can classify each user into a plurality of clusters using information regarding each user estimated from the sensor information.

(Evaluation unit 134)
The evaluation unit 134 uses the classification results by the classification unit 133 to evaluate the reliability of the second list information. For example, the evaluation unit 134 can derive the rate at which each user located in a predetermined ranking layer is assigned to the same cluster in the second list information, and evaluate the reliability of the second list information based on the derived rate. .

Furthermore, when the classification unit 133 classifies each user into a plurality of clusters for each behavior pattern using a plurality of behavior patterns, the evaluation unit 134 assigns a predetermined rank in the second list information for each of the plurality of behavior patterns. The reliability of the second list information can be evaluated by respectively deriving the ratios at which each user located in a layer is assigned to the same cluster, and by comprehensively considering each derived ratio.

[4. Processing procedure]
Hereinafter, a processing procedure by the information processing apparatus 100 according to the embodiment will be described using FIG. 7. FIG. 7 is a flowchart illustrating an example of a processing procedure by the information processing apparatus according to the embodiment. The processing procedure shown in FIG. 7 is executed by the control unit 130 of the information processing device 100. The processing procedure shown in FIG. 7 is repeatedly executed while the information processing device 100 is in operation.

As shown in FIG. 7, the classification unit 133 sets a predetermined action according to the operator's operation (step S101).

Subsequently, the classification unit 133 acquires second list information regarding the predetermined behavior set in step S101 from the second list information storage unit 122, and also acquires sensor information regarding the predetermined behavior set in step S101 from the user information storage unit. 123 (step S102).

Subsequently, the classification unit 133 classifies each user in the second list information acquired in step S102 into a plurality of clusters based on the commonality of the sensor information acquired in step S102 (step S103).

Then, the evaluation unit 134 evaluates the reliability of the second list information based on the classification result by the classification unit 133 (step S104), and ends the processing procedure shown in FIG. 7.

[5. Modified example]
The information processing device 100 described above may be implemented in various different forms other than the embodiments described above. Therefore, a modification of the embodiment will be described below.

(5-1. Regarding first list information and second list information)
In the embodiment described above, an example has been described in which the information processing device 100 generates first list information and second list information for each of a plurality of predetermined actions, but there is no need to be particularly limited to this example. For example, the information processing device 100 may create the first list information and the second list information based on context other than the target user's behavior (for example, demographic attributes, interests and preferences, etc.).

(5-2. Regarding cluster configuration users)
In the embodiment described above, the information processing device 100 may record information on clusters classified by the classification unit 133, for example, information on users forming the cluster. Then, at a predetermined timing, the information processing apparatus 100 updates the first list information and the second list information, creates a cluster for each user based on the updated second list information, and creates a cluster for each user who is a member of the created cluster. You may check whether there are any significant changes between the user and the recorded users of the cluster. Further, the information processing apparatus 100 may check whether the seed user is included in the cluster users.

[6. Hardware configuration]
The information processing apparatus 100 according to the embodiment is realized, for example, by a computer 1000 having a configuration as shown in FIG. FIG. 8 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment.

The computer 1000 is connected to an output device 1010 and an input device 1020, and has an arithmetic device 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 connected by a bus 1090. has.

The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and performs various processes. The primary storage device 1040 is a memory device such as a RAM that temporarily stores data used by the arithmetic unit 1030 for various calculations. Further, the secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), an HDD, a flash memory, or the like.

The output IF 1060 is an interface for transmitting information to be output to the output device 1010 that outputs various information such as a monitor or printer, and is, for example, a USB (Universal Serial Bus), a DVI (Digital Visual Interface), This is realized using a connector compliant with standards such as HDMI (registered trademark) (High Definition Multimedia Interface). Further, the input IF 1070 is an interface for receiving information from various input devices 1020 such as a mouse, a keyboard, and a scanner, and is realized by, for example, a USB or the like.

Note that the input device 1020 is, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), or a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like. Furthermore, the input device 1020 may be an external storage medium such as a USB memory.

Network IF 1080 receives data from other devices via network N and sends it to computing device 1030, and also sends data generated by computing device 1030 to other devices via network N.

Arithmetic device 1030 controls output device 1010 and input device 1020 via output IF 1060 and input IF 1070. For example, the arithmetic device 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040, and executes the loaded program.

For example, when the computer 1000 functions as the information processing device 100, the arithmetic device 1030 of the computer 1000 executes a program (for example, an information processing program) loaded on the primary storage device 1040, thereby performing the same operation as the control unit 130. Realize the functions of That is, the arithmetic device 1030 realizes processing by the information processing device 100 according to the embodiment in cooperation with a program (for example, an information processing program) loaded onto the primary storage device 1040.

[7. others]
Among the processes described in the embodiments described above, all or part of the processes described as being performed automatically can be performed manually, or all of the processes described as being performed manually can be performed manually. Alternatively, some of the steps can be performed automatically using known methods. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified.

In the embodiment described above, in order to realize the information processing method by the information processing apparatus 100 (for example, see FIG. 7), each part of the control unit 130 (the first generation unit 131, the second generation unit 132 , classification unit 133, and evaluation unit 134) may be realized as an add-on to an information processing program preinstalled in the information processing device 100, or may be implemented as a dedicated program using a lightweight programming language or the like. This may be realized by flexibly writing it as a providing program.

The information processing device 100 also stores, as information about each user, not only the history of search queries entered by each user, but also the purchase history of each user, the history of transaction objects viewed on the online shopping mall, and the history of transaction objects purchased. Purchase history, which is the history of content such as news that has been viewed, posting history, which is the history of texts, images, etc. posted on SNS (Social Networking Service), location history, etc. may be collected. In addition, the information processing device 100 reads, for example, a QR code (registered trademark) installed in a store using a smartphone owned by each user, and records usage history of payment services realized using the reading results and information about each user's usage history. A QR code may be displayed on a smartphone owned by the user, and the usage history of the payment service (for example, purchase date and time, purchased product, purchase amount, etc.) may be collected by having a store terminal read the QR code. Further, the information processing apparatus 100 may collect credit card usage history, bank account usage history, etc. held by each user.

Further, the information processing apparatus 100 may use information estimated based on the collected information as information for each user. For example, if the average monthly grocery purchase total is 100,000 yen or more based on the purchase history, the information processing device 100 determines whether the household monthly income or individual monthly income is 300,000 yen or more; It is also possible to estimate the family structure, such as a family of two people, or the structure of people living together, and use this information as information for each user. Further, the information processing device 100 may estimate the items owned by each user, the place of residence and workplace of each user, and use the estimated information as the information of each user, for example, based on the location history and purchase history.

Further, the information processing device 100 may obtain service usage history as information about each user, for example, from a server device that provides various services. Further, in the information processing device 100, a server device or a single server device that provides such a service may collect various information estimated from the usage history of the service as information about each user. Further, the information processing apparatus 100 may collect information indicating psychographic attributes such as various geographic attributes and hobbies and preferences registered by each user or estimated for each user as information about each user.

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured. For example, the classification section 133 and the evaluation section 134 of the control section 130 may be functionally integrated.

Further, the above-described embodiments and modified examples can be combined as appropriate within the range that does not conflict with the processing contents.

[8. effect]
The information processing device 100 according to the embodiment described above includes a first generation section 131, a second generation section 132, a classification section 133, and an evaluation section 134. The first generation unit 131 quantifies the relationship between the search query input by each seed user and the predetermined behavior based on the commonality of the search queries input by the plurality of seed users who have performed the predetermined behavior. first list information is generated. The second generation unit 132 quantifies the relationship between the predetermined behavior and each user based on the search query input by each user including the seed user and the first list information, and indicates the quantified relationship. Second list information is generated that ranks each user based on the values. The classification unit 133 classifies each user into a plurality of clusters based on the commonality of the sensor information of each user. The evaluation unit 134 uses the classification results by the classification unit 133 to evaluate the reliability of the second list information.

For this reason, the information processing apparatus 100 according to the embodiment clusters each user included in the second list information based on sensor information unrelated to the search query. It can be objectively confirmed whether each user listed has a certain degree of relevance, and the reliability of the second list information can be indirectly evaluated.

Furthermore, in the information processing apparatus 100 according to the embodiment, the evaluation unit 134 derives the ratio at which each user located in a predetermined rank layer in the second list information is assigned to the same cluster, and based on the derived ratio, Evaluate the reliability of the second list information. Thereby, the information processing apparatus 100 according to the embodiment can confirm, for example, in the second list information, up to which ranking users have a relationship with a predetermined behavior.

Furthermore, in the information processing apparatus 100 according to the embodiment, the classification unit 133 classifies each user into a plurality of clusters based on the similarity of the behavior patterns of each user identified using sensor information. Thereby, the information processing apparatus 100 according to the embodiment can classify users whose specific actions are similar to each other into the same cluster.

Furthermore, in the information processing apparatus 100 according to the embodiment, the classification unit 133 classifies each user into a plurality of clusters for each behavioral pattern using a plurality of behavioral patterns, and the evaluation unit 134 classifies each user into a plurality of clusters for each behavioral pattern. , derive the percentage of each user located in a predetermined ranking layer in the second list information being assigned to the same cluster, and evaluate the reliability of the second list information by comprehensively considering each derived percentage. . Thereby, the information processing apparatus 100 according to the embodiment can improve reliability evaluation accuracy.

Furthermore, in the information processing device 100 according to the embodiment, the classification unit 133 classifies each user into a plurality of clusters using sensor information that is related to a predetermined behavior.

Furthermore, in the information processing apparatus 100 according to the embodiment, the classification unit 133 classifies each user into a plurality of clusters using the information regarding each user estimated from the sensor information.

With these, the information processing apparatus 100 according to the embodiment can classify each user based on various criteria.

As mentioned above, the embodiments of the present application have been described in detail based on several drawings, but these are merely examples, and various modifications and variations can be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to carry out the invention in other forms with modifications.

Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the control section can be read as a control means or a control circuit.

10 Terminal device 100 Information processing device 110 Communication unit 120 Storage unit 121 First list information storage unit 122 Second list information storage unit 123 User information storage unit 130 Control unit 131 First generation unit 132 Second generation unit 133 Classification unit 134 Evaluation Department

Claims (8)

First list information that quantifies the relationship between the search query input by each seed user and the predetermined behavior based on the commonality of the search queries input by a plurality of seed users who have performed a predetermined behavior. a first generation unit that generates;
Based on a search query input by each user including the seed user and the first list information, the relationship between the predetermined action and each user is quantified, and a value indicating the quantified relationship is set. a second generation unit that generates second list information ranking each user based on the second list information;
a classification unit that classifies each user into a plurality of clusters based on the commonality of sensor information of each user;
An information processing device comprising: an evaluation section that evaluates reliability of the second list information using classification results by the classification section. The evaluation department is
The method is characterized by deriving a proportion of users located in a predetermined ranking layer in the second list information and being assigned to the same cluster, and evaluating reliability of the second list information based on the derived proportion. The information processing device according to claim 1. The classification section is
The information processing device according to claim 1 or 2, wherein each of the users is classified into a plurality of clusters based on similarity of behavior patterns of each of the users identified using the sensor information. The classification section is
Classifying each user into a plurality of clusters for each of the behavioral patterns using the plurality of behavioral patterns,
The evaluation department is
For each of the plurality of behavioral patterns, the proportion of each user located in a predetermined ranking layer in the second list information is assigned to the same cluster is derived, and the derived proportions are comprehensively taken into consideration. 4. The information processing device according to claim 3, wherein reliability of the 2-list information is evaluated. The classification section is
The information processing device according to any one of claims 1 to 4, wherein each of the users is classified into a plurality of clusters using sensor information that is related to the predetermined behavior. The classification section is
The information processing apparatus according to any one of claims 1 to 5, wherein the information processing apparatus classifies each user into a plurality of clusters using information regarding each user estimated from the sensor information. An information processing method performed by a computer, the method comprising:
First list information that quantifies the relationship between the search query input by each seed user and the predetermined behavior based on the commonality of the search queries input by a plurality of seed users who have performed a predetermined behavior. a first generation step of generating;
Based on a search query input by each user including the seed user and the first list information, the relationship between the predetermined action and each user is quantified, and a value indicating the quantified relationship is set. a second generation step of generating second list information ranking each of the users based on the
a classification step of classifying each of the users into a plurality of clusters based on the commonality of the sensor information of each of the users;
and an evaluation step of evaluating reliability of the second list information using the classification results obtained in the classification step. to the computer,
First list information that quantifies the relationship between the search query input by each seed user and the predetermined behavior based on the commonality of the search queries input by a plurality of seed users who have performed a predetermined behavior. a first generation procedure for generating;
Based on a search query input by each user including the seed user and the first list information, the relationship between the predetermined action and each user is quantified, and a value indicating the quantified relationship is set. a second generation procedure of generating second list information in which each of the users is ranked based on the second list information;
a classification procedure for classifying each user into a plurality of clusters based on the commonality of sensor information of each user;
and an evaluation procedure for evaluating reliability of the second list information using classification results obtained by the classification procedure.

Images